Express delivery stop area query method, device and equipment and storage medium

Abstract

The invention relates to the field of logistics, and discloses an express delivery stop area query method, device and equipment and a storage medium, and the method is used for querying an express delivery stop area and related information. The method comprises the following steps: receiving a stop area query request, and determining a query area; obtaining region parameters of the query region, determining an e-commerce activity intensity influence probability, a traffic control influence probability and a weather influence probability of the query region according to the region parameters, calculating a predicted stop probability of the query region, and screening out the query region of which the predicted stop probability exceeds a preset probability threshold as a candidate region; matching the candidate area with a pre-constructed stop area database according to an area boundary matching degree, a stop time overlapping degree and a service type matching degree, and calculating a comprehensive matching score of each area according to a matching result; and screening out regions with the comprehensive matching scores greater than a preset threshold score, generating a comprehensive query result, and pushing the comprehensive query result to the user.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of logistics, in particular to a query method, device and equipment for express delivery stop area and a storage medium. BACKGROUND

[0003] At present, the existing query method for express delivery stop area mostly depends on the static announcement published by the official website or APP of express delivery enterprises, and the user needs to manually search for relevant information, which is not only cumbersome, but also has a lag in information updating. For example, when the express delivery is stopped in a certain area due to sudden traffic control or bad weather, the traditional query method often cannot synchronize the latest information in time, resulting in inaccurate stop area data obtained by the user. At the same time, the existing query method lacks consideration of the intensity of e-commerce activities. During large e-commerce activities, the surge in order quantity may cause insufficient express delivery capacity in some areas, and thus lead to stop delivery, but the traditional method is difficult to predict such stop delivery caused by e-commerce activities in advance. In addition, the judgment of the stop delivery area in the prior art is mostly based on a single factor, such as only referring to the weather warning or traffic control influence probability, without analyzing multiple influence factors comprehensively, resulting in low reliability of the query result. Therefore, the prior art still needs to be improved and developed. SUMMARY The present application provides a query method, device and equipment for express delivery stop area and a storage medium.

[0004] The first aspect of the present application provides a query method for express delivery stop area, which comprises: receiving a stop area query request and analyzing the stop area query request to determine a query area; obtaining the area parameters of the query area and determining the e-commerce activity intensity influence probability, traffic control influence probability and weather influence probability of the query area according to the area parameters; calculating the predicted stop probability of the query area according to the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability, and screening out the query area with a predicted stop probability exceeding a preset probability threshold as a candidate area; matching the candidate area with a pre-constructed stop area database in terms of area boundary matching degree, stop time overlapping degree and business type matching degree, and calculating the comprehensive matching score of each area according to the matching result; screening out the area with a comprehensive matching score greater than a preset threshold score, and generating a comprehensive query result, which is pushed to the user, and the comprehensive query result contains the stop state, the predicted recovery time and the influence range.

[0005] Optionally, in the first implementation manner of the first aspect of the present application, the receiving of the stoppage area query request and the parsing of the stoppage area query request to determine the query area comprises: receiving a stoppage area query request submitted by a user, and performing format checking on the stoppage area query request to determine whether the stoppage area query request includes valid area pointing information; parsing the stoppage area query request that passes the format checking to obtain area characteristic information, the area characteristic information including at least one of an area name, an administrative division code, a latitude and longitude range, and a postal code; performing data cleaning on the area characteristic information, and determining the query area according to the cleaned area characteristic information.

[0006] Optionally, in the second implementation manner of the first aspect of the present application, the obtaining of the area parameters of the query area and the determination of the e-commerce activity intensity influence probability, the traffic control influence probability, and the weather influence probability of the query area according to the area parameters comprises: obtaining the area parameters of the query area, the area parameters including e-commerce activity intensity data, traffic control data, and weather warning data; calculating the e-commerce activity intensity influence probability according to the regional consumption density and the historical activity stoppage rate of the e-commerce activity intensity data; calculating the traffic control influence probability according to the regional control type and the duration of the traffic control data, and calculating the weather influence probability according to the disaster weather grade and the coverage of the weather warning data.

[0007] Optionally, in the third implementation manner of the first aspect of the present application, the calculation of the predicted stoppage probability of the query area according to the e-commerce activity intensity influence probability, the traffic control influence probability, and the weather influence probability, and the screening of the query area with a predicted stoppage probability exceeding a preset probability threshold as a candidate area comprises: calculating the weight parameters of the e-commerce activity intensity influence probability, the traffic control influence probability, and the weather influence probability through a gradient descent algorithm; weighting and adding the e-commerce activity intensity influence probability, the traffic control influence probability, and the weather influence probability based on the weight parameters of the e-commerce activity intensity influence probability, the traffic control influence probability, and the weather influence probability to obtain the predicted stoppage probability of each area; and screening the query area with a predicted stoppage probability exceeding a preset probability threshold as a candidate area.

[0008] Optionally, in a fourth implementation form of the first aspect of the present application, the weight parameters of the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability calculated by the gradient descent algorithm comprise: obtaining initial weight values of the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability; taking historical stoppage area data as training samples, taking historical e-commerce activity intensity influence probability, historical traffic control influence probability and historical weather influence probability in the training samples as inputs, and taking actual stoppage results as labels to construct a loss function; according to the gradient descent algorithm, partial derivatives of the initial weight values of the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability with respect to the loss function are respectively solved; the initial weight values of the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability are updated according to the calculated partial derivatives and a preset learning rate; when the number of iterations reaches a preset maximum number of iterations, the iteration is stopped, and the updated weight parameters are taken as the final weights of the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability; and the final weights of the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability are normalized, and the normalized weight parameters are used as the weight parameters of the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability.

