Communication fault emergency resource allocation method and device and storage medium

Abstract

The invention provides a communication fault emergency resource allocation method and device and a storage medium, and relates to the technical field of communication fault resource scheduling. The method mainly comprises the following steps: setting a fault base station judgment threshold to determine a multi-fault area, and calling an operator interface to collect key indexes; calculating an initial score based on the key index, calculating a network damage index by combining a base station and a scene value coefficient, and determining an emergency task priority based on index ranking; calculating an emergency index based on the key indicator to determine a response level; matching the key index with a historical task library, and determining the type and quantity of required emergency resources; and sending an approval request to an emergency personnel terminal according to the priority and the resource demand. According to the method, a whole-process deployment framework is constructed, links of fault identification, priority determination, response grading, resource matching and approval are linked, limitation of traditional artificial experience and static plans is broken through, multi-area emergency scheduling systematization and standardization are achieved, and large-scale communication fault emergency response efficiency is improved.

Description

Technical Field

[0001] This invention mainly relates to the field of communication fault resource scheduling technology, specifically to a communication fault emergency resource allocation method, device and storage medium. Background Technology

[0002] Currently, with the rapid development of technologies such as 5G, IoT, and cloud computing, the scale of communication networks continues to expand, and network architecture is becoming increasingly complex, significantly increasing the potential risk of large-scale communication failures. Sudden events such as natural disasters, cyberattacks, and cascading equipment failures can lead to regional communication outages, severely impacting social operations, emergency command, and public safety. For example, natural disasters such as earthquakes and floods can damage large areas of base stations and transmission lines, causing communication paralysis at the township level or even larger. Cyberattacks can specifically target and damage core communication nodes, leading to signal interruptions within a region. Cascading failures caused by aging equipment or maintenance negligence can also spread rapidly, forming large-scale communication outages. All of these situations directly hinder the transmission of emergency rescue instructions and the exchange of emergency assistance information with the public, posing a serious threat to social order and the safety of life and property.

[0003] However, traditional emergency response mechanisms for communication failures are no longer adequate for today's complex network environment and diverse failure scenarios. They primarily rely on human experience and static contingency plans for dispatching, which has significant limitations: when large-scale communication failures occur simultaneously in multiple areas, there is a lack of quantitative assessment methods for dimensions such as the scope of the failure, the affected groups, and the correlation with key scenarios. This leads to subjective and arbitrary prioritization of emergency tasks, making it impossible to scientifically distinguish between urgent and critical situations. Emergency resource allocation is based solely on pre-set lists, failing to accurately match resource types and quantities with the actual damage characteristics of the affected areas, often resulting in an imbalance where "high-demand areas have resource shortages, while low-demand areas have resource redundancy." Furthermore, the cumbersome and slow-responding human decision-making process makes it difficult to quickly connect failure detection and resource dispatch, ultimately leading to delays in the restoration of critical communication services and even secondary disasters caused by untimely rescue, further amplifying the losses caused by the failure.

[0004] Therefore, how to build an intelligent scheduling mechanism that can accurately identify the priority of fault areas and efficiently match emergency resources, break through the bottleneck of traditional reliance on manual experience, and improve the efficiency and accuracy of emergency response to large-scale communication failures has become a key issue that urgently needs to be addressed in the field of emergency support for communication failures. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a method, device and storage medium for emergency resource allocation in communication failures, in order to address the shortcomings of the prior art.

[0006] The technical solution of this invention to solve the above-mentioned technical problems is as follows: A method for emergency resource allocation in the event of communication failure, comprising the following steps: By setting a threshold for judging faulty base stations, multiple fault areas that have experienced large-scale communication failures are identified, and the operator's interface is called to collect key indicators corresponding to each fault area. The initial score is calculated based on the key indicators corresponding to each fault area. The network damage index of each fault area is calculated based on the initial score, base station value coefficient and scenario value coefficient. The priority of emergency tasks for each fault area is determined based on the ranking order of the network damage index. Emergency indices are calculated based on key indicators corresponding to each fault area, and the response level of each fault area is determined based on the calculated emergency indices. The key indicators corresponding to each fault area are matched and analyzed with the historical task database data, and the types and quantities of emergency resources required for each fault area are determined based on the analysis results. Approval requests are sent to the terminals of relevant emergency personnel based on the priority of emergency tasks and the type and quantity of emergency resources corresponding to each fault area.

