A Markov chain-based traffic dynamic prediction method and system

Abstract

The present application relates to the field of logistics and transportation technology, and in particular to a method and system for dynamic traffic prediction based on a Markov chain. The provided technical solution includes: comparing the first transportation personnel information with the first preset transportation efficiency data to obtain the third transportation personnel information, comparing the second transportation personnel information with the second preset transportation efficiency data to obtain the fourth transportation personnel information, and obtaining the specific number of high-quality transportation personnel and the specific number of general transportation personnel based on the first transportation personnel information, the second transportation personnel information, the third transportation personnel information and the fourth transportation personnel information. The technical effects include: obtaining more realistic predicted logistics data, and then the enterprise can further optimize the plan for the future, reduce operating costs, and optimize the configuration of transportation personnel. This method brings significant economic and social benefits to the enterprise.

Description

Technical Field

[0001] The present application relates to the field of logistics and transportation technology, and in particular to a method and system for dynamic flow prediction based on a Markov chain. Background Art

[0002] The working principle of the Markov chain model is mainly based on its "memorylessness" or "Markov property", that is, the state of a random process at a certain moment in the future is only related to the current state, but not to the past state. This property makes the Markov chain very useful in analyzing problems with time series characteristics.

[0003] In the logistics volume forecasting of the Markov chain model, its uncertainty can be used to effectively predict the quantity of goods that will appear in the future, and then the corresponding transportation strategy can be configured based on the predicted quantity of goods. However, in the existing forecasting models, the information obtained by simple retrieval is directly brought into the Markov chain model to predict the transportation volume, and no further analysis of the collected information is performed. The resulting forecast results deviate too much from reality, which affects the company's future strategic planning. Summary of the Invention

[0004] The present application provides a method and system for dynamic traffic prediction based on Markov chain to solve the problem that the existing technology directly brings the information obtained by simple retrieval into the Markov chain model to predict the transportation flow, and the prediction results deviate greatly from the actual situation.

[0005] In a first aspect, the present application provides a method for dynamic traffic prediction based on a Markov chain, comprising:

[0006] Acquire historical logistics data, establish a logistics database based on the historical logistics data, compare a number of historical logistics data in the first time period with the logistics database, and obtain a number of abnormal logistics data and a number of normal logistics data based on the comparison results;

[0007] Obtaining historical transportation data of a number of transport personnel during the first time period, comparing the historical transportation data with a preset transportation database, and obtaining information of a number of high-quality transport personnel and information of a number of general transport personnel based on the comparison results;

[0008] Bringing a plurality of preset transport personnel information into a first Markov chain model, and obtaining a plurality of first transport personnel information and a plurality of second transport personnel information through simulation of the first Markov chain model;

[0009] Comparing the first transport personnel information with the first preset transport efficiency data to obtain third transport personnel information, and comparing the second transport personnel information with the second preset transport efficiency data to obtain fourth transport personnel information, and obtaining the specific number of high-quality transport personnel and the specific number of general transport personnel based on the first transport personnel information, the second transport personnel information, the third transport personnel information, and the fourth transport personnel information;

[0010] The specific number of high-quality transport personnel and the specific number of general transport personnel are brought into the second Markov chain model, and the actual number of risk logistics orders is simulated and predicted by the second Markov chain model. The number of third transport personnel is determined based on the actual number of risk logistics orders, and the required additional cost is determined based on the number of third personnel.

[0011] The above technical solution has the following advantages:

[0012] Optionally, the comparing of the plurality of historical logistics data in the first time period with the logistics database to obtain a plurality of abnormal logistics data and a plurality of normal logistics data through the comparison results includes:

[0013] Wherein, the logistics database includes: preset logistics loss data and preset logistics time abnormality data;

[0014] The number of abnormal logistics data includes: the number of lost logistics information and the number of time-abnormal logistics information;

[0015] The number of general logistics data includes: the number of other logistics data except abnormal logistics data in the plurality of historical logistics data in the first time period;

[0016] Comparing the plurality of logistics information with the preset logistics loss data, if the logistics information matches the preset logistics loss data, determining it as lost logistics information, and recording the number of lost logistics information;

[0017] Compare the logistics information with the preset logistics time abnormality data. If the logistics information meets the preset logistics time abnormality data, it is determined as time abnormal logistics information, and the number of the time abnormal logistics information is recorded.

[0018] The above technical solution has the following advantages: it can not only detect and deal with problems in the logistics process in a timely manner, but also predict future logistics data, providing strong support for the company's decision-making.

[0019] Optionally, the acquiring of historical transport data of a plurality of transport personnel in the first time period, comparing the historical transport data with a preset transport database, and obtaining information of a plurality of high-quality transport personnel and information of a plurality of general transport personnel based on the comparison results, including:

[0020] The historical transportation data includes: historical lost data and historical timeout data;

[0021] Wherein, the preset transport database includes: a preset lost data threshold and a preset timeout threshold;

[0022] Comparing the plurality of historical lost data with the preset lost data threshold, and if the historical lost data is less than the preset lost data threshold, generating a first transport mark and attaching it to the historical transport data of the transport personnel;

[0023] Comparing the historical timeout data with the preset timeout threshold, and if the historical timeout data is less than the preset timeout threshold, generating a second transport mark and appending it to the historical transport data of the transport personnel;

[0024] If the transport personnel's historical transport data has both the first transport mark and the second transport mark, high-quality transport information is generated, and the transport personnel is determined to be the high-quality transport personnel based on the high-quality transport information.

[0025] Acquire a number of high-quality transport personnel data, and obtain first quantity information according to the number of high-quality transport personnel data;

[0026] If the transport personnel's historical transport data does not contain both the first transport mark and the second transport mark, then general transport information is generated, and the transport personnel is determined to be the general transport personnel through the general transport information.

[0027] A number of the general transport personnel data are obtained, and second quantity information is determined according to the number of the general transport personnel data.

[0028] The above technical solution has the following advantages: high-quality transport personnel can be identified based on historical data, and the performance of the entire transport team can be evaluated based on the number of high-quality transport personnel and the number of general transport personnel. This information can provide support for future transportation planning.

[0029] Optionally, the step of bringing the plurality of preset transport personnel information into the first Markov chain model and simulating the first Markov chain model to obtain the plurality of first transport personnel information and the plurality of second transport personnel information includes:

[0030] The preset transport personnel information is brought into the first Markov chain model, and the first Markov chain model is used to simulate and predict to obtain predicted risk logistics order information and predicted general logistics order information. According to the predicted risk logistics order information, the risk logistics order is assigned to the high-quality transport personnel to obtain the first transport personnel information. According to the predicted general logistics order information, the general logistics order is assigned to the general transport personnel to obtain the second transport personnel information.

[0031] The above technical solution has the following advantages: it can predict the risk level of logistics orders based on historical data, and it can also reasonably allocate transportation personnel based on the prediction results, thereby improving the efficiency and accuracy of logistics transportation.

[0032] Optionally, the first transport personnel information is compared with the first preset transport efficiency data to obtain third transport personnel information, and the second transport personnel information is compared with the second preset transport efficiency data to obtain fourth transport personnel information. The specific number of high-quality transport personnel and the specific number of general transport personnel are obtained based on the first transport personnel information, the second transport personnel information, the third transport personnel information, and the fourth transport personnel information, including:

[0033] Compare the first transport personnel information with the first preset transport efficiency data. If the first transport personnel information is lower than the first preset transport efficiency data, determine it as the third transport personnel information and obtain the number of the third transport personnel information.

