Emergency material distribution and treatment method, device, equipment and medium

Abstract

The invention relates to an emergency material distribution and treatment method and device, equipment and a medium, and the method comprises the steps: obtaining the spare part types of N emergency repair points, and obtaining the non-standard demand frequency of the N emergency repair points based on the spare part types; scene constraints are obtained, and feature vectors of each emergency repair point are constructed according to the non-standard demand frequency and the scene constraints; similarity clustering is carried out based on the feature vectors, and a space-similar point set is determined; calculating a comprehensive score of the target emergency repair point according to the space-similar point set, and determining a material distribution method according to the comprehensive score; and determining an evaluation period of each emergency repair point according to a material distribution method, and determining an inventory management method according to the evaluation period. The method has the effect of improving the material distribution and treatment accuracy.

Description

Technical Field

[0001] This invention belongs to the technical field of emergency material support, and in particular relates to a method, device, equipment and medium for the distribution and management of emergency materials. Background Technology

[0002] Currently, emergency material supply in scenarios such as power, transportation, and urban public safety generally adopts a ledger-based operational approach: maintaining material status through inbound and outbound documents, transfer records, and on-site inventory checks; allocating resources according to preset rules or experience thresholds; and temporarily weighting allocation based on region, priority, and historical consumption when an emergency occurs. To improve response efficiency, some practices introduce fixed allocation templates and periodic inventory checks, using site demand intensity and inventory turnover as key references, and combining geographical location and transportation accessibility to arrange batches and time limits.

[0003] Existing emergency material allocation and inventory management methods, which mainly rely on rule templates and periodic inventory checks, often suffer from inconsistencies in the caliber and timestamps of multiple source ledgers. This leads to the same event being counted repeatedly or omitted, thus affecting the judgment of demand intensity and inventory status. Allocation thresholds and templates are mostly statically configured, which are slow to respond to fluctuations in on-site operating conditions, pressure on delivery deadlines, and changes in the occupation of high-value materials, easily resulting in both local backlogs and shortages at key points. Reference sets are usually selected based on administrative regions or nearest neighbors by straight-line distance, which makes it difficult to reflect the true similarity of demand structure and accessibility, thereby weakening the effectiveness of statistical comparison. Incomplete or delayed feedback and inventory result recording after allocation execution cause the next round of calculations to use outdated parameters, resulting in supply and demand identification and instruction generation deviating from the actual situation on site.

[0004] The existing technical solutions mentioned above have the following drawbacks: due to inconsistent data standards and lagging rule updates, the existing rule template-driven and decentralized ledger governance methods have problems such as supply and demand identification deviations and allocation mismatches, so there is room for improvement. Summary of the Invention

[0005] The purpose of this invention is to provide an emergency material allocation and management method, device, equipment, and medium to solve the technical problems of supply and demand identification deviation and allocation mismatch caused by inconsistent data standards and lagging rule updates in existing rule template-driven and decentralized ledger management methods.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for the distribution and management of emergency supplies, the method comprising: Obtain the spare parts types of N emergency repair points, and obtain the non-standard demand frequency of N emergency repair points based on the spare parts types. The non-standard demand frequency represents the degree of demand for non-standard spare parts that do not conform to the standard models required by the emergency repair points. Obtain scenario constraints, and construct a feature vector for each emergency repair point based on the non-standard demand frequency and the scenario constraints; Similarity clustering is performed based on the feature vectors to determine a spatial set of similar points; Calculate the comprehensive score of the target emergency repair point based on the spatial-similar point set, and determine the material allocation method based on the comprehensive score; The assessment cycle for each emergency repair point is determined based on the material allocation method, and then the inventory management method is determined based on the assessment cycle.

[0007] By adopting the above technical solution, and by acquiring the spare parts types of N emergency repair points and obtaining the non-standard demand frequency of N emergency repair points based on the spare parts types, the degree of non-standard material usage at each repair point can be quantified with a unified standard, thus providing a reliable data foundation for subsequent differential analysis and resource allocation. By acquiring scenario constraints and constructing feature vectors for each emergency repair point based on non-standard demand frequency and scenario constraints, it is possible to simultaneously characterize demand-side anomalies and multi-dimensional constraints such as environment, timeliness, and value within the same feature space, thereby avoiding bias caused by single-indicator decisions. By standardizing the feature vectors and performing similarity clustering based on the standardization results, spatial-similar points can be determined. Sets can identify geographically similar and comparable reference groups while eliminating the influence of dimensions, thereby improving the relevance and feasibility of comparative analysis and mutual support decision-making. By calculating the comprehensive score of the target emergency repair point based on the spatial-similar point set and determining the material allocation method based on the comprehensive score, multi-dimensional features can be compressed into a single quantitative score, which can be used to distinguish different resource scenarios, thereby achieving automatic selection and priority ranking of material allocation rules. By determining the evaluation cycle of each emergency repair point based on the material allocation method and determining the inventory management method based on the evaluation cycle, the evaluation rhythm and allocation strategy can be linked and matched, thereby improving inventory turnover efficiency while meeting emergency support requirements.

[0008] In one example, the present invention can be further configured as follows: obtaining the spare parts types of N emergency repair points, and obtaining the non-standard demand frequencies of N emergency repair points based on the spare parts types, includes: Obtain the spare parts model and the corresponding required quantity for each of the aforementioned emergency repair points; According to the non-standard demand frequency formula The non-standard demand frequency fns for N emergency repair points is obtained by calculating the spare parts model and the required quantity. The number of emergency repair points, For spare parts types For spare parts type Standard storage model, For emergency repair points For spare parts type The demand quantity, For emergency repair points For spare parts type The required model This is an indicator function.

[0009] By adopting the above technical solution, by obtaining the spare parts model and corresponding demand quantity for each emergency repair point, and calculating the non-standard demand frequency fns for N emergency repair points based on the non-standard demand frequency formula, it is possible to accurately distinguish between standard and non-standard demands under the constraint of the standard model library and measure the degree of non-standardization in proportion form, thereby providing a refined basic quantitative indicator for subsequent risk identification and resource allocation based on non-standardization.

[0010] In one example, the present invention can be further configured as follows: the step of obtaining scenario constraints, constructing a feature vector for each emergency repair point based on the non-standard demand frequency and the scenario constraints, includes: Obtain multi-dimensional environmental factors, weight and combine these factors to generate an environmental difficulty coefficient E. i ; Obtain historical demand data for each of the aforementioned emergency repair points, calculate the median of the set of time thresholds from the initiation of the historical demand data to the delivery of the request, and normalize it to obtain the historical average demand urgency level Q. i ; The spare parts prices in the historical demand data are analyzed to calculate the total value of spare parts exceeding a preset value threshold. Then, the proportion K of high-value spare parts demand is determined based on the total spare parts value. i ; Based on the environmental difficulty coefficient of the emergency repair site, the historical average urgency of demand, the proportion of high-value spare parts demand, and the corresponding non-standard demand frequency f. nsi Construct the feature vector .

