Commodity distribution optimization method based on online scheduling management system

Abstract

The invention provides an online scheduling management system and a commodity distribution optimization method, and relates to the field of commodity distribution, and the system comprises an order distribution information module which is used for generating order distribution information; the external information module is used for acquiring weather forecast information of a distribution period; the order priority module is used for determining an order priority delivery coefficient according to the order delivery information and the weather forecast information; an order preferential delivery module used for determining an order needing preferential delivery according to the order preferential delivery coefficient; the rider information module is used for generating a load coefficient of a rider; and the rider scheduling module is used for determining a scheduled rider according to the load coefficient and the merchant address information. According to the method and the device, the distribution priority of the order can be accurately analyzed, and the riders can be accurately screened and scheduled according to the load conditions of the riders, so that the commodity distribution efficiency is improved, and the waste of scheduling resources is reduced.

Description

Technical Field

[0001] The present invention relates to the field of commodity distribution, and in particular to an online scheduling management system and a commodity distribution optimization method. Background Art

[0002] In the related art, CN107578202A discloses a method for dispatching and distributing goods based on the existing takeaway service, and its technical features include the following steps: demand proposal step, demand splitting step, route planning step, supplier screening step, supplier order grabbing step, final route planning step, rider order grabbing step and commodity delivery step, thereby finally completing the commodity delivery. The scheme is reasonably designed and can realize the one-time delivery function of takeaway and temporary demand goods. When the takeaway customer proposes the demand for goods, on the basis of planning multiple delivery routes between the takeaway customer and the restaurant, the order grabbing function of the commodity supplier on the planned route is added. After the supplier of takeaway and other goods is determined, a meal pick-up and goods delivery route is planned, thereby realizing the one-time delivery of takeaway goods and other goods, meeting the various shopping needs of customers, and being able to ensure the timeliness of delivery, saving manpower and financial resources.

[0003] CN114418477A discloses a method, system and electronic device for dispatching order goods based on data analysis. The method comprises obtaining order information; selecting a dispatching strategy for order goods through data analysis according to the order information and business focus; calculating the score data of the dispatching supplier under the dispatching strategy for order goods; and selecting the first dispatching supplier by comparing the score data of the dispatching supplier. The solution realizes data analysis of the basic data of multiple suppliers, performs intelligent dispatching according to the analysis results, accurately selects the best supplier, reduces inventory costs, improves delivery efficiency, and ensures product quality.

[0004] Based on the above-mentioned related technologies, the timeliness of delivery can be guaranteed. However, the related technologies do not take into account the impact of the order delivery priority and the rider's load condition on the product delivery, that is, the product delivery process cannot be optimized according to the order's priority delivery status and the rider's load condition.

[0005] The information disclosed in the background technology section of this application is only intended to deepen the understanding of the general background technology of this application, and should not be regarded as an admission or any form of suggestion that the information constitutes the prior art already known to those skilled in the art. Summary of the invention

[0006] The present invention provides an online scheduling management system and a commodity distribution optimization method, which can solve the technical problem that the related technology cannot optimize the commodity distribution process according to the priority of order distribution and the load condition of the rider.

[0007] According to a first aspect of the present invention, there is provided an online scheduling management system, comprising: An order delivery information module is used to generate order delivery information, wherein the order delivery information includes: merchant address information, delivery address information, merchant order acceptance time and order expedited identification result; An external information module is used to obtain weather forecast information for the delivery period, wherein the weather forecast data includes: temperature data, wind data and humidity data; An order priority module, used to determine an order priority delivery coefficient according to the order delivery information and the weather forecast information; An order priority delivery module, used to determine the orders that need priority delivery according to the order priority delivery coefficient; A rider information module, used to generate the rider's load factor; The rider dispatching module is used to determine the dispatched rider according to the load factor and the merchant address information.

[0008] According to a second aspect of the present invention, there is provided a commodity distribution optimization method, comprising: Generate order delivery information, wherein the order delivery information includes: merchant address information, delivery address information, merchant order acceptance time and order expedited identification result; Obtaining weather forecast information for the delivery period, wherein the weather forecast data includes: temperature data, wind speed data, and humidity data; Determining an order priority delivery coefficient according to the order delivery information and the weather forecast information; Determine the orders that need to be delivered first according to the order priority delivery coefficient; Generate rider load factor; The dispatched rider is determined based on the load factor and the merchant address information.