[0007] Another technical solution of the present invention to solve the above-mentioned technical problems is as follows: A communication failure emergency resource allocation device, comprising: The key indicator collection module is used to identify multiple fault areas where large-scale communication failures have occurred by using the set fault base station judgment threshold, and to call the operator interface to collect the key indicators corresponding to each fault area. The emergency task priority calculation module is used to calculate the corresponding initial score based on the key indicators of each fault area, and to calculate the network damage index of each fault area based on the initial score, base station value coefficient and scenario value coefficient. The emergency task priority of each fault area is determined based on the ranking order of the network damage index. The emergency response level determination module is used to calculate the emergency index based on the key indicators corresponding to each fault area, and to determine the response level of the fault area based on the calculated emergency index. The emergency resource demand matching module is used to match and analyze the key indicators corresponding to each fault area with the historical task database data, and determine the type and quantity of emergency resources required for each fault area based on the analysis results. The approval and sending module is used to send approval requests to the terminals of relevant emergency personnel based on the priority of emergency tasks and the type and quantity of emergency resources corresponding to each fault area.

[0008] Another technical solution of the present invention to solve the above-mentioned technical problems is as follows: a communication failure emergency resource allocation device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the communication failure emergency resource allocation method as described above.

[0009] Another technical solution of the present invention to solve the above-mentioned technical problems is as follows: a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the communication failure emergency resource allocation method as described above.

[0010] The beneficial effects of this invention are: it constructs a full-process framework for emergency resource allocation in communication failures, from fault area identification and key indicator collection to priority determination, response level judgment, resource matching, and finally to the sending of approval requests. It breaks through the limitations of traditional reliance on manual experience and static plans, and connects each link through standardized steps, realizing the systematization and standardization of emergency dispatch in multi-fault area scenarios, and effectively improving the overall efficiency of emergency response to large-scale communication failures. Attached Figure Description

[0011] Figure 1 A flowchart illustrating the emergency resource allocation method for communication failures provided in an embodiment of the present invention; Figure 2 This is a functional module block diagram of the communication failure emergency resource allocation device provided in an embodiment of the present invention; Figure 3 A flowchart for emergency priority scheduling of large-scale communication failures provided in an embodiment of the present invention. Detailed Implementation

[0012] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0013] like Figure 1 As shown in the figure, this embodiment of the invention provides a method for emergency resource allocation in case of communication failure, including the following steps: S1. Determine multiple fault areas where large-scale communication failures have occurred by setting fault base station judgment thresholds, and call the operator interface to collect key indicators corresponding to each fault area. S2. Calculate the initial score based on the key indicators corresponding to each fault area, and calculate the network damage index of each fault area based on the initial score, base station value coefficient and scenario value coefficient. Determine the priority of emergency tasks for each fault area based on the ranking order of the network damage index. S3. Calculate the emergency index based on the key indicators corresponding to each fault area, and determine the response level of the fault area based on the calculated emergency index. S4. Match and analyze the key indicators corresponding to each fault area with the historical task database data, and determine the type and quantity of emergency resources required for each fault area based on the analysis results. S5. Send approval requests to the terminals of relevant emergency personnel based on the priority of emergency tasks and the type and quantity of emergency resources corresponding to each fault area.

[0014] Specifically, in S1: S1.1 Data Monitoring: Based on the criterion that the number of faulty base stations in a single township exceeds 30, the number of faulty base stations in each township is monitored, and it is found that large-scale communication failures have occurred in townships A, B, and C. S1.2 Key Indicator Acquisition: By calling the operator's interface, the following seven indicators are obtained, based on townships: number of faulty base stations (units), number of available base stations (units), number of shared available base stations (units), coverage area of ​​faulty base stations (square kilometers), duration of base station failure (minutes), number of affected users (units), and number of complaints (times).

[0015] In the above embodiments, by using the set fault base station judgment threshold, multiple areas where large-scale communication failures have occurred can be quickly and accurately identified. At the same time, by calling the operator interface, key indicators corresponding to each fault area can be efficiently collected, providing a reliable data foundation for subsequent analysis. This solves the problems of low efficiency and untimely acquisition of indicators in traditional manual fault area investigation.

