Classification and grading and dynamic emergency plan generation method for online car-hailing operation events
Through the automated classification and grading of online ride-hailing operation events and the generation of dynamic emergency plans, the problems of slow response and low efficiency of traditional event processing methods are solved, and the nature and severity of events are quickly determined, and the efficiency of event processing and resource utilization are improved. .
Patent Information
- Application Number
- CN202411783748.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-06
- Publication Date
- 2025-02-07
AI Technical Summary
Traditional online ride-hailing emergency handling methods rely on manual monitoring and post-event response, resulting in slow response speed, low handling efficiency, poor information communication, and difficulty in handling emergencies in a timely manner, affecting urban traffic and passenger safety.
A classification and grading of online ride-hailing operation events and a dynamic emergency plan generation method are adopted. By obtaining operation events, traffic data and public opinion data, feature identification, event category and level determination are carried out, emergency plans are generated and processing information is sent.
Through the automated feature identification and classification and grading process, the nature and severity of the incident can be quickly determined, the time for emergency plan formulation is shortened, resource utilization efficiency is improved, and sufficient resources are required to respond to emergencies at critical moments, and event handling efficiency is improved.
Smart Images
Figure CN119398562A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of intelligent traffic management, and in particular to a method for classifying and grading online car-hailing operation events and generating dynamic emergency plans. Background Art
[0002] With the rapid development of the online car-hailing industry, online car-hailing has become an important part of the urban public transportation system, providing citizens with a convenient and flexible way of travel. However, the operation of online car-hailing also faces many challenges, especially the handling of various emergencies, which is crucial to ensuring passenger safety and maintaining urban traffic order.
[0003] The traditional way of handling emergencies in online ride-hailing services often relies on manual monitoring and post-event response, which has problems such as slow response, low handling efficiency, and poor information communication. Once an emergency occurs, such as a traffic accident, passenger dispute, or vehicle breakdown, it is often difficult to obtain accurate information in a timely manner, resulting in untimely handling of the incident, which may further aggravate the development of the situation and have a negative impact on urban traffic and passenger safety. Summary of the invention
[0004] The technical problem to be solved by the present invention is to provide a method for classifying and grading online car-hailing operation events and generating dynamic emergency plans, aiming to solve at least one of the above-mentioned technical problems.
[0005] The technical solution of the present invention to solve the above technical problems is as follows: In the first aspect, the present application provides a method for classifying and grading online car-hailing operation events and generating dynamic emergency plans, which adopts the following technical solutions: A method for classifying and grading online car-hailing operation events and generating dynamic emergency plans, comprising: Obtaining online car-hailing operation events and traffic data and public opinion data corresponding to the online car-hailing operation events, wherein the online car-hailing operation events are text information describing the operation of the online car-hailing; Performing feature recognition on the online car-hailing operation event to obtain feature information of the online car-hailing operation event; Determining the event category of the online car-hailing operation event based on the feature information and preset classification rules; Determine the event level of the online car-hailing operation event based on the characteristic information, the traffic data, the public opinion data and a preset classification rule, wherein the event level reflects the severity of the online car-hailing operation event; Based on the event category and the event level, an emergency plan for the online car-hailing operation event is generated, and emergency handling information is sent to relevant departments based on the emergency plan.
[0006] The beneficial effects of the present invention are as follows: the method combines traffic data and public opinion data, providing a more comprehensive and objective basis for event classification and grading. Through the automated feature recognition and classification and grading process, the nature and severity of online car-hailing operation events can be quickly determined, thereby greatly shortening the time for formulating emergency plans. According to the emergency plan for the event, emergency resources, such as rescue vehicles and personnel, can be deployed more specifically. This can not only improve the efficiency of resource utilization, but also ensure that there are sufficient resources to deal with emergencies at critical moments. The processing efficiency of online car-hailing operation events is improved.
[0007] Based on the above technical solution, the present invention can also be improved as follows.
[0008] Furthermore, the feature identification of the online car-hailing operation event to obtain feature information of the online car-hailing operation event includes: Performing word segmentation processing on the online car-hailing operation event to obtain multiple keywords of the online car-hailing operation event; Classifying the multiple keywords based on the KNN text classification model to determine the dimension to which each keyword belongs, wherein the dimension represents the category of the corresponding keyword; Based on the dimension of each keyword, respectively perform lexical analysis on the keyword corresponding to each dimension to obtain a lexical analysis result of the online car-hailing operation event, wherein for each keyword, the lexical analysis result includes part of speech and semantic information of the keyword; Based on the lexical analysis results and dimensions of all the keywords, characteristic information of the online car-hailing operation event is extracted, and the characteristic information includes casualty information, vehicle information, driver and passenger information, event location and event time.
[0009] The beneficial effect of adopting the above further scheme is: by performing word segmentation on the event, multiple keywords are obtained, and then the keywords are classified based on the KNN text classification model to determine the dimension to which each keyword belongs, thereby ensuring the accuracy of keyword category recognition. Next, the keywords corresponding to each dimension are subjected to lexical analysis to obtain lexical analysis results containing part of speech and semantic information, further improving the richness and accuracy of feature information. Finally, based on the lexical analysis results, detailed feature information including casualty information, vehicle information, driver and passenger information, event location and event time is extracted, providing reliable data support for subsequent event classification and grading.