[0009] Technical effect: According to the present invention, the priority of order delivery can be accurately analyzed according to order delivery information and weather information, so as to determine the priority delivery orders, and the load status of the rider can be accurately evaluated, and the riders for delivery can be screened out based on the load status of the rider and the distance between the rider and the merchant, thereby improving the efficiency of commodity delivery and reducing the waste of rider scheduling resources. When determining the delivery time relationship function, the delivery time relationship function can be determined according to the historical order delivery time and the historical weather forecast information, and the relationship between the delivery time and the humidity data, wind data and temperature data is accurately analyzed. In the calculation process, the periodic influence of humidity data, wind data and temperature data on the delivery time is fully considered, thereby improving the accuracy of the delivery time relationship function. When determining the order priority delivery coefficient, the order priority delivery coefficient can be determined according to the order delivery information and the estimated order delivery time. In the calculation process, the influence of the order waiting delivery time, the expedited status and the estimated order delivery time on the priority delivery degree of the order is fully considered, thereby improving the accuracy and objectivity of the order priority delivery coefficient. When determining the load coefficient, the rider's load coefficient can be generated based on the number of orders held, east-west location information, north-south location information, the standard deviation of the east-west location information, the standard deviation of the north-south location information and the remaining delivery time. During the calculation process, the rider's load level can be evaluated based on three aspects: the number of orders held by the rider, the remaining delivery time of the orders held and the distribution density of the orders held, thereby improving the comprehensiveness and accuracy of the load coefficient.

[0010] It should be understood that the above general description and the following detailed description are exemplary and explanatory only and do not limit the present invention. Other features and aspects of the present invention will become more apparent from the following detailed description of exemplary embodiments with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other embodiments can be obtained based on these drawings without creative work. Figure 1 A block diagram based on an online scheduling management system according to an embodiment of the present invention is exemplarily shown; Figure 2 The following is a flow chart showing a method for optimizing product distribution according to an embodiment of the present invention. DETAILED DESCRIPTION

[0012] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0013] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0014] Figure 1 A block diagram based on an online scheduling management system according to an embodiment of the present invention is exemplarily shown, and the system includes: An order delivery information module is used to generate order delivery information, wherein the order delivery information includes: merchant address information, delivery address information, merchant order acceptance time and order expedited identification result; An external information module is used to obtain weather forecast information for the delivery period, wherein the weather forecast data includes: temperature data, wind data and humidity data; An order priority module, used to determine an order priority delivery coefficient according to the order delivery information and the weather forecast information; An order priority delivery module, used to determine the orders that need priority delivery according to the order priority delivery coefficient; A rider information module, used to generate the rider's load factor; The rider dispatching module is used to determine the dispatched rider according to the load factor and the merchant address information.

[0015] According to the online scheduling management system based on the embodiment of the present invention, the priority of order delivery can be accurately analyzed according to the order delivery information and weather information, so as to determine the orders for priority delivery. In addition, the load status of the rider can be accurately evaluated, and the delivery riders can be screened out based on the rider's load status and the distance between the rider and the merchant, thereby improving the efficiency of commodity delivery and reducing the waste of rider scheduling resources.

[0016] According to one embodiment of the present invention, in an order delivery information module, order delivery information is generated, wherein the order delivery information includes: merchant address information, delivery address information, merchant order acceptance time and order expedited identification result.

[0017] For example, in the order delivery information module, the system will generate merchant address information (product shipping address), merchant order acceptance time, delivery address information (recipient address) and expedited identification results (some orders may be marked as expedited due to special user needs), and save the generated information.

[0018] According to an embodiment of the present invention, in the external information module, weather forecast information of the delivery period is obtained, wherein the weather forecast data includes: temperature data, wind data and humidity data.

[0019] For example, in the external information module, the system will obtain the temperature, wind speed and humidity conditions during the delivery cycle based on the local weather forecast information.