[0016] The initial score is calculated based on key indicators, and then the network damage index is calculated by combining the base station value coefficient and the scenario value coefficient. The priority of emergency tasks is determined by ranking the index size, which no longer relies on human experience. This makes the priority determination more objective and scientific, avoids the unreasonable priority caused by subjective judgment in the traditional method, and ensures that emergency resources are tilted towards more critical areas.

[0017] By calculating the emergency index based on key indicators, and then determining the response level of the fault area, the severity of the fault can be quantitatively graded. This allows for more accurate matching of emergency response resources and measures at different levels, improving the targeting and effectiveness of emergency response compared to the traditional vague response level classification.

[0018] By matching and analyzing key indicators of the fault area with historical task database data, and making full use of historical experience, the type and quantity of emergency resources required for each fault area can be quickly and accurately determined. This solves the problems of blind allocation of resources and mismatch between resources and needs in traditional resource allocation, and improves resource utilization efficiency.

[0019] Based on emergency task priorities and resource needs, approval requests are sent to the terminals of relevant emergency personnel, making the approval process more standardized and efficient. This ensures that emergency resource allocation decisions can be quickly approved and executed, reducing delays in intermediate steps and improving the overall emergency response speed.

[0020] Preferably, the initial score is calculated based on the key indicators corresponding to each fault area, including: If the key indicator is a positive indicator and includes x sample values, let the maximum value be a and the minimum value be b, then the normalized result of the nth sample value is (na) / (ba). If the key indicator is a negative indicator and includes x sample values, let the maximum value be a and the minimum value be b, then the normalized result of the nth sample value is (bn) / (ba). The index sample proportion p of the nth sample under the key indicator is calculated using the index sample proportion formula. n The formula for the sample proportion of the indicator is: p n =n / (n1 + n2 + ... +nx), Where n1, n2 ... nx represent the normalized results of all sample values ​​under a certain key indicator; Using the entropy calculation formula and the indicator sample proportion p n Calculate the entropy value E of each key indicator. , Where x is the number of samples; Subtract the entropy value E of each key indicator from 1 to obtain the variation index of each key indicator. Divide the variation index of each key indicator by the sum of the variation indices of all key indicators to obtain the entropy weight of each key indicator. Multiply each normalized indicator value by its corresponding entropy weight, and then add all the products to obtain the initial score of the fault area.

[0021] In the above embodiments, the objectivity and accuracy of the initial score calculation are achieved through refined data processing and entropy weighting. First, differentiated normalization formulas are used for positive and negative key indicators to eliminate the influence of differences in indicator dimensions and data distribution. Second, entropy value calculation quantifies the information utility of the indicators, and the entropy weights obtained through the transformation of the variability index scientifically reflect the contribution of each indicator to the fault assessment, avoiding the arbitrariness of subjective weighting. This data-driven scoring method ensures the comparability and reliability of the basic assessment results for different fault areas, providing accurate data support for subsequent priority ranking.

[0022] Preferably, the network damage index for each fault area is calculated based on the initial score, base station value coefficient, and scenario value coefficient of each fault area, including: The base stations within the fault area are divided into i categories, denoted as follows: And assign a corresponding value index to each category, denoted as . For example, base stations within the fault area are divided into four categories: A, B, C, and D, with value indices of 4, 3, 2, and 1, respectively.

[0023] Let the total number of base stations of type j in the fault area be . The number of base stations of type j in the fault area is , The base station value coefficient J is calculated based on the base station value calculation formula, which is: , in, The sum of the values ​​of all faulty base stations within the fault area. The total value of all base stations within the fault area; The scenario corresponding to the fault area is divided into k value levels, denoted as L1, L2, ..., L. k And L1 > L2 > ... > L k Each scenario level is assigned a corresponding value index, denoted as W1, W2…W k W1 > W2 > ... > W k For example, scenarios are divided into three levels based on value, with value indices of 3, 2, and 1 respectively. Level 1 scenarios include hospitals, government service centers, etc.; Level 2 scenarios include schools, transportation hubs, business districts, etc.; and Level 3 scenarios include residential areas, etc.