[0034] comparing the second transport personnel information with the second preset transport efficiency data; if the second transport personnel information is higher than the second preset transport efficiency data, determining it as the fourth transport personnel information; and obtaining the number of the fourth transport personnel information;

[0035] Obtaining the number of the first transport personnel information, and integrating it with the fourth transport personnel information to obtain the number of the specific high-quality transport personnel;

[0036] The second transport personnel information quantity is obtained, and it is integrated with the third transport personnel information quantity to obtain the specific general transport personnel quantity.

[0037] The above technical solution has the following advantages: it can more accurately understand the actual performance of different transportation personnel in the transportation team, making subsequent transportation forecasts more accurate and providing strong data support for the company's transportation management, personnel deployment and performance evaluation.

[0038] Optionally, the step of bringing the specific number of high-quality transport personnel and the specific number of general transport personnel into the second Markov chain model and obtaining the actual number of risk logistics orders through simulation and prediction using the second Markov chain model may further include:

[0039] The actual number of risky logistics orders includes: the number of first-risk order information, the number of second-risk order information, the number of third-risk order information, and the number of fourth-risk order information;

[0040] Substitute some of the abnormal logistics data into some of the specific high-quality transport personnel data to obtain some actual high-quality transport personnel data, and then substitute some of the actual high-quality transport personnel data into the second Markov chain model. Then, simulate and predict the number of first risk order information based on the second Markov chain model.

[0041] If the number of abnormal logistics data is greater than the number of specific high-quality transport personnel data, a quantity difference is formed, and the number of second risky order information is determined based on the quantity difference;

[0042] Substitute some of the general logistics data into some of the specific general transport personnel data to obtain some actual general transport personnel data, substitute some of the actual general transport personnel data into the second Markov chain model, and simulate and predict the number of third risk order information based on the second Markov chain model.

[0043] If the quantity of the general logistics data is greater than the quantity of the specific general transport personnel data, a quantity difference is formed, and the quantity of the fourth risk order information is determined based on the quantity difference.

[0044] The above technical solution has the following advantages: it can predict the number of risky logistics orders handled by specific high-quality transportation personnel and general transportation personnel, and can further predict the number of additional risky orders that may be caused by insufficient transportation personnel based on the difference in the quantity of abnormal logistics data and general logistics data.

[0045] Optionally, determining the number of third transport personnel according to the actual number of risk logistics orders, and determining the required additional costs according to the number of third transport personnel, includes:

[0046] Wherein, the third number of transport personnel includes: first additional transport personnel and second additional transport personnel;

[0047] Determining the number of the first additional transport personnel according to the number of the first risk order information and the number of the second risk order information;

[0048] The number of the second additional transport personnel is determined based on the number of the third risk order information and the number of the fourth risk order information.

[0049] The above technical solution has the following advantages: through such a process, the number of transport personnel can be flexibly adjusted according to the number of actual risk logistics orders, providing strong support for the company's planning and management.

[0050] In a second aspect, the present application provides a traffic dynamic prediction system based on a Markov chain, comprising:

[0051] An information acquisition module is used to acquire historical logistics data, establish a logistics database based on the historical logistics data, compare a number of historical logistics data in a first time period with the logistics database, and obtain a number of abnormal logistics data and a number of general logistics data based on the comparison results;

[0052] An information comparison module is used to obtain historical transportation data of a number of transportation personnel in a first time period, compare the historical transportation data with a preset transportation database, and obtain information of a number of high-quality transportation personnel and information of a number of general transportation personnel based on the comparison results;

[0053] A first information adding module is used to bring a plurality of preset transport personnel information into the first Markov chain model, and obtain a plurality of first transport personnel information and a plurality of second transport personnel information through simulation of the first Markov chain model;

[0054] an information confirmation module, configured to compare the first transport personnel information with the first preset transport efficiency data to obtain third transport personnel information, compare the second transport personnel information with the second preset transport efficiency data to obtain fourth transport personnel information, and obtain a specific number of high-quality transport personnel and a specific number of general transport personnel based on the first transport personnel information, the second transport personnel information, the third transport personnel information, and the fourth transport personnel information;

[0055] The second information adding module is used to bring the specific number of high-quality transport personnel and the specific number of general transport personnel into the second Markov chain model, simulate and predict the actual number of risk logistics orders through the second Markov chain model, determine the number of third transport personnel based on the actual number of risk logistics orders, and determine the required additional cost based on the number of third personnel.

[0056] Optionally, the information acquisition module is specifically used to:

[0057] Compare some historical logistics data of the first time period with the logistics database. Through the comparison results, some abnormal logistics data and some general logistics data are obtained, including:

[0058] The logistics database includes: preset logistics loss data and preset logistics time abnormality data;

[0059] The number of abnormal logistics data includes: the number of lost logistics information and the number of time-abnormal logistics information;

[0060] The number of general logistics data includes: the number of other logistics data except abnormal logistics data in a number of historical logistics data in the first time period;

[0061] Compare some logistics information with the preset logistics loss data. If the logistics information meets the preset logistics loss data, it will be determined as lost logistics information and the number of lost logistics information will be recorded;

[0062] Compare some logistics information with the preset logistics time abnormality data. If the logistics information meets the preset logistics time abnormality data, it will be determined as time abnormal logistics information, and the number of time abnormal logistics information will be recorded;

[0063] Optionally, the information comparison module is specifically used to:

[0064] Obtain historical transportation data of several transport personnel in a first time period, compare the historical transportation data with a preset transportation database, and obtain information of several high-quality transport personnel and information of several general transport personnel based on the comparison results, including:

[0065] Among them, historical transportation data includes: historical lost data and historical timeout data;

[0066] The preset transport database includes: a preset lost data threshold and a preset timeout threshold;

[0067] Comparing a number of historical lost data with a preset lost data threshold, and if the historical lost data is less than the preset lost data threshold, generating a first transport mark and attaching it to the historical transport data of the transporter;

[0068] Comparing the historical timeout data with a preset timeout threshold, if the historical timeout data is less than the preset timeout threshold, generating a second transport mark and attaching it to the historical transport data of the transport personnel;

[0069] If the transport personnel's historical transport data has both the first transport mark and the second transport mark, high-quality transport information is generated, and the transport personnel is determined to be a high-quality transport personnel based on the high-quality transport information.

[0070] Acquire a number of high-quality transport personnel data, and obtain first quantity information according to the number of high-quality transport personnel data;

[0071] If the transport personnel's historical transport data does not have both the first transport mark and the second transport mark, then general transport information is generated, and the transport personnel is determined to be a general transport personnel through the general transport information.

[0072] Acquire some general transport personnel data, and determine second quantity information according to the quantity of the general transport personnel data.

[0073] Optionally, the first information adding module is specifically configured to:

[0074] Bringing some preset transport personnel information into the first Markov chain model, and simulating the first Markov chain model to obtain some first transport personnel information and some second transport personnel information, including:

[0075] The preset transport personnel information is brought into the first Markov chain model, and the first Markov chain model is used to simulate and predict to obtain predicted risk logistics order information and predicted general logistics order information. According to the predicted risk logistics order information, the risk logistics order is assigned to the high-quality transport personnel to obtain the first transport personnel information. According to the predicted general logistics order information, the general logistics order is assigned to the general transport personnel to obtain the second transport personnel information.

