Line optimization evaluation method, device, equipment, medium and program product
By constructing a probability distribution model and sampling analysis, the time-consuming and operating speed characteristics of logistics lines are evaluated, and the problems of low efficiency and high cost of logistics lines optimization in the existing technology are solved, and accurate line optimization and cost reduction are achieved.
Patent Information
- Application Number
- CN202411159552.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-22
- Publication Date
- 2024-11-19
AI Technical Summary
The existing logistics line optimization methods mainly rely on manual analysis, which have low efficiency, high cost and lack of pre-mining optimization capabilities, and it is difficult to comprehensively consider the influence of multiple factors.
By constructing a probability distribution model based on historical transportation data, sampling and analyzing time-consuming and operating speed characteristics, evaluating whether the logistics line needs to be optimized, including determining the time-consuming and operating speed characteristic distribution, providing evaluation results for optimization.
Accurate evaluation and optimization of logistics lines has been achieved, the quality of transportation services has been improved, the cost of transportation services has been reduced, and potential problems can be discovered and adjusted in advance.
Smart Images

Figure CN118982128A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the fields of artificial intelligence and big data technology, and in particular to evaluation methods, devices, equipment, media and program products for line optimization. Background Art
[0002] Fixed shifts in logistics refer to logistics transportation services that are arranged according to certain time patterns and routes. Generally, they depart at fixed times every day, week or month, and are delivered along fixed routes and paths. This fixed-shift logistics service can improve the efficiency and reliability of logistics transportation, reduce logistics costs, and provide customers with more stable and efficient logistics services. For example, a logistics company departs from A at 8 am every day, passes through B, C, D, etc., and arrives at destination E at 5 pm. This model is a fixed shift in logistics. Whether the route is reasonable has a vital impact on the speed and cost of transportation services. Therefore, it is crucial to find out in time that the route needs to be optimized and optimize the route in time. Summary of the invention
[0003] In view of the above problems, the present disclosure provides a line optimization evaluation method, apparatus, device, medium and program product.
[0004] According to a first aspect of the present disclosure, a route optimization evaluation method is provided, comprising: determining the time taken by an object associated with the historical route to complete a transportation task based on historical transportation data associated with the historical route; constructing a probability distribution model with time taken as a random variable based on an operating speed parameter of the object, a time consumption parameter for the historical route, and a time consumption variance parameter; when it is determined that the distribution of the time consumption satisfies a test condition, sampling the probability distribution model in the dimensions of the time consumption parameter, the operating speed parameter, and the time consumption variance parameter, respectively, to obtain a time consumption characteristic distribution of the historical route and a running speed characteristic distribution of the object; and evaluating the historical route based on the time consumption characteristic distribution and / or the operating speed characteristic distribution to obtain an evaluation result for characterizing whether the historical route needs to be optimized.
[0005] According to an embodiment of the present disclosure, a historical route has a fixed path, a fixed planned time and a fixed object set; based on the time consumption feature distribution and / or the running speed feature distribution, the historical route is evaluated to obtain an evaluation result for characterizing whether the historical route needs to be optimized, including: based on the time consumption feature distribution, the fixed planned time is evaluated to obtain an evaluation result for characterizing whether the fixed planned time needs to be optimized; based on the running speed feature distribution, the fixed object set is evaluated to obtain an evaluation result for characterizing whether the fixed object set needs to be optimized; and based on the time consumption feature distribution and the running speed feature distribution, the fixed planned time and the fixed path are evaluated to obtain an evaluation result for characterizing whether the fixed planned time and the fixed path need to be optimized.
[0006] According to an embodiment of the present disclosure, based on the time consumption characteristic distribution and the running speed characteristic distribution, the fixed plan time consumption and the fixed path are evaluated to obtain an evaluation result for characterizing whether the fixed plan time consumption and the fixed path need to be optimized, including: determining the predicted time consumption for the historical route based on the quantile that meets the preset conditions in the time consumption characteristic distribution; determining the pause ratio value for the historical route based on the running speed characteristic distribution and the pause condition; and determining the evaluation result based on the pause ratio value and the difference between the predicted time consumption and the fixed plan time consumption.
[0007] According to an embodiment of the present disclosure, an evaluation result is determined based on the pause ratio value and the difference between the predicted time and the fixed plan time, including: when it is determined that the difference is less than a first threshold, an evaluation result is obtained that characterizes the need to optimize the fixed plan time; when it is determined that the difference is greater than a second threshold and the pause ratio is less than a third threshold, an evaluation result is obtained that characterizes the need to optimize the fixed plan time, wherein the second threshold is greater than the first threshold; when it is determined that the difference is greater than the second threshold and the pause ratio is greater than the third threshold, an evaluation result is obtained that characterizes the need to optimize the fixed path.
[0008] According to an embodiment of the present disclosure, the fixed plan time consumption is evaluated based on the time consumption feature distribution to obtain an evaluation result for characterizing whether the fixed plan time consumption needs to be optimized, including: determining the predicted time consumption for the historical route based on the quantile that meets the preset conditions in the time consumption feature distribution; and obtaining an evaluation result characterizing the need to optimize the fixed plan time consumption when it is determined that the difference between the predicted time consumption and the fixed plan time consumption is outside the preset difference range.
[0009] According to an embodiment of the present disclosure, historical transportation data includes abnormal task data and normal task data of an object when completing a transportation task; based on the running speed characteristic distribution, a fixed object set is evaluated to obtain an evaluation result for characterizing whether the fixed object set needs to be optimized, including: based on the running speed characteristic distribution, determining the running speed characteristic value of the object; based on the running speed characteristic value and the abnormality rate of the object, according to preset classification rules, determining the category to which the object belongs, wherein the abnormality rate is determined based on the abnormal task data and the normal task data; based on a label matching the category, determining the evaluation result of whether the fixed object set needs to be optimized.
[0010] According to an embodiment of the present disclosure, the probability distribution model includes a lognormal distribution; the line optimization evaluation method also includes: performing a hypothesis test of a lognormal distribution on the distribution of the time consumption in the dimensions of the time consumption parameter and the operating speed parameter, respectively, to obtain a test result, wherein the test result is used to characterize whether the time consumption satisfies the lognormal distribution; and when it is determined that the test result characterizes that the time consumption satisfies the lognormal distribution, determining that the distribution of the time consumption satisfies the test condition.
[0011] According to an embodiment of the present disclosure, when it is determined that the distribution of time consumption meets the test conditions, the probability distribution model is sampled in the dimensions of time consumption parameter, running speed parameter and time consumption variance parameter respectively to obtain the time consumption characteristic distribution of the historical route and the running speed characteristic distribution of the object, including: when it is determined that the distribution of time consumption meets the test conditions, for the time consumption parameter, running speed parameter and time consumption variance parameter respectively, the following operations are repeatedly performed: by presetting the sampled Markov chain length, determining the number of times Gibbs sampling is performed; and repeatedly performing Gibbs sampling based on the number of Gibbs sampling to obtain multiple sampling results; based on the multiple sampling results, determining the time consumption characteristic distribution of the historical route and the running speed characteristic distribution of the object.
