Intelligent broadcast television station comprehensive management method, system, storage medium and equipment

Abstract

This application provides a comprehensive management method and system for smart broadcasting and television stations, relating to the field of smart broadcasting and television technology. The technical solution provided in this application determines the type of broadcast time slot and the abnormal characteristics of content by obtaining the broadcast schedule, and calculates the risk transmission coefficient by combining it with historical risk evolution data for each time slot, generating a dynamic comprehensive risk score. This allows the risk assessment criteria to automatically adjust according to the importance of the broadcast time slot and the historical risk status, solving the problem that fixed threshold management methods cannot adapt to time slot differences. Simultaneously, it determines a set of associated stations based on the hierarchical position of the broadcasting and television station. When the target risk level reaches the linkage trigger condition, the initial management plan is adjusted based on hierarchical characteristics to obtain the target management plan. This enables multiple stations to coordinate and handle issues according to hierarchical responsibilities, avoiding insufficient response during important time slots and resource waste during unimportant time slots, thereby improving the operation and maintenance management effect of broadcasting and television stations.

Description

Technical Field

[0001] This application relates to the field of smart broadcasting technology, specifically to a comprehensive management method, system, storage medium, and device for smart broadcasting stations. Background Technology

[0002] Radio and television stations are specialized technical facilities responsible for the acquisition, production, transmission, and broadcasting of radio and television program signals, undertaking the important function of providing radio and television services to the public. The operation and maintenance (O&M) of a radio and television station refers to the technical activities of daily monitoring, maintenance, and management of the station's equipment, systems, and broadcast processes. The quality of O&M directly affects the security and continuity of program broadcasts. With the development of radio and television services and technological advancements, O&M management plays an increasingly important role in ensuring broadcast security and improving service quality.

[0003] Common operation and maintenance management methods in related technologies mainly adopt a monitoring and alarm mechanism with preset fixed thresholds. This involves setting uniform detection thresholds and handling procedures for various broadcast anomalies. When an abnormal signal is detected exceeding the preset threshold, an alarm is triggered and a predetermined emergency response plan is initiated. However, in practical applications, due to the unique time-slot differences in broadcasts by radio and television stations, the program types, audience groups, and social impacts of different broadcast times vary significantly. The fixed threshold management method cannot dynamically adjust risk assessment standards and emergency response strategies according to the importance of the broadcast time slot. This leads to insufficient response to minor anomalies during important times and over-response to normal fluctuations during unimportant times, resulting in inaccurate risk assessment and unreasonable allocation of emergency resources, ultimately leading to poor operation and maintenance management results. Summary of the Invention

[0004] This application provides a comprehensive management method and system for smart radio and television stations, which can adopt targeted operation and maintenance management solutions for different time periods and different broadcast content, thereby improving the operation and maintenance management effect of radio and television stations.

[0005] Firstly, this application provides a comprehensive management method for smart radio and television stations, the method comprising:

[0006] Obtain the broadcast schedule of the radio and television station, determine the broadcast time slot type corresponding to the current broadcast time, and the abnormal characteristics of the content of the currently broadcast program;

[0007] Obtain risk evolution data for historical periods prior to the current broadcast time, and calculate the risk transmission coefficient based on the risk evolution data. The risk transmission coefficient is used to characterize the degree of impact of the risk status of different historical periods on the currently broadcast program.

[0008] Calculate the dynamic comprehensive risk score corresponding to the current broadcast time based on the broadcast time type, abnormal content characteristics, and risk transmission coefficient;

[0009] Based on the target risk level of the dynamic comprehensive risk score, the initial management plan corresponding to the target risk level is retrieved from the preset operation and maintenance plan library;

[0010] Obtain the hierarchical position of the broadcasting station in the multi-level distributed architecture, and determine the set of associated stations based on the hierarchical position. The set of associated stations includes at least one associated station that has a hierarchical relationship with the broadcasting station.

[0011] When the target risk level reaches the preset linkage triggering condition, the initial management plan is adjusted according to the hierarchical characteristics of the associated station set to obtain the target management plan for the broadcasting station.

[0012] By adopting the above technical solution, the broadcast schedule is obtained to determine the type of broadcast time slot and the abnormal characteristics of the content. Combined with historical risk evolution data, a risk transmission coefficient is calculated to generate a dynamic comprehensive risk score. This allows the risk assessment criteria to automatically adjust according to the importance of the broadcast time slot and the historical risk status, solving the problem that fixed threshold management methods cannot adapt to time slot differences. Simultaneously, based on the hierarchical position of the broadcasting station, a set of related stations is determined. When the target risk level reaches the trigger condition for linkage, the initial management plan is adjusted based on hierarchical characteristics to obtain the target management plan. This enables multiple stations to coordinate their actions according to hierarchical responsibilities, avoiding insufficient response during important time slots and resource waste during unimportant time slots, thereby improving the operation and maintenance management effectiveness of broadcasting stations.

[0013] Secondly, this application provides a smart broadcasting and television station integrated management system, the system comprising:

[0014] The monitoring module is used to obtain the broadcast schedule of the broadcasting station, determine the broadcast time type corresponding to the current broadcast time, and identify any abnormal characteristics of the currently broadcast program.

[0015] The historical optimization module is used to obtain risk evolution data of historical periods before the current broadcast time, and calculate the risk transmission coefficient based on the risk evolution data. The risk transmission coefficient is used to characterize the degree of impact of the risk status of different historical periods on the currently broadcast program.

[0016] The scoring calculation module is used to calculate the dynamic comprehensive risk score corresponding to the current broadcast time based on the broadcast time type, content anomaly characteristics, and risk transmission coefficient.

[0017] The solution generation module is used to retrieve the initial management solution corresponding to the target risk level from the preset operation and maintenance solution library based on the target risk level of the dynamic comprehensive risk score.

[0018] The associated station determination module is used to obtain the hierarchical position of the broadcasting station in the multi-level distributed architecture, and determine the associated station set based on the hierarchical position. The associated station set includes at least one associated station that has a hierarchical relationship with the broadcasting station.

[0019] The scheme adjustment module is used to adjust the initial management scheme according to the hierarchical characteristics of the associated station set when the target risk level reaches the preset linkage trigger condition, so as to obtain the target management scheme for the broadcasting station.

[0020] Thirdly, this application provides a computer storage medium that stores multiple instructions adapted for loading by a processor and executing any of the methods described above.

[0021] Fourthly, this application provides an electronic device including a processor, a memory, and a transceiver. The memory is used to store instructions, the transceiver is used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform any of the methods described above.

[0022] In summary, the beneficial effects of the technical solution of this application include:

[0023] By adopting the above technical solution, the broadcast schedule is obtained to determine the type of broadcast time slot and the abnormal characteristics of the content. Combined with historical risk evolution data, a risk transmission coefficient is calculated to generate a dynamic comprehensive risk score. This allows the risk assessment criteria to automatically adjust according to the importance of the broadcast time slot and the historical risk status, solving the problem that fixed threshold management methods cannot adapt to time slot differences. Simultaneously, based on the hierarchical position of the broadcasting station, a set of related stations is determined. When the target risk level reaches the trigger condition for linkage, the initial management plan is adjusted based on hierarchical characteristics to obtain the target management plan. This enables multiple stations to coordinate their actions according to hierarchical responsibilities, avoiding insufficient response during important time slots and resource waste during unimportant time slots, thereby improving the operation and maintenance management effectiveness of broadcasting stations. Attached Figure Description

[0024] Figure 1 This is a flowchart illustrating a smart broadcasting and television station integrated management method according to an embodiment of this application;

[0025] Figure 2 This is a schematic diagram of the structure of a smart broadcasting and television station integrated management system according to an embodiment of this application;

[0026] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0027] Explanation of reference numerals in the attached drawings: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. Detailed Implementation

[0028] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification 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.

[0029] In the description of the embodiments of this application, words such as "illustrative," "for example," or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "illustrative," "for example," or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Rather, the use of words such as "illustrative," "for example," or "for example" is intended to present the relevant concepts in a specific manner.

[0030] In the description of the embodiments of this application, the term "multiple" means two or more. For example, multiple systems means two or more systems, and multiple screen terminals means two or more screen terminals. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0031] Please see Figure 1 This is a flowchart illustrating a comprehensive management method for a smart radio and television station, provided in an embodiment of this application. This method can be implemented using a computer program, a microcontroller, or run on a comprehensive management system for a smart radio and television station based on the von Neumann architecture. The computer program can be integrated into the application or run as a standalone utility application. The specific steps of the comprehensive management method for a smart radio and television station are described in detail below.

[0032] S101: Obtain the broadcast schedule of the broadcasting station, determine the broadcast time slot type corresponding to the current broadcast time, and the abnormal characteristics of the content of the currently broadcast program;

[0033] The broadcast schedule refers to the pre-arranged program playback plan of the broadcasting station, which details the start and end times, program names, and program types of programs broadcast within each time slot. Broadcast time slot types refer to the classification of time slots based on viewership characteristics, audience characteristics, and the importance of the broadcast content, including news slots, prime time, late-night slots, and children's slots, with different time slot types corresponding to different risk sensitivities. Content anomaly characteristics indicate deviations from normal conditions in terms of technical quality and content compliance of the currently broadcast program. These anomalies may include black screens, pixelation, and still frames in video footage; mute, abnormal volume, and audio-visual asynchrony in audio signals; and sensitive scenes, illegal subtitles, and overdue advertisements in terms of content compliance. The current broadcast time indicates the specific point in time when the system performs a risk assessment, corresponding to the currently broadcast program content and its broadcast time slot.

[0034] Specifically, the system first obtains complete broadcast schedule data from the station's program scheduling system. The system reads the current system clock to obtain the precise time of the current broadcast moment, then matches and compares this time with the start and end times of each segment recorded in the broadcast schedule to determine the specific broadcast segment to which the current broadcast moment belongs, and extracts the broadcast segment type information from the segment's attribute identifier. Simultaneously, the system collects real-time video and audio stream data of the currently broadcast program through multiple monitoring probes deployed along the broadcast link. It performs multi-dimensional quality detection and analysis on these real-time broadcast stream data, using image recognition technology to detect picture quality indicators, audio signal analysis technology to detect audio quality indicators, and content recognition and semantic analysis technology to detect compliance issues in the broadcast content. Based on parameters such as the type, severity, and duration of the detected quality issues, the system extracts and generates structured content anomaly feature data.