[0010] Further, determining the event category of the online car-hailing operation event based on the feature information and preset classification rules includes: Based on the rule matching algorithm, respectively calculating the matching degree between the feature information and the feature information corresponding to each preset event category; The event category corresponding to the highest matching degree between the characteristic information and the characteristic information corresponding to each of the preset event categories is used as the event category of the online car-hailing operation event.
[0011] The beneficial effect of adopting the above further solution is that by calculating the matching degree between the feature information and the preset event category definition, the accuracy and reliability of event category judgment can be ensured. This method not only improves the efficiency of event classification, but also reduces the possibility of human misjudgment.
[0012] Furthermore, the method for determining each of the preset event categories includes: Obtain a data set, the data set including multiple historical online car-hailing operation events; Preprocessing each of the historical online car-hailing operation events to obtain a preprocessing result of each of the historical online car-hailing operation events; Evaluate the preprocessing results of each of the historical online ride-hailing operation events based on the TF-IDF algorithm to obtain an evaluation result of each of the historical online ride-hailing operation events, wherein the evaluation result includes a feature vector of each word in the corresponding historical online ride-hailing operation event; Performing dimensionality reduction processing on the evaluation results of each of the historical online ride-hailing operation events based on dimensionality reduction technology to obtain dimensionality reduction results of each of the historical online ride-hailing operation events; Based on a preset clustering method and a dimensionality reduction result of each of the historical online car-hailing operation events, a clustering result is determined, wherein the clustering result includes a plurality of clusters, each cluster representing an event category; Get expert classification advice information; Based on the clustering result and the classification suggestion information, a plurality of preset event categories are determined, each of the event categories including a plurality of specific events and event definitions corresponding to the specific events.
[0013] The beneficial effects of adopting the above further scheme are: by preprocessing the data set of historical online car-hailing operation events and evaluating the TF-IDF algorithm, the key features of the events can be extracted. The application of dimensionality reduction technology further simplifies the data, reduces noise, makes the clustering results clearer, and helps to identify event categories with similar characteristics. Combined with the classification advice information from experts, it can ensure that the final event category meets both data characteristics and actual business needs and professional knowledge, improving the scientificity and accuracy of the classification.
[0014] Furthermore, the clustering result is determined based on the preset clustering method and the dimensionality reduction result of each of the historical online car-hailing operation events, including: Cluster the dimensionality reduction results corresponding to all historical online car-hailing operation events based on the K-Means algorithm to obtain the first clustering result; Based on the MiniBatchKMeans algorithm, the dimensionality reduction results corresponding to all historical online car-hailing operation events are clustered to obtain the second clustering result; Determining a target number of clusters based on the first clustering result, the second clustering result, the elbow rule, and the silhouette coefficient evaluation algorithm; The clustering results are determined based on the target number of clusters, the preset clustering algorithm and the dimensionality reduction results corresponding to all historical online car-hailing operation events.
[0015] The beneficial effect of adopting the above further scheme is that by combining the K-Means algorithm and the MiniBatchKMeans algorithm, they can verify and complement each other, thereby improving the accuracy and stability of clustering. Combining the elbow rule and the silhouette coefficient evaluation algorithm, the target number of clusters can be determined more accurately, thereby avoiding the problem of poor clustering effect caused by too many or too few clusters. By determining the target number of clusters and clustering the historical online car-hailing operation events after dimensionality reduction based on the cluster number and the preset clustering algorithm, the final clustering result can be obtained. The interpretability and practicality of the clustering results are improved.
[0016] Further, determining the event level of the online car-hailing operation event based on the feature information, the traffic data, the public opinion data and a preset classification rule includes: Determine a first level of the online car-hailing operation event based on the casualty information and a preset casualty index grading table, where the first level reflects the degree of impact of casualties caused by the online car-hailing operation event; Determining a second level of the online car-hailing operation event based on the traffic data, the second level reflecting the degree of impact of the online car-hailing operation event on congestion; Determine a public opinion index based on the public opinion data of the online car-hailing operation event, wherein the public opinion index represents the degree of public attention to the online car-hailing operation event; Based on the public opinion index and a preset public opinion index indicator grading table, determining the third level of the online car-hailing operation event, wherein the third level reflects the degree of influence of the online car-hailing operation event on public opinion; Based on the first level, the second level and the third level, the event level of the online car-hailing operation event is determined.
[0017] The beneficial effect of adopting the above further scheme is that the method comprehensively considers the casualties, traffic congestion and public opinion of the online car-hailing operation incident, so as to more comprehensively evaluate the impact of the incident. By using a preset grading table, a clear basis and standard is provided for the evaluation, reducing the uncertainty of subjective judgment.
[0018] Furthermore, generating an emergency plan for the online car-hailing operation event based on the event category and the event level includes: Based on the event category, determining a plurality of historical plans for a preset time period; Calculate the similarity between the online car-hailing operation event and the event corresponding to each of the historical plans respectively, and take the historical plan corresponding to the highest similarity between the online car-hailing operation event and the event corresponding to each of the historical plans as the target historical plan; Based on the event level, the target historical plan and the online car-hailing operation event, an emergency plan for the online car-hailing operation event is generated.
