A logistics route planning method and system based on artificial intelligence

Abstract

The present application relates to the field of logistics distribution, and in particular to a logistics route planning method and system based on artificial intelligence, the method comprising: calculating the temperature change anomaly evaluation of any collection point and adjacent collection points, traversing all collection points, the collection point corresponding to the maximum value of the temperature change anomaly evaluation is the first monitoring point, and the collection point corresponding to the minimum value of the temperature change anomaly evaluation is the second monitoring point; constructing the temperature curve set of the first monitoring point and the temperature curve set of the second monitoring point, obtaining the optimal temperature curve subset, and obtaining the predicted adjustment time according to the optimal temperature curve subset; obtaining the predicted travel time set according to the distance between the current warehouse and the remaining warehouses and the average speed of the vehicle, each warehouse corresponds to a predicted travel time, calculating the difference between the predicted travel time and the adjustment time, and taking the warehouse corresponding to the smallest positive number in the difference as the next distribution warehouse. The present application has the effect of reducing the deterioration or failure of transported goods.

Description

Technical Field

[0001] The present application relates to the field of logistics distribution, and in particular to a logistics route planning method and system based on artificial intelligence. Background Art

[0002] Distributed logistics and distribution builds distributed warehouses to store inventory in regional warehouses, making it easier for goods to be delivered to consumers faster. In cold chain logistics, this means that storage facilities in different locations can be managed more flexibly, optimizing the distribution and transportation of goods to ensure that perishable foods and other sensitive goods can reach consumers in the best condition. At the same time, big data analysis is used to determine the best storage location, distribution route and cargo tracking solution to ensure the quality and safety of products throughout the entire logistics process.

[0003] In the prior art, route planning is usually performed based on the distance between delivery points, with the shortest driving distance being given priority to reduce transportation costs and time. The delivery order may also be adjusted based on the importance or urgency of the delivery points.

[0004] In cold chain logistics, the temperature changes of the environment in which the goods are located have a great impact on the goods. The storage temperature in the compartment is adjusted by the refrigeration equipment in the cold chain vehicle. When the transport vehicle arrives at each branch warehouse for unloading or loading, after the compartment door is opened, the air in the compartment of the cold chain vehicle exchanges heat with the outside world, and the temperature changes. After the compartment door is closed, the temperature in the compartment gradually returns to the preset temperature due to the operation of the refrigeration equipment.

[0005] Each unloading takes a certain amount of time. If the temperature has not returned to the preset temperature after the last unloading, the next warehouse will unload again, which may cause the goods to be in an unsuitable temperature for a long time, causing the goods to deteriorate or become invalid. If the existing route planning is based on the shortest distance, the goods may deteriorate or become invalid due to inappropriate delivery sequence. Summary of the invention

[0006] In order to solve the technical problem of item deterioration or failure caused by inappropriate delivery sequence, the present application provides a logistics route planning method and system based on artificial intelligence.

[0007] In the first aspect, the present application provides a logistics route planning method based on artificial intelligence, which adopts the following technical solutions:

[0008] A logistics route planning method based on artificial intelligence comprises the following steps: establishing a database according to a temperature curve of the historical temperature of each collection point in a carriage; screening the temperature curve to remove the noise curve; calculating the temperature change anomaly evaluation of any collection point and the adjacent collection points, traversing all the collection points, the collection point corresponding to the maximum value of the temperature change anomaly evaluation is the first monitoring point, and the collection point corresponding to the minimum value of the temperature change anomaly evaluation is the second monitoring point; constructing multiple temperature curve sets of the first monitoring point, each temperature curve set contains multiple temperature curves arranged in a preset order, and the temperature curve set of the first monitoring point is obtained, and similarly, the temperature data set of the second monitoring point is obtained; constructing multiple subsets according to the same temperature curves in the temperature curve set of the first monitoring point and the temperature curve set of the second monitoring point, all the temperature curves in each subset can form a continuous temperature change interval, and the subset with the least number of temperature curves is used as the optimal temperature curve subset, and the cumulative sum of the temperature curve time periods contained in the optimal temperature curve subset is the predicted adjustment time; according to the distance between the current warehouse and the remaining warehouses and the average speed of the vehicle, a predicted travel time set is obtained, each warehouse corresponds to a predicted travel time, the difference between the predicted travel time and the adjustment time is calculated, and the warehouse corresponding to the smallest positive number in the difference is used as the next distribution warehouse.