[0024] Let F be the number of level m fault scenarios within the fault area. m Let m = 1, 2, ..., k, and the total number of scenarios at level m within the fault region be T. m , The scene value coefficient S is calculated based on the scene value calculation formula, which is: , in, This represents the sum of the values ​​of all failure scenarios within the failure area. The total value of all scenarios within the fault area; The network damage index of the faulty area is calculated by multiplying the initial score of the faulty area, the base station value coefficient, and the scenario value coefficient. Table 1 shows the base station value coefficient table. Table 1 Table 2 shows the scenario value coefficients, as shown in Table 2: Table 2 Next, the priority of emergency tasks for each fault area is determined based on the ranking of the various network damage indices.

[0025] Table 3 shows the emergency task priorities corresponding to the network damage index, as shown in Table 3: Table 3 In the above embodiments, a base station value coefficient and a scenario value coefficient are innovatively introduced, enabling a multi-dimensional quantitative assessment of the network damage index. At the base station level, the value coefficient is calculated by classifying and assigning values, combined with the proportion of faulty base stations, accurately capturing the differences in the impact of different types of base station faults. At the scenario level, the scenario value coefficient is calculated based on the value level and the distribution of fault scenarios, fully considering the social attributes and importance of the faulty area. The fusion calculation of these two factors with the initial score overcomes the limitations of single-indicator assessment, enabling the network damage index to comprehensively reflect the "technical damage level" and "social impact weight" of the fault, providing a more practical basis for the scientific prioritization of emergency tasks.

[0026] Preferably, an emergency index is calculated based on key indicators corresponding to each fault area, and the response level of the fault area is determined based on the calculated emergency indexes, including: The emergency index is calculated based on the emergency index calculation formula, combined with the entropy weights of the key indicators after summing for each fault area and the normalized values ​​of each indicator after summing. This yields the emergency index corresponding to the key indicators for each fault area. The emergency index calculation formula is as follows: , Where EI is the emergency response index, u is the total number of key indicators in the fault area, and x is the emergency response index. i Let i be the normalized value of the i-th key indicator. Let be the entropy weight of the i-th key indicator, and D be the correction factor; For example, the correction factor D is determined based on the time and scenario of the event. It is 1.2 during peak hours on weekdays (7:00-9:00, 17:00-20:00), 1.5 during major event security periods, 1.3 during orange weather warning periods, 1.4 during red weather warning periods, and 1.5 when a major disaster has occurred. The maximum value corresponding to the above scenarios is taken as the D value.

[0027] The calculated emergency index EI is compared with the first threshold. If the emergency index EI is less than the first threshold, the response level is normal. If the emergency index EI is between the first and second thresholds, the response level is Level 1. If the emergency index EI is between the second and third thresholds, the response level is Level 2. If the emergency index EI is greater than the third threshold, the response level is Level 3.

[0028] Specifically, an "Emergency Index" is defined as follows: the Emergency Index for a given event is equal to the sum of seven normalized indicators multiplied by their respective entropy weights, then multiplied by a correction factor D (considering the time and scenario of the event: 1.2 for weekday peak hours (7:00-9:00, 17:00-20:00), 1.5 for major event security, 1.3 for orange weather warnings, 1.4 for red weather warnings, and 1.5 for events involving major disasters; the maximum value is used). The magnitude of the "Emergency Index" determines whether an emergency response is needed. For example, an EI less than 60 is considered normal; an EI between 60 and 75 indicates a Level 1 response; an EI between 75 and 85 indicates a Level 2 response; and an EI above 85 indicates a Level 3 response.

[0029] In the above embodiments, a tiered response mechanism based on an emergency index was constructed, achieving precision and differentiation in fault handling. By reusing the normalized values ​​of key indicators and entropy weights to calculate the emergency index, and introducing correction factors to adapt to different scenario characteristics, the consistency and flexibility of index calculation were ensured. Simultaneously, a response level of "normal-Level 1-Level 2-Level 3" was defined based on multiple thresholds, clarifying the handling standards for different fault severity levels. This quantitative tiered approach avoids the ambiguity and lag of traditional responses, matching the corresponding level of handling resources and processes according to the actual severity of the fault, thus improving the targeting and timeliness of emergency response.