[0012] According to an embodiment of the present disclosure, the Gibbs sampling method includes: determining the mean of the probability distribution model as the sampling value of the current state, and determining the normal distribution with the variance of the probability distribution model as a preset value as the sampling function; inputting the sampling value into the sampling function to generate a target value; using the target value as the next transition state, determining the logarithmic probability difference before and after the transition; and when it is determined that the logarithmic probability difference meets the difference threshold, determining the target value as the sampling result.
[0013] According to an embodiment of the present disclosure, historical transportation data includes the number of the object, the date, start time and end time when the object completes the transportation task; based on the transportation data associated with the historical route, the time consumed by the object associated with the historical route to complete the transportation task is determined, including: grouping the dates with weeks as the granularity to obtain multiple date combinations, wherein each date combination in the multiple date combinations corresponds to a different historical route; determining the number of times the object completes the transportation task according to the number of dates corresponding to each date combination in the multiple date combinations; determining the time difference when the object completes each transportation task according to the start time and the end time; and determining the time consumed by the object associated with the historical route to complete the transportation task based on the number of times and the time difference when each transportation task is completed.
[0014] A second aspect of the present disclosure provides an evaluation device for route optimization, characterized in that the device includes: a determination module, which is used to determine the time consumed by an object associated with a historical route in completing a transportation task based on historical transportation data associated with the historical route; a construction module, which is used to construct a probability distribution model with time consumption as a random variable based on the running speed parameter of the object, the time consumption parameter for the historical route, and the time consumption variance parameter; a sampling module, which is used to sample the probability distribution model in the dimensions of time consumption parameter, running speed parameter, and time consumption variance parameter respectively when it is determined that the distribution of the time consumption meets the inspection conditions, so as to obtain the time consumption characteristic distribution of the historical route and the running speed characteristic distribution of the object; and an evaluation module, which is used to evaluate the historical route based on the time consumption characteristic distribution and / or the running speed characteristic distribution, and obtain an evaluation result used to characterize whether the historical route needs to be optimized.
[0015] A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the above-mentioned line optimization evaluation method.
[0016] The fourth aspect of the present disclosure further provides a computer-readable storage medium having a computer program or instruction stored thereon, which implements the steps of the above-mentioned line optimization evaluation method when the above-mentioned computer program or instruction is executed by a processor.
[0017] The fifth aspect of the present disclosure further provides a computer program product, including a computer program or instructions, which implement the steps of the above-mentioned line optimization evaluation method when the above-mentioned computer program or instructions are executed by a processor.
[0018] According to the embodiments of the present disclosure, based on the running speed parameters of the object, the time consumption parameters for the historical routes, and the time consumption variance parameters, a probability distribution model with time consumption as a random variable is constructed, and the time consumption characteristics of the historical routes and the running speed characteristics of the objects determined by sampling are used to determine whether the historical routes need to be optimized. The simulation sampling results that comprehensively consider the characteristic parameters of the historical routes and the objects are more accurate than simple descriptive statistics, and can predetermine whether the routes need to be optimized, improve the quality of transportation services, and reduce transportation service costs. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:
[0020] Figure 1 The application scenario diagram schematically shows the evaluation method, device, equipment, medium and program product of line optimization according to the embodiment of the present disclosure;
[0021] Figure 2 A flow chart schematically shows a method for evaluating line optimization according to an embodiment of the present disclosure;
[0022] Figure 3 A statistical histogram of sampling results according to an embodiment of the present disclosure is schematically shown;
[0023] Figure 4 A schematic diagram of line optimization according to an embodiment of the present disclosure is schematically shown;
[0024] Figure 5 A schematic diagram of driver optimization according to an embodiment of the present disclosure is schematically shown;
[0025] Figure 6 A structural block diagram schematically shows an evaluation device for line optimization according to an embodiment of the present disclosure; and
[0026] Figure 7 A block diagram of an electronic device suitable for implementing an evaluation method for line optimization according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION
[0027] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.
[0028] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.
[0029] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.
[0030] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).
[0031] In the technical solution of the present disclosure, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.
[0032] In the scenario of using personal information for automated decision-making, the methods, devices, and systems provided by the embodiments of the present disclosure provide users with corresponding operation portals for users to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered. The expression "automated decision-making" here refers to the activity of automatically analyzing and evaluating a person's behavioral habits, interests and hobbies, or economic, health, credit status, etc. through computer programs, and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by people who specialize in a certain field, have specialized experience, knowledge and skills, and have reached a certain level of professionalism.
[0033] In the technical solution of the embodiment of the present disclosure, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.
[0034] In the process of implementing the present disclosure, it is found that fixed shifts generally need to determine the departure time of the transport vehicle and also need to estimate the arrival time of the vehicle. The actual transportation on the route is often different from the planned time. In addition to random errors, this difference may also come from errors in the plan itself, problems with the driver, the complexity of road conditions, etc. How to discover these problems in a timely manner and optimize the route in a timely manner is crucial. At present, the existing optimization method is to continuously analyze and monitor the data through operators, and deal with the reported problems. However, the manual analysis of operators faces a large amount of operational data, which takes a lot of time and manpower. At the same time, manual judgment is often affected by subjective factors and may not analyze the problem completely objectively. The existing optimization method belongs to post-optimization, that is, to find the cause based on the problems that have occurred, and lacks ex ante mining optimization. In addition, some companies have also made descriptive statistical portraits of routes and transport drivers for perception, but the descriptive statistical portraits of routes and transport drivers are weak in comprehensive analysis of multiple factors. For example, when a certain route is portrayed, only the route is evaluated separately, and the quality of the drivers performing tasks on the route is not comprehensively considered. The operational problems of fixed routes often involve multiple related factors, which requires the algorithm to have the ability to conduct comprehensive analysis of multiple factors, but descriptive statistical profiling is relatively weak in this ability.
[0035] Based on this, the present disclosure provides an evaluation method for route optimization, which locates the optimization direction from the historical transportation data of transportation time, and can optimize the transportation route plan, such as optimizing the time plan of the transportation route with time deviation and / or optimizing the route path itself by analyzing the specific reasons for time anomalies. It can also optimize drivers or vehicles from the perspective of the capacity of performing transportation tasks, such as removing problematic drivers or vehicles from the alternative capacity pool in advance.
[0036] The embodiments of the present disclosure provide a method, device, equipment, medium and program product for evaluating route optimization. The method includes: determining the time taken by an object associated with the historical route to complete a transportation task based on historical transportation data associated with the historical route; constructing a probability distribution model with time taken as a random variable based on the running speed parameter of the object, the time taken parameter for the historical route and the time taken variance parameter; sampling the probability distribution model in the dimensions of the time taken parameter, the running speed parameter and the time taken variance parameter respectively when it is determined that the distribution of the time taken meets the test conditions, and obtaining the time taken characteristic distribution of the historical route and the running speed characteristic distribution of the object; and evaluating the historical route based on the time taken characteristic distribution and / or the running speed characteristic distribution, and obtaining an evaluation result for characterizing whether the historical route needs to be optimized.