[0020] According to one embodiment of the present invention, in the order priority module, the order priority delivery coefficient is determined based on the order delivery information and the weather forecast information.

[0021] According to an embodiment of the present invention, determining the order priority delivery coefficient according to the order delivery information and the weather forecast information includes: Get multiple historical order delivery information on multiple historical dates; Acquire multiple historical weather forecast information on multiple historical dates, wherein the historical weather forecast information includes: historical temperature data, historical humidity data, and historical wind speed data; Obtain similar historical order information in the historical order delivery information that is similar to the merchant address information and delivery address information of the current order; Determine similar historical merchant order acceptance times and similar historical delivery times based on the similar historical order information; Determine the historical order delivery time based on the similar historical merchant order acceptance time and the similar historical delivery time; Determine a delivery time relationship function according to the historical order delivery time and the historical weather forecast information; Determining an estimated order delivery time according to the delivery time relationship function and the weather forecast information; An order priority delivery coefficient is determined based on the order delivery information and the estimated order delivery time.

[0022] For example, obtain multiple historical order delivery information from multiple historical dates saved by the system, where the historical order delivery information also includes the delivery time of the historical orders (for example, if the rider delivers the order at nine o'clock, then the delivery time is nine o'clock); obtain historical weather forecast information from multiple historical dates; obtain similar historical order information from the historical order delivery information that is similar to the merchant address information and delivery address information of the current order. For example, if the delivery address information of the current order is merchant A, then the delivery address information of similar historical orders is also merchant A, and the delivery address information of the current order is Building C, Community B, then the delivery address information of similar historical orders is also within the scope of Community B; based on similar historical order information, determine the order acceptance time of similar historical orders (i.e., the order acceptance time of similar historical merchants) and the time when the rider delivered the historical orders. Similar historical delivery time when the order is delivered to the designated location; determine the historical order delivery time of each similar historical order based on the similar historical delivery time minus the similar historical merchant order acceptance time; temperature data, humidity data and wind data will affect the delivery time to a certain extent. For example, in rainy and snowy weather, the wind data and humidity data will be higher. Due to the poor traffic conditions in rainy and snowy weather, the delivery time will be longer. Based on the correlation of the above data, the delivery time relationship function between the temperature data, humidity data, wind data and delivery time can be determined; substitute the weather forecast information of the current delivery cycle into the delivery time relationship function to determine the estimated order delivery time; based on the delivery order delivery information and the estimated order delivery time, evaluate the priority delivery degree of the order and determine the order priority delivery coefficient.

[0023] According to an embodiment of the present invention, determining the delivery time relationship function according to the historical order delivery time and the historical weather forecast information includes: determining a first undetermined coefficient equation of the delivery time relationship function according to formula (1),

[0024] in, is the historical order delivery time of the e-th historical similar order, is the historical temperature data of the jth moment of the historical delivery cycle of the eth historical similar order, is the historical humidity data at the jth moment of the historical delivery cycle of the eth historical similar order, is the historical wind data at the jth moment of the historical delivery cycle of the eth historical similar order, To preset the humidity data threshold, To preset the wind data threshold, is the preset temperature data threshold, and is the first undetermined coefficient of the first undetermined coefficient equation, E is the number of similar historical orders, , e and E are both positive integers; According to the historical order delivery time, the historical temperature data, the historical humidity data and the historical wind data, the first undetermined coefficient is summed to obtain a solution value of the first undetermined coefficient; The delivery time relationship function is determined according to the solution value of the first undetermined coefficient and the first undetermined coefficient equation.