[0030] Preferably, the key indicators corresponding to each fault area are matched and analyzed with historical task database data, and the types and quantities of emergency resources required for each fault area are determined based on the analysis results, including: The normalized data of u key indicators are denoted as indicator vectors. , where x i Let be the normalized value of the i-th indicator, and establish a standardized dataset according to the structure "Task ID - Indicator Vector - Resource Configuration Details", where the fault region indicator vector of each historical task is denoted as . j is the historical mission number. This is the normalized value of the i-th metric for the j-th task; The cosine similarity formula is used to calculate the similarity between the fault region indicator vector and the indicator vectors of each historical task. The cosine similarity formula is as follows: , in, The similarity value ranges from [0,1]. The closer the value is to 1, the more similar the features of the fault region indicator vector and the historical task indicator vector are. X is the indicator vector of the current fault region. j Let be the fault area index vector corresponding to the j-th task in the historical task database. Let X be the norm of the index vector. For index vector X j The 2-norm of the algorithm is given by u, where u is the total number of key indicators in the fault region. This algorithm can effectively measure the directional consistency of two vectors and is suitable for similarity judgment across multiple indicator dimensions.

[0031] The index vector X of the target fault region is sequentially compared with the index vectors X of all valid tasks in the historical task database. j Similarity calculations are performed to generate a similarity list of "historical task ID - similarity value". The g historical tasks with the highest similarity are selected from the similarity list as reference samples. From the selected reference samples, the configuration quantities of various emergency resources are extracted to form a resource configuration set. , where r jt Let be the quantity of resource type t in the j-th historical task.

[0032] Specifically, regarding resource requirements: the cosine similarity values ​​(a, b, c) for the seven key indicators of the three townships are calculated respectively. The most similar required resource types are then matched in the historical database. For example, township A needs 2 portable base stations, 3 large communication vehicles, 1 drone, and 15 emergency personnel; township B needs 1 portable base station, 1 large communication vehicle, and 8 emergency personnel; and township C needs 1 large communication vehicle and 4 emergency personnel.

[0033] Priority allocation: When allocating resources to a township (e.g., township A), first determine the level of resources to be used (city level → provincial level → provincial allocation → other provinces), and then select the resources closest to the township from the available resources at the same level. After completing the resource allocation for the township, allocate resources to the next township (e.g., township C, B) in the same way.

[0034] Approval Process: Initiate the approval process, which is then approved by management personnel.

[0035] Task assignment: Issue tasks to relevant personnel, including resource allocation, assembly and departure, and proceed to the site to carry out the tasks step by step.

[0036] In the above embodiments, a historical data matching strategy was employed to achieve efficient and accurate prediction of emergency resource needs. By matching the fault area indicator vector with the historical task database using cosine similarity, past cases with similar characteristics can be quickly located, fully utilizing historical handling experience. Simultaneously, resource allocation for reference samples is weighted using similarity as a weight, and corrected by factors such as current resource status. This avoids blind resource allocation and solves the imbalance problem of "shortage in high-demand areas and redundancy in low-demand areas." This historical data-driven resource matching method significantly improves the accuracy of determining resource types and quantities, reduces manual decision-making costs, and provides scientific support for the efficient scheduling of emergency resources.

[0037] like Figure 3 As shown, Figure 3 Flowchart for emergency priority scheduling of large-scale communication failures; This method is applicable to emergency dispatch scenarios involving large-scale communication failures. The method of this invention will be described below from the perspectives of three main entities: operators, systems, and emergency response teams.

[0038] 1. Operator segment: The operator is responsible for monitoring and detecting emergency events, and then transmitting the relevant information to the system.

[0039] At the same time, there is an approval process, and instructions will be issued after approval.

[0040] 2. System components: The system responds after receiving an emergency event from the operator.

[0041] Next, the scoring operation is performed. During the scoring process, the base station value coefficient and the scenario value coefficient are calculated separately.

[0042] Then, the network damage index is used to rank the tasks and determine the priority of emergency response.

[0043] Then, by calculating the cosine similarity, the emergency resource requirements for the fault area are obtained.

[0044] 3. Emergency Response Team Phase: The emergency response team executes the corresponding emergency tasks based on the emergency task priorities determined by the system and the calculated resource requirements. The process is completed after the task is executed.