[0076] Optionally, the information confirmation module is specifically used to:

[0077] The first transport personnel information is compared with the first preset transport efficiency data to obtain the third transport personnel information, and the second transport personnel information is compared with the second preset transport efficiency data to obtain the fourth transport personnel information. Based on the first transport personnel information, the second transport personnel information, the third transport personnel information, and the fourth transport personnel information, the specific number of high-quality transport personnel and the specific number of general transport personnel are obtained, including:

[0078] Compare the first transport personnel information with the first preset transport efficiency data. If the first transport personnel information is lower than the first preset transport efficiency data, determine it as the third transport personnel information and obtain the number of third transport personnel information.

[0079] Comparing the plurality of second transport personnel information with the second preset transport efficiency data, and if the second transport personnel information is higher than the second preset transport efficiency data, determining it as the fourth transport personnel information, and obtaining the number of the fourth transport personnel information;

[0080] Obtain the number of first transport personnel information, and integrate it with the number of fourth transport personnel information to obtain the specific number of high-quality transport personnel;

[0081] The second transport personnel information quantity is obtained, and it is integrated with the third transport personnel information quantity to obtain the specific general transport personnel quantity.

[0082] Optionally, the second information adding module is specifically configured to:

[0083] The specific number of high-quality transport personnel and the specific number of general transport personnel are brought into the second Markov chain model. The actual number of risk logistics orders is simulated and predicted by the second Markov chain model, which also includes:

[0084] The actual number of risky logistics orders includes: the number of first-risk order information, the number of second-risk order information, the number of third-risk order information, and the number of fourth-risk order information;

[0085] Bring some abnormal logistics data into some specific high-quality transport personnel data to obtain some actual high-quality transport personnel data. Bring some actual high-quality transport personnel data into the second Markov chain model, and simulate and predict the number of first risk order information based on the second Markov chain model.

[0086] If the number of abnormal logistics data is greater than the number of specific high-quality transport personnel data, a quantity difference is formed. Based on the quantity difference, the number of second-risk order information is determined;

[0087] Substitute some general logistics data into some specific general transport personnel data to obtain some actual general transport personnel data. Substitute some actual general transport personnel data into the second Markov chain model, and simulate and predict the third risk order information quantity based on the second Markov chain model.

[0088] If the quantity of general logistics data is greater than the quantity of specific general transport personnel data, a quantity difference is formed. Based on the quantity difference, the quantity of the fourth risk order information is determined.

[0089] Optionally, the second information adding module is specifically configured to:

[0090] The number of third-party transport personnel is determined based on the actual number of risk logistics orders, and the additional costs required are determined based on the number of third-party personnel, including:

[0091] The third number of transport personnel includes: the first additional transport personnel and the second additional transport personnel;

[0092] Determine the number of first additional transport personnel according to the number of first risk order information and the number of second risk order information;

[0093] The number of the second additional transport personnel is determined based on the number of third risk order information and the number of fourth risk order information. BRIEF DESCRIPTION OF THE DRAWINGS

[0094] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0095] Figure 1 A schematic diagram of an application scenario provided in one embodiment of the present application;

[0096] Figure 2 A flow chart of a Markov chain-based traffic dynamic prediction method and system provided in one embodiment of the present application;

[0097] Figure 3 A flow chart of a Markov chain-based traffic dynamic prediction method and system provided in one embodiment of the present application; DETAILED DESCRIPTION

[0098] To make the purpose, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0099] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document, unless otherwise specified, generally indicates an "or" relationship between the related objects.

[0100] The embodiments of the present application are described in further detail below with reference to the accompanying drawings.

[0101] In the logistics volume forecasting of the Markov chain model, its uncertainty can be used to effectively predict the quantity of goods that will appear in the future, and then the corresponding transportation strategy can be configured based on the predicted quantity of goods. However, in the existing forecasting models, the information obtained by simple retrieval is directly brought into the Markov chain model to predict the transportation volume, and no further analysis of the collected information is performed. The resulting forecast results deviate too much from reality, which affects the company's future strategic planning.

[0102] Based on this, the present application provides a method and system for dynamic traffic prediction based on Markov chains.

[0103] Figure 1A schematic diagram of an application scenario provided for this application. Based on historical data, a first Markov chain model was constructed, and then the preset transportation personnel information was brought into the model for simulation, and a number of first transportation personnel information and a number of second transportation personnel information were obtained. This information represents the possible performance of different transportation personnel in the future. The first transportation personnel information was further compared with the first preset transportation efficiency data to obtain the third transportation personnel information; the second transportation personnel information was compared with the second preset transportation efficiency data to obtain the fourth transportation personnel information. Through these comparison results, the transportation efficiency of each transportation personnel can be accurately understood. According to the predicted number of risk logistics orders, the required number of third transportation personnel is determined, and the required additional costs are calculated accordingly. These costs include employee wages, insurance costs, etc., so that more realistic predicted logistics data can be obtained, and then the enterprise can further optimize the plan for the future, reduce operating costs, and optimize the configuration of transportation personnel. The specific implementation method can refer to the following embodiments.

[0104] Figure 2 This is a flowchart of a Markov chain-based traffic dynamic prediction method and system provided in one embodiment of the present application. The method of this embodiment can be applied to the server in the above scenario. Figure 2 As shown, the method includes:

[0105] S201. Acquire historical logistics data, establish a logistics database based on the historical logistics data, compare some historical logistics data of the first time period with the logistics database, and obtain some abnormal logistics data and some general logistics data based on the comparison results.

[0106] Among them, the first time period is: a preset historical reference time period. Logistics data within this historical time period is collected and all logistics data are evaluated to help predict future logistics data.

[0107] Specifically, historical logistics data from a certain period of time was collected, and a logistics database was established based on this data. At the same time, historical transportation data of transportation personnel was also collected, including historical lost data and historical timeout data. The logistics data was compared with the logistics database, and several abnormal logistics data and some general logistics data were identified through comparison.

[0108] S202: Obtain historical transportation data of several transportation personnel in the first time period, compare the historical transportation data with a preset transportation database, and obtain information of several high-quality transportation personnel and information of several general transportation personnel based on the comparison results.

[0109] Specifically, the historical transportation data of the transport personnel is compared with the preset transportation database (including the preset lost data threshold and the preset timeout threshold), and the information of some high-quality transport personnel and some general transport personnel is obtained. These historical data are subsequently analyzed to identify potential problems in the logistics process.

[0110] S203 : Bringing some preset transport personnel information into the first Markov chain model, and obtaining some first transport personnel information and some second transport personnel information through simulation of the first Markov chain model.

[0111] Specifically, the preset transport personnel information is brought into the first Markov chain model for simulation, and a number of first transport personnel information and a number of second transport personnel information are obtained. These information represent the possible performance of different transport personnel in the future.

[0112] S204. Compare the first transport personnel information with the first preset transport efficiency data to obtain the third transport personnel information, and compare the second transport personnel information with the second preset transport efficiency data to obtain the fourth transport personnel information. According to the first transport personnel information, the second transport personnel information, the third transport personnel information and the fourth transport personnel information, obtain the specific number of high-quality transport personnel and the specific number of general transport personnel.

[0113] Specifically, based on the obtained number of high-quality transport personnel and the number of general transport personnel, these data were brought into the second Markov chain model for simulation and prediction. Through the simulation, the predicted value of the actual number of risk logistics orders was obtained.