[0019] The beneficial effect of adopting the above further scheme is that by determining multiple historical plans for a preset time period based on the event category, the method can screen out historical plans with a high degree of similarity to the current online car-hailing operation event as a reference. By calculating the similarity between the online car-hailing operation event and the event corresponding to each historical plan, and selecting the historical plan with the highest similarity as the target historical plan, the method can quickly locate the plan template that best suits the current event. Based on the target historical plan, the specific circumstances of the current online car-hailing operation event, and the event level, the measures and steps in the plan can be flexibly adjusted to adapt to events of different levels and categories.
[0020] In the second aspect, the present application provides a device for classifying and grading online car-hailing operation events and generating dynamic emergency plans, which adopts the following technical solutions: A device for classifying and grading online car-hailing operation events and generating dynamic emergency plans, comprising: An acquisition module, used to acquire online car-hailing operation events and traffic data and public opinion data corresponding to the online car-hailing operation events, wherein the online car-hailing operation events are text information describing the operation of the online car-hailing; A feature recognition module, used to perform feature recognition on the online car-hailing operation event to obtain feature information of the online car-hailing operation event; A classification module, used to determine the event category of the online car-hailing operation event based on the feature information and a preset classification model; A grading module, configured to determine the event level of the online car-hailing operation event based on the feature information, the traffic data, the public opinion data and a preset grading rule, wherein the event level reflects the severity of the online car-hailing operation event; The plan generation module is used to generate an emergency plan for the online car-hailing operation event based on the event category and the event level, and send emergency handling information to relevant departments based on the emergency plan.
[0021] In a third aspect, the present application provides an electronic device, which adopts the following technical solution: An electronic device comprises a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executes the method for classifying and grading online car-hailing operation events and generating dynamic emergency plans as described in any one of the first aspects.
[0022] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium storing a computer program that can be loaded by a processor and execute the method for classifying and grading online car-hailing operation events and generating dynamic emergency plans as described in any one of the first aspects.
[0023] Additional aspects and advantages of the present application will be partially given in the following description, which will become apparent from the following description, or will be understood through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] Figure 1 A flow chart of a method for classifying and grading online car-hailing operation events and generating a dynamic emergency plan provided by an embodiment of the present invention; Figure 2 A structural block diagram of a device for classifying and grading online car-hailing operation events and generating dynamic emergency plans provided by one embodiment of the present invention; Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0025] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0026] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.
[0027] An embodiment of the present application provides a method for classifying and grading online ride-hailing operation events and generating dynamic emergency plans. The method can be executed by an electronic device, which can be a server or a mobile terminal device. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services; the mobile terminal device can be a laptop computer, a desktop computer, etc., but is not limited to this.
[0028] like Figure 1 As shown, a method for classifying and grading online car-hailing operation events and generating dynamic emergency plans mainly includes steps S11 to S15: Step S11, obtaining an online car-hailing operation event and traffic data and public opinion data corresponding to the online car-hailing operation event, wherein the online car-hailing operation event is text information describing the operation of the online car-hailing operation; In one implementation, events occurring during the operation of the online ride-hailing service are discovered and recorded in a timely manner through real-time monitoring of vehicle operating status, passenger feedback, driver reports and other channels.
[0029] By cooperating with the traffic management department, we can obtain the traffic data of the surrounding roads when the online car-hailing operation incident occurs. The traffic data is obtained at a statistical interval of no more than 15 minutes, and the traffic data includes the average travel speed of each section of the network.
[0030] Use Baidu Index API to obtain public opinion data corresponding to online ride-hailing operation events. This public opinion data is the public opinion data within seven days when the online ride-hailing operation event occurs.
[0031] Step S12, performing feature recognition on the online car-hailing operation event to obtain feature information of the online car-hailing operation event; In one implementation, specifically, performing feature recognition on the online car-hailing operation event to obtain feature information of the online car-hailing operation event includes: Performing word segmentation processing on the online car-hailing operation event to obtain multiple keywords of the online car-hailing operation event; Classifying the multiple keywords based on the KNN text classification model to determine the dimension to which each keyword belongs, wherein the dimension represents the category of the corresponding keyword; Based on the dimension of each keyword, respectively perform lexical analysis on the keyword corresponding to each dimension to obtain a lexical analysis result of the online car-hailing operation event, wherein for each keyword, the lexical analysis result includes part of speech and semantic information of the keyword; Based on the lexical analysis results and dimensions of all the keywords, characteristic information of the online car-hailing operation event is extracted, and the characteristic information includes casualty information, vehicle information, driver and passenger information, event location and event time.
[0032] In the above implementation, a natural language processing library is used to perform word segmentation on the online car-hailing operation events, and multiple keywords of the online car-hailing operation events are output. For example, the online car-hailing operation event is "On May 1, 2023, an online car-hailing vehicle had a rear-end collision in Chaoyang District, Beijing. The driver was slightly injured and the passenger was unharmed." The word segmentation results are "May 1, 2023", "a", "online car-hailing vehicle", "in", "Chaoyang District, Beijing", "occurred", "rear-end collision", "accident", "driver", "suffer", "minor injuries", "passenger", "unharmed".