[0035] S102: Obtain risk evolution data for historical periods prior to the current broadcast time, and calculate the risk transmission coefficient based on the risk evolution data. The risk transmission coefficient is used to characterize the degree of influence of the risk status of different historical periods on the currently broadcast program.

[0036] Historical time periods refer to time intervals that have occurred before the current broadcast time. These time periods can be divided according to fixed time intervals or according to the actual duration of the broadcast program. Risk evolution data is used to represent the changes in the risk status of the broadcasting station within a historical time period. This data includes detailed information such as the occurrence time of risk events, event type, event severity, the trajectory of risk level changes, the measures taken, and their effects. The risk transmission coefficient is a numerical parameter that quantifies the degree to which the risk status of historical time periods affects the current broadcast program. This coefficient comprehensively considers multiple factors such as the severity, duration, and effectiveness of historical risks, as well as the time interval from the current moment. The larger the coefficient value, the more significant the impact of historical risks on the present.

[0037] Specifically, the system first queries and extracts relevant historical risk evolution data from the risk event database and operation and maintenance log system according to a preset historical data collection time range. This data is organized in time series format. The system divides the entire historical time range into multiple consecutive historical time windows according to a preset time granularity. It then performs statistical analysis on the risk evolution data within each time window, calculating risk status indicators, including the number of risk events, peak risk level, and duration of risk. Next, the system calculates the time interval between each historical time window and the current broadcast time, and assigns a corresponding time decay weight to each historical time window based on a time decay function, giving higher weights to historical time windows closer to the current time. Finally, the system integrates the risk status indicators and corresponding time decay weights of each historical time window, calculating the risk transmission coefficient through weighted summation or other mathematical models.

[0038] S103: Calculate the dynamic comprehensive risk score corresponding to the current broadcast time based on the broadcast time type, abnormal content characteristics, and risk transmission coefficient;

[0039] Among them, the dynamic comprehensive risk score refers to a quantitative risk level value calculated by a mathematical model by comprehensively considering multiple factors such as the current broadcast status, time period characteristics and historical risk impact. This score is a dynamically changing indicator that will be updated in real time as the broadcast status, time period type and historical risk situation change.

[0040] Specifically, the system first queries and retrieves the corresponding time-period sensitivity coefficient from a pre-configured time-period sensitivity configuration table based on the broadcast time-period type determined in step S101. This configuration table stores the mapping relationship between various broadcast time-period types and their sensitivity coefficients in key-value pairs. Next, the system quantifies and scores the various content anomaly features identified in step S101. For each anomaly type, the system looks up the corresponding base score from a preset scoring rule table or calculates it using a scoring formula based on its anomaly severity and duration. Finally, the system accumulates or weighted sums the base scores of all detected anomaly features to obtain a basic content anomaly score. Then, the system dynamically corrects the basic content anomaly score using the risk transmission coefficient calculated in step S102. The correction method can be a simple multiplication operation or a more complex nonlinear function mapping. This correction process assigns a higher risk score to the current content anomaly when there are many risk events in the historical time period. Finally, the system inputs the time-period sensitivity coefficient and the content anomaly score corrected for historical risks into a preset risk score calculation model for final calculation. The result of the calculation is the dynamic comprehensive risk score corresponding to the current broadcast time.

[0041] In some embodiments, the calculation of dynamic comprehensive risk score can be achieved in various ways. Optionally, the system can adopt a multi-factor weighted model, specifically including: first, reading the time-segment sensitivity coefficient corresponding to the current broadcast time-segment type from the time-segment sensitivity configuration table; then, calculating a basic score for each detected content anomaly feature, calculating the basic score for each anomaly type based on the duration and severity of the anomaly, and then summing the basic scores of all anomalies to obtain the total content anomaly basic score; next, obtaining the risk transmission coefficient calculated in step S102, and using the formula to calculate the content anomaly score after historical risk correction; finally, substituting the time-segment sensitivity coefficient and the corrected content anomaly score into the linear weighted model to calculate the dynamic comprehensive risk score. It is understood that other calculation models can also be used to achieve accurate assessment of dynamic comprehensive risk score, which is not limited here.

[0042] S104: Based on the target risk level of the dynamic comprehensive risk score, retrieve the initial management plan corresponding to the target risk level from the preset operation and maintenance plan library;

[0043] The target risk level refers to the risk classification determined by the score range falling within the dynamic comprehensive risk score. Risk levels are typically divided into multiple discrete levels, each corresponding to a specific scoring threshold range. The system compares the calculated dynamic comprehensive risk score with these thresholds to determine the current target risk level. The initial management plan represents a standardized management plan retrieved from the operations and maintenance plan library that matches the current target risk level. This plan provides a basic framework and standard operating procedures for handling this risk level.

[0044] Specifically, the system first compares the calculated dynamic comprehensive risk score with preset risk level classification thresholds to determine the target risk level to which the score belongs. This judgment process is typically implemented using piecewise functions or conditional judgment logic. Through a series of IF-ELSE or CASE statements, the score value is compared with the upper and lower limits of each level. When the score value falls within the threshold range of a certain level, that level is determined as the target risk level, and its identifier is recorded. Next, the system uses the identifier of the target risk level as the index key to query and retrieve the corresponding management plan record from the operation and maintenance plan database. The operation and maintenance plan database is stored in the form of a relational database or document database. Each plan record contains complete plan elements such as risk level identifier, plan name, applicable scenario description, monitoring parameter configuration, early warning threshold setting, emergency response step sequence, resource requirement list, personnel role allocation, and notification template. The system obtains the plan record that precisely matches the target risk level through database query operations and reads it into memory as the initial management plan. This plan defines a standard risk handling process framework.

[0045] S105: Obtain the hierarchical position of the broadcasting station in the multi-level distributed architecture, and determine the set of associated stations based on the hierarchical position. The set of associated stations includes at least one associated station that has a hierarchical relationship with the broadcasting station.

[0046] The multi-level distributed architecture refers to a hierarchical organizational structure adopted by broadcast television systems, divided according to administrative levels or business functions. Stations at each level have hierarchical management and business collaboration relationships. Hierarchical position refers to the rank of a specific broadcast television station within the multi-level distributed architecture. This positional information includes attributes such as the station's administrative level, region, and jurisdiction, used to determine the station's position and role within the entire broadcast television network. The associated station set represents the collection of other stations with hierarchical or collaborative relationships with the broadcast television station. This set includes the station's superior and subordinate stations. These associated stations need to share information and coordinate responses in risk-linked management.

[0047] Specifically, the system first reads the hierarchical attribute information of the current radio and television station from the station's basic information database. This information includes key fields such as the station's administrative level identifier, its regional code, the identifier of its superior station, and a list of subordinate stations. Based on the superior station identifier in the hierarchical attribute information, the system queries upwards to find the station's direct superior station and even higher-level superior stations, constructing a superior station chain. Simultaneously, based on the list of subordinate stations, the system queries downwards to find the station's direct subordinate stations and their subordinates, constructing a subordinate station tree. The system then summarizes and organizes all the information on stations with hierarchical relationships, including detailed information such as the station identifier, station name, hierarchical position, contact information, technical capabilities, and resource status of each related station, forming a data structure of related station sets.

[0048] S106: When the target risk level reaches the preset linkage triggering condition, the initial management plan is adjusted according to the hierarchical characteristics of the associated station set to obtain a target management plan for the broadcasting station.

[0049] The linkage triggering condition refers to a pre-set risk level threshold or specific scenario condition that requires the activation of the cross-station linkage management mechanism. When the target risk level reaches or exceeds this condition, the system determines that the current risk has exceeded the handling capacity of a single station and requires the mobilization of resources and capabilities of related stations for coordinated handling. This triggering condition can be a specific risk level value or a combination of risk type and level. Hierarchical features represent the hierarchical attributes and hierarchical relationships of each station in the set of related stations. These features include the differentiated characteristics of each related station, such as administrative level, technical capability, resource reserves, and response speed, as well as the hierarchical distance, command relationship, and collaboration mode between the current station and each related station. The target management plan refers to the final risk management plan after adjusting the hierarchical features to suit the specific situation and linkage needs of the current station. This plan adds linkage management content such as cross-station coordination mechanisms, resource allocation arrangements, and multi-level response processes to the initial management plan.

[0050] Specifically, the system first compares the target risk level determined in step S104 with the preset linkage triggering conditions to determine whether the conditions for initiating linkage management are met. This determination process can be a simple threshold comparison or a complex multi-condition comprehensive judgment. When the determination result indicates that linkage is required, the system initiates the scheme adjustment process. Next, the system analyzes the set of associated stations obtained in step S105, extracts the hierarchical characteristic information of each associated station, including assessing the technical support capabilities, emergency resource reserves, historical handling experience, and other capability indicators of each station, as well as calculating the hierarchical distance and response time between each station and the current station. Then, the system makes various adjustments and optimizations to the initial management plan based on hierarchical characteristics. Specific adjustments include: in resource allocation, adding a process for requesting support from higher-level stations and a resource application list based on the resource advantages of higher-level stations; and designing collaborative monitoring and backup broadcast arrangements for lower-level stations based on their distribution. In response processes, a multi-level linkage response mechanism is designed based on hierarchical relationships, clarifying the division of responsibilities and collaboration interfaces for each level of station. In notification mechanisms, the list of notification recipients is expanded based on hierarchical relationships, adding key personnel from higher-level stations and contact persons from lower-level stations. Finally, the system integrates all the adjusted elements into the initial management plan to form a complete target management plan. This plan fully considers the current station's position and relationships within the multi-level distributed architecture, enabling it to more effectively respond to high-level risk events.

[0051] Based on the above embodiments, as an optional implementation method, the method of obtaining the broadcast schedule of the broadcasting station in S101, determining the broadcast time period type corresponding to the current broadcast time, and the abnormal characteristics of the content of the currently broadcast program can be implemented through the following steps S201-S204.

[0052] S201: Obtain the broadcast schedule of the broadcasting station. The broadcast schedule includes the start and end times of each broadcast period and the period attribute identifier.