[0114] S205. The specific number of high-quality transport personnel and the specific number of general transport personnel are brought into the second Markov chain model, and the actual number of risk logistics orders is simulated and predicted by the second Markov chain model. The number of third transport personnel is determined based on the actual number of risk logistics orders, and the required additional cost is determined based on the number of third personnel.

[0115] Specifically, based on the predicted number of risk logistics orders, the company determined the number of third-party transportation personnel required and calculated the additional costs required, including staff salaries, training costs, etc.

[0116] Through the method provided in this embodiment, more realistic predicted logistics data can be obtained, and the enterprise can further optimize future plans, reduce operating costs, and optimize the configuration of transportation personnel. This method brings significant economic and social benefits to the enterprise.

[0117] In some embodiments, the logistics database includes: preset logistics lost data and preset logistics time abnormality data; the number of abnormal logistics data includes: the number of lost logistics information and the number of time abnormal logistics information; the number of general logistics data includes: the number of other logistics data except abnormal logistics data in a number of historical logistics data in the first time period; comparing a number of logistics information with the preset logistics lost data, if the logistics information meets the preset logistics lost data, it is determined as lost logistics information, and the number of lost logistics information is recorded; comparing a number of logistics information with the preset logistics time abnormality data, if the logistics information meets the preset logistics time abnormality data, it is determined as time abnormal logistics information, and the number of time abnormal logistics information is recorded;

[0118] Among them, the preset logistics loss data is: the preset logistics loss data refers to a threshold or standard for logistics loss (such as cargo loss, damage, etc.) that is pre-set during the logistics process based on historical data and industry experience.

[0119] Among them, the preset logistics time abnormal data is: the preset logistics time abnormal data refers to a threshold or standard for logistics time (such as delivery time, transportation time, etc.) that is pre-set in the logistics process based on historical data and industry experience.

[0120] Specifically, compare lost logistics data: each piece of logistics information is compared with the preset lost logistics data one by one. "Lost" here may include situations where the goods are lost, damaged, or cannot be tracked during transportation. If a piece of logistics information meets the preset loss criteria, it will be marked as lost logistics information and the number of lost items will be recorded;

[0121] Comparison of time-anomaly logistics data: Compare logistics information with pre-set logistics time-anomaly data. Time anomalies may include delayed delivery, premature delivery, or delivery during off-hours. Similarly, if a piece of logistics information meets the time anomaly criteria, it will be marked as time-anomaly logistics information and the number of such anomalies will be recorded.

[0122] Through these two steps, we obtain a number of abnormal logistics data and a number of general logistics data. The abnormal logistics data include the number of lost logistics information and the number of time-abnormal logistics information, while the general logistics data are other normal logistics data except these abnormal data.

[0123] Subsequent analysis of these historical data can be carried out to identify potential problems in the logistics process. For example, if the number of lost logistics information is found to have increased significantly in a certain area or within a certain time period, it can be inferred that there may be problems in the distribution link in that area, which requires further investigation and optimization. Similarly, if the number of abnormal logistics information at a certain time is large, the cause can be analyzed and corresponding measures can be taken to reduce the occurrence of such abnormal situations. In addition, these historical data can provide data support for subsequent judgments on the capabilities of transportation personnel.

[0124] The solution provided by this embodiment can not only promptly discover and handle problems in the logistics process, but also predict future logistics data, providing strong support for the company's decision-making.

[0125] In some embodiments, the historical transportation data includes: historical lost data and historical timeout data; the preset transportation database includes: a preset lost data threshold and a preset timeout threshold; a number of the historical lost data are compared with the preset lost data threshold, if the historical lost data is less than the preset lost data threshold, a first transportation mark is generated and attached to the historical transportation data of the transportation personnel; a number of the historical timeout data are compared with the preset timeout threshold, if the historical timeout data is less than the preset timeout threshold, a second transportation mark is generated and attached to the historical transportation data of the transportation personnel; if the transportation personnel If the historical transportation data contains both the first transportation mark and the second transportation mark, high-quality transportation information is generated, and the transportation personnel is determined to be the high-quality transportation personnel through the high-quality transportation information, and a number of the high-quality transportation personnel data are obtained. According to the number of the high-quality transportation personnel data, the first quantity information is obtained; if the historical transportation data of the transportation personnel does not contain both the first transportation mark and the second transportation mark, general transportation information is generated, and the transportation personnel is determined to be the general transportation personnel through the general transportation information, and a number of the general transportation personnel data are obtained. According to the number of the general transportation personnel data, the second quantity information is determined.

[0126] Among them, historical timeout data refers to the data of transportation tasks or distribution tasks that were completed beyond the scheduled time during previous logistics transportation processes. These data include information such as the type of timeout task, timeout time, reason for timeout, and transportation personnel or vehicles involved.

[0127] Among them, historical lost data refers to the record data of goods lost or damaged in the previous logistics transportation process. These data include the type, quantity, time of loss, location of loss, transportation personnel and other related information of the lost goods.

[0128] The preset loss data threshold is: a specific value or percentage, which represents the maximum loss rate or loss quantity allowed during the transportation process.

[0129] Among them, the preset timeout threshold is: a time limit used to measure whether the transportation task is completed on time, which is a reasonable time range calculated based on a specific transportation distance or conditions.

[0130] Among them, the first transport mark is: This mark represents that the transport personnel has performed well in terms of cargo loss, which is below the preset threshold, and is therefore regarded as having achieved a high standard in loss control.

[0131] Among them, the second transportation mark is: This mark indicates that the transportation personnel has performed well in on-time delivery, which is lower than the preset threshold, and is therefore considered to have achieved a high standard in timeliness.

[0132] Specifically, the historical loss data of each transport personnel is compared with a preset loss data threshold. If the historical loss data of a transport personnel is less than or equal to the preset loss data threshold, a first transport mark (for example, a "low loss mark") is generated in the historical transport data.

[0133] Comparing historical timeout data: Compare the historical timeout data of each transport personnel with the preset timeout threshold. If the historical timeout data of the transport personnel is less than or equal to the preset timeout threshold, a second transport mark (such as "on time mark") is generated in the historical transport data.

[0134] Identify high-quality transport personnel: If a transport personnel's historical transport data has both the "low loss mark" and the "on-time mark", the transport personnel is considered to be a high-quality transport personnel, and a high-quality transport information is generated. The information of all high-quality transport personnel is recorded, and their number is counted as the first quantity information.

[0135] Determine general transport personnel: If a transport personnel's historical transport data does not have at least one of the "low loss mark" and "on time mark", the transport personnel is considered to be a general transport personnel, and general transport information is generated, the information of all general transport personnel is recorded, and their number is counted as the second quantity information.

[0136] Through the solution provided by this embodiment, through this process, high-quality transportation personnel can be identified based on historical data, and the performance of the entire transportation team can be evaluated based on the number of high-quality transportation personnel and the number of general transportation personnel. This information can provide support for future transportation planning and can also provide strong support for the company's transportation management and human resources decision-making. For example, the company can formulate reward and training plans based on this information to motivate transportation personnel to improve transportation efficiency and service quality.

[0137] In some embodiments, preset transport personnel information is brought into a first Markov chain model, and simulation and prediction are performed by the first Markov chain model to obtain predicted risk logistics order information and predicted general logistics order information. Based on the predicted risk logistics order information, the risk logistics order is assigned to a high-quality transport personnel to obtain first transport personnel information. Based on the predicted general logistics order information, the general logistics order is assigned to a general transport personnel to obtain second transport personnel information.