[0025] According to one embodiment of the present invention, is the average historical order delivery time of E historical similar orders, which means the time consumed for similar order delivery when the influence of accidental factors is eliminated. is the ratio of the historical humidity data at the jth moment of the historical delivery cycle of the eth historical similar order to the preset humidity data threshold. The closer the ratio is to 1, the smaller the impact of humidity data changes on delivery time changes. is the ratio of the historical wind data at the jth moment of the historical delivery cycle of the eth historical similar order to the preset wind data threshold. The closer the ratio is to 1, the smaller the impact of wind data changes on delivery time changes. is the relative difference between the historical temperature data at the jth moment of the historical delivery cycle of the eth historical similar order and the preset temperature data threshold. The closer the ratio is to 1, the smaller the impact of temperature data changes on delivery time changes. is a function to be fitted in the form of a sine function, representing a fitting term with a certain periodicity. For example, the current weather condition is cloudy and rainy, and half an hour later, the weather condition becomes sunny. Within a change cycle, temperature data, humidity data, and wind data can have a temporary impact on the delivery time. In general, humidity data and wind data are positively correlated with delivery time, and the difference between temperature data and preset temperature data threshold is positively correlated with delivery time. For example, when humidity data and wind data are large, the weather condition may be heavy rain, the road traffic condition is poor, and the delivery time is relatively long. When the difference between temperature data and preset temperature data threshold is large, it may be cold wave weather or high temperature weather, the delivery is difficult, and the delivery time is relatively long. Therefore, with the periodic changes of humidity data, wind data and temperature data in a short period of time, the delivery time in a short period of time may be periodically affected. Therefore, the historical humidity data, historical wind data and historical temperature data at the jth moment of the historical delivery cycle where the eth historical similar order is located can be periodically fitted with the first undetermined coefficient, so as to express the part of the historical order delivery time change that conforms to the short-term periodic change, and obtain the first undetermined coefficient equation, so as to express the relationship between the historical order delivery time, historical humidity data, historical wind data and historical temperature data.

[0026] According to one embodiment of the present invention, fitting can be performed based on multiple parameters involved in the above undetermined coefficient equation, that is, fitting can be performed based on the average historical order delivery time of E historical similar orders, the historical temperature data, historical humidity data and historical wind data of the historical delivery period of the e-th historical similar order, to solve the above multiple first undetermined coefficients. There are 6 first undetermined coefficients, namely, and ,according to The average historical order delivery time of the e-th historical similar order and the historical temperature data, historical humidity data and historical wind speed data at multiple moments of the historical delivery cycle of the e-th historical similar order are used to calculate the first unknown coefficients of the above six The above six first unknown coefficients Substitute the solved values ​​of the above 6 first undetermined coefficients into the first relationship function to determine the first undetermined function.

[0027] In this way, the delivery time relationship function can be determined based on the historical order delivery time and historical weather forecast information, and the relationship between the delivery time and the humidity data, wind data and temperature data can be accurately analyzed. During the calculation process, the periodic impact of humidity data, wind data and temperature data on the delivery time is fully considered, thereby improving the accuracy of the delivery time relationship function.

[0028] According to an embodiment of the present invention, determining the order priority delivery coefficient according to the order delivery information and the estimated order delivery time includes: determining the order priority delivery coefficient of the rth order at the jth moment of the delivery cycle according to formula (2): ,

[0029] in, is the estimated order delivery time of the rth order, For the management cycle a moment, The merchant acceptance time for the rth order, The result of expediting the order for the rth order. , The preset multiple.

[0030] According to one embodiment of the present invention, is the difference between the merchant acceptance time of the jth moment in the management cycle and the rth order, indicating the waiting delivery time of the rth order at the jth moment in the management cycle. It is the product of the expedited result of the r-th order and the waiting delivery time of the r-th order at the j-th moment of the management cycle. The larger the value, the more urgent the delivery of the order is. It represents the order priority delivery coefficient of the r-th order. The larger the ratio is, the more urgent the delivery of the r-th order is, or the shorter the estimated order delivery time of the r-th order is (orders with short estimated order delivery time are given priority delivery, which can quickly release scheduling resources when scheduling resources are scarce), and the rider is scheduled to deliver the order first.

[0031] In this way, the order priority delivery coefficient can be determined based on the order delivery information and the estimated order delivery time. During the calculation process, the impact of the order's waiting delivery time, expedited status and estimated order delivery time on the order's priority delivery degree is fully considered, thereby improving the accuracy and objectivity of the order priority delivery coefficient.

[0032] According to one embodiment of the present invention, in the order priority delivery module, orders that need priority delivery are determined based on the order priority delivery coefficient.