[0053] The broadcast schedule is a pre-prepared program playback plan document by the radio and television station. This document records the program arrangements for each time slot throughout the day in a timeline format. Start and end times refer to the specific start and end times of each broadcast slot, clearly defining the boundaries between different broadcast slots. Slot attribute identifiers are descriptive labels attached to each broadcast slot, used to indicate the nature and category of that slot, including categories such as news slots, prime time, late-night slots, and children's slots. Different attribute identifiers reflect the differences in viewership, audience demographics, and content importance of that slot.

[0054] Specifically, the system reads the complete broadcast schedule data structure from the station's program scheduling management system. This data structure is organized chronologically and contains records of all broadcast time slots from midnight of the current day to midnight of the next day. Each time slot record includes a start time field, an end time field, a program name field, a program type field, and a time slot attribute identifier field. The system accesses the program scheduling database through database queries or API calls to extract all time slot records containing the above-mentioned field information. The system loads the extracted data into memory, constructing a data structure that facilitates subsequent queries and matching. This data structure supports quick location of the corresponding broadcast time slot by time point. To ensure the timeliness and accuracy of the data, the system periodically updates the broadcast schedule from the source database, and promptly refreshes the time schedule data in memory when program scheduling is adjusted.

[0055] S202: Determine the broadcast time slot type corresponding to the current broadcast time based on the time position of the current broadcast time in the broadcast schedule;

[0056] Among them, time position refers to the position of the current broadcast time in the broadcast schedule. By comparing the current time with the start and end times of each broadcast period, it can be determined which specific broadcast period the current time falls within.

[0057] The system obtains the current system time as the current broadcast time and converts it into a standard timestamp format for subsequent comparison. The system iterates through all time slot records in the acquired broadcast schedule, extracting the start and end time fields for each record, and determining if the current broadcast time is greater than or equal to the start time and less than the end time of that time slot. When the condition is met, it indicates that the current broadcast time falls within the time range of that time slot, and the system stops iterating and records the index position of that time slot. The system reads the value of the time slot attribute identifier field from the successfully matched time slot records; this field value indicates the broadcast time slot type corresponding to the current broadcast time.

[0058] S203: Obtain the real-time broadcast stream data of the currently broadcast program, and perform multi-dimensional quality inspection on the real-time broadcast stream data. The multi-dimensional quality inspection includes video picture quality inspection, audio signal quality inspection, and broadcast content compliance inspection.

[0059] Real-time broadcast stream data refers to the audio and video signal data stream being transmitted and broadcast by broadcasting stations. This data stream includes video image sequences and audio signal sequences. Multi-dimensional quality inspection refers to the process of analyzing and identifying quality issues in broadcast stream data from multiple angles and levels. Video image quality inspection analyzes the image quality of video image sequences, including indicators such as brightness distribution, color reproduction accuracy, image sharpness, and image continuity. Audio signal quality inspection analyzes the sound quality of audio signal sequences, including indicators such as audio level, signal-to-noise ratio, frequency response, and audio-visual synchronization. Broadcast content compliance inspection analyzes the compliance of broadcast content with regulations, including compliance indicators such as whether the image content contains illegal elements, whether the subtitle information complies with regulations, and whether the advertising duration exceeds the limit.

[0060] Specifically, the system acquires the audio and video data stream of the currently broadcast program in real time through signal acquisition probes deployed at key nodes in the broadcast link. The signal acquisition probes perform non-intrusive sampling of the broadcast stream and transmit the sampled data packets to the quality inspection server. The quality inspection server analyzes the received video data frame by frame, extracting image data from each frame and calculating the brightness histogram of pixels within the frame. By analyzing the histogram distribution characteristics, it determines whether there are completely black scenes or abnormal brightness distributions. The server performs motion analysis on the video frame sequence, calculating pixel differences between consecutive frames to identify whether there are long periods of static or unchanging images. The server performs signal analysis on the audio data, calculating the power spectral density and loudness level of the audio stream to determine whether there are long periods of silence or abnormal volume fluctuations. The server runs content recognition algorithms to perform semantic analysis and sensitive information detection on the video images and subtitle text, identifying potentially illegal content. All detection tasks are executed in parallel, and the detection results are summarized in real time into the result data structure.

[0061] S204: Based on the results of multi-dimensional quality inspection, generate content anomaly characteristics of the currently broadcast program. Content anomaly characteristics include black screen anomaly, mute anomaly, mosaic anomaly, signal interruption anomaly, and content violation anomaly.

[0062] Among these, black screen anomalies refer to a situation where the video screen is completely black or nearly completely black, usually caused by signal loss, equipment malfunction, or program source problems. Muted audio anomalies refer to a situation where the audio signal is silent for an extended period or at extremely low volume, possibly caused by audio channel malfunction, audio source problems, or the equipment being muted. Mosaic anomalies refer to a situation where the video screen displays blocky distortion or pixel misalignment, usually caused by signal transmission errors, encoding / decoding problems, or insufficient bandwidth. Signal interruption anomalies refer to a situation where audio and video signals are completely lost or severely discontinuous, possibly caused by equipment power failure, line interruption, or system crash. Content violation anomalies refer to an situation where the broadcast content does not comply with broadcast television management regulations, including the appearance of prohibited images, illegal subtitles, and excessive advertising timeouts.

[0063] Specifically, the system reads the detailed results of each quality inspection from the detection result data structure. For video image quality inspection results, the system determines whether there are multiple consecutive frames with an average brightness value lower than a preset black level threshold. If so, and the duration exceeds a set value, a black level anomaly feature record is generated, containing attributes such as the anomaly start time, duration, and severity. The system analyzes the motion feature detection results of the video frame sequence to determine whether there are multiple consecutive frames with inter-frame differences lower than a preset still frame threshold. If so, a still frame anomaly feature is generated. For audio signal quality inspection results, the system determines whether the audio power is consistently lower than a preset silence threshold. If so, a silence anomaly feature record is generated. The system checks video decoding error statistics. If the error rate exceeds a threshold or severe block artifacts appear, a mosaic anomaly feature is generated. The system checks signal continuity indicators. If a complete signal interruption or prolonged packet loss is detected, a signal interruption anomaly feature is generated. For content compliance inspection results, the system reads sensitive information identification results and rule matching results. If illegal content is found, a content violation anomaly feature is generated. The system aggregates and integrates all generated anomaly features to construct a complete content anomaly feature data structure, which contains all detected anomaly types and their detailed attribute information.

[0064] Based on the above embodiments, as an optional implementation method, the method of obtaining risk evolution data of historical time periods before the current broadcast time in S102 and calculating the risk transmission coefficient based on the risk evolution data can be specifically implemented through the following steps S301-S304.

[0065] S301: Obtain risk evolution data for historical periods within a preset time range prior to the current broadcast time. The risk evolution data includes risk event records, risk level change records, and risk handling records for each historical period.

[0066] The historical time period refers to several time segments divided chronologically within a preset time range, with each segment corresponding to a specific broadcast time interval in the past. The risk event record is a detailed record of various risk issues that occurred during historical broadcasts, including the event's time, type, and description. The risk level change record records how the severity of a risk changes over time, including the initial risk level, the time of escalation, the time of de-escalation, and the final risk level. The risk handling record records the response measures taken in response to risk events and their effects, including the start time, method, and result of the handling.

[0067] Specifically, the system determines the starting time point of the historical data to be queried based on preset time range parameters. This starting time point is equal to the current broadcast time minus the duration of the preset time range. The system accesses the broadcast risk management database and constructs a database query statement. The time condition of this query statement is set to the time interval between the starting time point and the current broadcast time. The database returns all risk event record data within this time interval. Each record contains fields such as event identifier, occurrence time, event type, severity, and scope of impact. The system continues to query the risk level change table, extracting all level change records within the same time interval. These records are arranged in chronological order and record the time node of each risk level adjustment and the adjusted level value. The system queries the risk handling operation table to obtain all handling operation records executed within this time period, including manual intervention records, automatic switching records, and emergency plan activation records.

[0068] S302: Divide the preset time range into multiple historical time windows according to the preset time granularity, and count the risk status indicators in each historical time window. The risk status indicators include the number of risk events, the peak risk level, and the duration of risk.

[0069] Here, time granularity refers to the length of the time interval used when dividing a time range into discrete time units; this interval length determines the level of detail in historical data statistical analysis. A historical time window refers to several time segments formed by equally dividing a preset time range according to time granularity; each time segment represents an independent statistical analysis unit. Risk status indicators are a set of numerical indicators that quantitatively describe the risk status within a specific time window. The number of risk events refers to the cumulative number of risk events detected within a certain historical time window. The peak risk level refers to the highest risk level value that has occurred within a certain historical time window. The duration of risk refers to the cumulative length of time that the risk status persists within a certain historical time window.

[0070] Specifically, the system reads a preset time granularity parameter value, which defines the duration of each historical time window. The system divides the total duration of the preset time range by the time granularity value to obtain the total number of historical time windows to be divided. Starting from the beginning time of the preset time range, the system sequentially generates the start and end time boundaries of each historical time window according to the time granularity value. The start time of each window is equal to the end time of the previous window, and the duration of the window is equal to the time granularity value. The system traverses each historical time window, and for the currently traversed window, it filters out all risk event records whose occurrence time falls within the time range of the window from the risk evolution data obtained in step S301. The system counts the filtered risk event records to obtain the number of times the risk events occurred in the window. The system traverses the risk level change records within the window, extracts all level values, and finds the maximum value, which is the peak risk level of the window. The system calculates the sum of the durations of all risk events within the window. For risk events that cross the window boundaries, only the duration within the current window is calculated, and the sum is used to obtain the total risk duration of the window. The system associates and stores the calculated values ​​of the three indicators with the corresponding window identifiers to form a risk status indicator dataset for each historical time window.

[0071] S303: Calculate the time decay weight corresponding to each historical time window based on the time interval between each historical time window and the current broadcast time. The closer the historical time window is to the current broadcast time, the greater the time decay weight it corresponds to.

[0072] The time interval refers to the time difference between the center moment of a historical time window and the current broadcast moment, reflecting the timeliness of historical data. The time decay weight is a weighting coefficient calculated based on the time interval. This coefficient is used to adjust the influence of historical data at different time intervals on the current risk prediction, and the weight value decreases as the time interval increases.