[0045] like Figure 2 As shown, this embodiment of the invention also provides a communication failure emergency resource allocation device, comprising: The key indicator collection module is used to identify multiple fault areas where large-scale communication failures have occurred by using the set fault base station judgment threshold, and to call the operator interface to collect the key indicators corresponding to each fault area. The emergency task priority calculation module is used to calculate the corresponding initial score based on the key indicators of each fault area, and to calculate the network damage index of each fault area based on the initial score, base station value coefficient and scenario value coefficient. The emergency task priority of each fault area is determined based on the ranking order of the network damage index. The emergency response level determination module is used to calculate the emergency index based on the key indicators corresponding to each fault area, and to determine the response level of the fault area based on the calculated emergency index. The emergency resource demand matching module is used to match and analyze the key indicators corresponding to each fault area with the historical task database data, and determine the type and quantity of emergency resources required for each fault area based on the analysis results. The approval and sending module is used to send approval requests to the terminals of relevant emergency personnel based on the priority of emergency tasks and the type and quantity of emergency resources corresponding to each fault area.

[0046] Preferably, the initial score is calculated based on the key indicators corresponding to each fault area, including: If the key indicator is a positive indicator and includes x sample values, let the maximum value be a and the minimum value be b, then the normalized result of the nth sample value is (na) / (ba). If the key indicator is a negative indicator and includes x sample values, let the maximum value be a and the minimum value be b, then the normalized result of the nth sample value is (bn) / (ba). The index sample proportion p of the nth sample under the key indicator is calculated using the index sample proportion formula. n The formula for the sample proportion of the indicator is: p n =n / (n1 + n2 + ... +nx), Where n1, n2 ... nx represent the normalized results of all sample values ​​under a certain key indicator; Using the entropy calculation formula and the indicator sample proportion p n Calculate the entropy value E of each key indicator. , Where x is the number of samples; Subtract the entropy value E of each key indicator from 1 to obtain the variation index of each key indicator. Divide the variation index of each key indicator by the sum of the variation indices of all key indicators to obtain the entropy weight of each key indicator. Multiply each normalized indicator value by its corresponding entropy weight, and then add all the products to obtain the initial score of the fault area.

[0047] Preferably, the network damage index for each fault area is calculated based on the initial score, base station value coefficient, and scenario value coefficient of each fault area, including: The base stations within the fault area are divided into i categories, denoted as follows: And assign a corresponding value index to each category, denoted as . , Let the total number of base stations of type j in the fault area be . The number of base stations of type j in the fault area is , The base station value coefficient J is calculated based on the base station value calculation formula, which is: , in, The sum of the values ​​of all faulty base stations within the fault area. The total value of all base stations within the fault area; The scenario corresponding to the fault area is divided into k value levels, denoted as L1, L2, ..., L. k And L1 > L2 > ... > L k Each scenario level is assigned a corresponding value index, denoted as W1, W2…W k W1 > W2 > ... > W k ; Let F be the number of level m fault scenarios within the fault area. m Let m = 1, 2, ..., k, and the total number of scenarios at level m within the fault region be T. m , The scene value coefficient S is calculated based on the scene value calculation formula, which is: , in, This represents the sum of the values ​​of all failure scenarios within the failure area. The total value of all scenarios within the fault area; The network damage index of the faulty area is obtained by multiplying the initial score of the faulty area, the base station value coefficient, and the scene value coefficient.

[0048] This invention also provides a communication failure emergency resource allocation device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the communication failure emergency resource allocation method as described above.

[0049] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the communication failure emergency resource allocation method described above.

[0050] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0051] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described apparatus and unit can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0052] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0053] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of the present invention, depending on actual needs.

[0054] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0055] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for communication failure emergency resource allocation, characterized in that, The method comprises the following steps: determining a plurality of failure areas of a scale communication failure through a set failure base station judgment threshold, and calling an operator interface to collect key indicators corresponding to each failure area; calculating an initial score corresponding to each failure area based on the key indicators corresponding to each failure area, and respectively calculating a network damage index of each failure area based on the initial score of each failure area, a base station value coefficient and a scene value coefficient, and determining an emergency task priority of each failure area based on the size ranking order of each network damage index; calculating an emergency index based on the key indicators corresponding to each failure area, and determining a response level of the failure area based on each calculated emergency index; matching and analyzing the key indicators corresponding to each failure area with historical task library data respectively, and determining the type and quantity of emergency resources required by each failure area based on the analysis results; sending an approval request to relevant emergency personnel terminals based on the emergency task priority of each failure area and the type and quantity of emergency resources.