[0033] According to an embodiment of the present invention, determining the orders that need to be delivered first according to the order priority delivery coefficient includes: Arrange multiple orders in descending order according to their order priority delivery coefficients to determine the order priority delivery sequence; Determine the orders that require priority delivery based on the order corresponding to the first element of the order priority delivery sequence.

[0034] For example, the order priority delivery sequence is determined by arranging the order priority delivery coefficients of multiple orders to be delivered in descending order. The first element of the order priority delivery sequence is the element with the largest order priority delivery coefficient, and the order corresponding to the element is determined as the order that needs priority delivery.

[0035] According to one embodiment of the present invention, in the rider information module, the rider's load factor is generated.

[0036] According to one embodiment of the present invention, generating a rider's load factor includes: Get the number of orders held by the rider; Obtain the delivery address information of the rider's held orders; According to the order delivery address information, determine the real-time location information of each held order in the real-time coordinate system, wherein the real-time coordinate system is a coordinate system established with the rider's location as the coordinate origin; Determine the east-west position information of the holding order on the x-axis of the real-time coordinate system according to the real-time position information; Determine the north-south position information of the holding order on the y-axis of the real-time coordinate system according to the real-time position information; Determine the standard deviation of the east-west position information based on the east-west position information of the plurality of held orders; Determine the standard deviation of the north-south position information based on the north-south position information of a plurality of holding orders; Get the estimated delivery time of the rider's held orders; Determine the remaining delivery time based on the estimated delivery time of the held order; The rider's load factor is generated based on the number of orders held, the east-west position information, the north-south position information, the standard deviation of the east-west position information, the standard deviation of the north-south position information and the remaining delivery time.

[0037] For example, according to the distribution platform, the number of orders held by the rider and the delivery addresses of the held orders are obtained; a real-time coordinate system is established with the rider's location as the origin of the coordinate system, the east-west direction as the x-axis, and the north-south direction as the y-axis, and the real-time position information of each held order in the real-time coordinate system is determined according to the delivery address information of the held orders; according to the real-time position information, the position of each held order on the x-axis and y-axis of the real-time coordinate system, that is, the east-west position information and the north-south position information, is determined respectively; according to the east-west position information of multiple held orders, the average east-west position information is determined, and according to the average east-west position information, the standard deviation of the east-west position information is determined; according to the north-south position information of multiple held orders, the average north-south position information is determined, and according to the average north-south position information, the standard deviation of the north-south position information is determined; the estimated delivery time of the rider's held orders is obtained, and the remaining delivery time is determined according to the estimated delivery time of the held orders; according to the number of held orders, the east-west position information, the north-south position information, the standard deviation of the east-west position information, the standard deviation of the north-south position information and the remaining delivery time, the rider's load condition is evaluated to generate the rider's load coefficient.

[0038] According to one embodiment of the present invention, the load factor of the rider is generated according to the number of orders held, the east-west location information, the north-south location information, the standard deviation of the east-west location information, the standard deviation of the north-south location information and the remaining delivery time, including: determining the load factor of the i-th rider at the j-th moment of the delivery cycle according to formula (3): ,

[0039] in, and is the preset weight, if is the conditional function, is the number of orders held by the i-th rider at the j-th moment of the delivery cycle, To preset the threshold of the number of orders held, is the preset multiple, is the east-west location information of the kth order at the jth moment of the delivery cycle, is the standard deviation of the east-west position information, is the north-south position information of the kth order at the jth moment of the delivery cycle, is the standard deviation of the north-south position information, is the remaining delivery time of the K orders held by the i-th rider at the j-th moment of the delivery cycle, is the preset time threshold, To hold the order quantity, , k and K are both positive integers.

[0040] According to one embodiment of the present invention, It is the relative difference between the number of orders held by the ith rider at the jth moment of the delivery cycle and the preset threshold of the number of orders held. The larger the ratio is, the more orders the ith rider holds at the jth moment of the delivery cycle, and the greater the load of the ith rider at the jth moment of the delivery cycle. It is the relative difference between the preset time threshold and the average remaining delivery time of the K held orders of the ith rider at the jth moment of the delivery cycle. The larger the ratio is, the shorter the average remaining delivery time of the K held orders of the ith rider at the jth moment of the delivery cycle, and the greater the load of the ith rider at the jth moment of the delivery cycle.