[0033] The dimension to which the keyword belongs is any one or more of the time dimension, location dimension, vehicle dimension, personnel dimension, event dimension, and casualty dimension.
[0034] According to the dimension of each keyword, the keyword corresponding to each dimension is subjected to lexical analysis. For example, the keyword is "online car-hailing", its part of speech is noun, and its semantics is the type of transportation. This improves the richness and accuracy of feature information. The feature information of the online car-hailing operation event is extracted through the dimension and lexical analysis results of each keyword, making the feature information extraction of the online car-hailing operation event more accurate.
[0035] Step S13, determining the event category of the online car-hailing operation event based on the feature information and preset classification rules; In one embodiment, step S13 mainly includes: calculating the matching degree between the feature information and the feature information corresponding to each preset event category based on a rule matching algorithm; The event category corresponding to the highest matching degree between the characteristic information and the characteristic information corresponding to each of the preset event categories is used as the event category of the online car-hailing operation event.
[0036] In the above implementation mode, the preset event categories are driver extreme behavior, industry department management, online car-hailing platform operation and special event.
[0037] Among them, the category of extreme driver behavior includes traffic violations and sudden psychological and physiological events. The category of industry management includes online car-hailing supervision events and online car-hailing policy events. The category of online car-hailing platforms includes online car-hailing platform management events, online car-hailing platform system events and online car-hailing gathering events. The category of special events includes extreme weather events and other major events.
[0038] Each event category has at least one definition for each specific event.
[0039] Traffic violations are defined as: drivers who, while transporting passengers, violate traffic regulations due to improper driving behaviors such as speeding, ignoring traffic signals, unsafe lane changes, etc., resulting in property damage, injury to passengers and other road users, or even more serious consequences.
[0040] As an optional implementation manner, the method for determining each of the preset event categories includes steps S131 to S137: Step S131, obtaining a data set, wherein the data set includes a plurality of historical online car-hailing operation events; Step S132, pre-processing each of the historical online car-hailing operation events to obtain a pre-processing result of each of the historical online car-hailing operation events; In the embodiment of the present application, preprocessing includes data cleaning processing, data formatting processing, word segmentation processing, etc.
[0041] Step S133, evaluating the preprocessing result of each of the historical online ride-hailing operation events based on the TF-IDF algorithm to obtain an evaluation result of each of the historical online ride-hailing operation events, wherein the evaluation result includes a feature vector of each word in the corresponding historical online ride-hailing operation event; In an embodiment of the present application, the word frequency and inverse document frequency of each historical online car-hailing operation event are calculated. The word frequency is the frequency of a word appearing in a document, and the inverse document frequency is the general importance of a word.
[0042] The formula for calculating word frequency is as follows: ; The calculation formula for inverse document frequency is as follows: ; The feature vector of each word in the historical online car-hailing operation events is the product of the word frequency and the inverse document frequency.
[0043] Step S134, performing dimensionality reduction processing on the evaluation results of each of the historical online ride-hailing operation events based on dimensionality reduction technology to obtain dimensionality reduction results of each of the historical online ride-hailing operation events; In the embodiment of the present application, a method such as SVD (Singular Value Decomposition) is used to reduce the dimension of the feature vector.
[0044] Step S135, determining a clustering result based on a preset clustering method and a dimensionality reduction result of each of the historical online car-hailing operation events, wherein the clustering result includes a plurality of clusters, each cluster representing an event category; In the embodiment of the present application, the clustering result is determined based on the preset clustering method and the dimensionality reduction result of each of the historical online car-hailing operation events, including: First, the dimensionality reduction results corresponding to all historical online car-hailing operation events are clustered based on the K-Means algorithm to obtain the first clustering result; Secondly, the dimensionality reduction results corresponding to all historical online car-hailing operation events are clustered based on the MiniBatchKMeans algorithm to obtain the second clustering result; Then, based on the first clustering result, the second clustering result, the elbow rule and the silhouette coefficient evaluation algorithm, a target number of clusters is determined; Finally, the clustering result is determined based on the target number of clusters, the preset clustering algorithm and the dimensionality reduction results corresponding to all historical online car-hailing operation events.
[0045] By combining the K-Means algorithm and the MiniBatchKMeans algorithm, they can verify and complement each other, thereby improving the accuracy and stability of clustering. Combining the elbow rule and the silhouette coefficient evaluation algorithm, the target number of clusters can be determined more accurately, thereby avoiding the problem of poor clustering results caused by too many or too few clusters. By determining the target number of clusters and clustering the historical online car-hailing operation events after dimensionality reduction based on the cluster number and the preset clustering algorithm, the final clustering result can be obtained. The interpretability and practicality of the clustering results are improved.
[0046] Step S136, obtaining classification suggestion information from experts; Step S137: Based on the clustering result and the classification suggestion information, a plurality of preset event categories are determined, each of which includes a plurality of specific events and an event definition corresponding to each of the specific events.