[0138] The preset transport personnel information is: virtual transport personnel information with the average transport level of the region, which is a standard reference model parameter;

[0139] The first transporter information is: the high-quality transporter information attached with the predicted risk logistics order information. Since the predicted risk logistics order has risks such as damage, loss, and timeout, when the high-quality transporter information is attached, the high-quality transporter's transportation efficiency will be reduced, which more intuitively reflects the actual efficiency of the high-quality transporter in transporting the predicted risk logistics order.

[0140] Among them, the second transport personnel information is: general transport personnel information with predicted general logistics order information attached. Since general risk logistics orders will not have risks such as damage, loss and timeout, when it is attached to general transport personnel, general transport personnel may be able to transport it faster, thereby improving transportation efficiency, and can more intuitively reflect the actual efficiency of general transport personnel in transporting predicted risk logistics orders.

[0141] Specifically, we first set a preset transport personnel information, which represents a virtual transport personnel with the average transport level of the region, and it serves as the standard reference model parameter.

[0142] Then, this preset transport personnel information is brought into the first Markov chain model for simulation prediction. The Markov chain model is a probability-based prediction method that can predict future status based on historical data. In this scenario, the model will predict the risk level of each logistics order, that is, predict risk logistics order information and predict general logistics order information.

[0143] After the prediction is completed, the logistics orders are assigned to the corresponding transport personnel according to the prediction results. For the logistics orders with predicted risks, they are assigned to high-quality transport personnel because these orders have risks such as damage, loss and timeout, and require more experienced transport personnel to handle them. At the same time, these predicted risk logistics orders will be attached to the high-quality transport personnel information to form a high-quality transport personnel information with predicted risk logistics orders. Since predicted risk logistics orders may have a negative impact on the transportation efficiency of high-quality transport personnel, this information combination can more intuitively reflect the actual efficiency of high-quality transport personnel in handling these orders.

[0144] For the predicted general logistics order information, it is assigned to general transportation personnel. Since the risks of these orders are lower, general transportation personnel can complete the transportation tasks more quickly. Similarly, these predicted general logistics order information will be attached to the general transportation personnel information to form general transportation personnel information with attached predicted general logistics order information. Such an information combination can reflect the actual efficiency of general transportation personnel in handling these orders.

[0145] Through the solution provided in this embodiment, the risk level of logistics orders can be predicted based on historical data, and transportation personnel can be reasonably allocated based on the prediction results to improve the efficiency and accuracy of logistics transportation, which is of great significance to the operation management and cost control of logistics companies.

[0146] In some embodiments, several first transport personnel information are compared with the first preset transport efficiency data. If the first transport personnel information is lower than the first preset transport efficiency data, it is determined as the third transport personnel information, and the number of third transport personnel information is obtained. Several second transport personnel information are compared with the second preset transport efficiency data. If the second transport personnel information is higher than the second preset transport efficiency data, it is determined as the fourth transport personnel information, and the number of fourth transport personnel information is obtained; the number of first transport personnel information is obtained, and it is integrated with the number of fourth transport personnel information to obtain the specific number of high-quality transport personnel; the number of second transport personnel information is obtained, and it is integrated with the number of third transport personnel information to obtain the specific number of general transport personnel.

[0147] Among them, the third transportation personnel refers to those transportation personnel whose actual transportation efficiency is lower than the preset transportation efficiency standard when processing predicted risk logistics orders. These transportation personnel fail to achieve the expected transportation efficiency or service quality when performing high-risk or specific logistics tasks.

[0148] Among them, the fourth transportation personnel are: the fourth transportation personnel refers to the transportation personnel whose actual transportation efficiency exceeds the preset transportation efficiency standard when processing general logistics orders. These transportation personnel have demonstrated transportation efficiency or service quality that exceeds expectations when performing routine or low-risk logistics tasks.

[0149] Among them, the first preset transportation efficiency data is: the expected transportation efficiency standard set for transportation personnel who handle predicted risk logistics orders. This standard is usually determined based on factors such as company policies, industry standards, historical data or the needs of specific tasks.

[0150] Among them, the second preset transportation efficiency data is: the expected transportation efficiency standard set for transportation personnel handling general logistics orders. Similar to the first preset transportation efficiency data, this standard is also determined based on a series of factors, but is usually adjusted according to the characteristics of routine or low-risk logistics tasks.

[0151] Specifically, firstly, a first preset transportation efficiency data and a second preset transportation efficiency data are defined. These preset data are formulated based on company standards, historical data or industry standards and are used to evaluate the transportation efficiency of transportation personnel.

[0152] Next, the first transport personnel information (i.e., high-quality transport personnel information with predicted risk logistics order information) is compared with the first preset transport efficiency data. If the actual transport efficiency in a certain first transport personnel information is lower than the first preset transport efficiency data, it is determined as the third transport personnel information, that is, the efficiency of the transport personnel in processing the predicted risk logistics order does not meet the expected standard, and the number of all third transport personnel information is recorded.

[0153] Then, the second transporter information (i.e., the general transporter information with the predicted general logistics order information) is compared with the second preset transport efficiency data. If the actual transport efficiency of a certain second transporter information is higher than the second preset transport efficiency data, it is identified as the fourth transporter information, that is, the transporter's efficiency in processing the predicted general logistics order exceeds the expected standard. Similarly, the number of all fourth transporter information is recorded.

[0154] Finally, based on these comparison results, the specific number of high-quality transport personnel and general transport personnel is determined. The specific steps are as follows:

[0155] The number of high-quality transporters (i.e., the total number of high-quality transporters) is obtained by adding the number of high-quality transporters (i.e., the number of high-quality transporters who perform well in handling general logistics orders) to obtain the specific number of high-quality transporters. This number reflects the total number of high-quality transporters who can maintain high transportation efficiency when handling logistics orders of different risk levels.

[0156] The number of secondary transporters (i.e., the total number of general transporters) is obtained and added to the number of tertiary transporters (i.e., the number of general transporters who performed poorly when handling risky logistics orders) to obtain the specific number of general transporters. This number reflects the total number of general transporters with relatively low efficiency when handling logistics orders of different risk levels.

[0157] Through the solution provided in this embodiment, through such an evaluation process, the actual performance of different transportation personnel in the transportation team can be understood more accurately, so that subsequent transportation forecasts are more accurate, and strong data support is provided for the company's transportation management, personnel deployment and performance appraisal. For example, by rewarding the fourth transportation personnel, it is helpful to stimulate the enthusiasm of other personnel.

[0158] In some embodiments, the actual number of risk logistics orders includes: the number of first risk order information, the number of second risk order information, the number of third risk order information and the number of fourth risk order information; a number of abnormal logistics data are brought into a number of specific high-quality transport personnel data to obtain a number of actual high-quality transport personnel data, and the number of actual high-quality transport personnel data are brought into the second Markov chain model, and the first risk order information number is obtained by simulation and prediction according to the second Markov chain model. If the number of abnormal logistics data is greater than the number of specific high-quality transport personnel data, a quantity difference is formed, and the second risk order information number is determined based on the quantity difference; a number of general logistics data are brought into a number of specific general transport personnel data to obtain a number of actual general transport personnel data, and the number of actual general transport personnel data are brought into the second Markov chain model, and the third risk order information number is obtained by simulation and prediction according to the second Markov chain model. If the number of general logistics data is greater than the number of specific general transport personnel data, a quantity difference is formed, and the fourth risk order information number is determined based on the quantity difference.

[0159] Among them, the number of first-risk order information is: the number of orders that still have risks such as loss and timeout after being transported by specific high-quality transportation personnel.