[0041] According to one embodiment of the present invention, in formula (3), the conditional function The value of includes the following two cases, when it satisfies When the condition is met, it means that the east-west position information of the kth order at the jth moment of the delivery cycle is within an interval with the average east-west position information as the center and the standard deviation of twice the preset multiple as the interval length. The value of the condition function is 0. When it is not met When the condition is met, the value of the conditional function is 1. If the east-west position information of the kth order at the jth moment of the delivery cycle meets the above conditions, it means that the deviation between the east-west position information of this order and the mean is small, and this order is in the order-intensive area in terms of the east-west position. It is the ratio of the number of orders that are not in the order-dense area in the east-west direction to the total number of orders held. The larger the ratio is, the more dispersed the orders are in the east-west direction, the greater the delivery difficulty, and the greater the rider's load.

[0042] According to one embodiment of the present invention, in formula (3), the conditional function The value of includes the following two cases, when it satisfies When the condition is met, it means that the north-south position information of the kth order at the jth moment of the delivery cycle is within an interval with the average north-south position information as the center and the standard deviation of twice the preset multiple as the interval length. The value of the condition function is 0. When it is not met When the condition is met, the value of the conditional function is 1. If the north-south position information of the kth order at the jth moment of the delivery cycle meets the above conditions, it means that the north-south position information of this order has a small deviation from the mean, and this order is in the order-intensive area in terms of the north-south position. It is the ratio of the number of orders that are not in the order-dense area in the southeast and north directions to the total number of orders held. The larger the ratio is, the more dispersed the orders are in the north-south direction, the greater the delivery difficulty, and the greater the rider's load. It indicates the distribution density of held orders. The larger the ratio is, the lower the distribution density of held orders is, and the greater the delivery difficulty and load for the riders.

[0043] In this way, the rider's load coefficient can be generated based on the number of orders held, east-west location information, north-south location information, the standard deviation of the east-west location information, the standard deviation of the north-south location information and the remaining delivery time. During the calculation process, the rider's load level can be evaluated based on three aspects: the number of orders held by the rider, the remaining delivery time of the orders held and the distribution density of the orders held, thereby improving the comprehensiveness and accuracy of the load coefficient.

[0044] According to one embodiment of the present invention, in a rider dispatching module, a dispatched rider is determined based on the load factor and the merchant address information.

[0045] According to one embodiment of the present invention, determining a dispatch rider according to the load factor and the merchant address information includes: Determine load factors and real-time location information for multiple riders; Determine the distance to the store based on the real-time location information and the merchant address information; Determining a scheduling difficulty coefficient according to the distance to the store and the load factor; Arrange in ascending order according to the scheduling difficulty coefficients to determine a scheduling difficulty sequence; Determine the dispatching rider according to the rider corresponding to the first element of the dispatching difficulty sequence.

[0046] For example, based on the positioning system, the real-time location information of multiple riders is determined, and the distances from the multiple riders to the store are determined based on the real-time location information of the multiple riders and the merchant address information of the orders that need priority delivery. The scheduling difficulty coefficient is determined based on the product of the load factors of the multiple riders and the distances to the store. The scheduling difficulty coefficients are arranged in ascending order to determine a scheduling difficulty sequence. The rider corresponding to the first element of the scheduling difficulty sequence is a rider with relatively lower scheduling difficulty, and the rider is scheduled to deliver the orders that need priority delivery.