[0011] By adopting the above technical solution, the environmental difficulty coefficient Ei is generated by acquiring and weighting multi-dimensional environmental factors, the historical average demand urgency Qi and the proportion of high-value spare parts demand Ki are obtained by analyzing historical demand data, and a feature vector Vi=[fnsi,Ei,Qi,Ki] is constructed based on Ei, Qi, Ki and the corresponding non-standard demand frequency fnsi. This allows the complexity of the working environment, time urgency, capital occupation intensity and non-standard demand frequency to be included in a unified feature expression, thereby providing a multi-dimensional input that comprehensively reflects the risk characteristics and guarantee pressure of each emergency repair point for subsequent clustering and scoring.

[0012] In one example, the present invention can be further configured as follows: the step of performing similarity clustering based on the feature vector to determine the spatial-similar point set includes: The feature vectors of each emergency repair point are subjected to Z-score standardization to convert the data of each dimension into a preset normal distribution, and the standardization result is obtained. Based on the standardization results, the cluster profile coefficients for different cluster numbers K are calculated, so as to determine the optimal cluster number K according to the cluster profile coefficients. Based on the optimal number of clusters K, the standardized processing results are clustered using the K-Means algorithm to divide the N emergency repair points into K clusters. Based on the clustering results, the cluster to which the target emergency repair point belongs is determined. Within the cluster, neighboring emergency repair points that are geographically adjacent to the target emergency repair point or within a preset geographical range are obtained. The neighboring emergency repair points and the target emergency repair point are combined into the spatial-same-type point set.

[0013] By adopting the above technical solution, Z-score standardization is applied to the feature vectors of each emergency repair point, converting the data of each dimension into a preset normal distribution. This eliminates the influence of different feature dimensions and value ranges on distance measurement and clustering results, thereby improving the stability of similarity calculation and clustering. By calculating the clustering profile coefficient under different cluster numbers K based on the standardization results and determining the optimal cluster number K, the number of clusters more suitable for the current data structure can be adaptively selected, thus avoiding overly fine or coarse clustering caused by inappropriate cluster number selection. By using the K-Means algorithm to cluster under the optimal K value and dividing N emergency repair points into K clusters, site groups with similar demand patterns and scenario characteristics can be formed, thus providing a clear grouping basis for similar comparison and collaborative scheduling. By selecting emergency repair points based on geographical proximity within the target cluster according to the clustering results and combining them into a spatial-similar point set, spatial accessibility can be taken into account under the premise of feature similarity, thereby ensuring the accuracy and matching degree of subsequent reference groups.

[0014] In one example, the present invention can be further configured as follows: the step of calculating a comprehensive score for the target emergency repair point based on the spatial-similar point set, and determining a material allocation method based on the comprehensive score, includes: According to the preset scoring formula The comprehensive score Z of the target emergency repair point is obtained. i Where w1 and w2 are the weighting coefficients for non-standard demand frequency and environmental difficulty coefficient, respectively; Calculate the median and maximum comprehensive scores of all emergency repair points in the target emergency repair point space-similar point set, and determine the material allocation method based on the comprehensive scores, median, and maximum scores.

[0015] By adopting the above technical solution, and calculating the comprehensive score Zi of the target emergency repair point according to the preset scoring formula, the non-standard demand frequency and environmental difficulty coefficient can be combined into a single scoring index according to weights. This allows for a concise numerical reflection of the comprehensive degree of demand anomalies and environmental challenges during decision-making. By calculating the median and maximum comprehensive scores of each emergency repair point within the spatial-similar point set, and using the comprehensive score, median, and maximum score as the basis for determining the material allocation method, a group reference scale can be introduced while utilizing the absolute score of the target point. This achieves a balance between urgency and fairness among similar points in resource-limited scenarios.

[0016] In one example, the present invention can be further configured as follows: the method for determining the material allocation based on the comprehensive score, median, and maximum value includes: The comprehensive score is compared with the first preset threshold and the second preset threshold to identify the resource supply and demand status; If the comprehensive score is greater than or equal to the first preset threshold, the resource supply and demand status is determined to be sufficient. If the comprehensive score is greater than or equal to the maximum value, priority allocation is performed on the target emergency repair point and the allocation amount is set to the maximum expected demand amount. If the comprehensive score is less than the maximum value, materials are allocated to the target emergency repair point as needed. If the overall score is less than the first preset threshold and greater than or equal to the second preset threshold, the resource supply and demand status is determined to be resource shortage. If the overall score is greater than or equal to the median, priority allocation is performed to the target emergency repair point. If the overall score is less than the median, the target emergency repair point is allocated according to the standard procedure or the target emergency repair point is used as a resource output to provide support to other emergency repair points.

[0017] By adopting the above technical solutions, the resource supply and demand status can be identified by comparing the comprehensive score with the first and second preset thresholds. This allows continuous score intervals to be mapped to discrete states such as sufficient and scarce resources, thus providing clear criteria for switching allocation rules. When the comprehensive score is greater than or equal to the first preset threshold, a strategy can be selected between prioritizing the maximum expected demand and allocating on demand based on the relationship between the comprehensive score and the maximum value. This ensures sufficient protection for extremely high-risk points when resources are sufficient, while avoiding over-allocation to general points, thereby improving resource utilization efficiency. When the comprehensive score is between the first and second preset thresholds, the target emergency repair point can be prioritized, allocated according to standard, or act as a resource provider based on the relationship between the comprehensive score and the median. This enables tiered protection and orderly support for similar points under resource-scarce conditions, thereby enhancing the overall network's emergency resilience and coordination capabilities.

[0018] In one example, the present invention can be further configured as follows: determining the assessment period for each emergency repair point according to the material allocation method, and then determining the inventory management method according to the assessment period, includes: According to the material allocation method, the non-standard demand frequency of each emergency repair point in two adjacent assessment periods is obtained, the rate of change of the non-standard demand frequency is calculated, and the rate of change of the non-standard demand frequency of all emergency repair points is generated according to the spatial-similar point set to obtain the rate of change sequence. Calculate the coefficient of variation of the rate of change sequence. , where σ ΔF Let μ be the standard deviation of the rate of change series. ΔF The average value of the rate of change sequence; When the coefficient of variation is less than a preset consistency threshold, the evaluation period remains the preset evaluation period T. default When the coefficient of variation is greater than or equal to a preset consistency threshold, the evaluation period will be adjusted to... When the coefficient of variation is less than a preset consistency threshold and the average value of the rate of change sequence is less than a negative trend sensitivity threshold, the evaluation period will be adjusted to... , among which, T new For the new evaluation cycle, T min The minimum allowable evaluation period, β is the period reduction factor, and T max Maximum allowable evaluation period, γ increase This is the period amplification factor; When the new evaluation period is shorter than the preset evaluation period, a high-frequency monitoring mode is activated to continuously check the inventory status according to the new evaluation period and to manage the inventory collaboratively based on a spatial-similar point set. When the new evaluation period is longer than the preset evaluation period, a low-frequency optimization mode is activated to periodically check the inventory status according to the new evaluation period and to generate a procurement plan based on historical demand data as an inventory management method.