[0009] The beneficial effects are: while ensuring low energy consumption, the optimal power level and adjustment time are found, and the temperature adjustment process is optimized. If the predicted driving time is greater than the adjustment time, it means that the temperature in the car can be restored to the preset temperature before arriving at the next warehouse. If the predicted driving time is less than the adjustment time, it means that after the previous unloading is completed, the temperature has not yet returned to the preset temperature, and it arrives at the next warehouse for unloading again, which can easily cause the items to be at an unsuitable temperature for a long time, causing the items to deteriorate or fail.

[0010] The difference between the predicted travel time and the adjustment time is calculated. A positive number in the difference indicates that the predicted travel time is greater than the adjustment time. The smaller the predicted time, the smaller the distance the vehicle travels, and the shorter the distance between the two warehouses. Therefore, the warehouse corresponding to the smallest positive number is selected as the next distribution warehouse. The distance between warehouses and the time when items are stored at unsuitable temperatures are taken into consideration. While ensuring that the difference between the predicted travel time and the adjustment time is a positive number, the next warehouse is as close to the current warehouse as possible to achieve the purpose of route planning.

[0011] Optionally, a database is established based on the temperature curve of the historical temperature of each collection point in the car, including: obtaining the temperature and cooling power level at each moment in any collection point in the car, setting multiple moments as a time period, constructing a temperature curve about the time period and temperature under each cooling power level, traversing to obtain the temperature curves corresponding to all time periods, and constructing a database based on all temperature curves.

[0012] Optionally, multiple temperature curve sets for the first monitoring point are constructed, each temperature curve set contains multiple temperature curves arranged in a preset order, and the preset order is to satisfy a first condition and a second condition. The first condition is: the temperature of the end point of the first temperature curve is the temperature of the starting point of the next temperature curve, and the temperature of the end point of the last temperature curve is a preset temperature threshold; the second condition is: the cooling power level corresponding to each temperature curve is sorted in order from large to small or from small to large.

[0013] Optionally, the temperature change anomaly evaluation of any collection point and adjacent collection points is calculated using the following formula: ,in, To evaluate the abnormal temperature change at any collection point, is the temperature value sequence of any collection point in any period of time, is the temperature data of any adjacent collection point in any period of time, is the total number of adjacent collection points of any collection point, represents the Pearson correlation coefficient.

[0014] The beneficial effects are: The larger the value is, the greater the temperature change anomaly evaluation of the collection point is. The collection point corresponding to the maximum value of the temperature change anomaly evaluation is the first monitoring point, and the collection point corresponding to the minimum value of the temperature change anomaly evaluation is the second monitoring point. The temperature change of the first monitoring point is large, and the temperature change of the second monitoring point is small.

[0015] Optionally, at each collection point, the temperature curves with the same cooling power and the same starting point temperature are grouped as a temperature curve cluster, and the similarity between the temperature curves in each temperature curve cluster is calculated; the evaluation coefficient of any temperature curve is calculated; the evaluation coefficients of all temperature change curves in any temperature curve cluster are traversed to obtain the evaluation coefficients, the temperature curve with the largest evaluation coefficient is taken as the screened temperature curve, all temperature curve clusters are traversed to obtain the screened temperature curve of each temperature curve cluster.

[0016] The beneficial effect is that in the screened temperature curve, at each collection point, the temperature range, temperature curve and cooling power level correspond one to one, that is, there is a unique temperature curve in the same temperature range and the same cooling power level. Due to external factors such as ambient temperature differences or compartment sealing, at each collection point, there may be multiple temperature curves with the same cooling power, the same temperature range and a fixed time period. The change trends of these temperature curves are different. In order to reduce the amount of data calculation, the temperature curve needs to be screened.