[0047] According to the online scheduling management system of the embodiment of the present invention, the priority of order delivery can be accurately analyzed according to the order delivery information and weather information, so as to determine the priority delivery order, and the load condition of the rider can be accurately evaluated, and the rider for delivery can be screened out based on the load condition of the rider and the distance between the rider and the merchant, thereby improving the efficiency of commodity delivery and reducing the waste of rider scheduling resources. When determining the delivery time relationship function, the delivery time relationship function can be determined according to the historical order delivery time and the historical weather forecast information, and the relationship between the delivery time and the humidity data, wind data and temperature data is accurately analyzed. In the calculation process, the periodic influence of humidity data, wind data and temperature data on the delivery time is fully considered, thereby improving the accuracy of the delivery time relationship function. When determining the order priority delivery coefficient, the order priority delivery coefficient can be determined according to the order delivery information and the estimated order delivery time. In the calculation process, the influence of the waiting delivery time, the expedited status and the estimated order delivery time on the priority delivery degree of the order is fully considered, thereby improving the accuracy and objectivity of the order priority delivery coefficient. When determining the load coefficient, the rider's load coefficient can be generated based on the number of orders held, east-west location information, north-south location information, the standard deviation of the east-west location information, the standard deviation of the north-south location information and the remaining delivery time. During the calculation process, the rider's load level can be evaluated based on three aspects: the number of orders held by the rider, the remaining delivery time of the orders held and the distribution density of the orders held, thereby improving the comprehensiveness and accuracy of the load coefficient.

[0048] Figure 2 The following is a flow chart of a method for optimizing product distribution according to an embodiment of the present invention. The method includes: Generate order delivery information, wherein the order delivery information includes: merchant address information, delivery address information, merchant order acceptance time and order expedited identification result; Obtaining weather forecast information for the delivery period, wherein the weather forecast data includes: temperature data, wind speed data, and humidity data; Determining an order priority delivery coefficient according to the order delivery information and the weather forecast information; Determine the orders that need to be delivered first according to the order priority delivery coefficient; Generate rider load factor; The dispatched rider is determined based on the load factor and the merchant address information.

[0049] The present invention may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present invention.

[0050] It should be understood by those skilled in the art that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The purpose of the present invention has been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments, and the embodiments of the present invention may be deformed or modified in any way without departing from the principles.

Claims

1. An online scheduling management system, characterized in that: include: An order delivery information module is used to generate order delivery information, wherein the order delivery information includes: merchant address information, delivery address information, merchant order acceptance time and order expedited identification result; An external information module is used to obtain weather forecast information for the delivery period, wherein the weather forecast data includes: temperature data, wind data and humidity data; An order priority module, used to determine an order priority delivery coefficient according to the order delivery information and the weather forecast information; An order priority delivery module, used to determine the orders that need priority delivery according to the order priority delivery coefficient; A rider information module, used to generate the rider's load factor; The rider dispatching module is used to determine the dispatched rider according to the load factor and the merchant address information.

2. The online scheduling management system according to claim 1 is characterized in that: Determining the order priority delivery coefficient according to the order delivery information and the weather forecast information includes: Get multiple historical order delivery information on multiple historical dates; Acquire multiple historical weather forecast information on multiple historical dates, wherein the historical weather forecast information includes: historical temperature data, historical humidity data, and historical wind speed data; Obtain similar historical order information in the historical order delivery information that is similar to the merchant address information and delivery address information of the current order; Determine similar historical merchant order acceptance times and similar historical delivery times based on the similar historical order information; Determine the historical order delivery time based on the similar historical merchant order acceptance time and the similar historical delivery time; Determine a delivery time relationship function according to the historical order delivery time and the historical weather forecast information; Determining an estimated order delivery time according to the delivery time relationship function and the weather forecast information; An order priority delivery coefficient is determined based on the order delivery information and the estimated order delivery time.

3. The online scheduling management system according to claim 2 is characterized in that: Determining a delivery time relationship function according to the historical order delivery time and the historical weather forecast information includes: According to the formula ， Determine the first undetermined coefficient equation of the delivery time relationship function, where, is the historical order delivery time of the e-th historical similar order, is the historical temperature data of the jth moment of the historical delivery cycle of the eth historical similar order, is the historical humidity data at the jth moment of the historical delivery cycle of the eth historical similar order, is the historical wind data at the jth moment of the historical delivery cycle of the eth historical similar order, To preset the humidity data threshold, To preset the wind data threshold, is the preset temperature data threshold, and is the first undetermined coefficient of the first undetermined coefficient equation, E is the number of similar historical orders, , e and E are both positive integers; According to the historical order delivery time, the historical temperature data, the historical humidity data and the historical wind data, the first undetermined coefficient is summed to obtain a solution value of the first undetermined coefficient; The delivery time relationship function is determined according to the solution value of the first undetermined coefficient and the first undetermined coefficient equation.