2. The method of claim 1, wherein, calculating an initial score corresponding to each failure area based on the key indicators corresponding to each failure area, comprising: if the key indicator is a positive indicator and includes x sample values, and the maximum value is a and the minimum value is b, then the normalization result of the nth sample value is (n-a) / (b-a), if the key indicator is a negative indicator and includes x sample values, and the maximum value is a and the minimum value is b, then the normalization result of the nth sample value is (b-n) / (b-a); The index sample proportion p of the n th sample under the key index is calculated by an index sample proportion formula n , and the index sample proportion formula is p n = n / (n1 + n2 +... + nx), wherein n1, n2,..., and nx represent the normalization results of all sample values under a certain key indicator; The entropy value E of each key indicator is calculated by the entropy value calculation formula and the indicator sample proportion p n The entropy value E of each key indicator is calculated by the entropy value calculation formula and the indicator sample proportion p ， wherein x is the number of samples; subtracting the entropy value E of each key indicator from 1 to obtain the variation index of each key indicator, dividing the variation index of each key indicator by the sum of the variation indexes of all key indicators to obtain the entropy weight of each key indicator, multiplying each normalized indicator value by its corresponding entropy weight, and adding all the products to obtain the initial score of the failure area.

3. The method of claim 1, wherein, calculating a network damage index of each failure area based on the initial score of each failure area, a base station value coefficient and a scene value coefficient, comprising: The base stations in the fault area are divided into i categories, respectively denoted as , and each category is assigned a corresponding value index, respectively denoted as , Let the total number of base stations of the jth type in the failure area be , and the number of base stations of the jth type in the failure area be , calculating the base station value coefficient J based on a base station value calculation formula, wherein the base station value calculation formula is: ， wherein, is the sum of the values of all faulty base stations in the faulty area, is the total value of all base stations in the faulty area; The scene corresponding to the fault area is divided into k value levels, respectively denoted as L1, L2…L k , and L1>L2>…>L k Each scene level is assigned a corresponding value index, respectively denoted as W1, W2…W k , W1>W2>…>W k ; Let the number of the mth level fault scenarios in the fault area be F m , m = 1, 2, …, k, and the total number of the mth level fault scenarios in the fault area be T m , calculating the scene value coefficient S based on a scene value calculation formula, wherein the scene value calculation formula is: ， wherein, is the sum of the values for all failure scenarios within the failure region, is the total value for all scenarios within the failure region; multiplying the initial score of the failure area, the base station value coefficient and the scene value coefficient to obtain the network damage index of the failure area.

4. The method of claim 2, wherein, calculating an emergency index based on the key indicators corresponding to each failure area, and determining a response level of the failure area based on each calculated emergency index, comprising: calculating the emergency index based on an emergency index calculation formula combined with the entropy weight of the summed key indicators of each failure area and the summed normalized indicator values, to obtain the emergency index corresponding to the key indicators corresponding to each failure area, wherein the emergency index calculation formula is: ， wherein EI is an emergency index, u is the total number of key indicators of the fault area, x i is the normalized value of the i-th key indicator, is the entropy weight of the i-th key indicator, and D is a correction factor. The calculated emergency index EI is compared with the first threshold value, if the emergency index EI is less than the first threshold value, the response level is normal, if the emergency index EI is between the first threshold value and the second threshold value, the response level is a first response, if the emergency index EI is between the second threshold value and the third threshold value, the response level is a second response, and if the emergency index EI is greater than the third threshold value, the response level is a third response.

5. The method of claim 2, wherein, The key indicators corresponding to each fault area are respectively matched and analyzed with historical task library data, and the type and quantity of emergency resources required by each fault area are determined based on the analysis results, including: The normalized u-term key indicator data is denoted as an indicator vector , wherein x i is the normalized value of the i-th indicator, and a standardized dataset is established in the structure of "task ID-indicator vector-resource configuration details", wherein the failure area indicator vector of each historical task is denoted as , j is the historical task serial number, is the normalized value of the i-th indicator of the j-th task. The cosine similarity formula is used to calculate the similarity between the fault area indicator vector and each historical task indicator vector, and the cosine similarity formula is: ， wherein, is a similarity value, the value range is [0, 1], the value is closer to 1, indicating that the features of the fault region index vector and the historical task index vector are more similar, X is the index vector of the current fault region, X j is the index vector of the fault region corresponding to the jth task in the historical task library, is the norm of the index vector X, is the 2-norm of the index vector X j , u is the total number of key indexes of the fault region; The index vector X of the target fault area is sequentially compared with the index vectors X of all valid tasks in the historical task library j The similarity list of "historical task ID-similarity value" is generated by performing similarity calculation, g historical tasks with the highest similarity are selected from the similarity list as reference samples, and the configuration quantities of multiple emergency resources are extracted from the selected reference samples to form a resource configuration set , wherein r jt is the number of the tth resource in the jth historical task.