[0019] By adopting the above technical solution, and by obtaining the frequency of non-standard demand in two adjacent assessment cycles for each emergency repair point according to the material allocation method and calculating the rate of change, a rate of change sequence is generated within a spatial set of similar points. This dynamically characterizes the demand fluctuation characteristics of similar groups in the time dimension, thus providing a quantitative basis for adjusting the assessment cycle. By calculating the coefficient of variation (CV) of the rate of change sequence, the consistency and dispersion of demand changes at similar points can be measured, thereby identifying whether a stable assessment window should be used or whether the cycle needs to be adjusted. The assessment cycle is adjusted to T based on the coefficient of variation and the average value of the rate of change sequence under preset conditions. newIt can shorten the cycle when fluctuations are inconsistent and widen the cycle when the overall decline is consistent, thereby achieving adaptive adjustment of the assessment frequency to the business rhythm. By activating a high-frequency monitoring mode and coordinating inventory management when the new assessment cycle is shorter than the preset assessment cycle, and activating a low-frequency optimization mode and generating procurement pre-plans by periodic inventory counts when the new assessment cycle is longer than the preset assessment cycle, it can increase the monitoring and response frequency when demand is highly uncertain and reduce inventory count and replenishment costs when demand is relatively stable, thereby optimizing the investment of inventory management resources while ensuring emergency response.

[0020] In a second aspect, the present invention provides an emergency supplies distribution and management device, the device comprising: The spare parts frequency calculation module is used to obtain the spare parts types of N emergency repair points, and obtain the non-standard demand frequency of N emergency repair points based on the spare parts types. The non-standard demand frequency represents the degree of demand for non-standard spare parts that do not conform to the standard model required by the emergency repair points. The scene feature construction module is used to obtain scene constraints and construct a feature vector for each emergency repair point based on the non-standard demand frequency and the scene constraints. The clustering similarity analysis module is used to perform similarity clustering based on the feature vectors to determine the spatial set of similar points; The comprehensive scoring calculation module is used to calculate the comprehensive score of the target emergency repair point based on the spatial-similar point set, and to determine the material allocation method based on the comprehensive score. The cycle management optimization module is used to determine the assessment cycle of each emergency repair point according to the material allocation method, and then determine the inventory management method according to the assessment cycle.

[0021] By adopting the above technical solution, and by acquiring the spare parts types of N emergency repair points and obtaining the non-standard demand frequency of N emergency repair points based on the spare parts types, the degree of non-standard material usage at each repair point can be quantified with a unified standard, thus providing a reliable data foundation for subsequent differential analysis and resource allocation. By acquiring scenario constraints and constructing feature vectors for each emergency repair point based on non-standard demand frequency and scenario constraints, it is possible to simultaneously characterize demand-side anomalies and multi-dimensional constraints such as environment, timeliness, and value within the same feature space, thereby avoiding bias caused by single-indicator decisions. By standardizing the feature vectors and performing similarity clustering based on the standardization results, a spatial-similar point set can be determined. It can find reference groups with similar characteristics and geographical proximity while eliminating the influence of dimensions, thereby improving the pertinence and feasibility of comparative analysis and mutual support decision-making; by calculating the comprehensive score of the target emergency repair point based on the spatial-similar point set and determining the material allocation method based on the comprehensive score, it can compress multi-dimensional features into a single quantitative score and distinguish different resource scenarios accordingly, thereby realizing the automatic selection and priority ranking of material allocation rules; by determining the evaluation cycle of each emergency repair point based on the material allocation method and determining the inventory management method based on the evaluation cycle, it can link and match the evaluation rhythm with the allocation strategy, thereby improving inventory turnover and management costs while meeting emergency support requirements.

[0022] In a third aspect, the present invention provides an electronic device including a memory and a processor, wherein the memory stores a computer program, characterized in that the processor executes the computer program to implement the steps of the emergency material distribution and management method described above.

[0023] In a fourth aspect, the present invention provides a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the emergency material distribution and management method described above. Attached Figure Description

[0024] The accompanying drawings, which form part of this application, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings: Figure 1 This is a flowchart of an emergency supplies allocation and management method in an embodiment of the present invention; Figure 2 This is a structural block diagram of the emergency material distribution and management device according to an embodiment of the present invention; Figure 3 This is a structural block diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0025] The present invention will now be described in detail with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other.

[0026] The following detailed description is exemplary and intended to provide further detailed explanation of the invention. Unless otherwise specified, all technical terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used in this invention is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention.

[0027] Example 1 like Figure 1 As shown, this invention discloses a method for the distribution and management of emergency supplies, specifically including the following steps: S10: Obtain the spare parts types of N emergency repair points, and obtain the non-standard demand frequency of N emergency repair points based on the spare parts types. The non-standard demand frequency represents the degree of demand for non-standard spare parts that do not conform to the standard models required by the emergency repair points.

[0028] Specifically, under the premise of unified data standards, spare parts types of N emergency repair points are collected and organized. Spare parts models and their corresponding demand quantities from channels such as historical inbound and outbound records and on-site demand records are collected by emergency repair points. After data deduplication and field alignment are completed, the deviation between non-standard models and standard models is identified by spare parts type. The non-standard demand quantity and the total demand quantity are compared and the ratio is calculated in both the emergency repair point dimension and the overall dimension, so as to obtain the non-standard demand frequency corresponding to N emergency repair points.

[0029] S20: Obtain scenario constraints and construct feature vectors for each emergency repair point based on non-standard demand frequency and scenario constraints.

[0030] Specifically, based on obtaining the non-standard demand frequency, constraint information related to emergency scenarios is collected and organized. Data sources related to the working environment, time urgency, and spare parts value structure are standardized to ensure that scenario constraints match the non-standard demand frequency in terms of time, space, and coding dimensions. Then, at each emergency repair point dimension, the scenario constraint quantity and the corresponding non-standard demand frequency are combined into a multi-dimensional feature input to construct a feature vector for subsequent standardization processing and cluster analysis.

[0031] S30: Perform similarity clustering based on feature vectors to determine the spatial set of similar points.