[0009] Optionally, in a fifth implementation form of the first aspect of the present application, the matching of the candidate area with the pre-constructed stoppage area database in terms of area boundary matching degree, stoppage time overlap degree and business type matching degree, and the calculation of the comprehensive matching score of each area according to the matching result comprise: matching the candidate area with the pre-constructed stoppage area database in terms of area boundary matching degree, stoppage time overlap degree and business type matching degree to obtain area boundary matching degree scores, stoppage time overlap degree scores and business type matching degree scores; performing weight distribution on the area boundary matching degree scores, the stoppage time overlap degree scores and the business type matching degree scores through an attention mechanism neural network; and based on the distributed weights and the attention mechanism neural network, the area boundary matching degree scores, the stoppage time overlap degree scores and the business type matching degree scores are weighted and added to obtain the comprehensive matching score of each area.

[0010] Optionally, in the sixth implementation form of the first aspect of the present application, in the sixth implementation form of the first aspect of the present application, the method further comprises: screening out the region with the comprehensive matching score greater than the preset threshold score from the candidate regions, determining the region as a final stop region; integrating information of the final stop region, determining a stop state of each region, combining an e-commerce activity end time, a traffic control release plan, a weather warning dissipation prediction and a delivery enterprise's operation recovery scheme, predicting a predicted recovery time of each region, and delimiting an influence range of each stop region through a GIS system; and arranging the stop state, the predicted recovery time and the influence range into a structured comprehensive query result, and pushing the comprehensive query result to the user.

[0011] The second aspect of the present application provides a delivery stop region query device, comprising: an analysis module, configured to receive a stop region query request and analyze the stop region query request to determine a query region; a determination module, configured to obtain region parameters of the query region and determine an e-commerce activity intensity influence probability, a traffic control influence probability and a weather influence probability of the query region according to the region parameters; a screening module, configured to calculate a predicted stop probability of the query region according to the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability, and screen out a query region with a predicted stop probability greater than a preset probability threshold as a candidate region; a calculation module, configured to match the candidate region with a pre-constructed stop region database in terms of region boundary matching degree, stop time overlapping degree and business type matching degree, and calculate a comprehensive matching score of each region according to a matching result; and a generation module, configured to screen out a region with a comprehensive matching score greater than a preset threshold score, generate a comprehensive query result, and push the comprehensive query result to the user, wherein the comprehensive query result comprises a stop state, a predicted recovery time and an influence range.

[0012] Optionally, in the first implementation form of the second aspect of the present application, the analysis module comprises: a verification unit, configured to receive a stop region query request submitted by a user, and perform format verification on the stop region query request to determine whether the stop region query request comprises valid region pointing information; an analysis unit, configured to analyze the stop region query request that passes the format verification to obtain region characteristic information, wherein the region characteristic information comprises at least one of a region name, an administrative division code, a latitude and longitude range and a postal code; and a data cleaning unit, configured to clean the region characteristic information, and determine a query region according to the cleaned region characteristic information.

[0013] Optionally, in the second implementation manner of the second aspect of the present application, the first calculation module comprises: an acquisition unit, configured to acquire regional parameters of the query region, the regional parameters comprising e-commerce activity intensity data, traffic control data and weather warning data; a first calculation unit, configured to calculate an e-commerce activity intensity influence probability according to a regional consumption density and a historical activity stop rate of the e-commerce activity intensity data; and a second calculation unit, configured to calculate a traffic control influence probability according to a regional control type and a duration of the traffic control data, and calculate a weather influence probability according to a disaster weather level and a coverage of the weather warning data.

[0014] Optionally, in the third implementation manner of the second aspect of the present application, the screening module comprises: a third calculation unit, configured to calculate weight parameters of the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability by using a gradient descent algorithm; a fourth calculation unit, configured to add the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability by using the weight parameters to obtain a predicted stop probability of each region; and a screening unit, configured to screen a query region with a predicted stop probability exceeding a preset probability threshold as a candidate region.

[0015] Optionally, in the fourth implementation manner of the second aspect of the present application, the second calculation module comprises: a matching unit, configured to match the candidate region with a pre-constructed stop region database in terms of a regional boundary matching degree, a stop time overlap degree and a business type matching degree to obtain a regional boundary matching degree score, a stop time overlap degree score and a business type matching degree score; an allocation unit, configured to allocate weights to the regional boundary matching degree score, the stop time overlap degree score and the business type matching degree score by using an attention mechanism neural network; and a fifth calculation unit, configured to add the regional boundary matching degree score, the stop time overlap degree score and the business type matching degree score by using the allocated weights and the attention mechanism neural network to obtain a comprehensive matching score of each region.

[0016] Optionally, in the fifth implementation manner of the second aspect of the present application, the generation module comprises: a determination unit, configured to screen a region with a comprehensive matching score greater than a preset threshold from the candidate region, and determine the region as a final stop region; a processing unit, configured to integrate information of the final stop region, determine a stop state of each region, predict a predicted recovery time of each region in combination with an e-commerce activity end time, a traffic control release plan, a weather warning dissipation prediction and a recovery scheme of a delivery enterprise's transport capacity, and delineate an influence range of each stop region by using a GIS system; and a generation unit, configured to arrange the stop state, the predicted recovery time and the influence range into a structured comprehensive query result, and push the comprehensive query result to a user.

[0017] The third aspect of the present application provides a query device for a delivery suspension area, comprising a memory and at least one processor, the memory storing computer readable instructions, and the memory and the at least one processor being interconnected by a circuit; the at least one processor invoking the computer readable instructions in the memory to enable the query device for a delivery suspension area to perform each step of the query method for a delivery suspension area as described above.

[0018] The fourth aspect of the present application provides a computer readable storage medium storing computer readable instructions, which, when executed on a computer, enable the computer to perform each step of the query method for a delivery suspension area as described above.