[0047] By preprocessing the data set of historical online ride-hailing operation events and evaluating the TF-IDF algorithm, the key features of the events can be extracted. The application of dimensionality reduction technology further simplifies the data, reduces noise, makes the clustering results clearer, and helps to identify event categories with similar features. Combined with the classification advice information from experts, it can ensure that the final event category is consistent with both data characteristics and actual business needs and professional knowledge, improving the scientificity and accuracy of the classification.
[0048] Step S14, determining the event level of the online car-hailing operation event based on the feature information, the traffic data, the public opinion data and a preset classification rule, wherein the event level reflects the severity of the online car-hailing operation event; In one embodiment, determining the event level of the online car-hailing operation event based on the feature information, the traffic data, the public opinion data and a preset classification rule includes: Determine a first level of the online car-hailing operation event based on the casualty information and a preset casualty index grading table, where the first level reflects the degree of impact of casualties caused by the online car-hailing operation event; Determining a second level of the online car-hailing operation event based on the traffic data, the second level reflecting the degree of impact of the online car-hailing operation event on congestion; Determine a public opinion index based on the public opinion data of the online car-hailing operation event, wherein the public opinion index represents the degree of public attention to the online car-hailing operation event; Based on the public opinion index and a preset public opinion index indicator grading table, determining the third level of the online car-hailing operation event, wherein the third level reflects the degree of influence of the online car-hailing operation event on public opinion; Based on the first level, the second level and the third level, the event level of the online car-hailing operation event is determined.
[0049] In one implementation, if the first level, second level, and third level of an online ride-hailing operation event are different, the highest level is used as the event level of the online ride-hailing operation event.
[0050] The public opinion index is the sum of the daily average of the search index and the daily average of the consultation index.
[0051] The above-mentioned preset casualty index grading table is shown in Table 1, and the preset public opinion index index grading table is shown in Table 2.
[0052] Table 1: Table 2: In one implementation, specifically, based on the traffic data, determining the second level of the online car-hailing operation event mainly includes: First, based on the traffic data, the mileage ratios of sections in the expressways, trunk roads, secondary trunk roads and branch roads that are in a severe congestion operation level are counted respectively; Afterwards, the congestion mileage ratio of each level of road is weighted by the vehicle-kilometer ratio to calculate and determine the congestion mileage ratio of the road network; Then, based on the conversion relationship between the congestion mileage ratio of the road network and a preset road traffic operation index, a road traffic operation index is calculated, wherein the road traffic operation index represents the congestion degree of the road network; Finally, based on the road traffic operation index and the preset TPI index indicator classification table, the second level of the online car-hailing operation event is determined.
[0053] The above preset TPI index indicator classification table is shown in Table 3.
[0054] Table 3: In another embodiment, specifically, based on the traffic data, determining the second level of the online car-hailing operation event mainly includes: Firstly, based on the traffic data, the average travel speeds in the expressways, main roads, secondary roads and branch roads are calculated respectively; Afterwards, the operation level of the road network is determined based on the average travel speed in expressways, trunk roads, secondary trunk roads and branch roads, the preset road section traffic operation level classification table and the event level. The operation level represents the congestion level of the road network. Finally, based on the operation level and the preset event level table, the second level of the online car-hailing operation event is determined.
[0055] It should be noted that for expressways and trunk roads, the roads themselves may be in a congested state, that is, the operating level of the road network is the set level. The second level of the online car-hailing operation event will then be determined based on the dynamic threshold table and real-time traffic data.
[0056] For example, if the road is in light congestion or above, the dynamic threshold table judgment method is used to determine the second level of the online car-hailing operation event. Based on historical data and real-time traffic flow monitoring, the average speed during peak hours is selected as the speed baseline.
[0057] The preset level classification table for traffic operation on the above-mentioned road section is Table 4, the preset event level is Table 5, and the preset dynamic threshold table is Table 6.
[0058] Table 4:
[0059] Table 5: Table 6:
[0060] Step S15, based on the event category and the event level, generate an emergency plan for the online car-hailing operation event, and send emergency handling information to relevant departments based on the emergency plan.
[0061] In one embodiment, generating an emergency plan for the online car-hailing operation event based on the event category and the event level includes: Based on the event category, determining a plurality of historical plans for a preset time period; Calculate the similarity between the online car-hailing operation event and the event corresponding to each of the historical plans respectively, and take the historical plan corresponding to the highest similarity between the online car-hailing operation event and the event corresponding to each of the historical plans as the target historical plan; Based on the event level, the target historical plan and the online car-hailing operation event, an emergency plan for the online car-hailing operation event is generated.
[0062] In the above implementation, according to the identified event category, the historical plans related to the category are retrieved in the plan library. These historical plans are emergency measures and action plans formulated for similar events in the past. The similarity between the online car-hailing operation event and the event corresponding to each historical plan is calculated separately. The similarity calculation can be based on multiple dimensions such as event description, time of occurrence, location, and scope of influence. Among the calculated similarities, find the historical plan corresponding to the highest similarity and use it as the target historical plan. The target historical plan is the historical plan that is most similar to the online car-hailing operation event and has the most reference value. Combined with the event level, the target historical plan, and the specific circumstances of the online car-hailing operation event, an emergency plan is formulated to improve the efficiency of emergency plan formulation, and emergency handling information is sent to relevant departments so that relevant departments can quickly handle the event.