[0017] Optionally, the similarity is calculated as: ,in, For the Temperature curve With Temperature curve The similarity between express and The temperature value of the initial point, express and The temperature value at the end point of the curve, Indicates the time of collection.

[0018] The beneficial effect is that the similarity of two temperature curves in the whole time range is quantified by integration, and a numerical similarity measure is provided.

[0019] Optionally, the evaluation coefficient is calculated as: ,in, For the The evaluation coefficient of the temperature curve is For the The total number of temperature curves with the same cooling power and the same starting point temperature. For the The first temperature curve has the same cooling power and the same starting point temperature. A temperature curve.

[0020] In the second aspect, the present application provides a logistics route planning method system based on artificial intelligence, which adopts the following technical solutions:

[0021] A logistics route planning method system based on artificial intelligence, a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the logistics route planning method based on artificial intelligence is implemented.

[0022] This application has the following technical effects:

[0023] 1. Under the condition of ensuring low energy consumption, find the optimal power gear and adjustment time, and optimize the temperature adjustment process. If the predicted driving time is greater than the adjustment time, it means that the temperature in the car can be restored to the preset temperature before arriving at the next warehouse. If the predicted driving time is less than the adjustment time, it means that after the previous unloading is completed, the temperature has not yet returned to the preset temperature, and it arrives at the next warehouse for unloading again, which may easily cause the items to be in an unsuitable temperature for a long time, causing the items to deteriorate or fail.

[0024] 2. Calculate the difference between the predicted travel time and the adjusted time. A positive number in the difference indicates that the predicted travel time is greater than the adjusted time. The smaller the predicted time, the smaller the distance the vehicle travels, and the shorter the distance between the two warehouses. Therefore, the warehouse corresponding to the smallest positive number is selected as the next distribution warehouse. The distance between warehouses and the time when items are stored at unsuitable temperatures are taken into consideration. While ensuring that the difference between the predicted travel time and the adjusted time is a positive number, the next warehouse is as close to the current warehouse as possible to achieve the purpose of route planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become easily understood. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-restrictive manner, and the same or corresponding numbers represent the same or corresponding parts.

[0026] Figure 1 This is a method flow chart of a logistics route planning method based on artificial intelligence in an embodiment of the present application.

[0027] Figure 2 This is a flow chart of a method for screening temperature curves in an artificial intelligence-based logistics route planning method in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions 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 those skilled in the art without creative work are within the scope of protection of the present application.

[0029] It should be understood that when the terms "first", "second", etc. are used in the claims, specification and drawings of the present application, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the specification and claims of the present application indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections.

[0030] The present application embodiment discloses a logistics route planning method based on artificial intelligence, referring to Figure 1 , including steps S1 to S6, specifically including:

[0031] S1: Establish a database based on the temperature curve of the historical temperature of each collection point in the car.

[0032] Set up multiple collection points at different locations in the car, install temperature sensors at the collection points, and obtain the temperature data of the collection points. In the historical data, obtain the temperature and cooling power level of any collection point in the car at each moment, and set multiple moments as a period.

[0033] Exemplarily, the cooling power levels can be level 1, level 2, and level 3, where level 1 has the highest cooling power and level 3 has the lowest cooling power. The time period can be 5 seconds, and the cooling power level and time period can be set by the user according to the actual application scenario.

[0034] Construct the temperature curve of time period and temperature under each cooling power level, traverse and obtain the temperature curve corresponding to all time periods. The method of constructing the temperature curve is: set the nonlinear model as , is the temperature, is the temperature collection time, , , These are the parameters to be solved.

[0035] The historical temperature data and the data of the acquisition time of each acquisition point are input into the nonlinear model, and several parameter groups are obtained by traversing using the least squares method. , each parameter group corresponds to a nonlinear model. Among them, the least square method is to find the best data match by minimizing the sum of squares of errors, so as to estimate the value of unknown data. It is an existing technology and will not be described here.

[0036] Setting the loss function ,in is the loss function, is the minimum function, is the total number of parameter groups, Indicates Collection points The actual collection time, Indicates The actual temperature of each collection point, Represents the sampling points in the nonlinear model The predicted collection time, Represents the midpoint of a nonlinear model The predicted temperature.