[0019] In the technical solution provided by the present application, the potential suspension risk area is actively predicted based on the combination of e-commerce activities, traffic and weather, which can effectively compensate for the hysteresis of the static suspension area database; moreover, the high-probability candidate area is accurately screened through a preset threshold, which greatly reduces the subsequent comparison range and improves the efficiency; in addition, the multi-dimensional intelligent matching of the boundary, time and business type is performed in combination with the suspension area database, and the comprehensive score is calculated for secondary screening, which ensures the high accuracy, comprehensiveness and timeliness of the final query result, and provides fine suspension information including the state, recovery time and impact range for the user. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 The first flowchart of the query method for a delivery suspension area provided by the embodiment of the present application; Figure 2 The second flowchart of the query method for a delivery suspension area provided by the embodiment of the present application; Figure 3 The third flowchart of the query method for a delivery suspension area provided by the embodiment of the present application; Figure 4 The fourth flowchart of the query method for a delivery suspension area provided by the embodiment of the present application; Figure 5 The fifth flowchart of the query method for a delivery suspension area provided by the embodiment of the present application; Figure 6 The sixth flowchart of the query method for a delivery suspension area provided by the embodiment of the present application; Figure 7 The structure diagram of the query device for a delivery suspension area provided by the embodiment of the present application; Figure 8 The structure diagram of the query device for a delivery suspension area provided by the embodiment of the present application; DETAILED DESCRIPTION

[0021] The terms "first", "second", "third", "fourth" and the like in the description and in the claims of the present application, and above-mentioned drawings, if any, are used to distinguish between similar objects and not necessarily for describing a specific sequential or chronological order. It is to be understood that the use of the terms so construed herein can be interchanged, under appropriate circumstances, to describe the embodiments of the application described herein in other than the particular order described herein. Also, the terms "comprise" and "comprising" and any variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, system, product or apparatus that comprises a list of steps or units not necessarily limited to those specifically listed, but can include additional steps or units not expressly listed or inherent to such process, method, product or apparatus.

[0022] For the sake of understanding, the specific flow of the embodiments of the present application is described below, please refer to Figure 1 The first embodiment of the express delivery stop area query method in the embodiments of the present application comprises: S101, receiving a stop area query request and parsing the stop area query request to determine the query area.

[0023] In this embodiment, first, the stop area query request submitted by the user through the query platform is received, which may contain area name, detailed address and other information; then the request is processed by using text analysis technology to extract the key area information, and then the specific query area is determined.

[0024] It can be understood that the execution subject of the present application can be an express delivery stop area query device, and can also be a terminal or a server, which is not limited here. The embodiments of the present application take the server as the execution subject for example.

[0025] S102, obtaining the area parameters of the query area, and determining the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability of the query area according to the area parameters.

[0026] In this embodiment, the order quantity, promotion activity arrangement and other e-commerce data of the query area are obtained from the e-commerce platform through the data interface, the traffic control notice, restricted road section and other traffic data are obtained from the traffic management department, and the real-time weather, weather forecast, historical extreme weather and other meteorological data are obtained from the meteorological department. These data together constitute the area parameters; then statistical analysis method and probability model are used to analyze the correlation degree of each factor and stop, and the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability are calculated respectively.

[0027] S103, calculate the predicted stop delivery probability of the query area according to the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability, and screen the query area with the predicted stop delivery probability exceeding a preset probability threshold as a candidate area; In the embodiment, a weighted algorithm is adopted, corresponding weights are set according to the importance of the influence of e-commerce activities, traffic control and weather on the stop delivery of express delivery, the three influence probabilities are weighted calculated to obtain the predicted stop delivery probability of the query area. Then the predicted stop delivery probability is compared with the preset stop delivery threshold, and the query area with the predicted stop delivery probability exceeding the threshold is screened as a candidate area.

[0028] S104, match the candidate area with the pre-constructed stop delivery area database in terms of area boundary matching degree, stop delivery time overlap degree and business type matching degree, and calculate the comprehensive matching score of each area according to the matching result; In the embodiment, the pre-constructed stop delivery area database stores the boundary information, stop delivery time period, business type and other data of the historical stop delivery area.

[0029] In the embodiment, the boundary coincidence proportion of the candidate area and the stop delivery area in the stop delivery area database is calculated by geographic information system technology to obtain the area boundary matching degree; the overlap of the possible stop delivery time of the candidate area and the historical stop delivery time of the corresponding area in the stop delivery area database is compared to obtain the stop delivery time overlap degree; the consistency degree of the express delivery business type of the candidate area and the business type of the stop delivery area in the stop delivery area database is analyzed to obtain the business type matching degree. Finally, the three matching degrees are calculated to obtain the comprehensive matching score of each candidate area.

[0030] S105, screen the area with the comprehensive matching score greater than a preset threshold score, and generate a comprehensive query result, and push the comprehensive query result to the user, wherein the comprehensive query result includes the stop delivery state, the estimated recovery time and the influence range.

[0031] In the embodiment, the comprehensive matching score of each candidate area is compared with the preset threshold score, and the area with the score greater than the threshold score is screened. Then the related information of these areas is integrated, the estimated recovery time is estimated according to the historical recovery data and the change trend of the current influencing factors, the stop delivery state and the specific influence range are determined, and the comprehensive query result containing these contents is generated. Finally, the comprehensive query result is sent to the query interface of the user or the specified receiving channel through the information pushing mechanism for the user to view.

[0032] The embodiment provides a query method for a delivery suspension area, which actively predicts potential suspension risk areas based on multi-dimensional dynamic factors combined with e-commerce activities, traffic and weather, and can effectively compensate for the hysteresis of a static suspension area database; moreover, high-probability candidate areas are accurately screened out through a preset threshold, which greatly reduces the subsequent comparison range and improves efficiency; in addition, multi-dimensional intelligent matching of boundaries, time and business types is performed in combination with the suspension area database, and a comprehensive score is calculated for secondary screening, thereby ensuring the high accuracy, comprehensiveness and timeliness of the final query result, and providing fine suspension information including a state, a recovery time and an influence range for a user.

[0033] Referring to Figure 2 The second embodiment of the query method for a delivery suspension area in the embodiment of the present application includes the following steps. S201, receiving a suspension area query request submitted by a user, and performing format verification on the suspension area query request to determine whether the suspension area query request includes valid area pointing information.

[0034] In the embodiment, the suspension area query request initiated by the user is received through a preset interface (such as a Web API, an APP interface or an internal system calling interface). The request usually includes area-related information input by the user.

[0035] In the embodiment, the format verification on the suspension area query request includes two aspects.

[0036] One aspect is to check whether the basic structure of the request meets the expectation (for example, whether it is a legal JSON / XML format, and whether it includes necessary fields such as regionInput).