[0037] Figure 1 The application scenario diagram of the line optimization evaluation method, device, equipment, medium and program product according to the embodiment of the present disclosure is schematically shown.
[0038] like Figure 1 As shown, the application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.
[0039] The user may use at least one of the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).
[0040] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.
[0041] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.
[0042] It should be noted that the evaluation method for line optimization provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the evaluation device for line optimization provided in the embodiment of the present disclosure can generally be set in the server 105. The evaluation method for line optimization provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the evaluation device for line optimization provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.
[0043] It should be understood that Figure 1The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.
[0044] The following will be based on Figure 1 The scene described by Figure 2~Figure 5 The evaluation method for line optimization of the disclosed embodiment is described in detail.
[0045] Figure 2 The flowchart of the evaluation method for line optimization according to the embodiment of the present disclosure is schematically shown.
[0046] like Figure 2 As shown, the line optimization evaluation method 200 of this embodiment may include operations S210 to S240.
[0047] In operation S210 , based on the historical transportation data associated with the historical routes, the time taken by the object associated with the historical routes to complete the transportation task is determined.
[0048] According to an embodiment of the present disclosure, the historical route may include a vehicle operation route in a logistics transportation service arranged in a fixed logistics shift. The historical transportation data may be used to characterize the data generated by an object when completing a transportation task. The object may include a vehicle or a driver.
[0049] According to an embodiment of the present disclosure, historical transportation data may be acquired from an operation system, and then transportation time may be extracted from the historical transportation data, and the time consumption may be determined based on the transportation time.
[0050] In operation S220, a probability distribution model with the time consumption as a random variable is constructed based on the running speed parameter of the object, the time consumption parameter for the historical route, and the time consumption variance parameter.
[0051] According to the embodiments of the present disclosure, since the running speed, time consumption and other data of the object under consideration can be obtained based on historical transportation data, by analyzing these data and then locating the optimization direction, line problems can be discovered in time and feedback can be given to operators, which is conducive to timely optimization of the line.
[0052] Therefore, the present disclosure regards the time consumption as a random variable, which conforms to the probability distribution. The probability distribution may include the distribution of common continuous random variables. A multi-parameter probability distribution model may be constructed based on the running speed parameter of the object, the time consumption parameter for the historical route, and the time consumption variance parameter.
[0053] According to an embodiment of the present disclosure, a probability distribution model may be used to determine the distribution of the running speed of an object and the distribution of the time consumption for a historical route.
[0054] In operation S230, when it is determined that the distribution of time consumption meets the test condition, the probability distribution model is sampled in the dimensions of time consumption parameter, running speed parameter and time consumption variance parameter to obtain the time consumption characteristic distribution of the historical route and the running speed characteristic distribution of the object.
[0055] According to an embodiment of the present disclosure, the inspection condition may include that the distribution of time consumption conforms to the probability distribution.
[0056] According to an embodiment of the present disclosure, the time consumption feature distribution can be used to characterize the distribution of time consumption in historical routes. The object's running speed feature distribution can be used to characterize the distribution of the object's running speed when completing a transportation task for a historical route.
[0057] According to an embodiment of the present disclosure, sampling may include a probability distribution sampling method, such as a Markov Chain Monte Carlo method (MCMC for short).
[0058] In operation S240, the historical routes are evaluated based on the time consumption characteristic distribution and / or the running speed characteristic distribution to obtain an evaluation result indicating whether the historical routes need to be optimized.
[0059] According to an embodiment of the present disclosure, the time consumption characteristic distribution and / or the running speed characteristic distribution can be used as a priori probability, and the posterior probability estimation is obtained based on the priori probability. The historical route is evaluated based on the posterior probability estimation and the actual historical route plan.
[0060] For example, if the posterior probability estimate differs from the actual historical route plan by more than a preset value, an evaluation result may be obtained indicating that the historical route needs to be optimized.
[0061] According to the embodiments of the present disclosure, based on the running speed parameters of the object, the time consumption parameters for the historical routes, and the time consumption variance parameters, a probability distribution model with time consumption as a random variable is constructed, and the time consumption characteristics of the historical routes and the running speed characteristics of the objects determined by sampling are used to determine whether the historical routes need to be optimized. The simulation sampling results that comprehensively consider the characteristic parameters of the historical routes and the objects are more accurate than simple descriptive statistics, and can predetermine whether the routes need to be optimized, improve the quality of transportation services, and reduce transportation service costs.
[0062] According to an embodiment of the present disclosure, the historical transportation data may include the number of the object, the date when the object completes the transportation task, the start time, and the end time.
[0063] For example Figure 2The operation S210 shown, based on the transportation data associated with the historical route, determines the time taken by the object associated with the historical route to complete the transportation task, and may include the operations of: grouping the dates with weeks as the granularity to obtain multiple date combinations; determining the number of times the object completes the transportation task according to the number of dates corresponding to each date combination in the multiple date combinations; determining the time difference when the object completes each transportation task according to the start time and the end time; and determining the time taken by the object associated with the historical route to complete the transportation task based on the number of times and the time difference when each transportation task is completed.
[0064] According to an embodiment of the present disclosure, each of the multiple date combinations corresponds to a different historical route. For each historical route, the time taken by the object associated with the historical route to complete the transportation task can be determined.
[0065] According to an embodiment of the present disclosure, the time difference for each time an object completes a transportation task may be accumulated and summed, and then averaged to obtain the time taken by the object associated with the historical route to complete the transportation task.
[0066] According to the embodiments of the present disclosure, dates are divided into weeks, and routes on different dates are considered as different historical routes, which is beneficial to parameter estimation.
[0067] According to an embodiment of the present disclosure, if it is determined that each object has performed multiple transportation tasks on a historical route in a week, the median may be selected from the time differences as the time taken by the object associated with the historical route to complete the transportation task.
[0068] According to an embodiment of the present disclosure, the probability distribution model may include a log-normal distribution. The evaluation method for line optimization may include: Figure 2 In addition to the operations S210 to S240 shown, the following operations may also be included: performing a hypothesis test of a log-normal distribution on the distribution of the time consumption in the dimensions of the time consumption parameter and the running speed parameter to obtain a test result; and when it is determined that the test result indicates that the time consumption satisfies the log-normal distribution, determining that the distribution of the time consumption satisfies the test condition.
[0069] According to an embodiment of the present disclosure, the test result is used to characterize whether the time consumption satisfies the log-normal distribution.
[0070] According to an embodiment of the present disclosure, the logarithm of the time consumption is taken in the dimensions of the time consumption parameter and the running speed parameter, and then the normal distribution test is performed by the Shapiro-Wilk test method. The null hypothesis can be that the distribution of the time consumption satisfies the normal distribution, and the alternative hypothesis can be that the distribution of the time consumption does not satisfy the normal distribution. If the null hypothesis is not rejected, it means that the distribution of the time consumption is close to the normal distribution, and it can be further determined that the distribution of the time consumption meets the test conditions.