[0073] Specifically, the system iterates through each historical time window. For each window, it first calculates the center time, which is equal to the average of the window's start and end times. The system then calculates the time difference between the current broadcast time and the window's center time, obtaining the time interval between the window and the current time. The system uses a time decay function to convert the time interval; this decay function is a decreasing function, with the time interval value as input and the time decay weight value as output. The system substitutes the time interval value into the decay function for calculation. Windows closer to the current time have smaller time intervals and receive larger weight values, while windows farther from the current time have larger time intervals and receive smaller weight values. The system normalizes the original weight values ​​calculated for all windows by dividing each window's original weight value by the sum of all original weight values, resulting in a normalized time decay weight. The sum of the normalized window weight values ​​equals one. The system associates and stores the calculated time decay weights with the corresponding historical time window identifiers, establishing a mapping relationship between windows and weights.

[0074] S304: Calculate the risk transmission coefficient based on the risk status indicators of each historical time window and the corresponding time decay weight.

[0075] Specifically, the system reads risk status indicator data for each historical time window, along with the corresponding time decay weight data. For each historical time window, the system extracts three indicators: the number of risk events, the peak risk level, and the duration of the risk. The system performs a weighted combination calculation on these three indicators. First, it standardizes each indicator value, converting values ​​with different dimensions to a unified numerical range. The system assigns a fixed importance weight to each indicator, with the sum of the three weights equal to one, reflecting the relative importance of each indicator in risk transmission. The system multiplies the standardized indicator value for each window by its corresponding importance weight, then sums the three products to obtain the comprehensive risk intensity value for that window. The system then multiplies the comprehensive risk intensity value for each window by its corresponding time decay weight to obtain the weighted risk intensity value for that window. Finally, the system sums the weighted risk intensity values ​​for all historical time windows; the sum is the risk transmission coefficient, and the magnitude of this coefficient reflects the comprehensive influence of historical risk status on current risk prediction.

[0076] Based on the above embodiments, as an optional implementation method, the dynamic comprehensive risk score corresponding to the current broadcast time in S103 is calculated according to the broadcast time type, content abnormality characteristics and risk transmission coefficient, which can be implemented through the following steps S201-S204.

[0077] S401: Obtain the corresponding time period sensitivity coefficient from the preset time period sensitivity configuration table according to the broadcast time period type. The time period sensitivity coefficient is used to characterize the sensitivity of different broadcast time period types to risks.

[0078] Among them, the time-period sensitivity coefficient is a numerical parameter assigned to a specific broadcast time-period type. This parameter reflects the degree of impact on the safety of broadcast television when a risk event occurs during that time period and the level of social attention. Different time-period types have different sensitivity coefficient values ​​due to differences in the audience, program importance, and social influence.

[0079] Specifically, the system reads the broadcast time slot type identifier corresponding to the current broadcast time. The system accesses a pre-configured time slot sensitivity configuration table, which uses the broadcast time slot type as the primary key and includes a time slot type name field and a time slot sensitivity coefficient field. The system performs a query operation in the configuration table, with the matching condition being that the time slot type name equals the current broadcast time slot type identifier. The database returns the time slot sensitivity coefficient value from the matching record. This value is typically in the range of a few tenths of a second to a few units, with higher sensitivity coefficients set for prime time and news time slots, and lower sensitivity coefficients set for late-night and rebroadcast time slots. The system stores the retrieved time slot sensitivity coefficient value in a temporary variable, which is used as an important adjustment parameter in subsequent risk score calculations. If no matching record for the current time slot type exists in the configuration table, the system uses the default sensitivity coefficient value set in the configuration table as the return result.

[0080] S402: Calculate the basic content anomaly score based on the anomaly type, severity, and duration of various content anomaly characteristics;

[0081] Here, "Abnormality Type" refers to the risk category to which the abnormal content characteristics belong; different abnormality types represent broadcast issues of different natures. "Abnormality Severity" is a quantitative assessment of the scope and severity of the content abnormality's impact, categorizing its severity into multiple levels. "Abnormality Duration" refers to the length of time from the onset of the abnormal content state to its eventual disappearance. The "Basic Content Abnormality Score" is an initial risk score calculated based on the type, severity, and duration of the abnormal content; this score reflects the inherent risk level of the abnormality itself.

[0082] Specifically, the system reads the content anomaly feature data of the currently broadcast program, which includes all detected anomaly feature records. The system iterates through each anomaly feature record, extracting the anomaly type field value. Based on the anomaly type, it queries the corresponding type weight coefficient from a preset type risk weight table, setting the type weight coefficient for content violation anomalies to the highest value, followed by signal interruption anomalies, and decreasing in that order for black screen anomalies, silence anomalies, and mosaic anomalies. The system extracts the anomaly severity field value, which is typically a discrete level identifier. The system converts the level identifier into a corresponding severity score, with higher levels corresponding to higher scores. The system extracts the anomaly duration field value, which is a duration value in seconds or milliseconds. The system combines the type weight coefficient, severity score, and duration value for calculation. First, it multiplies the severity score by the duration value to obtain a time-weighted severity, then multiplies this result by the type weight coefficient to obtain the risk contribution value of a single anomaly. The system sums the risk contribution values ​​of all anomaly feature records; the sum is the basic content anomaly score, which reflects the immediate risk level of the currently broadcast content without considering historical factors.

[0083] S403: Dynamically adjust the basic content anomaly score based on the risk transmission coefficient to obtain the content anomaly score after historical risk correction.

[0084] Specifically, the system reads the basic content anomaly score and the risk transmission coefficient. The system determines the magnitude of the risk transmission coefficient, which reflects the impact of the frequency and severity of risk events in the historical period on the current moment. The system multiplies the risk transmission coefficient by the basic content anomaly score to obtain the historical risk contribution score. A larger risk transmission coefficient indicates a more severe risk situation in the historical period, and the historical risk contribution score increases accordingly. Conversely, a smaller risk transmission coefficient indicates a relatively stable risk situation in the historical period, and the historical risk contribution score decreases accordingly. The system adds the basic content anomaly score to the historical risk contribution score, and the sum of the two constitutes the content anomaly score after historical risk correction. This correction process reflects the characteristic of risk having a cumulative effect over time; even if the current anomaly level is not high, vigilance is needed when historical risk is high, while occasional minor anomalies will not lead to an excessively high score when historical risk is low. The system stores the calculated content anomaly score in the risk assessment result data structure, and this value serves as an important input parameter for subsequent comprehensive risk score calculations.

[0085] S404: Input the time period sensitivity coefficient and content anomaly score into the preset risk score calculation model to calculate the dynamic comprehensive risk score corresponding to the current broadcast time.

[0086] The risk scoring calculation model is a pre-built mathematical calculation model that takes multiple risk-related parameters as input and outputs the final risk score result through specific calculation logic.

[0087] Specifically, the system reads two parameter values: the time-period sensitivity coefficient and the content anomaly score. The system then calls a pre-defined risk scoring calculation model, which internally defines the calculation rules for parameter combinations. The system passes the time-period sensitivity coefficient and the content anomaly score as input parameters to the calculation model's input interface. The calculation model first checks the numerical range of the content anomaly score to ensure the input value is within a valid range. The model multiplies the content anomaly score by the time-period sensitivity coefficient. This operation modulates the risk score based on time-period characteristics; content anomalies occurring during sensitive periods have a magnified risk score, while content anomalies occurring during non-sensitive periods have a relatively stable risk score. The model normalizes the multiplication result, mapping it to a predefined scoring range, typically set to an integer interval from zero to one hundred. The model then formats the normalized value by rounding or retaining a specified number of decimal places to obtain the final dynamic comprehensive risk score.

[0088] Based on the above embodiments, as an optional implementation method, in S106, the initial management scheme is adjusted according to the hierarchical characteristics corresponding to the associated station set to obtain a target management scheme for broadcasting and television stations. This can be achieved through the following steps S501-S502.

[0089] S501: Based on the hierarchical characteristics and target risk level corresponding to the set of associated stations, determine the target stations to participate in the joint management from the set of associated stations;

[0090] Here, "hierarchical level" refers to the classification of stations within the administrative management system. Stations at different levels differ in terms of management authority, coverage, and resource allocation. "Hierarchical relationship" refers to the superior-subordinate relationship between stations within the management system or the upstream-downstream relationship in signal transmission. This relationship determines the collaboration methods and information transmission paths between stations. "Target linkage stations" are specific stations selected from the set of associated stations that need to participate in this risk linkage management. These stations are identified as linkage response targets based on their current risk level and hierarchical relationship.

[0091] Specifically, the system reads the hierarchical feature data of all stations in the associated station set. This data includes the hierarchical level identifier of each station and the hierarchical relationship direction identifier with the current station. The system reads the dynamic comprehensive risk score and maps the score to the corresponding target risk level according to the preset risk level classification rules. Risk levels are usually divided into discrete levels such as low, medium, high, and extremely high. The system queries the preset linkage range configuration table according to the target risk level. This configuration table defines the linkage station selection rules corresponding to different risk levels. The higher the risk level, the wider the range of stations that need to be linked. The system traverses the associated station set according to the selection rules. For each associated station, it first determines whether its hierarchical level meets the linkage conditions. When the risk level is low, only stations at the same level are linked. When the risk level is medium, stations at the same level and its direct superior are linked. When the risk level is high or extremely high, stations at the same level, its superior, and related subordinate stations are linked. The system further determines the hierarchical relationship between stations. For higher-level stations, it needs to report the risk status and accept command and dispatch; for stations at the same level, it needs to share risk information and coordinate handling; and for lower-level stations, it needs to issue control instructions and supervise their execution. The system marks all stations that meet the screening criteria as target linkage stations and stores the identifiers and hierarchical information of these stations in the target linkage station list. This list serves as the basis for subsequent plan adjustments and execution.

[0092] S502: Based on the hierarchical level and hierarchical relationship of the target linkage stations, adjust the scheme triggering parameters, scheme execution process and station collaboration mechanism in the initial management scheme to obtain the target management scheme.

[0093] The plan triggering parameters are a set of parameters that define the conditions for plan initiation and execution timing. These parameters include configuration items such as trigger threshold, trigger delay, and trigger priority. The plan execution process is a process definition describing the operational steps and execution sequence of each stage of emergency response. This process specifies the complete operational path from risk detection to response completion. The station collaboration mechanism is a specification defining how multiple stations divide labor, cooperate, and exchange information during coordinated response. This mechanism clarifies the allocation of responsibilities and collaboration methods among each station.