[0037] The other aspect is to check whether the area pointing information input by the user is valid and non-empty. For example, whether the input text string is empty or contains only blank characters, whether the input administrative division code meets the national / industry standard format (such as 6 digits), whether the input latitude and longitude coordinate format is correct (such as lat, lng or longitude, latitude) and within a reasonable range, and whether the input postal code format is correct (such as 6 digits in China).

[0038] S202, analyzing the suspension area query request that passes the format verification to obtain area feature information, the area feature information including at least one of a region name, an administrative division code, a latitude and longitude range and a postal code.

[0039] In this embodiment, the user input area information that passes the format check is subjected to semantic analysis and information extraction. If the input is a text address (such as "Beijing Haidian Zhongguancun Avenue"), the NLP technology (such as word segmentation, named entity recognition NER, address resolution library) is used to identify and extract the area name. The area name is: province, city, district / county, township / street, landmark / commercial area, and other hierarchical names.

[0040] If the input contains or can be mapped to a standard code, the administrative division code of the national standard (such as GB / T 2260 of China) is identified or mapped by name.

[0041] If the input is a coordinate point or range, the specific latitude value and longitude value are parsed.

[0042] If the input contains a zip code, the zip code itself is extracted.

[0043] S203, data cleaning is performed on the area feature information, and a query area is determined according to the cleaned area feature information.

[0044] In this embodiment, the data cleaning of the area feature information includes standardization processing, disambiguation processing, information completion processing, and verification consistency. The standardization processing includes converting aliases, abbreviations, and old names to official standard names, and unifying coordinate formats. The data processing includes verifying the validity of the zip code. The disambiguation processing refers to handling the case of the same name but different places (such as the "West Lake Street" in many places in China). Usually, it needs to be combined with the context (such as the user's IP location, previous selection). The information completion processing refers to inferring and completing the missing levels according to the existing information. For example, if the user only inputs "Haidian District", but the system knows that it is a district of Beijing City, the regionName is completed as "Beijing Haidian District"; if the zip code is input, the corresponding standard administrative division name or code is mapped.

[0045] The verification consistency processing refers to checking whether different feature information points to the same area (such as whether the extracted name and zip code match, and whether the name and administrative division code match). If there is a conflict, the most reliable feature is selected according to the preset rules (such as priority: code > coordinate > name > zip code) or marked for manual processing / return error.

[0046] In this embodiment, the area feature information obtained after cleaning is converted or mapped to a unique "query area" identifier defined internally by the system.

[0047] In this embodiment, through strict format checking, multi-dimensional analysis and data cleaning, the effectiveness, accuracy and standardization of user query request are ensured, which not only can filter invalid or format error input, reduce invalid load of system, but also can accurately extract key regional features from various user inputs (name, code, coordinate, zip code, etc.), eliminate ambiguity and complete information through cleaning, and finally convert the fuzzy user input into the standardized "query area" identification which can be accurately processed in the system, laying a solid and reliable foundation for subsequent accurate outage probability prediction and outage area database matching.

[0048] Referring to Figure 3 The third embodiment of the express delivery outage area query method in the embodiment of the application comprises: S301, acquiring regional parameters of a query area, the regional parameters comprising e-commerce activity intensity data, traffic control data and weather warning data.

[0049] In this embodiment, by connecting multiple source authoritative data interfaces, three types of core parameters of the query area are collected: E-commerce activity intensity data: from the e-commerce platform transaction system, the consumption density (order quantity / transaction amount / active user number) in the region per unit time (such as the past 7 days), historical same period similar activity outage records, etc. are obtained; Traffic control data: connecting the traffic management department database, obtaining the control information in the region at present and in the plan, including control type (such as full closure, one-way traffic restriction, time period control, etc.), control start and end time (calculate the duration); Weather warning data: access to the meteorological department warning system, obtain the effective disaster weather warning (such as heavy rain, typhoon, snowstorm, etc.) in the region, including warning level (blue / yellow / orange / red), specific sub-regional range covered by the warning (such as full coverage or part of the street).

[0050] S302, calculating the e-commerce activity intensity influence probability according to the regional consumption density of the e-commerce activity intensity data and the historical activity outage rate.

[0051] In this embodiment, the calculation of the e-commerce activity intensity influence probability is based on the quantitative calculation of the regional consumption density and the historical activity outage rate. Specifically, it includes: Determine the consumption density weight: compare the regional consumption density with the benchmark value (such as the average consumption density of the region), the higher the density (such as 200% higher than the benchmark value), the higher the weight (such as 0.6); Extract historical outage rate: statistics of the number of times of outage caused by e-commerce activities in the region in the past when the current consumption density is similar (such as 3 times of outage in the past 5 times of high consumption density, the historical outage rate is 60%); Calculate the impact probability: the result is obtained by a weighted formula (such as consumption density weight x historical outage rate) (such as 0.6 x 60% = 36%), and the higher the value, the greater the possibility of e-commerce activities causing outages.

[0052] S303, calculate the traffic control impact probability according to the area control type and duration of the traffic control data, and calculate the weather impact probability according to the disaster weather level and coverage of the weather warning data.

[0053] In this embodiment, the calculation of the traffic control impact probability is based on the calculation of the area control type and duration, which specifically includes: Assign a value to the control type: set a basic score according to the control strictness (such as full closure = 80 points, one-way traffic = 40 points, and time period control = 20 points); Calculate the time weight: take 24 hours as the basis, the longer the duration, the higher the weight (such as 12 hours of control = 0.5, 24 hours = 1.0, and 48 hours = 1.5); Calculate the impact probability: convert the type score x time weight to probability (such as 80 x 1.0 = 80 -> 80%), that is, the more strict and longer the control, the higher the impact probability.

[0054] In this embodiment, the calculation of the weather impact probability is based on the calculation of the disaster weather level and coverage, which specifically includes: Assign a value to the weather level: set a basic score according to the warning severity (red warning = 100 points, orange = 70 points, yellow = 40 points, and blue = 20 points); Calculate the coverage weight: take the total area of the region as the basis, the higher the coverage, the greater the weight (such as covering the whole region = 1.0, covering 50% of the region = 0.5); Calculate the impact probability: convert the level score x range weight to probability (such as 100 x 1.0 = 100 -> 100%), that is, the higher the weather level and the wider the coverage, the higher the impact probability.