[0071] According to the embodiments of the present disclosure, by performing a log-normal distribution hypothesis test on the distribution of time consumption, it is possible to further determine whether the hypothesis is reasonable, thereby facilitating further simulation sampling based on the constructed probability distribution model.
[0072] According to the embodiments of the present disclosure, Figure 2 The operation S230 shown, when it is determined that the distribution of time consumption meets the test conditions, samples the probability distribution model in the dimensions of time consumption parameter, running speed parameter and time consumption variance parameter respectively to obtain the time consumption characteristic distribution of the historical route and the running speed characteristic distribution of the object, may include the following operations: when it is determined that the distribution of time consumption meets the test conditions, repeatedly perform the following operations for the time consumption parameter, running speed parameter and time consumption variance parameter respectively: determine the number of times to perform Gibbs sampling by presetting the sampled Markov chain length; and repeatedly perform Gibbs sampling based on the number of Gibbs sampling to obtain multiple sampling results; based on the multiple sampling results, determine the time consumption characteristic distribution of the historical route and the running speed characteristic distribution of the object.
[0073] According to an embodiment of the present disclosure, the length of the Markov chain of the preset sampling can be determined according to the accuracy actually required. The length of the Markov chain of the preset sampling can be determined as the number of times Gibbs sampling is performed.
[0074] According to the embodiments of the present disclosure, the initial state and prior distribution of each parameter can be set. The initial value of the time-consuming parameter for the historical route is 0, and the prior distribution is the standard normal distribution. The initial value of the running speed parameter of the object is 0, and the prior distribution is the standard normal distribution. The initial value of the time-consuming variance parameter is 1, and the prior distribution is the log-normal distribution. Gibbs sampling is used to obtain the sampling result of the Markov chain length of the preset sampling.
[0075] Considering that the Markov chain needs to go through multiple state transitions to reach a stable state, the sampling is closer to the real distribution at this time. Therefore, a distribution close to the real distribution can be achieved by discarding a certain number of sampling results in the early stage.
[0076] For example, the length of the Markov chain for preset sampling can be set to 20,000, that is, the Gibbs sampling process is repeated 20,000 times, the first 5,000 samples are discarded, and the last 15,000 samples are retained as the final sampling results of the three parameters, and the mean of the sampling results is selected as the estimated value of the parameter. If the sample size is particularly large, the length of the Markov chain can be increased and the sampling length can be discarded based on the stability of the state transition process. After obtaining a stable sampling, the a posteriori probability expectation can be estimated as the final estimate to obtain the time-consuming characteristic distribution of the historical route and the running speed characteristic distribution of the object.
[0077] According to an embodiment of the present disclosure, the Gibbs sampling method may include the following operations: determining the mean of the probability distribution model as the sampling value of the current state, and determining the normal distribution with the variance of the probability distribution model as a preset value as the sampling function; inputting the sampling value into the sampling function to generate a target value; using the target value as the next transition state to determine the logarithmic probability difference before and after the transition; and determining the target value as the sampling result when it is determined that the logarithmic probability difference satisfies the difference threshold.
[0078] According to an embodiment of the present disclosure, the preset value may be 1. Whether the logarithmic probability difference satisfies the difference threshold may be determined by MH (Metropolis-Hastings) sampling. The present disclosure does not specifically limit how to determine whether the logarithmic probability difference satisfies the difference threshold.
[0079] According to the embodiments of the present disclosure, the sampling times are determined by presetting the length of the sampled Markov chain, so that the sampling results can be closer to the real distribution. The time consumption of historical routes and objects is comprehensively considered, and the characteristics of historical routes and objects are mined, which is more accurate than extracting basic statistical features from historical routes or objects alone.
[0080] Figure 3 A statistical histogram of sampling results according to an embodiment of the present disclosure is schematically shown.
[0081] According to an embodiment of the present disclosure, the running speed characteristic distribution of the object or the time consumption characteristic distribution of the historical route can be used for statistical testing whether there is a significant difference.
[0082] For example, a statistical test can be performed on whether there is a significant difference in the running speed characteristic distribution parameters of two objects. Taking the driver as an example, the estimated value of the running speed characteristic distribution parameter is obtained by calculating the posterior probability expectation through the Markov chain. The evaluation of this parameter can eliminate the impact of different routes on the time. For example, the routes that these two drivers usually take to complete transportation tasks may be completely different, and simple statistical mean variance is not comparable. However, the present disclosure can comprehensively sample all historical routes and all drivers, so the running speed characteristic obtained is a relative value that can be compared. Figure 3 As shown in the figure, the sampling results of driver 1 and driver 2 can be extracted, and then the frequency can be counted and plotted into a histogram. Figure 3 As can be seen from the histogram shown, driver 2's operating speed is better than driver 1.
[0083] According to one embodiment of the present disclosure, there may be multiple objects. The object may include a driver. There may be multiple historical routes. Based on multiple historical transportation data associated with multiple historical routes, a data table with driver number, route number, date, and time consumption as fields may be determined. Routes on different dates may be considered as different historical routes, and the data table with driver number, route number, date, and time consumption as fields may be converted into a table with date-route number as rows, driver number as columns, and time consumption as values, and the value corresponding to the driver number that did not participate in a certain date-route number may be a null value. Since sampling is based on posterior probability sampling and is not affected by null values, there is no need to fill in null values.
[0084] According to an embodiment of the present disclosure, the probability distribution may include a lognormal distribution. For example, there are i drivers, j historical routes, i.e., date-route numbers, and the value is time consuming t ij .
[0085] The probability density expression can be shown as follows:
[0086] (1)
[0087] Among them, x represents the time t ij ; Indicates the driver's running speed parameter; Indicates the time-consuming parameters of the historical route; represents the time-consuming variance parameter; Represents a random item.
[0088] The driver's running speed parameter can be determined by the driver's experience, safety awareness, seriousness and other factors. The time parameter of the historical route can be determined by the mileage, geography and other factors of the historical route. The driver's running speed parameter and the time parameter of the historical route can jointly determine the mean of the random distribution of the time it takes a driver to complete a transportation task on a certain historical route. Some influencing factors, such as weather, temporary road conditions, etc., can be summarized in the random terms. The time variance parameter can be the difference in time taken by the driver to complete the transportation task on different historical routes, which can be determined by the nature of the historical route itself.
[0089] According to an embodiment of the present disclosure, the historical route has a fixed path, a fixed planned time, and a fixed object set. Figure 2The operation S240 shown, based on the time consumption feature distribution and / or the running speed feature distribution, evaluates the historical routes to obtain an evaluation result for characterizing whether the historical routes need to be optimized, and may include the following operations: based on the time consumption feature distribution, evaluates the fixed plan time to obtain an evaluation result for characterizing whether the fixed plan time needs to be optimized; based on the running speed feature distribution, evaluates the fixed object set to obtain an evaluation result for characterizing whether the fixed object set needs to be optimized; and based on the time consumption feature distribution and the running speed feature distribution, evaluates the fixed plan time and the fixed path to obtain an evaluation result for characterizing whether the fixed plan time and the fixed path need to be optimized.