[0160] Among them, the number of second-risk order information is: indicating a part of abnormal logistics orders that cannot be processed in a timely manner due to insufficient high-quality transportation personnel.

[0161] Among them, the third risk order information is: the number of orders that are transported by specific general transport personnel and have risks such as loss and timeout.

[0162] Among them, the fourth risk order information is: it indicates a part of abnormal logistics orders that cannot be processed in time due to insufficient general transportation personnel.

[0163] Specifically, we first need to clarify the classification of the actual number of risky logistics orders, including the number of first-risk order information, second-risk order information, third-risk order information, and fourth-risk order information. These classifications will help to more finely manage risky logistics orders.

[0164] After that, the abnormal logistics data is processed. The abnormal logistics data includes some logistics information that exceeds the norm and requires special attention. These abnormal logistics data are brought into the specific high-quality transportation personnel data for simulation analysis to obtain the actual high-quality transportation personnel data. This actual high-quality transportation personnel data is then input into the second Markov chain model.

[0165] Since the Markov chain model has no memory during simulation, it is particularly important to determine the probability of each simulation of the Markov chain model. The specific calculation formula logic of the Markov chain model is:

[0166] P(Xn+1=x|X1=x1,X2=x2,...,Xn=xn)=P(Xn+1=x|Xn=xn)

[0167] Among them, Xn+1 and Xn represent two consecutive states in the state sequence, Xn+1 is the next state, and Xn is the current state.

[0168] The formula represents the probability of the value (x) of the n+1th state (Xn+1) given the first n states (X1, X2, ..., Xn). This probability depends only on the value (x) of the nth state (Xn) and has nothing to do with other states.

[0169] The repeatedly verified data of high-quality transport personnel is brought into the second Markov chain model based on the calculation formula logic to adjust the probability of the value (x) so that the conclusion obtained by the second Markov chain model during the simulation calculation is closer to the actual situation.

[0170] The number of first-risk orders is predicted through model simulation, which indicates how many high-risk logistics orders will appear under the processing of high-quality transportation personnel;

[0171] If the number of abnormal logistics data exceeds the number of specific high-quality transport personnel data, that is, there is a quantity difference, the number of second-risk order information will be determined based on this quantity difference. This indicates that due to a shortage of high-quality transport personnel, some abnormal logistics data may not be processed in a timely manner, thereby increasing the risk;

[0172] Similarly, general logistics data is processed and brought into specific general transport personnel data for simulation analysis to obtain actual general transport personnel data. This actual general transport personnel data is then input into the second Markov chain model. The model simulation is used to predict the number of third-risk order information, which indicates how many relatively low-risk logistics orders will appear under the processing of general transport personnel.

[0173] Similarly, the actual general transportation personnel data that has been repeatedly verified is brought into the second Markov chain model to adjust the probability of the value (x) so that the conclusion obtained by the second Markov chain model during the simulation calculation is closer to the actual situation;

[0174] If the quantity of general logistics data exceeds the quantity of specific general transport personnel data, that is, there is a quantity difference, the quantity of the fourth risk order information will be determined based on this quantity difference. This means that due to insufficient general transport personnel, some general logistics orders may not be completed in time, thereby increasing the risk.

[0175] The solution provided by this embodiment can not only predict the number of risky logistics orders handled by specific high-quality transportation personnel and general transportation personnel, but also further predict the number of additional risky orders that may be caused by insufficient transportation personnel based on the quantitative difference between abnormal logistics data and general logistics data. This information has important guiding significance for the risk management, resource allocation and order priority setting of logistics companies.

[0176] In some embodiments, the third number of transport personnel includes: a first additional transport personnel and a second additional transport personnel; the number of the first additional transport personnel is determined based on the first number of risk order information and the second number of risk order information; the number of the second additional transport personnel is determined based on the third number of risk order information and the fourth number of risk order information.

[0177] Among them, the first additional transportation personnel are: after predicting the number of first risk order information and the number of second risk order information, the transportation personnel are additionally deployed to cope with these high-risk logistics orders. These orders have higher risks of loss and timeout, so more transportation personnel are needed to handle them to ensure that the goods can be delivered safely and on time.

[0178] Among them, the second additional transportation personnel are: after predicting the number of third-risk order information and fourth-risk order information, additional transportation personnel are deployed to cope with these relatively low-risk logistics orders. Although the risks of these orders are relatively low, sufficient transportation personnel are also needed to ensure timely processing and completion of the orders.

[0179] Specifically, the composition of the number of third-party transport personnel should be clarified, including first-level additional transport personnel and second-level additional transport personnel. These two types of transport personnel are supplemented for different types of risk logistics orders respectively;

[0180] The number of first-level additional transport personnel is determined based on the number of first- and second-level risk order information. The number of first-level risk order information is usually related to high-risk logistics orders that require high-quality transport personnel to handle, while the number of second-level risk order information is related to additional risk orders caused by a shortage of high-quality transport personnel. Based on the number and transportation difficulty of these risky orders, the required number of first-level additional transport personnel is assessed. These additional transport personnel will be specifically used to handle high-risk logistics orders to ensure that the orders can be delivered on time and safely.

[0181] Similarly, the number of second-level additional transport personnel is determined based on the number of third-risk order information and the number of fourth-risk order information. The number of third-risk order information is related to general risk logistics orders that require general transport personnel to handle, while the number of fourth-risk order information is related to additional risk orders caused by insufficient general transport personnel. Based on the number and transportation difficulty of these risk orders, the required number of second-level additional transport personnel is assessed. These additional transport personnel will be used to handle general risk logistics orders to reduce the pressure on general transport personnel and ensure that orders can be processed in a timely manner.

[0182] After determining the number of the first additional transport personnel and the second additional transport personnel, further calculate the additional costs incurred by these additional transport personnel, which include recruitment costs, training costs, salary costs, etc. According to the actual situation of the company and market standards, these costs are estimated and included in the logistics cost budget.

[0183] Through the solution provided in this embodiment, through such a process, the number of transportation personnel can be flexibly adjusted according to the actual number of risk logistics orders to ensure the smooth progress of logistics transportation. At the same time, the additional costs incurred by additional transportation personnel can be accurately calculated, providing strong support for the company's planning and management.

[0184] Figure 3 A structural diagram of a flow dynamic prediction system based on a Markov chain is provided in an embodiment of the present application. Figure 3 As shown, the traffic dynamic prediction system 300 of this embodiment includes: an information acquisition module 301 , an information comparison module 302 , a first information adding module 303 , an information confirmation module 304 and a second information adding module 305 .

[0185] The information acquisition module 301 is used to acquire historical logistics data, establish a logistics database based on the historical logistics data, compare a number of historical logistics data in the first time period with the logistics database, and obtain a number of abnormal logistics data and a number of normal logistics data based on the comparison results;

[0186] An information comparison module 302 is configured to obtain historical transportation data of a plurality of transport personnel during a first time period, compare the historical transportation data with a preset transportation database, and obtain information of a plurality of high-quality transport personnel and information of a plurality of general transport personnel based on the comparison results;

[0187] The first information adding module 303 is used to bring a number of preset transport personnel information into the first Markov chain model, and obtain a number of first transport personnel information and a number of second transport personnel information through the first Markov chain model simulation;

[0188] The information confirmation module 304 is configured to compare the first transporter information with the first preset transport efficiency data to obtain third transporter information, compare the second transporter information with the second preset transport efficiency data to obtain fourth transporter information, and obtain the specific number of high-quality transporters and the specific number of general transporters based on the first transporter information, the second transporter information, the third transporter information, and the fourth transporter information;

[0189] The second information adding module 305 is used to bring the specific number of high-quality transportation personnel and the specific number of general transportation personnel into the second Markov chain model, simulate and predict the actual number of risk logistics orders through the second Markov chain model, determine the number of third transportation personnel based on the actual number of risk logistics orders, and determine the required additional cost based on the number of third personnel.