[0063] This method combines traffic data and public opinion data to provide a more comprehensive and objective basis for event classification and grading. Through the automated feature recognition and classification and grading process, the nature and severity of online ride-hailing operation events can be quickly determined, thereby greatly shortening the time for emergency plan formulation. According to the emergency plan for the event, emergency resources, such as rescue vehicles and personnel, can be deployed more specifically. This can not only improve resource utilization efficiency, but also ensure that there are sufficient resources to respond to emergencies at critical moments. Improve the efficiency of handling online ride-hailing operation events.
[0064] Figure 2 A structural block diagram of a device 200 for classifying and grading online car-hailing operation events and generating dynamic emergency plans, provided as an embodiment of the present invention.
[0065] like Figure 2 As shown, a classification and grading device 200 for online car-hailing operation events and a dynamic emergency plan generation device mainly includes: An acquisition module 201 is used to acquire an online car-hailing operation event and traffic data and public opinion data corresponding to the online car-hailing operation event, wherein the online car-hailing operation event is text information describing the operation of the online car-hailing operation; A feature recognition module 202 is used to perform feature recognition on the online car-hailing operation event to obtain feature information of the online car-hailing operation event; A classification module 203, used to determine the event category of the online car-hailing operation event based on the feature information and a preset classification model; A grading module 204, configured to determine the event level of the online car-hailing operation event based on the feature information, the traffic data, the public opinion data and a preset grading rule, wherein the event level reflects the severity of the online car-hailing operation event; The plan generation module 205 is used to generate an emergency plan for the online car-hailing operation event based on the event category and the event level, and send emergency handling information to relevant departments based on the emergency plan.
[0066] Optionally, the feature recognition module 202 is specifically used for: Performing word segmentation processing on the online car-hailing operation event to obtain multiple keywords of the online car-hailing operation event; Classifying the multiple keywords based on the KNN text classification model to determine the dimension to which each keyword belongs, wherein the dimension represents the category of the corresponding keyword; Based on the dimension of each keyword, respectively perform lexical analysis on the keyword corresponding to each dimension to obtain a lexical analysis result of the online car-hailing operation event, wherein for each keyword, the lexical analysis result includes part of speech and semantic information of the keyword; Based on the lexical analysis results and dimensions of all the keywords, characteristic information of the online car-hailing operation event is extracted, and the characteristic information includes casualty information, vehicle information, driver and passenger information, event location and event time.
[0067] Optionally, the classification module 203 is specifically used for: Based on the rule matching algorithm, respectively calculating the matching degree between the feature information and the feature information corresponding to each preset event category; The event category corresponding to the highest matching degree between the characteristic information and the characteristic information corresponding to each of the preset event categories is used as the event category of the online car-hailing operation event.
[0068] Optionally, the classification module 203 further includes: A first acquisition submodule is used to acquire a data set, wherein the data set includes a plurality of historical online car-hailing operation events; A preprocessing submodule, used to preprocess each of the historical online car-hailing operation events to obtain a preprocessing result for each of the historical online car-hailing operation events; An evaluation submodule, for evaluating the preprocessing results of each of the historical online ride-hailing operation events based on the TF-IDF algorithm, and obtaining an evaluation result of each of the historical online ride-hailing operation events, wherein the evaluation result includes a feature vector of each word in the corresponding historical online ride-hailing operation event; A dimensionality reduction processing submodule is used to perform dimensionality reduction processing on the evaluation results of each of the historical online car-hailing operation events based on dimensionality reduction technology to obtain dimensionality reduction results of each of the historical online car-hailing operation events; A clustering submodule, for determining a clustering result based on a preset clustering method and a dimensionality reduction result of each of the historical online car-hailing operation events, wherein the clustering result includes a plurality of clusters, each cluster representing an event category; The second acquisition submodule is used to obtain classification suggestion information from experts; The determination submodule is used to determine a plurality of preset event categories based on the clustering result and the classification suggestion information, each of the event categories including a plurality of specific events and an event definition corresponding to each of the specific events.
[0069] Optionally, the clustering submodule is specifically used for: Cluster the dimensionality reduction results corresponding to all historical online car-hailing operation events based on the K-Means algorithm to obtain the first clustering result; Based on the MiniBatchKMeans algorithm, the dimensionality reduction results corresponding to all historical online car-hailing operation events are clustered to obtain the second clustering result; Determining a target number of clusters based on the first clustering result, the second clustering result, the elbow rule, and the silhouette coefficient evaluation algorithm; The clustering results are determined based on the target number of clusters, the preset clustering algorithm and the dimensionality reduction results corresponding to all historical online car-hailing operation events.