[0055] In this embodiment, by comprehensively obtaining the three core parameters affecting the outage (e-commerce activities, traffic control, and weather), and quantitatively calculating the impact probability of each factor based on specific data indicators (such as consumption density and historical outage rate), the scientific evaluation of the impact of the query area outage is realized, which not only guarantees the comprehensiveness of the analysis, but also improves the accuracy and interpretability of the results.

[0056] Please refer to Figure 4 , the fourth embodiment of the express delivery outage area query method in the embodiment of the application includes: S401, calculate the weight parameters of the e-commerce activity intensity impact probability, the traffic control impact probability, and the weather impact probability by the gradient descent algorithm.

[0057] In the embodiment, the weight parameters of the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability are calculated by a gradient descent algorithm, including: obtaining initial weight values of the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability; taking historical stop and launch area data as training samples, taking historical e-commerce activity intensity influence probability, historical traffic control influence probability and historical weather influence probability in the training samples as inputs, and taking actual stop and launch results as labels to construct a loss function; according to the gradient descent algorithm, the partial derivatives of the loss function with respect to the initial weight values of the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability are solved respectively; according to the calculated partial derivatives and a preset learning rate, the initial weight values of the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability are updated; when the number of iterations reaches a preset maximum number of iterations, the iteration is stopped, and the updated weight parameters are taken as the final weights of the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability; the final weights of the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability are normalized, and the normalized weight parameters are used as the weight parameters of the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability.

[0058] In the embodiment, the loss function adopts cross-entropy loss.

[0059] S402, based on the weight parameters of the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability, the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability are weighted and added to obtain the predicted stop and launch probability of each area.

[0060] In the embodiment, the weights of each influencing factor are determined (such as e-commerce weight w1, traffic weight w2 and weather weight w3, and w1+w2+w3=1); The e-commerce activity intensity influence probability (P1), the traffic control influence probability (P2) and the weather influence probability (P3) of the query area are multiplied by the corresponding weights respectively, and then summed to obtain the total predicted stop and launch probability: predicted stop and launch probability=w1×P1+w2×P2+w3×P3; For example, if w1=0.3, P1=60%, w2=0.4, P2=50%, w3=0.3, P3=70%, then the predicted probability=0.3×60%+0.4×50%+0.3×70%=59%.

[0061] S403, screening out the query area with a predicted stop and launch probability exceeding a preset probability threshold as a candidate area.

[0062] In this embodiment, the probability threshold is preset according to the business needs. For example, if the probability threshold is 50%, the area with a prediction probability greater than or equal to 50% is considered as a high-risk area. In this embodiment, the prediction probability of each query area is compared with the preset threshold, and the areas with a probability value exceeding the threshold are screened out. These areas are output as candidate areas, providing accurate targets for subsequent suspension decisions (such as early warning or adjusting distribution).

[0063] In this embodiment, the gradient descent algorithm is used to dynamically optimize the weights of each influencing factor, ensuring that the weights are consistent with the actual influence degree. The weighted sum of the multi-dimensional probabilities is combined to comprehensively evaluate the suspension risk. Finally, the candidate areas are screened by the preset threshold to accurately lock the high-risk areas. The overall process takes into account the scientificity, comprehensiveness, and pertinence of the prediction.

[0064] Please refer to Figure 5 The fifth embodiment of the express suspension area query method in the embodiment of the present application includes: S501, match the candidate area with the pre-constructed suspension area database in terms of area boundary matching degree, suspension time overlapping degree, and business type matching degree to obtain area boundary matching degree score, suspension time overlapping degree score, and business type matching degree score.

[0065] In this embodiment, the suspension area database is constructed by the following methods: collecting suspension announcement data of express enterprises nationwide every month; converting the text description of the area boundary into latitude and longitude polygon coordinates through the GIS system; associating the suspension time period (accurate to the hour) and the business type label (such as e-commerce express, fresh cold chain); automatically updating the newly added suspension data every week.

[0066] In this embodiment, with the help of the geographic information system (GIS), the boundary of the candidate area and the suspension area in the suspension area database is converted into polygon coordinates, the overlapping area is calculated as a percentage of the total area of the candidate area, and it is converted into 0-100 points (80% corresponds to 80 points) according to the proportion. The higher the overlapping degree, the higher the score.

[0067] In this embodiment, the predicted suspension time range of the candidate area (such as July 25, 2025 to July 30, 2025) is extracted, and the actual suspension time range of the suspension area in the suspension area database (such as July 27, 2025 to July 29, 2025) is extracted. The time overlapping length (3 days in this case) is calculated as a percentage of the total suspension time length of the candidate area (6 days) (50%), and it is converted into 0-100 points (50% corresponds to 50 points) according to the proportion. The higher the overlapping degree, the higher the score.

[0068] In this embodiment, the business type of the candidate region (such as e-commerce express delivery) and the business type of the stop area in the stop area database (such as express logistics) are converted into structured labels, the type similarity (such as the similarity between e-commerce express delivery and express logistics is 85%) is calculated by the cosine similarity algorithm, and is converted into 0-100 points (85% corresponds to 85 points), and the higher the similarity, the higher the score.

[0069] S502, weight distribution is performed on the region boundary matching degree score, the stop time overlap score and the business type matching degree score by the attention mechanism neural network.

[0070] In this embodiment, an attention mechanism neural network is constructed, the attention mechanism neural network adopts a 3-layer fully connected network, the input layer is 3 matching degree scores, the hidden layer node number is 64 (ReLU activation), and the output layer is 3 weight values (Softmax activation).

[0071] The scores in three dimensions in the historical matching cases and the actual matching priority manually labeled are collected as training data, for example, in a certain case, the business type is more critical, and the labeled priority is higher.