[0032] Specifically, the feature vector set constructed from all emergency repair points is preprocessed, and each feature is standardized in terms of dimension to eliminate numerical scale differences caused by different units. Then, in the standardized feature space, appropriate similarity measures and clustering algorithms are selected to analyze the feature similarity relationship between emergency repair points. Combined with spatial geographical location constraints, a set of emergency repair points that are comparable to the target emergency repair point in both feature patterns and geographical location is selected from the clustering results to form a spatial-similar point set.

[0033] S40: Calculate the comprehensive score of the target emergency repair point based on the spatial set of similar points, and determine the material allocation method based on the comprehensive score.

[0034] Specifically, after determining the spatial set of similar points, the target emergency repair points are scored based on the relevant dimensions of each emergency repair point in the feature vector. Core indicators such as non-standard demand frequency and environmental difficulty are linearly combined according to weights to obtain a comprehensive score in the form of a single scalar. Based on this, combined with the corresponding threshold judgment rules, the comprehensive score is mapped to a specific material allocation method category, providing a basis for the subsequent generation of material allocation strategies for different resource states.

[0035] S50: Determine the assessment cycle for each emergency repair point based on the material allocation method, and then determine the inventory management method based on the assessment cycle.

[0036] Specifically, after mapping the comprehensive score to a specific material allocation method, the demand fluctuation of each emergency repair point is assessed based on the adopted material allocation method. Combining the characteristics of the change in non-standard demand frequency in adjacent historical assessment periods, the length of the assessment period is adaptively adjusted. This allows the assessment period to be shortened to increase the monitoring frequency when demand fluctuations are large or inconsistent, and the assessment period to be appropriately lengthened when demand changes are relatively consistent or the trend is clear. Different inventory management models are matched under the finally determined assessment period scale, thereby dynamically configuring inventory management in the time dimension.

[0037] In one embodiment, step S10, namely obtaining the spare parts types of N emergency repair points and obtaining the non-standard demand frequencies of N emergency repair points based on the spare parts types, includes: S11: Obtain the spare parts model and the corresponding required quantity for each emergency repair point.

[0038] Specifically, the spare parts demand data of each emergency repair point is parsed to extract the spare parts model and quantity fields related to the demand. Records from different demand sources within the same emergency repair point are merged by time, equipment or work order. Missing or conflicting model information is corrected and completed to form a structured dataset, so that the spare parts model and corresponding demand quantity of each emergency repair point are clearly expressed under the same structure.

[0039] S12: Based on the non-standard demand frequency formula Calculations were performed on the spare parts models and required quantities to obtain the non-standard demand frequencies fns for N emergency repair points, where, The number of emergency repair points, For spare parts types For spare parts type Standard storage model, For emergency repair points For spare parts type The demand quantity, For emergency repair points For spare parts type The required model This is an indicator function.

[0040] Specifically, based on the obtained spare parts model and required quantity, the corresponding spare parts type t and emergency repair point identifier i are determined for each requirement record, and the standard stored model corresponding to spare parts type t is obtained by calling the preset standard model library. For each record, determine the actual required model m. i,t Compared with standard models Check for consistency and construct an indicator function. ,when The indicator function is set to 1 if the time condition is met, and 0 otherwise, the formula is then followed. The required number of all emergency repair points, d i,t By performing summation and normalization operations, the numerator is summed for the demand quantities corresponding to non-standard models, and the denominator is summed for the total demand quantities, ultimately yielding the overall non-standard demand frequency f for the N emergency repair points. ns .

[0041] In one embodiment, in step S20, namely obtaining scenario constraints, a feature vector for each emergency repair point is constructed based on the frequency of non-standard demand and scenario constraints, including: S21: Obtain multi-dimensional environmental factors, weight and combine these factors, and generate an environmental difficulty coefficient E. i .

[0042] Specifically, the system acquires multi-dimensional environmental factors such as nighttime operations, severe weather, lighting conditions, suddenness of events, and geographical accessibility. It then assigns raw scores to these environmental factors across different dimensions and normalizes the scores to determine emergency repair points. In the Ratings across all dimensions The environmental difficulty coefficient of the target point is then obtained by summing the weight vectors. Where M is the number of environmental dimensions involved in the calculation, and wj is the weight of the j-th dimension, satisfying the following conditions: .

[0043] S22: Obtain historical demand data for each emergency repair point, calculate the median of the time threshold set from the initiation of historical demand data to the delivery of the request, and normalize it to obtain the historical average demand urgency level Q. i .

[0044] Specifically, the historical demand records of each emergency repair point are screened and organized to obtain the time difference between the initiation of each historical demand and the delivery of the demand. This time difference is used to form a time threshold set, denoted as T. i Let median(T) be the set of time intervals for repair point i. i Let be the median of all historical demand time thresholds for emergency repair point i, and let min(T) and max(T) be the minimum and maximum time thresholds for all emergency repair points, respectively. Then, calculate the historical average demand urgency level. .

[0045] S23: Analyze the spare parts prices based on historical demand data, calculate the total value of spare parts exceeding a preset value threshold, and then determine the proportion K of high-value spare parts demand based on the total spare parts value. i .

[0046] Specifically, the spare parts prices in the historical demand records of each emergency repair point are compiled, and prices in different currencies and with different effective dates are converted and aligned to a unified currency and a unified price effective standard. At the site level, a total spare parts set P is determined, and the set of spare parts whose unit price exceeds a preset percentile threshold is denoted as P. high The proportion of demand for high-value spare parts is obtained by calculating the value(p) of two sets of spare parts and then comparing the values ​​of the two sets. , where P all This is a collection of all required spare parts.

[0047] S24: Based on the environmental difficulty coefficient of the emergency repair site, the historical average urgency of demand, the proportion of high-value spare parts demand, and the corresponding frequency of non-standard demand f nsi Construct feature vectors .

[0048] Specifically, for different emergency repair points, from the non-standard demand frequency f ns Extract the non-standard demand frequency f of the current emergency repair point. nsi and f nsi The environmental difficulty coefficient, historical average demand urgency, and proportion of high-value spare parts demand are uniformly mapped in terms of fields and order, and the four scalars are combined into a feature vector in a preset order. This ensures that the meaning of each dimension remains consistent across different emergency repair points, so that subsequent standardization and cluster analysis can perform dimension-by-dimensional calculations on the features.

[0049] In one embodiment, step S30, namely, performing similarity clustering based on feature vectors to determine the spatial set of similar points, includes: S31: Perform Z-score standardization on the feature vectors of each emergency repair point, converting the data of each dimension into a preset normal distribution to obtain the standardization result.