6. A communication fault emergency resource allocation apparatus, characterized in that, Including: The key indicator collection module is used to determine a plurality of fault areas of the scale communication failure by setting a fault base station judgment threshold value, and to collect the key indicators corresponding to each fault area by calling an operator interface; The emergency task priority calculation module is used to calculate the initial score corresponding to each fault area based on the key indicators corresponding to each fault area, and to calculate the network damage index of each fault area based on the initial score of each fault area, the base station value coefficient and the scene value coefficient, respectively, and to determine the emergency task priority of each fault area based on the size ranking order of each network damage index; The emergency response level determination module is used to calculate the emergency index based on the key indicators corresponding to each fault area, and to determine the response level of the fault area based on the calculated emergency index of each fault area; The emergency resource demand matching module is used to match and analyze the key indicators corresponding to each fault area with historical task library data, respectively, and to determine the type and quantity of emergency resources required by each fault area based on the analysis results; The approval sending module is used to send an approval request to the related emergency personnel terminal based on the emergency task priority and the type and quantity of emergency resources corresponding to each fault area.

7. The apparatus of claim 6, wherein, The initial score corresponding to each fault area is calculated based on the key indicators, including: If the key indicator is a positive indicator and includes x sample values, and the maximum value is a and the minimum value is b, the normalization result of the nth sample value is (n-a) / (b-a), If the key indicator is a negative indicator and includes x sample values, and the maximum value is a and the minimum value is b, the normalization result of the nth sample value is (b-n) / (b-a); The index sample proportion p of the n th sample under the key index is calculated by an index sample proportion formula n The index sample proportion formula is: p n = n / (n1 + n2 +... + nx), Where n1, n2,..., nx represent the normalization results of all sample values under a certain key indicator; The entropy value E of each key indicator is calculated by the entropy value calculation formula and the indicator sample proportion p n The entropy value E of each key indicator is calculated by the entropy value calculation formula and the indicator sample proportion p ， Where x is the number of samples; The entropy of each key indicator is obtained by subtracting 1 from the entropy value of each key indicator, the entropy weight of each key indicator is obtained by dividing the entropy of each key indicator by the sum of the entropy of all key indicators, and the initial score of the fault area is obtained by multiplying each normalized indicator value by its corresponding entropy weight and adding all the products.

8. The apparatus of claim 6, wherein, The network damage index of each fault area is calculated based on the initial score of each fault area, the base station value coefficient and the scene value coefficient, including: The base stations in the fault area are divided into i categories, respectively denoted as , and each category is assigned a corresponding value index, respectively denoted as , Let the total number of base stations of the jth type in the failure area be , and the number of base stations of the jth type in the failure area be , The base station value coefficient J is calculated based on a base station value calculation formula, which is: ， wherein, is the sum of the values of all faulty base stations in the faulty area, is the total value of all base stations in the faulty area; The scene corresponding to the fault area is divided into k value levels, respectively denoted as L1, L2…L k , and L1>L2>…>L k Each scene level is assigned a corresponding value index, respectively denoted as W1, W2…W k , W1>W2>…>W k ; Let the number of the mth level fault scenarios in the fault region be F m , m = 1, 2, …, k, and the total number of the mth level fault scenarios in the fault region be T m , The scene value coefficient S is calculated based on a scene value calculation formula, which is: ， wherein, is the sum of the values for all failure scenarios within the failure region, is the total value for all scenarios within the failure region; The network damage index of the fault area is calculated by multiplying the initial score of the fault area, the base station value coefficient and the scene value coefficient.

9. A communication fault emergency resource deployment apparatus, characterized by, The computer program is stored in the memory and executable on the processor, and the processor executes the computer program to implement the communication fault emergency resource allocation method according to any one of claims 1 to 6.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1-9. The computer program is stored in the memory and executable on the processor, and the processor executes the computer program to implement the communication fault emergency resource allocation method according to any one of claims 1 to 6.

Images