[0072] After the model training is completed, the three matching degree scores are input, and dynamic weights are output, for example, in a certain scene, the region boundary weight is 0.3, the time weight is 0.2, and the business type weight is 0.5.

[0073] S503, based on the assigned weights and the attention mechanism neural network, the region boundary matching degree score, the stop time overlap score and the business type matching degree score are weighted and added to obtain the comprehensive matching score of each region.

[0074] In this embodiment, the weights output by the attention mechanism are used as coefficients, and are multiplied by the region boundary matching degree score, the stop time overlap score and the business type matching degree score respectively. The three product results are summed to obtain the comprehensive matching score, for example, 0.3x80+0.2x50+0.5x85=78.5 points, and the higher the score, the higher the matching degree of the candidate region and the stop area in the stop area database.

[0075] In this embodiment, through the matching of the three dimensions of regional boundaries, stop time, and service type, comprehensive comparison of the candidate region and the stop region in the stop region database is realized, and the one-dimension judgment is avoided. The attention mechanism neural network is introduced to dynamically allocate the weight, and the weight proportion can be flexibly adjusted according to the actual influence degree of each dimension in different scenarios (for example, when the service type difference is more critical for a specific industry, the weight will be automatically increased), and the limitation of fixed weight is overcome. Finally, the comprehensive matching score is obtained by weighted summation, the matching degree of the two is accurately quantified, a scientific and objective basis is provided for subsequent decision-making, and the comprehensiveness of comparison, the adaptability of weight and the accuracy of result are considered.

[0076] Please refer to Figure 6 The sixth embodiment of the express stop region query method in the embodiment of the application includes: S601, regions with a comprehensive matching score greater than a preset threshold value are selected from the candidate regions, and the regions are determined as final stop regions.

[0077] In this embodiment, the preset threshold value of the comprehensive matching score is set according to the actual business needs and historical data, for example, 70 points. The comprehensive matching score of the candidate region is compared with the threshold value, and the region with a score greater than the threshold value is determined as the final stop region.

[0078] S602, the information of the final stop region is integrated, the stop state of each region is determined, the end time of the e-commerce activity, the traffic control release plan, the weather warning dissipation prediction and the express enterprise's recovery scheme of transport capacity are combined, the predicted recovery time of each region is predicted, and the influence range of each stop region is delimited through the GIS system.

[0079] In this embodiment, the current stop state of the final stop region is determined according to the comprehensive matching score of the final stop region and the historical stop record of the corresponding region in the stop region database, such as stop, stop soon, etc. In this embodiment, the end time of the e-commerce activity, the traffic control release plan, the weather warning dissipation prediction of the meteorological department, and the recovery scheme of transport capacity of the express enterprise for the region are combined, and the predicted recovery time is obtained after comprehensive analysis. When multiple factors affect the recovery time, the longest influence time is taken as the reference. For example, if the e-commerce activity ends after 3 days, the traffic control is released after 2 days, and the weather warning is dissipated after 1 day, the comprehensive judgment is that the predicted recovery time is 3 days later. In this embodiment, the administrative division code of the stop region is input into the GIS system, and the boundary coordinates of the region are automatically retrieved. If it is a sudden stop (such as traffic control), the control point is taken as the center, and a circular influence range with a radius of 2 kilometers is generated to cover all affected express points.

[0080] S603, collate the stop state, the expected recovery time and the influence range into a structured comprehensive query result, and push the comprehensive query result to the user.

[0081] The stop state, the expected recovery time and the influence range are collated into structured content according to a preset format, such as a table or a clear text description, and the comprehensive query result is pushed to the user through short message, APP push, webpage pop-up window and the like, so as to ensure that the user obtains the information in time.

[0082] In the embodiment, the regions with a comprehensive matching score meeting a standard are screened through a preset threshold, so that the final stop region is accurately locked and misjudgment is avoided; when the information is integrated, the stop state, the expected recovery time and the influence range are determined based on multi-dimensional data, so that the result is comprehensive and practical; finally, the result is pushed in a structured form, so that the user can clearly obtain key information and the query experience is improved. The above describes the express stop region query method in the embodiment of the application, and the device in the embodiment of the application is described below, please refer to Figure 7 The implementation of the express stop region query device in the embodiment of the application includes: The analysis module 701 is configured to receive a stop region query request, analyze the stop region query request, and determine a query region. The first calculation module 702 is configured to obtain region parameters of the query region, and determine an e-commerce activity intensity influence probability, a traffic control influence probability and a weather influence probability of the query region according to the region parameters. The screening module 703 is configured to calculate a predicted stop probability of the query region according to the e-commerce activity intensity influence probability, the traffic control influence probability and the weather influence probability, and screen out a query region with a predicted stop probability exceeding a preset probability threshold as a candidate region. The second calculation module 704 is configured to match the candidate region with a pre-constructed stop region database in terms of region boundary matching degree, stop time overlapping degree and business type matching degree, and calculate a comprehensive matching score of each region according to the matching result. The generation module 705 is configured to screen out a region with a comprehensive matching score greater than a preset threshold score, generate a comprehensive query result, and push the comprehensive query result to the user, wherein the comprehensive query result includes a stop state, an expected recovery time and an influence range.

[0083] In the embodiment, the parsing module 701 comprises: a checking unit 7011 configured to receive a user-submitted stoppage area query request, and perform format checking on the stoppage area query request to determine whether the stoppage area query request comprises valid area pointing information; a parsing unit 7012 configured to parse the stoppage area query request that passes the format checking to obtain area characteristic information, the area characteristic information comprising at least one of an area name, an administrative division code, a latitude and longitude range, and a postal code; and a data cleaning unit 7013 configured to perform data cleaning on the area characteristic information, and determine a query area according to the cleaned area characteristic information.

[0084] In the embodiment, the first calculation module 702 comprises: an acquisition unit 7021 configured to acquire area parameters of the query area, the area parameters comprising e-commerce activity intensity data, traffic control data, and weather warning data; a first calculation unit 7022 configured to calculate an e-commerce activity intensity influence probability according to a regional consumption density and a historical activity stoppage rate of the e-commerce activity intensity data; and a second calculation unit 7023 configured to calculate a traffic control influence probability according to a regional control type and a duration of the traffic control data, and calculate a weather influence probability according to a disaster weather grade and a coverage of the weather warning data.