[0050] Specifically, after obtaining the feature vector of each emergency repair point, the mean and standard deviation of the entire sample of each dimension are calculated. The Z-score standardization formula is used to transform each value in the dimension, that is, the original value is subtracted from the mean of the dimension and divided by the standard deviation of the dimension. The transformed result is used as the new feature value, so that the feature values ​​of each dimension as a whole satisfy the normal distribution assumption of a mean of 0 and a standard deviation of 1, thereby obtaining a new feature vector set containing all emergency repair points, which is used as the standardization result.

[0051] S32: Based on the standardized processing results, calculate the cluster profile coefficients for different cluster numbers K, so as to determine the optimal cluster number K based on the cluster profile coefficients.

[0052] Specifically, based on the standardized processing results, a set of candidate cluster numbers K values ​​are pre-set. For each candidate K value, a clustering algorithm is called to generate the corresponding clustering partitioning result. Then, the silhouette coefficient of each sample under this partition is calculated. The silhouette coefficients of all samples are averaged to obtain the average silhouette coefficient under this K value. The average silhouette coefficients corresponding to different K values ​​are compared, and the K with the largest average silhouette coefficient is selected as the optimal number of clusters K. For example, when K=3, the average silhouette coefficient is 0.6, when K=4, it is 0.55, and when K=5, it is 0.5. Therefore, K=3 is determined to be the optimal number of clusters.

[0053] S33: Based on the optimal number of clusters K, the standardized processing results are clustered using the K-Means algorithm to divide the N emergency repair points into K clusters.

[0054] Specifically, the K-Means algorithm is run with the optimal number of clusters K. K points are randomly selected from the standardized feature vectors as initial centroids. The Euclidean distance from each point to each centroid is calculated, and each point is assigned to the cluster to which the nearest centroid belongs. The centroid of each cluster is then updated with the assignment results. The assignment and update are repeated until the centroid no longer changes significantly or the maximum number of iterations is reached. Finally, the cluster assignment result of each site is obtained.

[0055] S34: Determine the cluster to which the target emergency repair point belongs based on the clustering results, obtain the neighboring emergency repair points that are geographically adjacent to the target emergency repair point or within a preset geographical range within the cluster, and combine the neighboring emergency repair points with the target emergency repair point into a spatial-same-type point set.

[0056] Specifically, after obtaining the cluster label, the cluster identifier of the target emergency repair point is first queried, and all other emergency repair points that have been classified into the same cluster are enumerated within that cluster. Then, geographic information data is called to obtain the geographic coordinates or distance information between these emergency repair points and the target emergency repair point. According to the preset geographic proximity judgment rules, emergency repair points that are geographically adjacent or located within the preset geographic range of the target emergency repair point are selected. The selected neighboring emergency repair points are collected together with the target emergency repair point to form a spatial-same-category point set containing the target emergency repair point and its geographically adjacent points in the same cluster.

[0057] In one embodiment, step S40, namely calculating the comprehensive score of the target emergency repair point based on the spatial-similar point set, and determining the material allocation method based on the comprehensive score, includes: S41: Calculate the score according to the preset scoring formula. The comprehensive score Z of the target emergency repair point was obtained. i Where w1 and w2 are the weighting coefficients for non-standard demand frequency and environmental difficulty coefficient, respectively.

[0058] Specifically, when calculating the comprehensive score, the non-standard demand frequency f of the target emergency repair point is read. nsi and environmental difficulty coefficient E i Load the preset weight coefficients w1 and w2, and calculate the score according to the formula. Perform a weighted summation operation to obtain the comprehensive score Zi of the target emergency repair point.

[0059] S42: Calculate the median and maximum of the comprehensive scores of all emergency repair points in the target emergency repair point space-similar point set, and determine the material allocation method based on the comprehensive scores, median and maximum values.

[0060] Specifically, after obtaining the comprehensive score of the target emergency repair point, the comprehensive score calculation process is repeated for each emergency repair point in its spatial-similar point set to obtain a comprehensive score sequence for all emergency repair points in that set. This score sequence is then sorted by numerical value, and the median is calculated as a representative indicator of central tendency. Simultaneously, the maximum value in the sequence is obtained as the reference value for the highest comprehensive score in that set. For example, if the target emergency repair point A is assigned to a spatial-similar point set containing points A, B, C, and D, with preset weights w1=0.7 and w2=0.3, then point A's score is Z. A =0.7×0.15+0.3×0.80=0.345, the score for point B is Z. B =0.7×0.10+0.3×0.60=0.250, the score for point C is Z. C =0.7×0.20+0.3×0.90=0.410, the score for point D is Z. D =0.7×0.18+0.3×0.70=0.336. The comprehensive score set of this set is {0.345,0.250,0.410,0.336}. The median is calculated to be 0.341 and the maximum value is 0.410. The maximum value represents the most extreme and riskiest demand situation in this similar group, which is used to set the upper limit of protection when resources are sufficient. The median represents the typical risk level of this group, which is used as the baseline for priority allocation when resources are scarce. By comparing the score of the target point with the median and the maximum value, the allocation decision that best suits the global resources is automatically made.

[0061] In one embodiment, step S42, namely determining the material allocation method based on the comprehensive score, median, and maximum value, includes: S421: Compare the comprehensive score with the first preset threshold and the second preset threshold to identify the resource supply and demand status.

[0062] Specifically, when determining the method of material allocation, the comprehensive score Z of the target emergency repair point will be used. i Compare the values ​​with the first preset threshold and the second preset threshold, when Z i When the value is greater than or equal to the first preset threshold, or between the first preset threshold and the second preset threshold, or lower than the second preset threshold, it corresponds to different resource supply and demand status categories. This comparison process completes the mapping from continuous score values ​​to discrete resource status identifiers, laying the foundation for subsequent invocation of corresponding allocation rules based on status.

[0063] S422: If the comprehensive score is greater than or equal to the first preset threshold, the resource supply and demand status is determined to be sufficient. If the comprehensive score is greater than or equal to the maximum value, priority allocation is performed to the target emergency repair point and the allocation amount is set to the maximum expected demand. If the comprehensive score is less than the maximum value, materials are allocated to the target emergency repair point as needed.

[0064] Specifically, in scenarios where the comprehensive score is greater than or equal to a first preset threshold, the target emergency repair point is determined to be in a resource-sufficient state. In this state, the comprehensive score of the target emergency repair point is further compared with the maximum value of the comprehensive score of the spatial-similar point set. When Z... i When Z is greater than or equal to this maximum value, the target emergency repair point is identified as the point with the most prominent demand and environmental pressure in the set, and priority allocation is performed on it with the material allocation quantity set to the pre-assessed maximum expected demand. i When the amount is less than the maximum value, materials are still allocated to the target emergency repair point under the condition of sufficient resources. However, the allocation amount is determined on demand according to the current demand and inventory constraints, so as to take into account the needs of other points under the premise of sufficient resources.