[0090] According to an embodiment of the present disclosure, a fixed planned time is used to represent the scheduled time from the departure point to the destination. A fixed path is used to represent the scheduled path from the departure point to the destination. A fixed object set is used to represent the scheduled optional object set from the departure point to the destination.
[0091] According to the embodiments of the present disclosure, historical routes of different dates can be aggregated and counted to obtain the time consumption feature distribution corresponding to the historical routes, and the time consumption feature can be estimated by posterior probability expectation to obtain an estimated value. According to the difference between the estimated value and the fixed plan time consumption, an evaluation result of whether the fixed plan time consumption needs to be optimized can be accurately characterized. For example, if the difference between the estimated value and the fixed plan time consumption is large, the fixed plan time consumption needs to be optimized. If the difference between the estimated value and the fixed plan time consumption is small, there is no need to optimize the fixed plan time consumption.
[0092] According to the embodiments of the present disclosure, the running speed characteristics can be estimated based on the distribution of the running speed characteristics of the object, and the speed estimation value can be obtained. The running speed means of all objects on the historical line are averaged to obtain the speed standard value. According to the difference between the speed estimation value and the speed standard value, the evaluation result of whether the fixed object set needs to be optimized can be accurately characterized. For example, if the difference between the speed estimation value and the speed standard value is large, the fixed object set needs to be optimized, such as removing the corresponding object from the fixed object set. If the difference between the speed estimation value and the speed standard value is small, there is no need to optimize the fixed object set.
[0093] According to the embodiments of the present disclosure, the difference between the estimated value and the fixed plan time consumption can be combined with the number of stop paths in the historical route to accurately characterize the evaluation result of whether the fixed plan time consumption and the fixed path need to be optimized. For example, if the time consumption difference is large and the number of stop paths is large, the fixed plan time consumption and the fixed path need to be optimized.
[0094] According to the embodiments of the present disclosure, by obtaining the time-consuming characteristic distribution and / or the running speed characteristic distribution based on the probability distribution model, it is possible to accurately evaluate whether it is necessary to optimize the historical routes, and provide accurate optimization reference suggestions for operators, thereby improving the quality of transportation services and reducing transportation service costs.
[0095] According to an embodiment of the present disclosure, based on the time consumption feature distribution, the fixed plan time consumption is evaluated to obtain an evaluation result for characterizing whether the fixed plan time consumption needs to be optimized, which may include the following operations: determining the predicted time consumption for the historical route based on the quantile that meets the preset conditions in the time consumption feature distribution; and obtaining an evaluation result characterizing the need to optimize the fixed plan time consumption when it is determined that the difference between the predicted time consumption and the fixed plan time consumption is outside the preset difference range.
[0096] According to an embodiment of the present disclosure, a quantile, which may also be referred to as a quantile point, may refer to a numerical point that divides the probability distribution range of a random variable into several equal parts. The preset condition may include a preset percentage quantile of the time-consuming characteristic distribution when the transportation task is expected to be completed on time. For example, the quantile that meets the preset condition may be the 95% quantile of the time-consuming characteristic distribution when the transportation task is expected to be completed on time 95%.
[0097] According to an embodiment of the present disclosure, the quantile can be logarithmically transformed to obtain the predicted time consumption for the historical route. The preset difference can be determined according to the accuracy of actual needs. For example, the difference can be 20% of the fixed plan time consumption. If the difference exceeds 20% of the fixed plan time consumption, the fixed plan time consumption needs to be optimized. For example, a label that the fixed plan time consumption needs to be adjusted can be marked for the historical route and pushed to the operator so that the operator can modify the fixed plan time consumption.
[0098] According to the embodiments of the present disclosure, by comparing the difference between the predicted time consumption and the fixed planned time consumption, it is possible to accurately evaluate whether the fixed planned time consumption needs to be adjusted.
[0099] Figure 4 A schematic diagram of line optimization according to an embodiment of the present disclosure is schematically shown.
[0100] According to an embodiment of the present disclosure, based on the time consumption characteristic distribution and the running speed characteristic distribution, the fixed plan time consumption and the fixed path are evaluated to obtain an evaluation result for characterizing whether the fixed plan time consumption and the fixed path need to be optimized, which may include the following operations: determining the predicted time consumption for the historical route based on the quantile that meets the preset conditions in the time consumption characteristic distribution; determining the pause ratio value for the historical route based on the running speed characteristic distribution and the pause condition; and determining the evaluation result based on the pause ratio value and the difference between the predicted time consumption and the fixed plan time consumption.
[0101] According to an embodiment of the present disclosure, the quantiles in the time consumption feature distribution that meet preset conditions may be logarithmically transformed to obtain the predicted time consumption for the historical route.
[0102] According to an embodiment of the present disclosure, the pause condition may include performing two differences on the data of the remaining mileage of the object in the dimension of preset minutes when the transportation task is completed, obtaining the running speed of the object, and determining the case where the running speed of the object is lower than half of the average speed as a pause. According to the pause condition, the pause ratio value for the historical route can be determined from the running speed characteristic distribution.
[0103] According to an embodiment of the present disclosure, historical routes can be classified according to pause ratio values and difference values to obtain categories to which the historical routes belong, target labels having a mapping relationship with the categories to which the historical routes belong are matched, and evaluation results are determined according to the target labels.
[0104] According to an embodiment of the present disclosure, historical routes may be classified into three categories, namely, route category 1, route category 2, and route category 3, based on pause ratio values and difference values in advance, and each category forms a mapping relationship with a label for indicating an evaluation result.
[0105] For example, the pause ratio value may be divided into a target dividing value, and the difference value may be divided into two dividing values, a first dividing value and a second dividing value, wherein the first dividing value is smaller than the second dividing value.
[0106] If the difference is less than the first demarcation value or the pause ratio is less than the target demarcation value and the difference is greater than the second demarcation value, it is classified as route category 1, and a mapping relationship is formed with the label that the time reservation is unreasonable and the fixed plan needs to be modified. If the difference is greater than the first demarcation value and less than the second demarcation value, it is classified as route category 2, and a mapping relationship is formed with the label of the conventional category and no route optimization is required. If the difference is greater than the second demarcation value and the pause ratio is greater than the target demarcation value, it is classified as route category 3, and a mapping relationship is formed with the label that it is necessary to check whether a certain path of the line is frequently congested or abnormal, and the line path needs to be updated.
[0107] For example, the first cutoff value may be the 10th percentile, the second cutoff value may be the 90th percentile, and the target cutoff value may be 70%.
[0108] like Figure 4As shown, based on the difference of multiple historical routes, the time deviation distribution can be determined, and the time deviation less than the 10% percentile, the time deviation greater than the 90% percentile and the pause ratio value less than 70% are classified as route category 1, and the corresponding matching label is: unreasonable time reservation, and the fixed plan time consumption needs to be modified. The time deviation greater than the 10% percentile and the time deviation less than the 90% percentile are classified as route category 2, and the corresponding matching label is: general category, no route optimization is required. The time deviation greater than the 90% percentile and the pause ratio value greater than 70% are classified as route category 3, and the corresponding matching label is: general category, it is necessary to check whether a certain path of the line is frequently congested or abnormal, and the line path needs to be updated.