[0037] When the loss function approaches 0, the nonlinear model is the optimal model, and we get , , The optimal model is stored in the database as a temperature curve.

[0038] S2: Screen the temperature curve to remove the noise curve.

[0039] At each collection point, under the same cooling power, multiple temperature curves may appear in a fixed period. In order to reduce the amount of calculation in subsequent steps, it is necessary to screen out the optimal temperature curve from the multiple temperature curves. The screening process includes steps S20 to S22, which are as follows:

[0040] S20: At each collection point, the temperature curves with the same cooling power and the same starting point temperature are grouped as a temperature curve cluster, and the similarity between the temperature curves in each temperature curve cluster is calculated.

[0041] The similarity calculation formula is: ,in, For the Temperature curve With Temperature curve The similarity between express and The temperature value of the initial point, express and The temperature value at the end point of the curve, Indicates the time of collection.

[0042] S21: Calculate the evaluation coefficient of any temperature curve.

[0043] The calculation formula of the evaluation coefficient is: ,in, For the The evaluation coefficient of the temperature curve is For the The total number of temperature curves with the same cooling power and the same starting point temperature. For the The first temperature curve has the same cooling power and the same starting point temperature. A temperature curve.

[0044] S22: Traverse to obtain the evaluation coefficients of all temperature change curves in any temperature curve cluster, take the temperature curve with the largest evaluation coefficient as the screened temperature curve, traverse all temperature curve clusters, and obtain the screened temperature curve of each temperature curve cluster.

[0045] For example, the cooling power level is 3 and the temperature range is There are three temperature curves in the temperature curve clustering. The temperature curve with the largest evaluation coefficient among the three temperature curves is used as the screened temperature curve, and the other two temperature curves are deleted.

[0046] In the filtered temperature curve, at each collection point, the temperature range, temperature curve and cooling power level correspond one to one, that is, there is a unique temperature curve in the same temperature range and cooling power level. Due to external factors such as ambient temperature differences or compartment sealing, at each collection point, there may be multiple temperature curves with the same cooling power, temperature range and fixed time period. The change trends of these temperature curves are different. In order to reduce the amount of data calculation, the temperature curve needs to be filtered.

[0047] S3: Calculate the temperature change anomaly evaluation of any collection point and adjacent collection points, traverse all collection points, and the collection point corresponding to the maximum value of the temperature change anomaly evaluation is the first monitoring point, and the collection point corresponding to the minimum value of the temperature change anomaly evaluation is the second monitoring point.

[0048] The calculation formula for temperature change abnormality evaluation is:

[0049] ,in, To evaluate the abnormal temperature change at any collection point, is the temperature value sequence of any collection point in any period of time, is the temperature data of any adjacent collection point in any period of time, is the total number of adjacent collection points of any collection point, Represents the Pearson correlation coefficient, which is used to calculate the correlation between temperature value sequences. The value of the Pearson correlation coefficient is between and between, indicates a completely positive correlation. indicates a completely negative correlation. Indicates no correlation.

[0050] The larger the value is, the greater the temperature change anomaly evaluation of the collection point is. The collection point corresponding to the maximum value of the temperature change anomaly evaluation is the first monitoring point, and the collection point corresponding to the minimum value of the temperature change anomaly evaluation is the second monitoring point. The temperature change of the first monitoring point is large, and the temperature change of the second monitoring point is small.

[0051] The first monitoring point is the location where there is a sealing problem, such as the collection point near the door. The second monitoring point is the collection point near the refrigeration outlet. The temperature near the door changes greatly, and it takes a long time to recover to the preset temperature. That is, there are differences in the temperature changes and temperature recovery conditions at various locations in the car. If the maximum power is used for cooling at this time, the cost is high. If the medium and low power gears are used, the temperature of some locations in the car may not reach the preset temperature, causing the items to be in a low temperature environment for a long time, causing the items to deteriorate or fail. This application can find the optimal power gear and adjustment time while ensuring low energy efficiency, and optimize the temperature adjustment process.