[0065] S423: If the comprehensive score is less than the first preset threshold and greater than or equal to the second preset threshold, the resource supply and demand status is determined to be resource shortage. If the comprehensive score is greater than or equal to the median, priority allocation is performed to the target emergency repair point. If the comprehensive score is less than the median, the target emergency repair point is allocated according to the standard procedure or the target emergency repair point is used as a resource output to provide support to other emergency repair points.

[0066] Specifically, in scenarios where the comprehensive score is less than a first preset threshold but greater than or equal to a second preset threshold, the target emergency repair point is determined to be in a resource-scarce state. In this state, the comprehensive score of the target emergency repair point is further compared with the median of the comprehensive score of the spatial-similar point set. When Z... i When Z is greater than or equal to the median, the target emergency repair point is identified as a priority target under stress conditions, and a priority allocation strategy is implemented for it. i When the score is less than the median, the target emergency repair point is considered to be under relatively low pressure. It is then allocated materials according to standard procedures. Alternatively, if necessary, the emergency repair point can be configured as a resource provider to provide material support to other target emergency repair points with higher comprehensive scores. This allows for the adjustment and support between similar points under stress.

[0067] In one embodiment, step S50 involves determining the assessment period for each emergency repair point based on the material allocation method, and then determining the inventory management method based on the assessment period, including: S51: Based on the material allocation method, obtain the non-standard demand frequency of each emergency repair point in two adjacent assessment periods, calculate the rate of change of the non-standard demand frequency, and generate the rate of change of the non-standard demand frequency of all emergency repair points based on the spatial-similar point set, thus obtaining the rate of change sequence.

[0068] Specifically, while implementing the material allocation method, the non-standard demand frequency of each emergency repair point in two adjacent assessment cycles is extracted. The non-standard demand frequency of the current cycle is compared with that of the previous cycle. The change rate of the non-standard demand frequency of each emergency repair point is calculated according to the preset change rate calculation method. The change rate values ​​of all emergency repair points are summarized within the scope of the spatial-similar point set. These change rates are arranged in the order of emergency repair points to form a change rate sequence, providing input data for subsequent statistical analysis and assessment cycle adjustment.

[0069] S52: Calculate the coefficient of variation of the rate of change series. , where σ ΔF Let μ be the standard deviation of the rate of change series. ΔF This is the average value of the rate of change sequence.

[0070] Specifically, after obtaining the rate of change sequence, the average value μ of the sequence is calculated. ΔF and standard deviation σ ΔF Then, according to the coefficient of variation formula The calculation is performed to process the average value in absolute value form to avoid the instability of the denominator caused by the average value approaching zero, and the coefficient of variation (CV) is obtained to measure the degree of dispersion and consistency of the rate of change within a spatial set of similar points.

[0071] S53: When the coefficient of variation is less than the preset consistency threshold, the evaluation period is kept at the preset evaluation period T. default When the coefficient of variation is greater than or equal to the preset consistency threshold, the evaluation period will be adjusted to... When the coefficient of variation is less than the preset consistency threshold and the average value of the rate of change sequence is less than the negative trend sensitivity threshold, the evaluation period will be adjusted to... , among which, T new For the new evaluation cycle, T min The minimum allowable evaluation period, β is the period reduction factor, and T max Maximum allowable evaluation period, γ increase This is the period amplification factor.

[0072] Specifically, when CV is less than this threshold, the evaluation period will be maintained at the preset evaluation period T. default When CV is greater than or equal to the preset consistency threshold, the evaluation cycle will be adjusted according to the formula. Adjustments are made when the CV is less than a preset consistency threshold and the average value μ of the rate of change sequence. ΔF When it is less than the negative trend sensitivity threshold, then according to the formula... Adjustments will be made.

[0073] S54: When the new assessment period is shorter than the preset assessment period, the high-frequency monitoring mode is activated, the inventory status is continuously checked according to the new assessment period, and the inventory is managed collaboratively based on the spatial-similar point set; when the new assessment period is longer than the preset assessment period, the low-frequency optimization mode is activated, the inventory status is checked periodically according to the new assessment period, and a procurement pre-plan is generated based on historical demand data as an inventory management method.

[0074] Specifically, upon obtaining the new evaluation period T new After that, T new With the preset evaluation period T default Comparison, when T new Less than T default When entering high-frequency monitoring mode, press T. new To periodically conduct continuous or higher-frequency inventory checks on inventory status, and combined with the structure of spatial-similar point sets, to perform linked analysis and collaborative management of inventory information at various emergency repair points, when T new Greater than T default When entering low-frequency optimization mode, press T. new Periodic inventory checks are performed on the inventory status, and a procurement plan is generated based on the statistical results of historical demand data within a longer time window. The procurement plan is used as the output of the inventory management method to guide replenishment decisions and inventory structure adjustments.

[0075] Example 2 like Figure 2 As shown, based on the same inventive concept as the above embodiments, the present invention also provides an emergency material distribution and management device, comprising: The spare parts frequency calculation module is used to obtain the spare parts types of N emergency repair points, and obtain the non-standard demand frequency of N emergency repair points based on the spare parts types. The non-standard demand frequency represents the degree of demand for non-standard spare parts that do not conform to the standard models required by the emergency repair points. The scene feature construction module is used to obtain scene constraints and construct feature vectors for each emergency repair point based on the frequency of non-standard demand and scene constraints. The clustering similarity analysis module is used to perform similarity clustering based on feature vectors to determine the spatial set of similar points; The comprehensive scoring calculation module is used to calculate the comprehensive score of the target emergency repair point based on the spatial set of similar points, and to determine the material allocation method based on the comprehensive score. The cycle management optimization module is used to determine the assessment cycle of each emergency repair point based on the material allocation method, and then determine the inventory management method based on the assessment cycle.

[0076] Optionally, the spare parts frequency calculation module includes: The demand acquisition submodule is used to obtain the spare parts model and the corresponding required quantity for each emergency repair point; The frequency calculation submodule is used to calculate frequencies based on non-standard requirement formulas. Calculations were performed on the spare parts models and required quantities to obtain the non-standard demand frequencies fns for N emergency repair points, where, The number of emergency repair points, For spare parts types For spare parts type Standard storage model, For emergency repair points For spare parts type The demand quantity, For emergency repair points For spare parts type The required model This is an indicator function.