[0109] According to the embodiments of the present disclosure, by combining the pause ratio value and the difference between the predicted time and the fixed planned time, it is possible to automatically find that the time plan in the route plan is unreasonable and determine that time adjustment is required. In addition, it is also possible to clearly identify the path that needs to be optimized, so that operators can optimize the historical routes in a timely manner according to the evaluation results.
[0110] According to one embodiment of the present disclosure, an evaluation result is determined based on the pause ratio value and the difference between the predicted time and the fixed plan time, and the operation may also be included: when it is determined that the difference is less than a first threshold, an evaluation result is obtained that indicates that the fixed plan time needs to be optimized; when it is determined that the difference is greater than a second threshold and the pause ratio is less than a third threshold, an evaluation result is obtained that indicates that the fixed plan time needs to be optimized, wherein the second threshold is greater than the first threshold; when it is determined that the difference is greater than the second threshold and the pause ratio is greater than the third threshold, an evaluation result is obtained that indicates that the fixed path needs to be optimized.
[0111] According to an embodiment of the present disclosure, the first threshold, the second threshold, and the third threshold may be determined empirically.
[0112] According to the embodiments of the present disclosure, by comparing the threshold values, it is not only possible to accurately determine whether to optimize the route, but also possible to further determine whether to optimize the fixed planned time consumption or the fixed path.
[0113] Figure 5 A schematic diagram of driver optimization according to an embodiment of the present disclosure is schematically shown.
[0114] According to an embodiment of the present disclosure, historical transportation data may include abnormal task data and normal task data of an object when completing a transportation task. Based on the running speed characteristic distribution, a fixed object set is evaluated to obtain an evaluation result for characterizing whether the fixed object set needs to be optimized, which may include: determining the running speed characteristic value of the object based on the running speed characteristic distribution; determining the category of the object based on the running speed characteristic value and the abnormal rate of the object according to a preset classification rule, wherein the abnormal rate is determined based on the abnormal task data and the normal task data; determining whether the fixed object set needs to be optimized based on a label matching the category.
[0115] According to an embodiment of the present disclosure, the number of abnormalities can be determined based on abnormal task data. The normal number can be determined based on normal task data. The number of tasks can be determined based on the sum of the normal number and the number of abnormalities. The abnormality rate of an object can be obtained based on the ratio of the number of abnormalities to the number of tasks.
[0116] According to an embodiment of the present disclosure, the preset classification rules may include classifying objects based on a comparison between a running speed characteristic value and a preset classification standard value corresponding to the running speed characteristic value and a comparison between an abnormality rate of the object and a preset classification standard value corresponding to the abnormality rate.
[0117] According to an embodiment of the present disclosure, the category to which an object belongs has a mapping relationship with a label. A fixed object set may also be a fixed transport capacity set, which may include a fixed vehicle set and a fixed driver set.
[0118] For example, Figure 5 As shown, taking drivers as an example, after obtaining the distribution of transportation speed characteristics of all drivers, multiple drivers can be classified according to the transportation speed characteristics of the 10% percentile, combined with the 50% abnormality rate, and the preset classification rules. Drivers whose transportation speed characteristic values are less than the 10% percentile and whose abnormality rate is greater than 50% can be classified into category 1, and the corresponding label can be: long-term slow speed and many abnormalities, it is recommended to be removed from the fixed driver set. Drivers whose transportation speed characteristic values are less than the 10% percentile and whose abnormality rate is less than 50% are classified into category 2, and the corresponding label can be: relative to all drivers, the long-term speed is slow, it is recommended that they pay attention to improving the transportation punctuality rate. Drivers whose transportation speed characteristic values are greater than the 90% percentile and whose abnormality rate is greater than 50% are classified into category 3, and the corresponding label can be: relative to all drivers, the long-term speed is fast and there are many abnormalities, it is recommended that they optimize the abnormalities. Drivers whose transportation speed characteristic values are greater than the 10% percentile and whose transportation speed characteristic values are less than the 90% percentile are classified into category 4, and the corresponding label can be: regular category, no need to optimize the fixed driver set. Drivers whose transport speed characteristic value is greater than the 90th percentile and whose abnormality rate is less than 50% are classified into category 5. The corresponding label can be: excellent transport resources, which can be used as input features for dispatching orders and given priority.
[0119] According to the embodiments of the present disclosure, by combining the running speed characteristics and the abnormality rate of the object, the object can be accurately classified, and the label matching the category can be used as the evaluation basis to accurately obtain the evaluation result.
[0120] Based on the above-mentioned line optimization evaluation method, the present disclosure also provides a line optimization evaluation device. Figure 6 The device is described in detail.
[0121] Figure 6 The structural block diagram of the circuit optimization evaluation device according to the embodiment of the present disclosure is schematically shown.
[0122] like Figure 6 As shown, the evaluation device 600 for line optimization of this embodiment includes a determination module 610 , a construction module 620 , a sampling module 630 and an evaluation module 640 .
[0123] The determination module 610 is used to determine the time taken by the object associated with the historical route to complete the transportation task based on the historical transportation data associated with the historical route. In one embodiment, the determination module 610 can be used to perform the operation S210 described above, which will not be described in detail here.
[0124] The construction module 620 is used to construct a probability distribution model with time consumption as a random variable based on the running speed parameter of the object, the time consumption parameter for the historical route, and the time consumption variance parameter. In one embodiment, the construction module 620 can be used to perform the operation S220 described above, which will not be repeated here.
[0125] The sampling module 630 is used to sample the probability distribution model in the dimensions of time consumption parameter, running speed parameter and time consumption variance parameter respectively when it is determined that the distribution of time consumption meets the inspection condition, so as to obtain the time consumption characteristic distribution of the historical route and the running speed characteristic distribution of the object. In one embodiment, the sampling module 630 can be used to perform the operation S230 described above, which will not be repeated here.
[0126] The evaluation module 640 is used to evaluate the historical route based on the time consumption characteristic distribution and / or the running speed characteristic distribution, and obtain an evaluation result for indicating whether the historical route needs to be optimized. In one embodiment, the evaluation module 640 can be used to perform the operation S240 described above, which will not be repeated here.
[0127] According to an embodiment of the present disclosure, the historical route has a fixed path, a fixed planned time and a fixed object set. The evaluation module 640 may include: a time evaluation unit, an object evaluation unit and a mixed evaluation unit.
[0128] The time consumption evaluation unit is used to evaluate the fixed plan time consumption based on the time consumption feature distribution, and obtain an evaluation result for indicating whether the fixed plan time consumption needs to be optimized.
[0129] The object evaluation unit is used to evaluate the fixed object set based on the running speed characteristic distribution, and obtain an evaluation result used to characterize whether the fixed object set needs to be optimized.
[0130] The hybrid evaluation unit is used to evaluate the fixed plan time consumption and the fixed path based on the time consumption characteristic distribution and the running speed characteristic distribution, and obtain an evaluation result for indicating whether the fixed plan time consumption and the fixed path need to be optimized.