[0094] Specifically, the system reads the complete configuration data of the initial management plan, which stores the various parameters and process definitions of the plan in a structured form. The system reads the target linkage station list determined in step S501 and extracts the hierarchical level and hierarchical relationship information of each station in the list. The system determines whether the target linkage stations include a superior station. If a superior station is included, the system adjusts the report delay setting in the plan trigger parameters, shortening the delay for reporting to the superior station to ensure that the superior station can be informed of the risk status in a timely manner. Simultaneously, a process node waiting for superior instructions is added to the plan execution flow, and this node is equipped with a timeout jump mechanism to avoid process blockage. The system determines whether the target linkage stations include peer stations. If peer stations are included, information sharing configuration is added to the station collaboration mechanism, setting the information exchange interface and data synchronization frequency with peer stations. A collaborative decision node is inserted into the plan execution flow, which realizes status synchronization and strategy negotiation among multiple stations. The system determines whether the target linked stations include subordinate stations. If so, it adjusts the command priority in the scheme trigger parameters to enhance control over subordinate stations. It adds command distribution and execution monitoring steps to the scheme execution process and configures execution feedback channels for subordinate stations in the station collaboration mechanism. The system adjusts concurrent execution parameters based on the number and distribution of various stations. When the number of linked stations is large, a parallel processing mechanism is activated; when stations are widely distributed, communication timeout parameters are adjusted. The system integrates all adjusted parameters and process configurations into a target management scheme.

[0095] Based on the above embodiments, as an optional implementation method, the method of adjusting the scheme triggering parameters in S502 can be implemented through the following steps.

[0096] Obtain the preset baseline risk threshold in the initial management plan; when the target linked station's level is higher than that of the broadcasting station, adjust the baseline risk threshold to the first risk threshold according to the target linked station's level, where the first risk threshold is lower than the baseline risk threshold; when the target linked station's level is lower than that of the broadcasting station, adjust the baseline risk threshold to the second risk threshold according to the target linked station's level, where the second risk threshold is higher than the baseline risk threshold; determine the first risk threshold or the second risk threshold as the scheme trigger parameter of the target management plan.

[0097] The baseline risk threshold is a pre-set standard risk score in the initial management plan that triggers the execution of the plan. The plan automatically starts execution when the actual risk score reaches or exceeds this threshold. The first risk threshold is an adjusted trigger threshold for high-level linkage stations. This threshold is lower than the baseline risk threshold, allowing the plan to be triggered when the risk level is relatively low. The second risk threshold is an adjusted trigger threshold for low-level linkage stations. This threshold is higher than the baseline risk threshold, allowing the plan to be triggered only when the risk level reaches a higher level.

[0098] Specifically, the system reads the value of the baseline risk threshold field from the configuration data of the initial management plan. This value is typically a fraction between zero and one hundred. The system iterates through each station in the target linkage station list, reading its hierarchical level identifier. The system compares the hierarchical level of each target linkage station with the hierarchical level of the current broadcasting station, determining their relative importance by querying a preset hierarchical mapping table. This mapping table defines the hierarchical order of provincial, municipal, and county levels. When a target linkage station's hierarchical level is determined to be higher than the current broadcasting station's, the system performs a downward adjustment of the threshold. The system queries a threshold adjustment coefficient table based on the hierarchical difference between the higher-level station and the current station; the larger the hierarchical difference, the larger the adjustment. The system multiplies the baseline risk threshold by an adjustment coefficient less than one to obtain the first risk threshold. This reduction in the threshold allows for timely reporting to the superior station and triggering of linkage measures even before the risk reaches the baseline level, reflecting the requirement for timely reporting to superior stations. When a target linkage station is determined to be at a lower level than the current broadcasting station, the system adjusts the threshold upwards. The system queries the threshold adjustment coefficient table based on the level difference between the lower-level station and the current station. The system multiplies the baseline risk threshold by an adjustment coefficient greater than one to obtain a second risk threshold. This increased threshold ensures that control instructions are only issued to lower-level stations and linkage actions are triggered when the risk reaches a high level, avoiding frequent responses from lower-level stations due to minor risks and resulting resource waste. The system stores the first or second risk thresholds calculated for different station levels in the corresponding linkage configuration items. When the target linkage stations include both high-level and low-level stations, the system sets corresponding trigger thresholds for each level. During implementation, the linkage actions of the corresponding level stations are triggered based on the comparison between the actual risk score and the different thresholds. The system integrates all adjusted trigger threshold parameters into the trigger parameter configuration section of the target management scheme, replacing the unified baseline threshold in the initial scheme, forming a multi-level triggering mechanism with hierarchical differentiation. This mechanism ensures that the upper-level stations can intervene in risk management at an early stage, while the lower-level stations only participate in linkage when necessary, realizing hierarchical and precise control of linkage response.

[0099] Based on the above embodiments, as an optional implementation method, the method of adding a station collaboration mechanism in S502 can be implemented through the following steps.

[0100] Obtain the standard execution process in the initial management plan, identify each process node and execution sequence in the standard execution process, including risk detection nodes, risk handling nodes, and risk assessment nodes; obtain the risk assessment results fed back by the risk assessment nodes, generate the collaborative processing tasks corresponding to the risk assessment results; divide the collaborative processing tasks into corresponding collaborative processing nodes, and add the collaborative processing nodes to the corresponding process nodes according to the execution sequence to obtain the target management plan.

[0101] The standard execution process is a predefined sequence of risk handling operations in the initial management plan, arranged chronologically from risk discovery to handling completion. Process nodes are the basic execution units in the standard execution process, each representing a specific handling operation or inspection task. Risk detection nodes are responsible for monitoring and identifying broadcast risks, performing monitoring operations such as signal quality checks and content compliance checks. Risk handling nodes are responsible for implementing specific emergency handling measures, performing operations such as signal switching, backup broadcast activation, and fault repair. Risk assessment nodes are responsible for assessing the risk status and handling effectiveness, performing assessment operations such as risk level determination and handling effectiveness analysis. Execution order refers to the sequential execution relationship and logical dependency between process nodes. Collaborative handling tasks are handling tasks generated based on risk assessment results, requiring multiple stations to complete jointly. These tasks decompose the overall handling objective into sub-tasks that can be executed by different stations. Collaborative handling nodes are node units that transform collaborative handling tasks into node units that can be embedded in the standard execution process; each node corresponds to a collaborative operation that needs to be performed by a specific station.

[0102] Specifically, the system reads the standard execution process configuration data from the initial management plan. This data stores the complete handling process definition in the form of a flowchart structure or a node linked list. The system parses the process configuration data, extracts all process node identifiers, reads the node type attribute of each node, and classifies the nodes into three categories based on the type attribute: risk detection nodes, risk handling nodes, and risk assessment nodes. The system reads the connection relationship data between nodes and constructs a directed relationship graph between nodes. This graph reflects the execution order and logical dependencies of each node. The system sorts the nodes according to a topological sorting algorithm to obtain a complete execution sequence. The system locates the risk assessment node in the standard execution process. This node is usually located after the risk detection and risk handling nodes in the process and is responsible for evaluating the current risk status and the effectiveness of the implemented handling measures. The system reads the risk assessment result data output by this risk assessment node during this execution process. This result data includes assessment information such as risk level, risk type, scope of impact, and handling effect. The system determines whether a collaborative processing task needs to be generated based on the risk level and impact scope information in the risk assessment results. When the risk level reaches the threshold requiring multi-station linkage or the impact scope involves the coverage areas of multiple stations, the system initiates the collaborative task generation process. The system queries a pre-set collaborative task template library and selects a matching template based on the risk type and the hierarchical relationship of the involved target stations. This template defines elements such as the collaborative task's objectives, participating stations, and task decomposition methods. Based on the selected template, the system generates a specific collaborative processing task, which includes complete information such as a task objective description, a list of participating stations, the allocation of responsibilities for each station, and task execution sequence requirements. The system decomposes the generated collaborative processing task according to the responsibilities of the participating stations, generating corresponding sub-tasks for each participating station. Each sub-task specifies the specific operations that the station needs to perform and the completion deadline. The system transforms each station's sub-tasks into corresponding collaborative processing nodes. Each collaborative processing node includes attributes such as node identifier, executing station, operation content, input / output data definition, and timeout settings. The system analyzes the execution sequence of the standard execution flow to determine the insertion positions of collaborative processing nodes. For collaborative nodes requiring reporting to higher-level stations, they are inserted immediately after the risk assessment node. For nodes requiring collaborative decision-making with peer stations, they are inserted before the risk handling node to establish a pre-decision mechanism. For nodes requiring control and management by lower-level stations, they are inserted within the risk handling node as parallel execution branches. The system adds each collaborative processing node to the standard execution flow according to the determined insertion positions, updates the connections between nodes, and establishes data transfer channels and execution dependencies between collaborative processing nodes and existing process nodes.The system performs integrity verification on the process after adding collaborative processing nodes, checking whether the process has infinite loops, unreachable nodes, and whether the preconditions of all nodes are met. After the verification is passed, the adjusted process configuration is saved as the execution process part of the target management solution.

[0103] Based on the above embodiments, this embodiment provides an integrated monitoring method for smart broadcasting and television stations based on multi-element fusion. This method deeply integrates multiple dimensions such as signal monitoring, equipment management, environmental monitoring, and security management to build an intelligent security system covering all elements.

[0104] First, a unified data acquisition platform is established, which simultaneously connects to the signal monitoring sub-sub ... The security monitoring sub-sub collects security-related data such as video surveillance footage, personnel entry and exit records, and area intrusion events through devices such as video surveillance cameras, access control systems, and intrusion alarms. The operations and maintenance management sub-sub-sub retrieves management data such as manually recorded operations and maintenance information, fault handling records, and equipment inspection data from duty logs, work order management, and inspection records.

[0105] The heterogeneous data collected from each of the above sub-collections were standardized and time-aligned. A unified data model was established to address the differences in data formats from different data sources, converting various types of data into a standardized data structure containing fields such as timestamps, data source identifiers, monitored object identifiers, parameter types, parameter values, and parameter statuses. A high-precision clock synchronization mechanism was employed to assign a unified timestamp accurate to the millisecond level to all collected data, ensuring precise alignment of data from different sub-collections on the timeline. The standardized multi-source data was organized according to time series, constructing a multi-dimensional time-series database containing signal quality data streams, device status data streams, environmental parameter data streams, security event data streams, and operation and maintenance data streams. This database supports rapid querying and correlation analysis based on various conditions such as time range, data source type, and monitored object.