[0077] Optionally, the scene feature construction module includes: The environmental coefficient submodule is used to acquire multi-dimensional environmental factors, perform weighted merging of these factors, and generate the environmental difficulty coefficient E. i ; The urgency level submodule is used to obtain historical demand data for each emergency repair point, calculate the median of the set of time thresholds from the initiation of historical demand data to the delivery of the request, and normalize it to obtain the historical average demand urgency level Q. i ; The value proportion submodule analyzes spare parts prices from historical demand data, calculates the total value of spare parts exceeding a preset value threshold, and then determines the demand proportion K of high-value spare parts based on the total spare parts value. i ; The vector construction submodule is used to determine the environmental difficulty coefficient of the emergency repair point, the historical average urgency of demand, the proportion of high-value spare parts demand, and the corresponding non-standard demand frequency f. nsi Construct feature vectors .

[0078] Optional, the clustering homogeneity analysis module includes: The vector standard submodule is used to perform Z-score standardization on the feature vectors of each emergency repair point, converting the data of each dimension into a preset normal distribution to obtain the standardization result; The cluster number evaluation submodule is used to calculate the cluster profile coefficient under different cluster numbers K based on the standardized processing results, so as to determine the optimal cluster number K based on the cluster profile coefficient; The clustering submodule is used to cluster the standardized results according to the optimal number of clusters K, and divide the N emergency repair points into K clusters using the K-Means algorithm. The same-category filtering submodule is used to determine the cluster to which the target emergency repair point belongs based on the clustering results, obtain the neighboring emergency repair points that are geographically adjacent to the target emergency repair point or within a preset geographical range within the cluster, and combine the neighboring emergency repair points with the target emergency repair point into a spatial-same-category point set.

[0079] Optional, the comprehensive score calculation module includes: The scoring formula submodule is used to calculate scores based on preset scoring formulas. The comprehensive score Z of the target emergency repair point was obtained. i Where w1 and w2 are the weighting coefficients for non-standard demand frequency and environmental difficulty coefficient, respectively; The statistical reference submodule is used to calculate the median and maximum comprehensive scores of all emergency repair points in the target emergency repair point space-similar point set, and to determine the material allocation method based on the comprehensive scores, median and maximum scores.

[0080] Optionally, the statistical reference submodule includes: The status discrimination unit is used to compare the comprehensive score with the first preset threshold and the second preset threshold to identify the resource supply and demand status; The resource sufficiency unit is used to determine the resource supply and demand status as sufficient when the comprehensive score is greater than or equal to the first preset threshold. If the comprehensive score is greater than or equal to the maximum value, priority allocation is performed to the target emergency repair point and the allocation amount is set to the maximum expected demand. If the comprehensive score is less than the maximum value, materials are allocated to the target emergency repair point as needed. The resource shortage unit is used to determine the resource supply and demand status as resource shortage when the comprehensive score is less than the first preset threshold and greater than or equal to the second preset threshold. If the comprehensive score is greater than or equal to the median, priority allocation is performed to the target emergency repair point. If the comprehensive score is less than the median, the target emergency repair point is allocated according to the standard procedure or the target emergency repair point is used as a resource output to provide support to other emergency repair points.

[0081] Optional, the periodic governance optimization module includes: The rate of change sequence submodule is used to obtain the non-standard demand frequency of each emergency repair point in two adjacent assessment periods according to the material allocation method, calculate the rate of change of the non-standard demand frequency, and generate the rate of change of the non-standard demand frequency of all emergency repair points according to the spatial-similar point set, so as to obtain the rate of change sequence. The coefficient of variation submodule is used to calculate the coefficient of variation of a rate of change sequence. , where σ ΔF Let μ be the standard deviation of the rate of change series. ΔF The average value of the rate of change sequence; The periodic adjustment submodule is used to maintain the evaluation period at the preset evaluation period T when the coefficient of variation is less than the preset consistency threshold. default When the coefficient of variation is greater than or equal to the preset consistency threshold, the evaluation period will be adjusted to... When the coefficient of variation is less than the preset consistency threshold and the average value of the rate of change sequence is less than the negative trend sensitivity threshold, the evaluation period will be adjusted to... , among which, T new For the new evaluation cycle, T min The minimum allowable evaluation period, β is the period reduction factor, and T max Maximum allowable evaluation period, γ increase This is the period amplification factor; The strategy mode submodule is used to activate the high-frequency monitoring mode when the new evaluation period is less than the preset evaluation period, continuously count the inventory status according to the new evaluation period, and perform collaborative management of inventory based on spatial-similar point sets; when the new evaluation period is greater than the preset evaluation period, the low-frequency optimization mode is activated, periodically count the inventory status according to the new evaluation period, and generate a procurement pre-plan based on historical demand data as an inventory management method.

[0082] Example 3 like Figure 3 As shown, the present invention also provides an electronic device 100 for implementing a method for the distribution and management of emergency supplies; The electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on at least one processor 102, and at least one communication bus 104.

[0083] The memory 101 can be used to store computer program 103. The processor 102 implements the steps of the emergency material distribution and management method of Embodiment 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101.

[0084] The memory 101 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created based on the use of the electronic device 100 (such as audio data), etc. In addition, the memory 101 may include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0085] At least one processor 102 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 102 may be a microprocessor or any conventional processor. Processor 102 is the control center of electronic device 100, connecting various parts of electronic device 100 via various interfaces and lines.

[0086] The memory 101 in the electronic device 100 stores multiple instructions to implement an emergency supplies distribution and management method, and the processor 102 can execute multiple instructions to achieve the following: Obtain the spare parts types of N emergency repair points, and obtain the non-standard demand frequency of N emergency repair points based on the spare parts types. The non-standard demand frequency represents the degree of demand for non-standard spare parts that do not conform to the standard models required by the emergency repair points. Obtain scenario constraints and construct feature vectors for each emergency repair point based on the frequency of non-standard demand and scenario constraints; Similarity clustering is performed based on feature vectors to determine the spatial set of similar points; Calculate the comprehensive score of the target emergency repair point based on the spatial set of similar points, and determine the material allocation method based on the comprehensive score; The assessment cycle for each emergency repair point is determined based on the material allocation method, and then the inventory management method is determined based on the assessment cycle.

[0087] Example 4 If the modules / units integrated in the electronic device 100 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, and read-only memory (ROM).

[0088] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0089] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0090] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0091] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0092] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for the distribution and management of emergency supplies, characterized in that, The method includes: Obtain the spare parts types of N emergency repair points, and obtain the non-standard demand frequency of N emergency repair points based on the spare parts types. The non-standard demand frequency represents the degree of demand for non-standard spare parts that do not conform to the standard models required by the emergency repair points. Obtain scenario constraints, and construct a feature vector for each emergency repair point based on the non-standard demand frequency and the scenario constraints; Similarity clustering is performed based on the feature vectors to determine a spatial set of similar points; Calculate the comprehensive score of the target emergency repair point based on the spatial-similar point set, and determine the material allocation method based on the comprehensive score; The assessment cycle for each emergency repair point is determined based on the material allocation method, and then the inventory management method is determined based on the assessment cycle.