[0131] According to an embodiment of the present disclosure, based on the time consumption characteristic distribution and the running speed characteristic distribution, the fixed plan time consumption and the fixed path are evaluated to obtain an evaluation result for characterizing whether the fixed plan time consumption and the fixed path need to be optimized, which may include: determining the predicted time consumption for the historical route based on the quantile that meets the preset conditions in the time consumption characteristic distribution; determining the pause ratio value for the historical route based on the running speed characteristic distribution and the pause condition; and determining the evaluation result based on the pause ratio value and the difference between the predicted time consumption and the fixed plan time consumption.
[0132] According to an embodiment of the present disclosure, determining an evaluation result based on the pause ratio value and the difference between the predicted time and the fixed plan time may include: when it is determined that the difference is less than a first threshold, obtaining an evaluation result indicating that the fixed plan time needs to be optimized; when it is determined that the difference is greater than a second threshold and the pause ratio value is less than a third threshold, obtaining an evaluation result indicating that the fixed plan time needs to be optimized, wherein the second threshold is greater than the first threshold; when it is determined that the difference is greater than the second threshold and the pause ratio value is greater than the third threshold, obtaining an evaluation result indicating that the fixed path needs to be optimized.
[0133] According to an embodiment of the present disclosure, based on the time consumption feature distribution, the fixed plan time consumption is evaluated to obtain an evaluation result for characterizing whether the fixed plan time consumption needs to be optimized, which may include: determining the predicted time consumption for the historical route based on the quantile in the time consumption feature distribution that meets the preset conditions; and when it is determined that the difference between the predicted time consumption and the fixed plan time consumption is outside the preset difference range, obtaining an evaluation result characterizing the need to optimize the fixed plan time consumption.
[0134] According to an embodiment of the present disclosure, historical transportation data includes abnormal task data and normal task data of an object when completing a transportation task; based on the running speed feature distribution, a fixed object set is evaluated to obtain an evaluation result for characterizing whether the fixed object set needs to be optimized, which may include: determining the running speed feature value of the object based on the running speed feature distribution; determining the category to which the object belongs based on the running speed feature value and the abnormality rate of the object according to preset classification rules, wherein the abnormality rate is determined based on the abnormal task data and the normal task data; determining whether the fixed object set needs to be optimized based on a label that matches the category.
[0135] According to an embodiment of the present disclosure, the probability distribution model may include a log-normal distribution; the evaluation device 600 for line optimization may further include: a verification module and a verification result determination module.
[0136] The test module is used to perform a log-normal distribution hypothesis test on the distribution of the time consumption in the dimensions of the time consumption parameter and the running speed parameter, respectively, to obtain a test result, wherein the test result is used to characterize whether the time consumption satisfies the log-normal distribution.
[0137] The test result determination module is used to determine that the distribution of the time consumption satisfies the test condition when it is determined that the test result characterization time consumption satisfies the log-normal distribution.
[0138] According to an embodiment of the present disclosure, the sampling module 630 may include: a repetitive execution unit and a feature distribution determination unit.
[0139] The repeated execution unit is used to repeatedly execute the following operations for the time consumption parameter, the running speed parameter and the time consumption variance parameter respectively when it is determined that the distribution of the time consumption meets the inspection conditions: determining the number of times Gibbs sampling is executed by presetting the sampling Markov chain length; and repeatedly executing Gibbs sampling based on the number of Gibbs sampling to obtain multiple sampling results.
[0140] The feature distribution determination unit is used to determine the time-consuming feature distribution of the historical route and the running speed feature distribution of the object based on multiple sampling results.
[0141] According to an embodiment of the present disclosure, the Gibbs sampling method may include: determining the mean of the probability distribution model as the sampling value of the current state, and determining the normal distribution with the variance of the probability distribution model as a preset value as the sampling function; inputting the sampling value into the sampling function to generate a target value; using the target value as the next transition state, determining the logarithmic probability difference before and after the transition; and when it is determined that the logarithmic probability difference meets the difference threshold, determining the target value as the sampling result.
[0142] According to an embodiment of the present disclosure, the determination module 610 may include: a grouping unit, a task number determination unit, a time difference determination unit, and a time consumption determination unit.
[0143] The grouping unit is used to group the dates with weeks as the granularity to obtain a plurality of date combinations, wherein each of the plurality of date combinations corresponds to a different historical route.
[0144] The task number determination unit is used to determine the number of times the object completes the transportation task according to the number of dates corresponding to each date combination in the multiple date combinations.
[0145] The time difference determination unit is used to determine the time difference when the object completes each transportation task according to the start time and the end time.
[0146] The time consumption determination unit is used to determine the time consumption of the object associated with the historical route in completing the transportation task based on the number of times and the time difference of each transportation task.
[0147] According to an embodiment of the present disclosure, any multiple modules of the determination module 610, the construction module 620, the sampling module 630 and the evaluation module 640 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the determination module 610, the construction module 620, the sampling module 630 and the evaluation module 640 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware and firmware or in any appropriate combination of any of them. Alternatively, at least one of the determination module 610, the construction module 620, the sampling module 630 and the evaluation module 640 can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function can be performed.
[0148] Figure 7 A block diagram of an electronic device suitable for implementing an evaluation method for line optimization according to an embodiment of the present disclosure is schematically shown.
[0149] like Figure 7As shown, the electronic device 700 according to an embodiment of the present disclosure includes a processor 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 to a random access memory (RAM) 703. The processor 701 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 701 may also include an onboard memory for caching purposes. The processor 701 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.
[0150] In RAM 703, various programs and data required for the operation of electronic device 700 are stored. Processor 701, ROM 702 and RAM 703 are connected to each other via bus 704. Processor 701 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 702 and / or RAM 703. It should be noted that the program can also be stored in one or more memories other than ROM 702 and RAM 703. Processor 701 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in one or more memories.
[0151] According to an embodiment of the present disclosure, the electronic device 700 may further include an input / output (I / O) interface 705, which is also connected to the bus 704. The electronic device 700 may further include one or more of the following components connected to the I / O interface 705: an input portion 706 including a keyboard, a mouse, etc.; an output portion 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 708 including a hard disk, etc.; and a communication portion 709 including a network interface card such as a LAN card, a modem, etc. The communication portion 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage portion 708 as needed.
[0152] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.
[0153] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, it may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 702 and / or RAM 703 described above and / or one or more memories other than ROM 702 and RAM 703.
[0154] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the method provided by the embodiment of the present disclosure.
[0155] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 701. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.
[0156] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 709, and / or installed from the removable medium 711. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.
[0157] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the processor 701, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.
[0158] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).
[0159] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0160] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways without departing from the spirit and teachings of the present disclosure. All of these combinations and / or combinations fall within the scope of the present disclosure.
[0161] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.