[0106] Then, artificial intelligence technology is used to perform in-depth analysis of the fused multi-dimensional monitoring data to achieve cross-dimensional anomaly identification and associated fault diagnosis. First, anomaly detection is performed on data from each dimension. For signal quality data, a deep learning-based video quality assessment model is used to intelligently analyze the video content. This model can identify visual anomalies. Simultaneously, an audio feature extraction algorithm is used to detect audio anomalies, and the detected signal anomalies are classified according to severity. For equipment status data, a equipment performance baseline model is established. This model learns the performance parameter distribution characteristics of the equipment under normal operating conditions and can identify abnormal deviations in equipment performance. When parameters such as CPU utilization and memory usage exceed normal fluctuation ranges, it is determined that the equipment performance is abnormal. When the equipment temperature exceeds a safety threshold or the fan speed decreases abnormally, it is determined that the equipment hardware is abnormal. For environmental parameter data, environmental monitoring thresholds are set. When the computer room temperature exceeds the set upper limit or falls below the lower limit, a temperature anomaly alarm is triggered. When the relative humidity exceeds the suitable range, a humidity anomaly alarm is triggered. When a smoke detector detects smoke or a water immersion sensor detects water leakage, an environmental hazard alarm is immediately triggered. When the power supply voltage or current fluctuates abnormally, a power anomaly alarm is triggered. For security incident data, video intelligent analysis technology is used to analyze the surveillance footage in real time to identify security incidents such as unauthorized personnel entry, abnormal personnel behavior, and items left behind. At the same time, the card swipe records of access control are monitored to identify abnormal access behaviors such as entry at abnormal times and unauthorized card swipes.

[0107] The following section explains the specific operation and maintenance aspects of the smart radio and television station.

[0108] In terms of automated program scheduling and primary / backup switching linkage, a dual-path monitoring mechanism for the broadcast link is established. The primary and backup broadcast links are each configured with independent broadcast servers, encoders, and modulators. The output signals of both links converge to an automatic switcher, which selects to output the primary or backup signal based on signal quality and instructions. The signal quality parameters and equipment operating status of both primary and backup paths are monitored in real time. When a serious signal quality anomaly or critical equipment failure is detected in the primary broadcast link, the primary / backup switching process is immediately initiated. First, the status of the backup broadcast link is assessed. After confirming that the backup signal quality is acceptable and the equipment is operating normally, a switching control command is sent to the automatic switcher. Upon receiving the command, the switcher executes the signal switching action, switching the output signal from the primary to the backup path. Seamless switching technology is used to ensure a smooth transition of picture and sound during the switching process, avoiding blackouts, silences, or abrupt image changes. After completing the primary / backup switch, a switching notification is immediately sent to maintenance personnel, informing them of the switching time, reason for switching, and current broadcast link status. Simultaneously, the fault diagnosis process for the primary link is initiated to analyze the specific cause of the primary link anomaly and generate fault handling suggestions.

[0109] The master / backup switchover mechanism is deeply integrated with the program scheduling process. When a master / backup switchover is detected during program broadcast, the remaining broadcast time of the current program is assessed. If the remaining time is short and the switchover may cause broadcast interruption, the switchover operation is delayed until the current program finishes broadcasting, and the switchover is performed during the program break to minimize the impact on broadcast. If the anomaly level reaches the point where an immediate switchover is necessary, the program broadcast schedule is adjusted simultaneously with the switchover, and the broadcast times of affected subsequent programs are fine-tuned to ensure the continuity of the overall broadcast plan. Detailed logs of all master / backup switchover events are recorded, including switchover trigger time, trigger reason, switchover execution time, switchover completion time, signal quality comparison data before and after the switchover, and equipment status change records. This log data is used for subsequent switchover effect evaluation and switchover strategy optimization.

[0110] In terms of transmitter monitoring and intelligent power regulation, the transmitter's operating parameters are collected in real time through the communication interface with the transmitter controller. These parameters include key electrical parameters such as output power, reflected power, VSWR, excitation power, grid voltage, grid current, plate voltage, plate current, filament voltage, and filament current, as well as thermal management parameters such as the temperature of each power amplifier module, fan speed, coolant temperature, and coolant flow rate. The collected transmitter parameters are compared with the preset normal operating range in real time. When the output power deviates from the allowable range of rated power, a power anomaly alarm is triggered. When the reflected power exceeds the safety threshold, it is determined that there may be a problem with the antenna feeder. When the VSWR exceeds the limit value, it indicates that the antenna is mismatched and needs maintenance. When the power amplifier module temperature exceeds the safe temperature, an over-temperature alarm is issued and the temperature protection mechanism is activated.

[0111] Intelligent adjustment of transmission power is implemented based on the importance of broadcast time slots and coverage requirements. The program type and importance markers for the current time slot are extracted from the broadcast schedule. For important broadcast time slots such as news and prime time, the transmitter power is automatically adjusted to 100% of its rated power to ensure maximum signal coverage. For less important time slots such as late-night and rebroadcast periods, the transmission power can be appropriately reduced to 70% to 80% of the rated power to reduce energy consumption and equipment wear while maintaining basic coverage. A coverage quality assessment mechanism based on viewer feedback is established. By collecting signal quality complaint data from viewers and field strength test data from monitoring points, the actual coverage effect under the current transmission power is evaluated. When an increase in signal quality complaints in certain areas or a decrease in field strength at monitoring points is detected, it is analyzed whether this is due to insufficient power. If it is confirmed that power needs to be increased, the transmission power is automatically increased, and the improvement in coverage effect is continuously monitored.

[0112] To achieve automatic primary / backup transmitter failover, a primary and backup transmitter are configured at the transmitting station, with their outputs connected to a shared antenna via an RF switcher. The operating status and output signal quality of the primary transmitter are continuously monitored. When a serious fault is detected in the primary transmitter, preventing further transmission, the primary / backup failover process is immediately initiated. First, the backup transmitter is started and warmed up to operational status. Once the backup transmitter's output power and signal quality meet requirements, the RF switcher is activated to switch the antenna input from the primary to the backup transmitter. After the switchover, the faulty primary transmitter is shut down to prevent interference with the backup transmitter. Simultaneously, a failover notification and primary transmitter fault information are sent to maintenance personnel to guide them in troubleshooting and repairing the primary transmitter. Complete process data for the transmitter failover event is recorded, including key indicators such as fault detection time, failover decision time, backup transmitter startup time, switchover execution time, failover completion time, and signal interruption duration during the failover. This data is used to evaluate the reliability and response speed of the failover, providing a basis for optimizing the failover strategy.

[0113] In terms of integrated power and environmental protection, regarding power supply monitoring, the system monitors parameters such as three-phase voltage, three-phase current, frequency, and power factor of the mains input, and assesses the mains power quality in real time. When mains voltage fluctuations exceed the allowable range or phase loss or frequency abnormalities are detected, a mains abnormality alarm is immediately issued. The system also monitors parameters such as input voltage, output voltage, output current, load rate, battery voltage, battery capacity, and remaining battery time of the UPS uninterruptible power supply, assessing the UPS's operating status and backup power capacity. When the UPS switches to battery power mode, a mains power interruption alarm is triggered, and the duration of backup power is assessed based on the remaining battery time. If the battery power supply time is expected to be insufficient to support mains power restoration, an emergency plan is activated, notifying maintenance personnel to prepare to start the diesel generator or execute an orderly shutdown procedure. The system monitors the operating parameters of the diesel generator, including generator output voltage, output current, output frequency, engine speed, oil pressure, coolant temperature, and fuel level. When the mains power is interrupted for a long time and the generator needs to be started, it automatically sends a start command. After the generator starts, it monitors whether its operating parameters are normal. Once it confirms that the generator output is stable, it controls the automatic transfer switch to switch the load to generator power supply.

[0114] In terms of environmental monitoring, temperature and humidity sensors deployed in various areas of the computer room collect ambient temperature and relative humidity data in real time. This data is compared with the suitable operating environment range for the equipment. When the computer room temperature exceeds the set upper limit threshold, it is determined that the air conditioning cooling capacity is insufficient or malfunctioning. A cooling enhancement command is immediately sent to the air conditioning control system, and a high-temperature alarm is sent to maintenance personnel, prompting them to check the air conditioning operation status. When the temperature continues to rise and reaches the critical value for the equipment's safe temperature, the equipment temperature protection mechanism is activated, implementing power reduction or orderly shutdown for non-critical equipment, prioritizing the safe operation of core broadcast equipment. The system monitors the operating parameters of the precision air conditioning, including the air conditioning operating mode, set temperature, actual supply air temperature, return air temperature, compressor operating status, and fan speed. When frequent compressor starts and stops or abnormally high supply air temperature are detected, it is determined that the air conditioning may have faults such as insufficient refrigerant, clogged filters, or poor condenser heat dissipation. An air conditioning fault warning is generated, and maintenance suggestions are pushed out.

[0115] In terms of fire monitoring, the system integrates the status and alarm signals of detectors used for automatic fire alarms. When a smoke detector detects excessive smoke concentration or a heat detector detects a sharp rise in temperature, a fire alarm is triggered. Upon receiving the fire alarm signal, the integrated monitoring system immediately executes the fire linkage process. First, it sends a fire alarm notification to all on-duty personnel, indicating the fire location and evacuation routes. Simultaneously, it activates the audible and visual alarms, activating the fire emergency plan, cutting off non-fire-fighting power supplies, starting fire pumps and sprinklers, opening access control for fire exits, starting smoke exhaust fans, and closing fire doors in fire compartments. During fire alarm handling, the system continuously monitors the operational status of each fire-fighting device, confirming successful fire pump startup, open sprinkler valves, and normal operation of smoke exhaust fans. If any fire-fighting equipment fails to start, the system immediately reports the equipment malfunction to the fire control room and maintenance personnel.