[0190] Optionally, the information acquisition module 301 is specifically configured to compare a number of historical logistics data in the first time period with the logistics database, and obtain a number of abnormal logistics data and a number of general logistics data based on the comparison results, including:

[0191] The logistics database includes: preset logistics loss data and preset logistics time abnormality data;

[0192] The number of abnormal logistics data includes: the number of lost logistics information and the number of time-abnormal logistics information;

[0193] The number of general logistics data includes: the number of other logistics data except abnormal logistics data in a number of historical logistics data in the first time period;

[0194] Compare some logistics information with the preset logistics loss data. If the logistics information meets the preset logistics loss data, it will be determined as lost logistics information and the number of lost logistics information will be recorded;

[0195] Compare some logistics information with the preset logistics time abnormality data. If the logistics information meets the preset logistics time abnormality data, it will be determined as time abnormal logistics information, and the number of time abnormal logistics information will be recorded;

[0196] Optionally, the information comparison module 302 is specifically configured to obtain historical transportation data of a number of transport personnel during a first time period, compare the historical transportation data with a preset transportation database, and obtain information of a number of high-quality transport personnel and information of a number of general transport personnel based on the comparison results, including:

[0197] Among them, historical transportation data includes: historical lost data and historical timeout data;

[0198] The preset transport database includes: a preset lost data threshold and a preset timeout threshold;

[0199] Comparing a number of historical lost data with a preset lost data threshold, and if the historical lost data is less than the preset lost data threshold, generating a first transport mark and attaching it to the historical transport data of the transporter;

[0200] Comparing the historical timeout data with a preset timeout threshold, if the historical timeout data is less than the preset timeout threshold, generating a second transport mark and attaching it to the historical transport data of the transport personnel;

[0201] If the transport personnel's historical transport data has both the first transport mark and the second transport mark, high-quality transport information is generated, and the transport personnel is determined to be a high-quality transport personnel based on the high-quality transport information.

[0202] Acquire a number of high-quality transport personnel data, and obtain first quantity information according to the number of high-quality transport personnel data;

[0203] If the transport personnel's historical transport data does not have both the first transport mark and the second transport mark, then general transport information is generated, and the transport personnel is determined to be a general transport personnel through the general transport information.

[0204] Acquire some general transport personnel data, and determine second quantity information according to the quantity of the general transport personnel data.

[0205] Optionally, the first information adding module 303 is specifically configured to: bring a plurality of preset transport personnel information into the first Markov chain model, and obtain a plurality of first transport personnel information and a plurality of second transport personnel information through simulation of the first Markov chain model, including:

[0206] The preset transport personnel information is brought into the first Markov chain model, and the first Markov chain model is used to simulate and predict to obtain predicted risk logistics order information and predicted general logistics order information. According to the predicted risk logistics order information, the risk logistics order is assigned to the high-quality transport personnel to obtain the first transport personnel information. According to the predicted general logistics order information, the general logistics order is assigned to the general transport personnel to obtain the second transport personnel information.

[0207] Optionally, the information confirmation module 304 is specifically configured to: compare the first transport personnel information with the first preset transport efficiency data to obtain third transport personnel information, compare the second transport personnel information with the second preset transport efficiency data to obtain fourth transport personnel information, and obtain the specific number of high-quality transport personnel and the specific number of general transport personnel based on the first transport personnel information, the second transport personnel information, the third transport personnel information, and the fourth transport personnel information, including:

[0208] Compare the first transport personnel information with the first preset transport efficiency data. If the first transport personnel information is lower than the first preset transport efficiency data, determine it as the third transport personnel information and obtain the number of third transport personnel information.

[0209] Comparing the plurality of second transport personnel information with the second preset transport efficiency data, and if the second transport personnel information is higher than the second preset transport efficiency data, determining it as the fourth transport personnel information, and obtaining the number of the fourth transport personnel information;

[0210] Obtain the number of first transport personnel information, and integrate it with the number of fourth transport personnel information to obtain the specific number of high-quality transport personnel;

[0211] The second transport personnel information quantity is obtained, and it is integrated with the third transport personnel information quantity to obtain the specific general transport personnel quantity.

[0212] Optionally, the second information adding module 305 is specifically configured to: bring the specific number of high-quality transport personnel and the specific number of general transport personnel into the second Markov chain model, and simulate and predict the actual number of risk logistics orders through the second Markov chain model, and further includes:

[0213] The actual number of risky logistics orders includes: the number of first-risk order information, the number of second-risk order information, the number of third-risk order information, and the number of fourth-risk order information;

[0214] Bring some abnormal logistics data into some specific high-quality transport personnel data to obtain some actual high-quality transport personnel data. Bring some actual high-quality transport personnel data into the second Markov chain model, and simulate and predict the number of first risk order information based on the second Markov chain model.

[0215] If the number of abnormal logistics data is greater than the number of specific high-quality transport personnel data, a quantity difference is formed. Based on the quantity difference, the number of second risk order information is determined;

[0216] Substitute some general logistics data into some specific general transport personnel data to obtain some actual general transport personnel data. Substitute some actual general transport personnel data into the second Markov chain model, and simulate and predict the third risk order information quantity based on the second Markov chain model.

[0217] If the quantity of general logistics data is greater than the quantity of specific general transport personnel data, a quantity difference is formed. Based on the quantity difference, the quantity of the fourth risk order information is determined.

[0218] Optionally, the second information adding module 305 is specifically configured to determine the number of third transport personnel according to the actual number of risk logistics orders, and determine the required additional costs according to the number of third transport personnel, including:

[0219] The third number of transport personnel includes: the first additional transport personnel and the second additional transport personnel;

[0220] Determine the number of first additional transport personnel according to the number of first risk order information and the number of second risk order information;

[0221] The number of the second additional transport personnel is determined based on the number of third risk order information and the number of fourth risk order information.

[0222] The traffic dynamic prediction system of this embodiment can be used to execute the method of any of the above embodiments. Its implementation principles and technical effects are similar and will not be repeated here.

Claims

1. A method for dynamic traffic prediction based on Markov chain, characterized in that: The prediction method is applicable to a Markov chain model, wherein the Markov chain model includes a first Markov chain model and a second Markov chain model. The traffic dynamic prediction method is applied to a server and includes: Acquire historical logistics data, establish a logistics database based on the historical logistics data, compare a number of historical logistics data in the first time period with the logistics database, and obtain a number of abnormal logistics data and a number of normal logistics data based on the comparison results; Obtaining historical transportation data of a number of transport personnel during the first time period, comparing the historical transportation data with a preset transportation database, and obtaining information of a number of high-quality transport personnel and information of a number of general transport personnel based on the comparison results; Bringing a plurality of preset transport personnel information into a first Markov chain model, and obtaining a plurality of first transport personnel information and a plurality of second transport personnel information through simulation of the first Markov chain model; Comparing the first transport personnel information with the first preset transport efficiency data to obtain third transport personnel information, and comparing the second transport personnel information with the second preset transport efficiency data to obtain fourth transport personnel information, and obtaining the specific number of high-quality transport personnel and the specific number of general transport personnel based on the first transport personnel information, the second transport personnel information, the third transport personnel information, and the fourth transport personnel information; The specific number of high-quality transport personnel and the specific number of general transport personnel are brought into the second Markov chain model, and the actual number of risk logistics orders is simulated and predicted by the second Markov chain model. The number of third transport personnel is determined based on the actual number of risk logistics orders, and the required additional cost is determined based on the number of third personnel.