[0085] In the embodiment, the screening module 703 comprises: a third calculation unit 7031 configured to calculate weight parameters of the e-commerce activity intensity influence probability, the traffic control influence probability, and the weather influence probability by a gradient descent algorithm; a fourth calculation unit 7032 configured to weight and add the e-commerce activity intensity influence probability, the traffic control influence probability, and the weather influence probability based on the weight parameters of the e-commerce activity intensity influence probability, the traffic control influence probability, and the weather influence probability to obtain a predicted stoppage probability of each area; and a screening unit 7033 configured to screen a query area with a predicted stoppage probability exceeding a preset probability threshold as a candidate area.

[0086] In the embodiment, the second calculation module 704 comprises: a matching unit 7041 configured to match the candidate area with a pre-constructed stoppage area database in terms of area boundary matching degree, stoppage time overlapping degree, and business type matching degree to obtain area boundary matching degree scores, stoppage time overlapping degree scores, and business type matching degree scores; an allocation unit 7042 configured to weight allocate the area boundary matching degree scores, the stoppage time overlapping degree scores, and the business type matching degree scores by an attention mechanism neural network; and a fifth calculation unit 7043 configured to weight and add the area boundary matching degree scores, the stoppage time overlapping degree scores, and the business type matching degree scores based on the allocated weights and the attention mechanism neural network to obtain a comprehensive matching score of each area.

[0087] In the embodiment, the generating module 705 includes: a determining unit 7051 configured to filter out, from the candidate regions, a region with a comprehensive matching score greater than a preset threshold value, and determine the region as a final stop delivery region; a processing unit 7052 configured to integrate information of the final stop delivery region, determine a stop delivery state of each region, in combination with an e-commerce activity end time, a traffic control release plan, a weather warning dissipation prediction, and a delivery enterprise's operation capacity recovery scheme, predict a predicted recovery time of each region, and demarcate an influence range of each stop delivery region through a GIS system; and a generating unit 7053 configured to arrange the stop delivery state, the predicted recovery time, and the influence range into a structured comprehensive query result, and push the comprehensive query result to a user.

[0088] In the embodiment, the potential stop delivery risk region is actively predicted based on the multi-dimensional dynamic factors of the e-commerce activity, the traffic, and the weather, which can effectively compensate for the hysteresis of the static stop delivery region database; moreover, the high-probability candidate region is accurately filtered out through the preset threshold value, which greatly reduces the subsequent comparison range and improves the efficiency; in addition, the multi-dimensional intelligent matching of the boundary, the time, and the business type is performed in combination with the stop delivery region database, and the comprehensive score is calculated for secondary screening, which ensures the high accuracy, comprehensiveness, and timeliness of the final query result, and provides the user with the fine stop delivery information including the state, the recovery time, and the influence range.

[0089] Figure 7 The structure of the illustrated express delivery stop delivery region query device does not constitute a limitation on the express delivery stop delivery region query device, and can implement the steps of the express delivery stop delivery region query method provided in each method embodiment.

[0090] The above Figure 7 The express delivery stop delivery region query device in the embodiment is described in detail from the perspective of the modular functional entity, and the express delivery stop delivery region query device in the embodiment is described in detail from the perspective of hardware processing.

[0091] Figure 8is a structural schematic view of an express delivery stop area query device provided by an embodiment of the present application. The device 800 can have great differences due to different configurations and performances, and can include one or more than one central processing unit (CPU) 810 (for example, one or more than one processor) and a memory 820, one or more than one storage medium 830 (for example, one or more than one mass storage device) storing an application program 833 or data 832. The memory 820 and the storage medium 830 can be temporary storage or persistent storage. The program stored in the storage medium 830 can include one or more than one module (not shown in the figure), and each module can include a series of instruction operations in the device 800. Further, the processor 810 can be configured to communicate with the storage medium 830 and execute a series of instruction operations in the storage medium on the device 800.

[0092] The device 800 can also include one or more than one power supply 840, one or more than one wired or wireless network interface 850, one or more than one input and output interface 860, and / or one or more than one operating system 831, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, etc.

[0093] The embodiment of the present application also provides a computer readable storage medium, which can be a non-volatile computer readable storage medium or a volatile computer readable storage medium. The computer readable storage medium stores instructions, and when the instructions run on a computer, the computer executes the steps of the express delivery stop area query method.

[0094] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system or device, unit can refer to the corresponding process in the foregoing method embodiment, which will not be described here.

[0095] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the entire or part of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0096] The above description and the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for some technical features. These modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for querying areas where express delivery is suspended, characterized in that, The methods for querying areas where express delivery services are suspended include: Receive a request to query a region where service is suspended, and parse the request to determine the region to be queried. Obtain the regional parameters of the query area, and determine the probability of influence of e-commerce activity intensity, traffic control, and weather in the query area based on the regional parameters; The predicted suspension probability of the query area is calculated based on the probability of the impact of the e-commerce activity intensity, the probability of the impact of traffic control, and the probability of the impact of weather. Query areas with predicted suspension probabilities exceeding a preset probability threshold are selected as candidate areas. The candidate regions are matched with the pre-built database of suspended regions based on region boundary matching degree, suspension time overlap degree, and service type matching degree, and the comprehensive matching score of each region is calculated based on the matching results. Regions with a comprehensive matching score greater than a preset threshold are selected, and comprehensive query results are generated and pushed to the user. The comprehensive query results include the suspension status, the estimated recovery time, and the scope of impact.

2. The method for querying express delivery suspension areas according to claim 1, characterized in that, The process of receiving a request to query a suspended region and parsing the request to determine the query region includes: Receive a user-submitted request for a suspended region query and perform format validation on the request to determine whether it includes valid region pointing information. The query request for the suspended region that passes the format validation is parsed to obtain the region feature information, which includes at least one of the region name, administrative division code, latitude and longitude range, and postal code. The region feature information is cleaned, and the query region is determined based on the cleaned region feature information.