4. The online scheduling management system according to claim 2 is characterized in that: Determining an order priority delivery coefficient according to the order delivery information and the estimated order delivery time includes: According to the formula ， Determine the order priority distribution coefficient of the rth order at the jth moment of the distribution cycle ,in, is the estimated order delivery time of the rth order, is the jth moment of the management cycle, The merchant acceptance time for the rth order, The result of expediting the order for the rth order. , The preset multiple.

5. The online scheduling management system according to claim 1 is characterized in that: According to the order priority delivery coefficient, the orders that need priority delivery are determined, including: Arrange multiple orders in descending order according to their order priority delivery coefficients to determine the order priority delivery sequence; Determine the orders that require priority delivery based on the order corresponding to the first element of the order priority delivery sequence.

6. The online scheduling management system according to claim 1 is characterized in that: Generates the rider's load factor, including: Get the number of orders held by the rider; Obtain the delivery address information of the rider's held orders; According to the order delivery address information, determine the real-time location information of each held order in the real-time coordinate system, wherein the real-time coordinate system is a coordinate system established with the rider's location as the coordinate origin; Determine the east-west position information of the holding order on the x-axis of the real-time coordinate system according to the real-time position information; Determine the north-south position information of the holding order on the y-axis of the real-time coordinate system according to the real-time position information; Determine the standard deviation of the east-west position information based on the east-west position information of the plurality of held orders; Determine the standard deviation of the north-south position information based on the north-south position information of a plurality of holding orders; Get the estimated delivery time of the rider's held orders; Determine the remaining delivery time based on the estimated delivery time of the held order; The rider's load factor is generated based on the number of orders held, the east-west position information, the north-south position information, the standard deviation of the east-west position information, the standard deviation of the north-south position information and the remaining delivery time.

7. The online scheduling management system according to claim 6 is characterized in that: The load factor of the rider is generated according to the number of held orders, the east-west position information, the north-south position information, the standard deviation of the east-west position information, the standard deviation of the north-south position information, and the remaining delivery time, including: According to the formula ， Determine the load factor of the i-th rider at the j-th moment in the delivery cycle ,in, and is the preset weight, if is the conditional function, The number of orders held by the i-th rider at the j-th moment of the delivery cycle, To preset the threshold of the number of orders held, is the preset multiple, For the holds the east-west location information of the order at the jth moment in the delivery cycle, is the standard deviation of the east-west position information, is the north-south position information of the kth order at the jth moment of the delivery cycle, is the standard deviation of the north-south position information, is the remaining delivery time of the K orders held by the i-th rider at the j-th moment of the delivery cycle, is the preset time threshold, To hold the order quantity, , k and K are both positive integers.

8. The online scheduling management system according to claim 1 is characterized in that: Determining the dispatching rider according to the load factor and the merchant address information includes: Determine load factors and real-time location information for multiple riders; Determine the distance to the store based on the real-time location information and the merchant address information; Determining a scheduling difficulty coefficient according to the distance to the store and the load factor; Arrange in ascending order according to the scheduling difficulty coefficients to determine a scheduling difficulty sequence; Determine the dispatching rider according to the rider corresponding to the first element of the dispatching difficulty sequence.

9. A method for optimizing commodity distribution, characterized in that: include: Generate order delivery information, wherein the order delivery information includes: merchant address information, delivery address information, merchant order acceptance time and order expedited identification result; Obtaining weather forecast information for the delivery period, wherein the weather forecast data includes: temperature data, wind speed data, and humidity data; Determining an order priority delivery coefficient according to the order delivery information and the weather forecast information; Determine the orders that need to be delivered first according to the order priority delivery coefficient; Generate rider load factor; The dispatched rider is determined based on the load factor and the merchant address information.

Images