[0070] Optionally, the classification module 204 is specifically used for: Determine a first level of the online car-hailing operation event based on the casualty information and a preset casualty index grading table, where the first level reflects the degree of impact of casualties caused by the online car-hailing operation event; Determining a second level of the online car-hailing operation event based on the traffic data, the second level reflecting the degree of impact of the online car-hailing operation event on congestion; Determine a public opinion index based on the public opinion data of the online car-hailing operation event, wherein the public opinion index represents the degree of public attention to the online car-hailing operation event; Based on the public opinion index and a preset public opinion index indicator grading table, determining the third level of the online car-hailing operation event, wherein the third level reflects the degree of influence of the online car-hailing operation event on public opinion; Based on the first level, the second level and the third level, the event level of the online car-hailing operation event is determined.
[0071] Optional, plan generation module, specifically used for: Based on the event category, determining a plurality of historical plans for a preset time period; Calculate the similarity between the online car-hailing operation event and the event corresponding to each of the historical plans respectively, and take the historical plan corresponding to the highest similarity between the online car-hailing operation event and the event corresponding to each of the historical plans as the target historical plan; Based on the event level, the target historical plan and the online car-hailing operation event, an emergency plan for the online car-hailing operation event is generated.
[0072] In one example, the module in any of the above devices can be one or more integrated circuits configured to implement the above methods, such as: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.
[0073] For another example, when the modules in the device can be implemented in the form of a processing element scheduling program, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call a program. For another example, these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC).
[0074] Various objects such as various messages / information / equipment / network elements / systems / devices / actions / operations / processes / concepts that may appear in this application are named. It can be understood that these specific names do not constitute a limitation on the relevant objects. The names assigned may change with factors such as scenarios, contexts or usage habits. The understanding of the technical meaning of the technical terms in this application should be mainly determined from the functions and technical effects embodied / executed in the technical scheme.
[0075] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0076] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0077] Figure 3 This is a structural block diagram of an electronic device 300 according to an embodiment of the present application.
[0078] like Figure 3 As shown, the electronic device 300 includes a processor 301 and a memory 302 , and may further include one or more of an information input / information output (I / O) interface 303 , a communication component 304 , and a communication bus 305 .
[0079] The processor 301 is used to control the overall operation of the electronic device 300 to complete all or part of the steps in the above-mentioned classification and grading of online car-hailing operation events and dynamic emergency pre-examination generation method; the memory 302 is used to store various types of data to support the operation of the electronic device 300, and these data may include, for example, instructions for any application or method used to operate on the electronic device 300, and application-related data. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, EPROM), programmable read-only memory (Programmable Read-Only Memory, PROM), read-only memory (Read-Only Memory, ROM), magnetic memory, flash memory, disk or optical disk. One or more.
[0080] The I / O interface 303 provides an interface between the processor 301 and other interface modules, and the above-mentioned other interface modules can be keyboards, mice, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 304 is used to test the wired or wireless communication between the electronic device 300 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 304 can include: Wi-Fi components, Bluetooth components, NFC components.
[0081] The communication bus 305 may include a path to transmit information between the above components. The communication bus 305 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 305 may be divided into an address bus, a data bus, a control bus, etc.
[0082] The electronic device 300 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components, and is used to execute the classification and grading of online car-hailing operation events and the dynamic emergency pre-examination generation method given in the above embodiment.
[0083] The computer-readable storage medium provided in the embodiments of the present application is introduced below. The computer-readable storage medium described below and the classification and grading of online car-hailing operation events and the dynamic emergency pre-examination generation method described above can be referenced to each other.
[0084] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned classification and grading of online car-hailing operation events and dynamic emergency pre-examination generation method are implemented.
[0085] The computer-readable storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.
[0086] The terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus.
[0087] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned application concept. For example, the above features are replaced with (but not limited to) technical features with similar functions applied in the present application.
Claims
1. A method for classifying and grading online car-hailing operation events and generating dynamic emergency plans, characterized in that: include: Obtaining online car-hailing operation events and traffic data and public opinion data corresponding to the online car-hailing operation events, wherein the online car-hailing operation events are text information describing the operation of the online car-hailing; Performing feature recognition on the online car-hailing operation event to obtain feature information of the online car-hailing operation event; Determining the event category of the online car-hailing operation event based on the feature information and preset classification rules; Determine the event level of the online car-hailing operation event based on the feature information, the traffic data, the public opinion data and a preset classification rule, wherein the event level reflects the severity of the online car-hailing operation event; Based on the event category and the event level, an emergency plan for the online car-hailing operation event is generated, and emergency handling information is sent to relevant departments based on the emergency plan.
2. According to claim 1, a method for classifying and grading online car-hailing operation events and generating dynamic emergency plans is characterized in that: The feature identification of the online car-hailing operation event to obtain feature information of the online car-hailing operation event includes: Performing word segmentation processing on the online car-hailing operation event to obtain multiple keywords of the online car-hailing operation event; Classifying the multiple keywords based on the KNN text classification model to determine the dimension to which each keyword belongs, wherein the dimension represents the category of the corresponding keyword; Based on the dimension of each keyword, respectively perform lexical analysis on the keyword corresponding to each dimension to obtain a lexical analysis result of the online car-hailing operation event, wherein for each keyword, the lexical analysis result includes part of speech and semantic information of the keyword; Based on the lexical analysis results and dimensions of all the keywords, characteristic information of the online car-hailing operation event is extracted, and the characteristic information includes casualty information, vehicle information, driver and passenger information, event location and event time.