3. The method for querying express delivery suspension areas according to claim 1, characterized in that, The step of obtaining the regional parameters of the query region and determining the probability of influence of e-commerce activity intensity, traffic control, and weather on the query region based on the regional parameters includes: Obtain the regional parameters of the query area, including e-commerce activity intensity data, traffic control data, and weather warning data; The probability of the impact of e-commerce activity intensity is calculated based on the regional consumption density and historical activity cancellation rate of the e-commerce activity intensity data. The probability of traffic control impact is calculated based on the regional control type and duration of the traffic control data, and the probability of weather impact is calculated based on the severe weather level and coverage of the weather warning data.

4. The method for querying express delivery suspension areas according to claim 1, characterized in that, The step of calculating the predicted suspension probability of the query region based on the probability of influence from the e-commerce activity intensity, the probability of influence from traffic control, and the probability of influence from weather, and filtering query regions whose predicted suspension probability exceeds a preset probability threshold as candidate regions, includes: The weight parameters for the probability of impact of e-commerce activity intensity, the probability of impact of traffic control, and the probability of impact of weather are calculated using the gradient descent algorithm. The predicted suspension probability for each region is obtained by weighting the probability of impact from the intensity of e-commerce activities, the probability of impact from traffic control, and the probability of impact from weather, based on the weighted parameters of these factors. Query regions whose predicted probability of discontinuation exceeds a preset probability threshold are selected as candidate regions.

5. The method for querying express delivery suspension areas according to claim 4, characterized in that, The weight parameters for the impact probabilities of the e-commerce activity intensity, traffic control, and weather, calculated using the gradient descent algorithm, include: Obtain the initial weight values ​​for the probability of influence of e-commerce activity intensity, the probability of influence of traffic control, and the probability of influence of weather. Using historical data on areas where services were suspended as training samples, and taking the historical probability of the impact of e-commerce activity intensity, historical probability of the impact of traffic control, and historical probability of the impact of weather in the training samples as inputs, and taking the actual suspension results as labels, a loss function was constructed. Based on the gradient descent algorithm, the partial derivatives of the loss function with respect to the initial weight values ​​of the probability of influence of the e-commerce activity intensity, the probability of influence of traffic control, and the probability of influence of weather are calculated respectively. Based on the calculated partial derivatives and the preset learning rate, the initial weight values ​​of the probability of influence of e-commerce activity intensity, the probability of influence of traffic control, and the probability of influence of weather are updated. When the number of iterations reaches the preset maximum number of iterations, the iteration stops, and the updated weight parameters are used as the final weights for the probability of influence of e-commerce activity intensity, the probability of influence of traffic control, and the probability of influence of weather. The final weights of the probability of influence of e-commerce activity intensity, the probability of influence of traffic control, and the probability of influence of weather are normalized, and the normalized weight parameters are used as the weight parameters of the probability of influence of e-commerce activity intensity, the probability of influence of traffic control, and the probability of influence of weather.

6. The method for querying express delivery suspension areas according to claim 1, characterized in that, The process of matching the candidate regions with a pre-built database of discontinued regions based on region boundary matching degree, discontinued time overlap degree, and service type matching degree, and calculating a comprehensive matching score for each region based on the matching results, includes: The candidate regions are matched with the pre-built suspension region database based on region boundary matching degree, suspension time overlap degree, and service type matching degree to obtain region boundary matching degree score, suspension time overlap score, and service type matching degree score. The region boundary matching score, the termination time overlap score, and the service type matching score are weighted using an attention mechanism neural network. The comprehensive matching score for each region is obtained by weighting and adding the region boundary matching score, the termination time overlap score, and the service type matching score using a neural network based on the assigned weights and attention mechanism.

7. The method for querying express delivery suspension areas according to claim 1, characterized in that, The process involves filtering out regions where the overall matching score is greater than a preset threshold, generating comprehensive query results, and pushing these results to the user. The comprehensive query results include the suspension status, estimated recovery time, and scope of impact, including: The regions with a comprehensive matching score greater than a preset threshold score are selected from the candidate regions and determined as the final regions to be stopped from firing. The information on the final suspension areas is integrated to determine the suspension status of each area. Combined with the end time of e-commerce activities, traffic control lifting plans, weather warning dissipation forecasts, and express delivery companies' capacity recovery plans, the estimated recovery time of each area is predicted, and the impact range of each suspension area is delineated through the GIS system. The suspension status, estimated recovery time, and scope of impact are compiled into a structured comprehensive query result, which is then pushed to the user.

8. A device for querying areas where express delivery is suspended, characterized in that, include: The parsing module is used to receive a stop-transmission area query request, parse the stop-transmission area query request, and determine the query area; The first calculation module is used to obtain the regional parameters of the query area, and determine the probability of influence of e-commerce activity intensity, traffic control and weather in the query area based on the regional parameters. The filtering module is used to calculate the predicted suspension probability of the query area based on the probability of the influence of the e-commerce activity intensity, the probability of the influence of traffic control, and the probability of the influence of weather, and to filter out the query areas whose predicted suspension probability exceeds a preset probability threshold as candidate areas. The second calculation module is used to match the candidate regions with the pre-built database of suspended regions based on the degree of regional boundary matching, the degree of overlap of suspension time, and the degree of service type matching, and to calculate the comprehensive matching score of each region based on the matching results. The generation module is used to filter out regions whose comprehensive matching score is greater than a preset threshold score, generate comprehensive query results, and push the comprehensive query results to the user. The comprehensive query results include the suspension status, the estimated recovery time, and the scope of impact.

9. A device for querying areas where express delivery is suspended, characterized in that, It includes a memory and at least one processor, wherein the memory stores computer-readable instructions; The at least one processor invokes the computer-readable instructions in the memory to perform the steps of the express delivery suspension area query method as described in any one of claims 1-7.

10. A computer-readable storage medium storing computer-readable instructions thereon, characterized in that, When the computer-readable instructions are executed by a processor, they implement the steps of the express delivery suspension area query method as described in any one of claims 1-7.

Images