Claims
1. A line optimization evaluation method, characterized in that: The method comprises: Based on the historical transportation data associated with the historical route, determining the time taken by the object associated with the historical route to complete the transportation task; Based on the running speed parameter of the object, the time consumption parameter for the historical route and the time consumption variance parameter, a probability distribution model with the time consumption as a random variable is constructed; When it is determined that the distribution of the time consumption satisfies the inspection condition, the probability distribution model is sampled in the dimensions of the time consumption parameter, the running speed parameter, and the time consumption variance parameter to obtain the time consumption characteristic distribution of the historical route and the running speed characteristic distribution of the object; and Based on the time consumption characteristic distribution and / or the running speed characteristic distribution, the historical route is evaluated to obtain an evaluation result for indicating whether the historical route needs to be optimized.
2. The method according to claim 1, characterized in that The historical route has a fixed path, a fixed planned time and a fixed object set; The evaluating the historical route based on the time consumption characteristic distribution and / or the running speed characteristic distribution to obtain an evaluation result for indicating whether the historical route needs to be optimized includes: Based on the time consumption characteristic distribution, the fixed plan time consumption is evaluated to obtain the evaluation result used to characterize whether the fixed plan time consumption needs to be optimized; Based on the running speed characteristic distribution, the fixed object set is evaluated to obtain the evaluation result used to indicate whether the fixed object set needs to be optimized; and Based on the time consumption characteristic distribution and the running speed characteristic distribution, the fixed plan time consumption and the fixed path are evaluated to obtain the evaluation result for indicating whether the fixed plan time consumption and the fixed path need to be optimized.
3. The method according to claim 2, characterized in that The step of evaluating the fixed plan time consumption and the fixed path based on the time consumption characteristic distribution and the running speed characteristic distribution to obtain the evaluation result for indicating whether the fixed plan time consumption and the fixed path need to be optimized includes: Determining the predicted time consumption for the historical route based on the quantile that meets the preset conditions in the time consumption feature distribution; Determining a pause ratio value for the historical route based on the running speed characteristic distribution and the pause condition; and The evaluation result is determined based on the pause ratio value and the difference between the predicted time consumption and the fixed planned time consumption.
4. The method according to claim 3, characterized in that The determining the evaluation result based on the pause ratio value and the difference between the predicted time consumption and the fixed planned time consumption includes: When it is determined that the difference is less than the first threshold, obtaining the evaluation result indicating that the time consumption of the fixed plan needs to be optimized; When it is determined that the difference is greater than a second threshold and the pause ratio is less than a third threshold, obtaining the evaluation result indicating that the fixed plan time consumption needs to be optimized, wherein the second threshold is greater than the first threshold; When it is determined that the difference is greater than the second threshold and the pause ratio is greater than the third threshold, the evaluation result indicating that the fixed path needs to be optimized is obtained.
5. The method according to claim 2, characterized in that: The step of evaluating the fixed plan time consumption based on the time consumption feature distribution to obtain the evaluation result used to characterize whether the fixed plan time consumption needs to be optimized includes: Determining the predicted time consumption for the historical route based on the quantiles that meet the preset conditions in the time consumption feature distribution; and When it is determined that the difference between the predicted time consumption and the fixed planned time consumption is outside a preset difference range, the evaluation result indicating that the fixed planned time consumption needs to be optimized is obtained.
6. The method according to claim 2, characterized in that The historical transportation data includes abnormal task data and normal task data of the object when completing the transportation task; The step of evaluating the fixed object set based on the running speed characteristic distribution to obtain the evaluation result used to characterize whether the fixed object set needs to be optimized includes: Determining a running speed characteristic value of the object based on the running speed characteristic distribution; Based on the running speed characteristic value and the abnormality rate of the object, determining the category to which the object belongs according to a preset classification rule, wherein the abnormality rate is determined based on the abnormal task data and the normal task data; Based on the label matching the category, determining whether the evaluation result of optimizing the fixed object set is required.
7. The method according to claim 1, characterized in that The probability distribution model includes a lognormal distribution; The method further comprises: Performing a hypothesis test of the log-normal distribution on the distribution of the time consumption in the dimensions of the time consumption parameter and the running speed parameter, respectively, to obtain a test result, wherein the test result is used to indicate whether the time consumption satisfies the log-normal distribution; and In the case where it is determined that the inspection result indicates that the time consumption satisfies the log-normal distribution, it is determined that the distribution of the time consumption satisfies the inspection condition.
8. The method according to claim 1, characterized in that When it is determined that the distribution of the time consumption satisfies the inspection condition, the probability distribution model is sampled in the dimensions of the time consumption parameter, the running speed parameter, and the time consumption variance parameter to obtain the time consumption characteristic distribution of the historical route and the running speed characteristic distribution of the object, including: When it is determined that the distribution of the time consumption satisfies the test condition, the following operations are repeatedly performed for the time consumption parameter, the running speed parameter, and the time consumption variance parameter respectively: Determining the number of Gibbs samplings to be performed by presetting the length of the sampled Markov chain; and Repeating the Gibbs sampling based on the number of Gibbs sampling to obtain multiple sampling results; Based on the plurality of sampling results, the time consumption characteristic distribution of the historical route and the running speed characteristic distribution of the object are determined.
9. The method according to claim 8, characterized in that The Gibbs sampling method includes: Determine the mean of the probability distribution model as the sampling value of the current state, and determine the normal distribution whose variance of the probability distribution model is a preset value as the sampling function; Inputting the sampled value into the sampling function to generate a target value; Taking the target value as the next transition state, determining the logarithmic probability difference before and after the transition; and When it is determined that the logarithmic probability difference satisfies a difference threshold, the target value is determined as the sampling result.
10. The method according to claim 1, characterized in that The historical transportation data includes the number of the object, the date, start time and end time when the object completes the transportation task; The determining, based on the transportation data associated with the historical route, the time consumed by the object associated with the historical route to complete the transportation task includes: The dates are grouped with weeks as the granularity to obtain a plurality of date combinations, wherein each of the plurality of date combinations corresponds to a different historical route; Determining the number of times the object completes the transportation task according to the number of dates corresponding to each date combination in the multiple date combinations; Determine the time difference when the object completes each transportation task according to the start time and the end time; and The time consumed by the object associated with the historical route in completing the transportation task is determined based on the number of times and the time difference between each transportation task.
11. A circuit optimization evaluation device, characterized in that: The device comprises: A determination module, configured to determine the time taken by an object associated with the historical route to complete a transportation task based on historical transportation data associated with the historical route; A construction module, used to construct a probability distribution model with the time consumption as a random variable based on the running speed parameter of the object, the time consumption parameter for the historical route and the time consumption variance parameter; a sampling module, configured to sample the probability distribution model in the dimensions of the time consumption parameter, the running speed parameter, and the time consumption variance parameter respectively, to obtain the time consumption characteristic distribution of the historical route and the running speed characteristic distribution of the object, when it is determined that the distribution of the time consumption meets the inspection condition; and An evaluation module is used to evaluate the historical route based on the time consumption characteristic distribution and / or the running speed characteristic distribution, and obtain an evaluation result used to characterize whether the historical route needs to be optimized.
12. An electronic device comprising: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 10.
13. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.
14. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.