[0116] In terms of security monitoring, video surveillance, access control, and intrusion alarms are integrated to achieve unified management of security monitoring. Video surveillance cameras deployed in key areas such as station entrances / exits, server room entrances, equipment areas, and duty rooms are connected. The system intelligently analyzes the surveillance footage to identify events such as personnel entering / exiting, loitering, and items left behind. When personnel enter the server room area outside of working hours, an abnormal intrusion alarm is triggered, retrieving relevant camera recordings and sending them to duty personnel for verification. Access control authorization information and card swipe records are managed, allowing for differentiated access permissions for different personnel. Information such as the time of each card swipe, the cardholder, and the access control location is recorded. When unauthorized card swipes or tailgating are detected, an abnormal access control alarm is triggered. Intrusion alarm sensors such as infrared detectors, microwave detectors, and glass break detectors are connected. Intrusion alarm arming mode is activated outside of working hours. When a detector detects movement or the sound of breaking glass, an intrusion alarm is triggered, triggering relevant cameras to record video and simultaneously sending an alarm notification to security personnel.

[0117] Secondly, a machine learning-based fault prediction model is established. This model learns the correlation between historical equipment failure events and changes in equipment operating parameters before the failure, enabling it to issue early warnings when equipment exhibits signs of failure. Continuous collection of multi-dimensional data, including equipment performance parameters, environmental parameters, runtime, and load changes, is used to input this real-time data into the trained prediction model. The model calculates the probability of equipment failure within a future time window. When the failure probability exceeds a preset threshold, a health warning is generated, prompting maintenance personnel to monitor the equipment and schedule preventative maintenance. Specialized prediction models are developed for different types of equipment. The fault prediction model for broadcast servers focuses on signs such as declining disk read / write performance and increased memory error rates, while the fault prediction model for transmitters focuses on signs such as rising power amplifier module temperatures and drifting current and voltage parameters. These specialized models improve the accuracy of predictions.

[0118] An intelligent operation and maintenance (O&M) decision engine is constructed, integrating multi-dimensional monitoring data, anomaly diagnosis results, fault prediction results, and an O&M knowledge base to provide decision-making suggestions for O&M personnel. When an anomaly is detected, the decision engine first retrieves matching handling solutions from the O&M knowledge base. The knowledge base stores structured knowledge such as symptom descriptions, cause analyses, handling steps, and precautions for various typical faults. The decision engine evaluates the suitability of the retrieved solutions based on the specific characteristics of the current anomaly and selects the most suitable solution as the recommended handling solution. The decision engine further analyzes the current broadcast status and resource status, assessing the impact of different handling solutions on broadcast and the required resource conditions. For handling solutions that require interrupting broadcast or switching equipment, the decision engine assesses whether the current time window for interruption is available. For solutions that require calling backup equipment or spare parts, the decision engine queries the availability status of backup resources. The decision engine calculates a comprehensive score for each candidate solution based on factors such as solution matching degree, broadcast impact, and resource availability. The solution with the highest score is presented as the preferred recommended solution to O&M personnel, while other alternative solutions are listed for reference.

[0119] In terms of electronic duty management, an electronic duty log is provided for duty personnel. Duty personnel record various events during their duty period through the interface, including equipment inspection records, abnormal event records, fault handling records, visitor records, etc. Each record is automatically timestamped and the recorder's information is added to ensure accuracy and traceability. Based on a preset duty task list, the system automatically reminds duty personnel to perform routine tasks such as scheduled inspections, periodic meter readings, and shift handover checks. After completing the corresponding tasks, duty personnel confirm their completion in the system, recording the task completion time and archiving the inspection data. If a duty personnel fails to complete a task within the specified time, a task timeout reminder is sent to ensure the standardized execution of duty work. A duty handover function is provided. The outgoing duty personnel fill in the handover details, including important events that occurred during the shift, equipment operating status, outstanding issues, and precautions. The incoming duty personnel log in to view the handover details and confirm their takeover, recording the handover time and mutual confirmation information, achieving electronic and standardized duty handover.

[0120] Establish an operation and maintenance work order management process to achieve closed-loop management from fault reporting to resolution completion. When an abnormal event is detected or a manual fault report is received, an operation and maintenance work order is automatically generated. The work order records information such as fault description, occurrence time, equipment information, preliminary diagnostic results, and recommended handling solutions. Work orders are automatically prioritized based on the urgency and impact of the fault. High-priority work orders that severely affect broadcasting are immediately pushed to relevant operation and maintenance personnel and require timely response. General maintenance work orders are assigned to the corresponding maintenance personnel according to the normal process. After receiving the work order, the operation and maintenance personnel record the handling process, including fault confirmation, handling measures, component replacement, testing and verification, and other operational steps. After the handling is completed, the operation and maintenance personnel fill in the handling results and equipment recovery status in the work order and submit a work order completion application. Management personnel review and accept completed work orders. After confirming that the fault has been completely resolved, the work order is closed. Work order processing time, handling effectiveness, and other indicators are statistically analyzed to evaluate operation and maintenance response efficiency and service quality.

[0121] Finally, a comprehensive monitoring screen was established to visualize multi-dimensional monitoring data and intuitively present the operational status. The monitoring screen adopts a partitioned layout design, dividing the entire display area into functional zones such as signal monitoring, equipment status, environmental and power systems, security monitoring, alarm information, and statistical analysis. The signal monitoring zone simultaneously displays real-time images of the main broadcast signal, backup broadcast signal, and various input signals in a multi-screen format. Next to each signal image, the technical quality indicators of that signal are displayed, including real-time values ​​and change curves of parameters such as video bitrate, audio level, and bit error rate. When a signal exhibits quality abnormalities, the corresponding image border is highlighted in red and flashes as a warning. The equipment status zone displays the operational status of each key device in the form of a device topology diagram or list. Devices such as broadcast servers, encoders, and transmitters are displayed as icons. The color of the device icon indicates the device status: green indicates normal operation, yellow indicates an alarm, red indicates a device malfunction, and gray indicates the device is offline. Clicking on a device icon allows viewing detailed parameters and historical operating curves for that device.

[0122] The Environmental Power Zone displays information such as temperature and humidity distribution, power supply and distribution status, and air conditioning operation status within the computer room. It uses a temperature heatmap to show the temperature distribution in different areas of the room, with high-temperature areas highlighted in red, suitable temperature areas in green, and low-temperature areas in blue. Maintenance personnel can easily identify areas with abnormal temperatures using the heatmap. The power supply and distribution zone uses a single-line diagram, indicating the connections and current flow of mains power, UPS, generators, distribution cabinets, and other equipment. The diagram displays real-time voltage, current, and power parameters for each node. An abnormality in a line segment or device is highlighted in an abnormal color on the diagram. The Air Conditioning Operation Status Zone displays the operating mode, set temperature, actual temperature, and load rate for each air conditioner. Faulty or malfunctioning air conditioners are clearly indicated.

[0123] The security monitoring area integrates video surveillance footage and access control status information, selectively displaying surveillance footage from key areas. When security detects an abnormal event, it automatically switches to displaying the surveillance footage from the relevant area. Access control status is shown in a floor plan format, displaying the location and open / closed status of each access point. The latest access control card swipe records are displayed in a scrolling list format. The alarm information area displays all currently unprocessed alarm information in a list format, sorted by alarm level, with high-level alarms displayed at the top of the list. Each alarm message displays key information such as alarm time, alarm object, alarm type, and alarm level. The alarm list uses color coding to distinguish different levels: red for emergency alarms, orange for important alarms, and yellow for general alarms. The statistical analysis area displays operational statistical indicators, including daily broadcast duration, signal quality pass rate, number of equipment failures, number of primary / backup switchovers, and average fault handling time, among other key performance indicators. These are displayed using various chart formats such as digital meters, bar charts, and line charts to help managers comprehensively understand the operational status and maintenance effectiveness.

[0124] A mobile application is provided, enabling operations and maintenance (O&M) personnel to view monitoring data and receive alarm notifications anytime on their mobile devices. The mobile application synchronizes data with the monitoring platform in real time. After logging into the application via mobile phone or tablet, O&M personnel can view real-time monitoring screens, device operating status, alarm information, and other key data. When a high-level alarm occurs, the mobile application promptly alerts O&M personnel via push notifications, ensuring they are aware of the anomaly even when not at the monitoring center. The mobile application supports remote operation functions, allowing O&M personnel to perform operations such as signal switching, device restart, and alarm confirmation via mobile devices, enabling rapid response in emergencies. The mobile application logs all remote operations, including operator information, operation time, and operation content, ensuring traceability and secure control over remote operations.

[0125] Through the above-mentioned integrated monitoring implementation method, comprehensive monitoring and intelligent management of all elements of smart radio and television stations, including signal quality, equipment operation, environmental power, security protection, and operation and maintenance management, have been realized. An intelligent protection system covering the entire process of monitoring, analysis, early warning, decision-making, and handling has been constructed, which has significantly improved the safe broadcasting guarantee capability of radio and television stations, reduced operation and maintenance manpower costs, and improved the scientific and standardized level of operation and maintenance management.

[0126] The following are system embodiments of this application, which can be used to execute the method embodiments of this application. For details not disclosed in the system embodiments of this application, please refer to the method embodiments of the application.

[0127] Please see Figure 2 This illustration shows a schematic diagram of the structure of a smart radio and television station integrated management system provided in an exemplary embodiment of this application. The system can be implemented as all or part of a larger system through software, hardware, or a combination of both. The smart radio and television station integrated management system includes:

[0128] The monitoring module is used to obtain the broadcast schedule of the broadcasting station, determine the broadcast time type corresponding to the current broadcast time, and identify any abnormal characteristics of the currently broadcast program.

[0129] The historical optimization module is used to obtain risk evolution data of historical periods before the current broadcast time, and calculate the risk transmission coefficient based on the risk evolution data. The risk transmission coefficient is used to characterize the degree of impact of the risk status of different historical periods on the currently broadcast program.

[0130] The scoring calculation module is used to calculate the dynamic comprehensive risk score corresponding to the current broadcast time based on the broadcast time type, content anomaly characteristics, and risk transmission coefficient.

[0131] The solution generation module is used to retrieve the initial management solution corresponding to the target risk level from the preset operation and maintenance solution library based on the target risk level of the dynamic comprehensive risk score.

[0132] The associated station determination module is used to obtain the hierarchical position of the broadcasting station in the multi-level distributed architecture, and determine the associated station set based on the hierarchical position. The associated station set includes at least one associated station that has a hierarchical relationship with the broadcasting station.