2. The method according to claim 1, characterized in that The plurality of historical logistics data of the first time period is compared with the logistics database, and a plurality of abnormal logistics data and a plurality of general logistics data are obtained through the comparison results. include: Wherein, the logistics database includes: preset logistics loss data and preset logistics time abnormality data; The number of abnormal logistics data includes: the number of lost logistics information and the number of time-abnormal logistics information; The number of general logistics data includes: the number of other logistics data except abnormal logistics data in the plurality of historical logistics data in the first time period; Compare a number of logistics information with preset logistics loss data. If the logistics information matches the preset logistics loss data, determine it as lost logistics information and record the number of lost logistics information; Compare the logistics information with the preset logistics time abnormality data. If the logistics information meets the preset logistics time abnormality data, it is determined as time abnormal logistics information, and the number of the time abnormal logistics information is recorded.

3. The method according to claim 2, characterized in that The historical transportation data of several transportation personnel in the first time period are obtained, and the historical transportation data are compared with a preset transportation database, and information of several high-quality transportation personnel and information of several general transportation personnel are obtained according to the comparison results. include: The historical transportation data includes: historical lost data and historical timeout data; Wherein, the preset transport database includes: a preset lost data threshold and a preset timeout threshold; Comparing the plurality of historical lost data with the preset lost data threshold, and if the historical lost data is less than the preset lost data threshold, generating a first transport mark and attaching it to the historical transport data of the transporter; Comparing the plurality of historical timeout data with the preset timeout threshold, and if the historical timeout data is less than the preset timeout threshold, generating a second transport mark and appending it to the historical transport data of the transport personnel; If the transport personnel's historical transport data has both the first transport mark and the second transport mark, high-quality transport information is generated, and the transport personnel is determined to be the high-quality transport personnel based on the high-quality transport information. Acquire a number of high-quality transport personnel data, and obtain first quantity information according to the number of high-quality transport personnel data; If the transport personnel's historical transport data does not contain both the first transport mark and the second transport mark, then general transport information is generated, and the transport personnel is determined to be the general transport personnel through the general transport information. A number of the general transport personnel data are obtained, and second quantity information is determined according to the number of the general transport personnel data.

4. The method according to claim 3, characterized in that The step of bringing the plurality of preset transport personnel information into the first Markov chain model and simulating the first Markov chain model to obtain the plurality of first transport personnel information and the plurality of second transport personnel information includes: The preset transport personnel information is brought into the first Markov chain model, and the first Markov chain model is used to simulate and predict to obtain predicted risk logistics order information and predicted general logistics order information. According to the predicted risk logistics order information, the risk logistics order is assigned to the high-quality transport personnel to obtain the first transport personnel information. According to the predicted general logistics order information, the general logistics order is assigned to the general transport personnel to obtain the second transport personnel information.

5. The method according to claim 4, characterized in that The first transport personnel information is compared with the first preset transport efficiency data to obtain third transport personnel information, the second transport personnel information is compared with the second preset transport efficiency data to obtain fourth transport personnel information, and the specific number of high-quality transport personnel and the specific number of general transport personnel are obtained based on the first transport personnel information, the second transport personnel information, the third transport personnel information, and the fourth transport personnel information, including: Compare the first transport personnel information with the first preset transport efficiency data. If the first transport personnel information is lower than the first preset transport efficiency data, determine it as the third transport personnel information and obtain the number of the third transport personnel information. comparing the second transport personnel information with the second preset transport efficiency data; if the second transport personnel information is higher than the second preset transport efficiency data, determining it as the fourth transport personnel information; and obtaining the number of the fourth transport personnel information; Obtaining the number of the first transport personnel information, and integrating it with the fourth transport personnel information to obtain the number of the specific high-quality transport personnel; The second transport personnel information quantity is obtained, and it is integrated with the third transport personnel information quantity to obtain the specific general transport personnel quantity.

6. The method according to claim 5, characterized in that The specific number of high-quality transport personnel and the specific number of general transport personnel are brought into the second Markov chain model, and the actual number of risk logistics orders is obtained through simulation and prediction of the second Markov chain model. include: The actual number of risky logistics orders includes: the number of first-risk order information, the number of second-risk order information, the number of third-risk order information, and the number of fourth-risk order information; Substitute some of the abnormal logistics data into some of the specific high-quality transport personnel data to obtain some actual high-quality transport personnel data, and then substitute some of the actual high-quality transport personnel data into the second Markov chain model. Then, simulate and predict the number of first risk order information based on the second Markov chain model. If the number of abnormal logistics data is greater than the number of specific high-quality transport personnel data, a quantity difference is formed, and the number of second risky order information is determined based on the quantity difference; Substitute some of the general logistics data into some of the specific general transport personnel data to obtain some actual general transport personnel data, substitute some of the actual general transport personnel data into the second Markov chain model, and simulate and predict the number of third risk order information based on the second Markov chain model. If the quantity of the general logistics data is greater than the quantity of the specific general transport personnel data, a quantity difference is formed, and the quantity of the fourth risk order information is determined based on the quantity difference.

7. The method according to claim 6, characterized in that The number of third transport personnel is determined according to the actual number of risk logistics orders, and the required additional costs are determined according to the number of third transport personnel. include: Wherein, the third number of transport personnel includes: first additional transport personnel and second additional transport personnel; Determining the number of the first additional transport personnel according to the number of the first risk order information and the number of the second risk order information; The number of the second additional transport personnel is determined based on the number of the third risk order information and the number of the fourth risk order information.

8. A traffic dynamic prediction system based on Markov chain, characterized in that: include: An information acquisition module is used to acquire historical logistics data, establish a logistics database based on the historical logistics data, compare a number of historical logistics data in a first time period with the logistics database, and obtain a number of abnormal logistics data and a number of normal logistics data based on the comparison results; an information comparison module, configured to obtain historical transportation data of a plurality of transport personnel during the first time period, compare the historical transportation data with a preset transportation database, and obtain information of a plurality of high-quality transport personnel and information of a plurality of general transport personnel based on the comparison results; A first information adding module is used to bring a plurality of preset transport personnel information into the first Markov chain model, and obtain a plurality of first transport personnel information and a plurality of second transport personnel information through simulation of the first Markov chain model; an information confirmation module, configured to compare the first transport personnel information with first preset transport efficiency data to obtain third transport personnel information, compare the second transport personnel information with second preset transport efficiency data to obtain fourth transport personnel information, and obtain a specific number of high-quality transport personnel and a specific number of general transport personnel based on the first transport personnel information, the second transport personnel information, the third transport personnel information, and the fourth transport personnel information; The second information adding module is used to bring the specific number of high-quality transport personnel and the specific number of general transport personnel into the second Markov chain model, simulate and predict the actual number of risk logistics orders through the second Markov chain model, determine the number of third transport personnel based on the actual number of risk logistics orders, and determine the required additional cost based on the number of third personnel.

Images