3. A method for classifying and grading online car-hailing operation events and generating dynamic emergency plans according to claim 2, characterized in that: The determining the event category of the online car-hailing operation event based on the feature information and the preset classification rules includes: Based on the rule matching algorithm, respectively calculating the matching degree between the feature information and the feature information corresponding to each preset event category; The event category corresponding to the highest matching degree between the characteristic information and the characteristic information corresponding to each of the preset event categories is used as the event category of the online car-hailing operation event.
4. A method for classifying and grading online car-hailing operation events and generating dynamic emergency plans according to claim 3, characterized in that: The method for determining each of the preset event categories includes: Obtain a data set, the data set including multiple historical online car-hailing operation events; Preprocessing each of the historical online car-hailing operation events to obtain a preprocessing result of each of the historical online car-hailing operation events; Evaluate the preprocessing results of each of the historical online ride-hailing operation events based on the TF-IDF algorithm to obtain an evaluation result of each of the historical online ride-hailing operation events, wherein the evaluation result includes a feature vector of each word in the corresponding historical online ride-hailing operation event; Performing dimensionality reduction processing on the evaluation results of each of the historical online ride-hailing operation events based on dimensionality reduction technology to obtain dimensionality reduction results of each of the historical online ride-hailing operation events; Based on a preset clustering method and a dimensionality reduction result of each of the historical online car-hailing operation events, a clustering result is determined, wherein the clustering result includes a plurality of clusters, each cluster representing an event category; Get expert classification advice information; Based on the clustering result and the classification suggestion information, a plurality of preset event categories are determined, each of the event categories including a plurality of specific events and an event definition corresponding to each of the specific events.
5. A method for classifying and grading online car-hailing operation events and generating dynamic emergency plans according to claim 4, characterized in that: The clustering result is determined based on the preset clustering method and the dimension reduction result of each of the historical online car-hailing operation events, including: Cluster the dimensionality reduction results corresponding to all historical online car-hailing operation events based on the K-Means algorithm to obtain the first clustering result; Based on the MiniBatchKMeans algorithm, the dimensionality reduction results corresponding to all historical online car-hailing operation events are clustered to obtain the second clustering result; Determining a target number of clusters based on the first clustering result, the second clustering result, the elbow rule, and the silhouette coefficient evaluation algorithm; The clustering results are determined based on the target number of clusters, the preset clustering algorithm and the dimensionality reduction results corresponding to all historical online car-hailing operation events.
6. A method for classifying and grading online car-hailing operation events and generating dynamic emergency plans according to claim 2, characterized in that: The determining the event level of the online car-hailing operation event based on the feature information, the traffic data, the public opinion data and a preset classification rule includes: Determine a first level of the online car-hailing operation event based on the casualty information and a preset casualty index grading table, where the first level reflects the degree of impact of casualties caused by the online car-hailing operation event; Determining a second level of the online car-hailing operation event based on the traffic data, the second level reflecting the degree of impact of the online car-hailing operation event on congestion; Determine a public opinion index based on the public opinion data of the online car-hailing operation event, wherein the public opinion index represents the degree of public attention to the online car-hailing operation event; Based on the public opinion index and a preset public opinion index indicator grading table, determining the third level of the online car-hailing operation event, wherein the third level reflects the degree of influence of the online car-hailing operation event on public opinion; Based on the first level, the second level and the third level, the event level of the online car-hailing operation event is determined.
7. A method for classifying and grading online car-hailing operation events and generating dynamic emergency plans according to claim 1, characterized in that: The generating of the emergency plan for the online car-hailing operation event based on the event category and the event level includes: Based on the event category, determining a plurality of historical plans for a preset time period; Calculate the similarity between the online car-hailing operation event and the event corresponding to each of the historical plans respectively, and take the historical plan corresponding to the highest similarity between the online car-hailing operation event and the event corresponding to each of the historical plans as the target historical plan; Based on the event level, the target historical plan and the online car-hailing operation event, an emergency plan for the online car-hailing operation event is generated.
8. A device for classifying and grading online car-hailing operation events and generating dynamic emergency plans, characterized in that: include: An acquisition module, used to acquire online car-hailing operation events and traffic data and public opinion data corresponding to the online car-hailing operation events, wherein the online car-hailing operation events are text information describing the operation of the online car-hailing; A feature recognition module, used to perform feature recognition on the online car-hailing operation event to obtain feature information of the online car-hailing operation event; A classification module, used to determine the event category of the online car-hailing operation event based on the feature information and a preset classification model; A grading module, configured to determine the event level of the online car-hailing operation event based on the feature information, the traffic data, the public opinion data and a preset grading rule, wherein the event level reflects the severity of the online car-hailing operation event; The plan generation module is used to generate an emergency plan for the online car-hailing operation event based on the event category and the event level, and send emergency handling information to relevant departments based on the emergency plan.
9. An electronic device, characterized in that: comprising a processor coupled to a memory; The processor is configured to execute a computer program stored in the memory, so that the electronic device executes the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The method comprises a computer program or an instruction, and when the computer program or the instruction is executed on a computer, the computer is caused to execute the method according to any one of claims 1 to 7.