[0133] The scheme adjustment module is used to adjust the initial management scheme according to the hierarchical characteristics of the associated station set when the target risk level reaches the preset linkage trigger condition, so as to obtain the target management scheme for the broadcasting station.

[0134] This application also provides a computer storage medium that can store multiple instructions. The instructions are adapted to be loaded and executed by a processor as described in the above embodiments of the intelligent broadcasting and television station integrated management method. For the specific execution process, please refer to the detailed description of the embodiments, which will not be repeated here.

[0135] Please see Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 3 As shown, the electronic device 300 may include: at least one processor 301, at least one network interface 304, user interface 303, memory 305, and at least one communication bus 302.

[0136] The communication bus 302 is used to enable communication between these components.

[0137] The user interface 303 may include a display screen and a camera.

[0138] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0139] The processor 301 may include one or more processing cores. The processor 301 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling data stored in the memory 305. Optionally, the processor 301 may be implemented using at least one hardware form of digital signal processing, field-programmable gate array, or programmable logic array. The processor 301 may integrate one or more of the following: a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 301 and may be implemented as a separate chip.

[0140] The memory 305 may include random access memory (RAM) or read-only memory (ROM). Optionally, the memory 305 may include a non-transitory computer-readable medium. The memory 305 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), instructions for implementing the various method embodiments described above, etc.; the data storage area may store data involved in the various method embodiments described above, etc. Optionally, the memory 305 may also be at least one storage device located remotely from the aforementioned processor 301. Figure 3 As shown, the memory 305, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for a comprehensive management method of a smart broadcasting station.

[0141] exist Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and to obtain the user input data; while the processor 301 can be used to call the application program of a smart broadcasting station integrated management method stored in the memory 305. When executed by one or more processors, the electronic device executes one or more methods as described in the above embodiments.

[0142] The above are merely exemplary embodiments of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Those skilled in the art will readily conceive of other embodiments of this disclosure upon considering the specification and practical application disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure.

Claims

1. A method for comprehensive management of a smart broadcast television station, characterized in that, The method includes: Obtain the broadcast schedule of the radio and television station, determine the broadcast time slot type corresponding to the current broadcast time, and the abnormal characteristics of the content of the currently broadcast program; Obtain risk evolution data for historical periods prior to the current broadcast time, and calculate a risk transmission coefficient based on the risk evolution data. The risk transmission coefficient is used to characterize the degree of influence of the risk status of different historical periods on the currently broadcast program. The step of acquiring risk evolution data for historical periods prior to the current broadcast time and calculating the risk transmission coefficient based on the risk evolution data includes: The system acquires risk evolution data for historical periods within a preset time range prior to the current broadcast time. This risk evolution data includes records of risk events, risk level changes, and risk handling for each historical period. The preset time range is divided into multiple historical time windows according to a preset time granularity, and risk status indicators are statistically analyzed within each historical time window. These risk status indicators include the number of risk events, the peak risk level, and the duration of the risk. Based on the time interval between each historical time window and the current broadcast time, a time decay weight is calculated for each historical time window, with a larger time decay weight for historical time windows closer to the current broadcast time. Finally, a risk transmission coefficient is calculated based on the risk status indicators and corresponding time decay weights for each historical time window. Calculate the dynamic comprehensive risk score corresponding to the current broadcast time based on the broadcast time type, the abnormal characteristics of the content, and the risk transmission coefficient; The step of calculating the dynamic comprehensive risk score corresponding to the current broadcast time based on the broadcast time type, the abnormal content characteristics, and the risk transmission coefficient includes: According to the broadcast time period type, the corresponding time period sensitivity coefficient is obtained from the preset time period sensitivity configuration table. The time period sensitivity coefficient is used to characterize the sensitivity of different broadcast time period types to risks. According to the abnormality type, abnormality severity and abnormality duration of various content abnormality features, a basic content abnormality score is calculated. The basic content abnormality score is dynamically adjusted according to the risk transmission coefficient to obtain a content abnormality score corrected for historical risks. The time period sensitivity coefficient and the content abnormality score are input into a preset risk score calculation model to calculate the dynamic comprehensive risk score corresponding to the current broadcast time. Based on the target risk level of the dynamic comprehensive risk score, the initial management plan corresponding to the target risk level is retrieved from the preset operation and maintenance plan library; Obtain the hierarchical position of the broadcasting station in the multi-level distributed architecture, and determine the set of associated stations based on the hierarchical position. The set of associated stations includes at least one associated station that has a hierarchical relationship with the broadcasting station. When the target risk level reaches the preset linkage triggering condition, the initial management plan is adjusted according to the hierarchical characteristics corresponding to the associated station set to obtain a target management plan for the broadcasting station.

2. The method according to claim 1, characterized in that, The process of obtaining the broadcast schedule of the radio and television station, determining the broadcast time slot type corresponding to the current broadcast time, and identifying the abnormal characteristics of the currently broadcast program includes: Obtain the broadcast schedule of the broadcasting station, which includes the start and end times of each broadcast period and the period attribute identifier; Based on the current broadcast time's position in the broadcast schedule, determine the broadcast time slot type corresponding to the current broadcast time; The system acquires real-time broadcast stream data of the currently broadcast program and performs multi-dimensional quality detection on the real-time broadcast stream data. The multi-dimensional quality detection includes video picture quality detection, audio signal quality detection, and broadcast content compliance detection. Based on the results of the multi-dimensional quality detection, the content anomaly features of the currently broadcast program are generated. The content anomaly features include black screen anomaly, mute anomaly, mosaic anomaly, signal interruption anomaly, and content violation anomaly.

3. The method according to claim 1, characterized in that, The step of adjusting the initial management scheme according to the hierarchical characteristics corresponding to the associated station set to obtain a target management scheme for the broadcasting station includes: Based on the hierarchical characteristics corresponding to the set of associated stations and the target risk level, the target stations for joint management are determined from the set of associated stations. Based on the hierarchical level and hierarchical relationship of the target linkage stations, the scheme triggering parameters, scheme execution process and station collaboration mechanism in the initial management scheme are adjusted to obtain the target management scheme.

4. The method according to claim 3, characterized in that, The method further includes: Obtain the preset baseline risk threshold in the initial management plan; When the target linkage station's hierarchical level is higher than the broadcasting station's level, the benchmark risk threshold is adjusted to a first risk threshold based on the target linkage station's hierarchical level, and the first risk threshold is lower than the benchmark risk threshold. When the target linkage station's hierarchical level is lower than the broadcasting station's level, the baseline risk threshold is adjusted to a second risk threshold based on the target linkage station's hierarchical level, and the second risk threshold is higher than the baseline risk threshold. The first risk threshold or the second risk threshold is determined as the scheme triggering parameter of the target management scheme.

5. The method according to claim 3, characterized in that, The method further includes: Obtain the standard execution process in the initial management plan, identify each process node and execution order in the standard execution process, and the process nodes include risk detection nodes, risk handling nodes and risk assessment nodes; Obtain the risk assessment results fed back by the risk assessment node, and generate the collaborative processing task corresponding to the risk assessment results; The collaborative processing task is divided into corresponding collaborative processing nodes, and the collaborative processing nodes are added to the corresponding process nodes according to the execution order to obtain the target management scheme.

6. A smart radio and television station integrated management system, characterized in that, The system includes: The monitoring module is used to obtain the broadcast schedule of the broadcasting station, determine the broadcast time type corresponding to the current broadcast time, and identify any abnormal characteristics of the currently broadcast program. The historical optimization module is used to acquire risk evolution data of historical periods prior to the current broadcast time, and calculate a risk transmission coefficient based on the risk evolution data. The risk transmission coefficient is used to characterize the degree of influence of the risk status of different historical periods on the currently broadcast program. Acquiring the risk evolution data of historical periods prior to the current broadcast time and calculating the risk transmission coefficient based on the risk evolution data includes: acquiring risk evolution data of historical periods within a preset time range prior to the current broadcast time, the risk evolution data including risk event records, risk level change records, and risk handling records for each historical period; dividing the preset time range into multiple historical time windows according to a preset time granularity, and statistically analyzing risk status indicators within each historical time window, the risk status indicators including the number of risk events, the peak risk level, and the duration of risk; calculating the time decay weight corresponding to each historical time window based on the time interval between each historical time window and the current broadcast time, wherein the closer the historical time window is to the current broadcast time, the greater the time decay weight; and calculating the risk transmission coefficient based on the risk status indicators of each historical time window and the corresponding time decay weight. The scoring calculation module is used to calculate the dynamic comprehensive risk score corresponding to the current broadcast time based on the broadcast time type, the content anomaly characteristics, and the risk transmission coefficient. The calculation of the dynamic comprehensive risk score corresponding to the current broadcast time includes: obtaining the corresponding time-segment sensitivity coefficient from a preset time-segment sensitivity configuration table based on the broadcast time type, where the time-segment sensitivity coefficient characterizes the sensitivity of different broadcast time types to risk; calculating a basic content anomaly score based on the anomaly type, severity, and duration of various content anomaly characteristics; dynamically adjusting the basic content anomaly score based on the risk transmission coefficient to obtain a content anomaly score corrected for historical risks; and inputting the time-segment sensitivity coefficient and the content anomaly score into a preset risk scoring calculation model to calculate the dynamic comprehensive risk score corresponding to the current broadcast time. The solution generation module is used to retrieve the initial management solution corresponding to the target risk level from the preset operation and maintenance solution library based on the target risk level of the dynamic comprehensive risk score. The associated station determination module is used to obtain the hierarchical position of the broadcasting station in a multi-level distributed architecture, and determine the associated station set based on the hierarchical position. The associated station set includes at least one associated station that has a hierarchical relationship with the broadcasting station. The scheme adjustment module is used to adjust the initial management scheme according to the hierarchical characteristics corresponding to the associated station set when the target risk level reaches the preset linkage triggering condition, so as to obtain a target management scheme for the broadcasting station.

7. A computer storage medium, characterized in that, The computer storage medium stores a plurality of instructions, which are adapted to be loaded by a processor and executed as described in any one of claims 1 to 5.

8. An electronic device, characterized in that, The device includes a processor, a memory, and a transceiver, wherein the memory is used to store instructions, the transceiver is used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any one of claims 1 to 5.

Images