2. The emergency supplies allocation and management method according to claim 1, characterized in that, The process of obtaining spare parts types for N emergency repair points and, based on these spare parts types, determining the non-standard demand frequencies for the N emergency repair points includes: Obtain the spare parts model and the corresponding required quantity for each of the aforementioned emergency repair points; According to the non-standard demand frequency formula The non-standard demand frequency fns for N emergency repair points is obtained by calculating the spare parts model and the required quantity. The number of emergency repair points, For spare parts types For spare parts type Standard storage model, For emergency repair points For spare parts type The demand quantity, For emergency repair points For spare parts type The required model This is an indicator function.

3. The emergency supplies allocation and management method according to claim 1, characterized in that, The acquisition of scenario constraints involves constructing a feature vector for each emergency repair point based on the non-standard demand frequency and the scenario constraints, including: Obtain multi-dimensional environmental factors, weight and combine these factors to generate an environmental difficulty coefficient E. i ; Obtain historical demand data for each of the aforementioned emergency repair points, calculate the median of the set of time thresholds from the initiation of the historical demand data to the delivery of the request, and normalize it to obtain the historical average demand urgency level Q. i ; The spare parts prices in the historical demand data are analyzed to calculate the total value of spare parts exceeding a preset value threshold. Then, the proportion K of high-value spare parts demand is determined based on the total spare parts value. i ; Based on the environmental difficulty coefficient of the emergency repair site, the historical average urgency of demand, the proportion of high-value spare parts demand, and the corresponding non-standard demand frequency f. nsi Construct the feature vector .

4. The emergency supplies allocation and management method according to claim 1, characterized in that, The step of performing similarity clustering based on the feature vectors to determine the spatial set of similar points includes: The feature vectors of each emergency repair point are subjected to Z-score standardization to convert the data of each dimension into a preset normal distribution, and the standardization result is obtained. Based on the standardization results, the cluster profile coefficients for different cluster numbers K are calculated, so as to determine the optimal cluster number K according to the cluster profile coefficients. Based on the optimal number of clusters K, the standardized processing results are clustered using the K-Means algorithm, dividing the N emergency repair points into K clusters. Based on the clustering results, the cluster to which the target emergency repair point belongs is determined. Within the cluster, neighboring emergency repair points that are geographically adjacent to the target emergency repair point or within a preset geographical range are obtained. The neighboring emergency repair points and the target emergency repair point are combined into the spatial-same-type point set.

5. The emergency supplies distribution and management method according to claim 3, characterized in that, The step of calculating a comprehensive score for the target emergency repair point based on the spatial-similar point set, and determining a material allocation method based on the comprehensive score, includes: According to the preset scoring formula The comprehensive score Z of the target emergency repair point is obtained. i Where w1 and w2 are the weighting coefficients for non-standard demand frequency and environmental difficulty coefficient, respectively; Calculate the median and maximum comprehensive scores of all emergency repair points in the target emergency repair point space-similar point set, and determine the material allocation method based on the comprehensive scores, median, and maximum scores.

6. The emergency supplies distribution and management method according to claim 5, characterized in that, The method for determining the material allocation based on the comprehensive score, median, and maximum value includes: The comprehensive score is compared with the first preset threshold and the second preset threshold to identify the resource supply and demand status; If the comprehensive score is greater than or equal to the first preset threshold, the resource supply and demand status is determined to be sufficient. If the comprehensive score is greater than or equal to the maximum value, priority allocation is performed on the target emergency repair point and the allocation amount is set to the maximum expected demand amount. If the comprehensive score is less than the maximum value, materials are allocated to the target emergency repair point as needed. If the overall score is less than the first preset threshold and greater than or equal to the second preset threshold, the resource supply and demand status is determined to be resource shortage. If the overall score is greater than or equal to the median, priority allocation is performed to the target emergency repair point. If the overall score is less than the median, the target emergency repair point is allocated according to the standard procedure or the target emergency repair point is used as a resource output to provide support to other emergency repair points.

7. The emergency supplies allocation and management method according to claim 1, characterized in that, The step of determining the assessment cycle for each emergency repair point based on the material allocation method, and then determining the inventory management method based on the assessment cycle, includes: According to the material allocation method, the non-standard demand frequency of each emergency repair point in two adjacent assessment periods is obtained, the rate of change of the non-standard demand frequency is calculated, and the rate of change of the non-standard demand frequency of all emergency repair points is generated according to the spatial-similar point set to obtain the rate of change sequence. Calculate the coefficient of variation of the rate of change sequence. , where σ ΔF Let μ be the standard deviation of the rate of change series. ΔF The average value of the rate of change sequence; When the coefficient of variation is less than a preset consistency threshold, the evaluation period remains the preset evaluation period T. default When the coefficient of variation is greater than or equal to a preset consistency threshold, the evaluation period will be adjusted to... When the coefficient of variation is less than a preset consistency threshold and the average value of the rate of change sequence is less than a negative trend sensitivity threshold, the evaluation period will be adjusted to... , among which, T new For the new evaluation cycle, T min The minimum allowable evaluation period, β is the period reduction factor, and T max Maximum allowable evaluation period, γ increase This is the period amplification factor; When the new evaluation period is shorter than the preset evaluation period, a high-frequency monitoring mode is activated to continuously check the inventory status according to the new evaluation period and to manage the inventory collaboratively based on a spatial-similar point set. When the new evaluation period is longer than the preset evaluation period, a low-frequency optimization mode is activated to periodically check the inventory status according to the new evaluation period and to generate a procurement plan based on historical demand data as an inventory management method.

8. An emergency supplies distribution and management device, characterized in that, The device includes: The spare parts frequency calculation module is used to obtain the spare parts types of N emergency repair points, and based on the spare parts types, obtain the non-standard demand frequency of N emergency repair points. The non-standard demand frequency represents the degree of demand for non-standard spare parts that do not conform to the standard models required by the emergency repair points. The scene feature construction module is used to obtain scene constraints and construct a feature vector for each emergency repair point based on the non-standard demand frequency and the scene constraints. The clustering similarity analysis module is used to perform similarity clustering based on the feature vectors to determine the spatial set of similar points; The comprehensive scoring calculation module is used to calculate the comprehensive score of the target emergency repair point based on the spatial-similar point set, and to determine the material allocation method based on the comprehensive score. The cycle management optimization module is used to determine the assessment cycle of each emergency repair point according to the material allocation method, and then determine the inventory management method according to the assessment cycle.

9. An electronic device, characterized in that, It includes a processor and a memory, the processor being used to execute a computer program stored in the memory to implement the steps of the emergency supplies distribution and management method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one instruction, which, when executed by a processor, implements the steps of the emergency supplies distribution and management method as described in any one of claims 1 to 7.

Images