[0052] S4: construct multiple temperature curve sets of the first monitoring point, each temperature curve set includes multiple temperature curves arranged in a preset order, and obtain the temperature curve set of the first monitoring point. Similarly, obtain the temperature data set of the second monitoring point.

[0053] The preset order is to meet the first condition and the second condition. The first condition is: the temperature of the end point of the first temperature curve is the temperature of the starting point of the next temperature curve, and the temperature of the end point of the last temperature curve is the preset temperature threshold.

[0054] Exemplarily, the temperature threshold is set to -10°C, the temperature at the starting point of the first temperature curve is 10°C, and the temperature at the end point is 5°C, the temperature at the starting point of the second temperature curve is 5°C, and the temperature at the end point is 2°C, the temperature at the starting point of the third temperature curve is 2°C, and the temperature at the end point is -4°C, and the temperature at the starting point of the fourth temperature curve is -4°C, and the temperature at the end point is -10°C.

[0055] The second condition is that the cooling power levels corresponding to each temperature curve are sorted in order from large to small or from small to large.

[0056] Exemplarily, the first temperature curve corresponds to a refrigeration power level of level 3, the second temperature curve corresponds to a refrigeration power level of level 3, the third temperature curve corresponds to a refrigeration power level of level 2, and the fourth temperature curve corresponds to a refrigeration power level of level 1.

[0057] S5: construct multiple subsets based on the temperature curve set of the first monitoring point and the temperature curve set of the second monitoring point that are the same, all the temperature curves in each subset can form a continuous temperature change interval, and the subset with the least number of temperature curves is used as the optimal temperature curve subset, and the cumulative sum of the temperature curve time periods included in the optimal temperature curve subset is the predicted adjustment time.

[0058] For example, there are two temperature curves in one subset, and the temperature change ranges of the two temperature curves are 0℃-5℃ and 5℃-10℃ respectively. There are three temperature curves in another subset, and the temperature change ranges of the three temperature curves are 0℃-2℃, 2℃-5℃, and 5℃-10℃ respectively. The subset containing two temperature curves is selected as the optimal temperature curve subset, and the cumulative time period of the two temperature curves is 10s, which is used as the predicted adjustment time. The gears corresponding to the two temperature curves are used as the adjustment gears. For example, the gear is 3 when 0℃-5℃, and the gear is 2 when 5℃-10℃.

[0059] S6: According to the distance between the current warehouse and the remaining warehouses and the average speed of the vehicle, a set of predicted driving times is obtained. Each warehouse corresponds to a predicted driving time. The difference between the predicted driving time and the adjusted time is calculated, and the warehouse corresponding to the smallest positive number in the difference is used as the next distribution warehouse.

[0060] If the predicted driving time is greater than the adjustment time, it means that the temperature in the car can be restored to the preset temperature before arriving at the next warehouse. If the predicted driving time is less than the adjustment time, it means that the temperature has not returned to the preset temperature after the previous unloading is completed, and it arrives at the next warehouse for unloading again, which may easily cause the items to be at an unsuitable temperature for a long time, causing the items to deteriorate or fail.

[0061] The difference between the predicted travel time and the adjustment time is calculated. A positive number in the difference indicates that the predicted travel time is greater than the adjustment time. The smaller the predicted time, the smaller the distance the vehicle travels, and the shorter the distance between the two warehouses. Therefore, the warehouse corresponding to the smallest positive number is selected as the next distribution warehouse. The distance between warehouses and the time when items are stored at unsuitable temperatures are taken into consideration. While ensuring that the difference between the predicted travel time and the adjustment time is a positive number, the next warehouse is as close to the current warehouse as possible to achieve the purpose of route planning.

[0062] An embodiment of the present application also discloses an artificial intelligence-based logistics route planning method system, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an artificial intelligence-based logistics route planning method according to the present application is implemented.

[0063] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0064] In the present application, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high bandwidth memory HBM (High Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0065] Although this specification has shown and described a plurality of embodiments of the present application, it is obvious to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will think of many changes, modifications and alternatives without departing from the thought and spirit of the present application. It should be understood that in the process of practicing the present application, various alternatives to the embodiments of the present application described herein may be adopted.

[0066] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A logistics route planning method based on artificial intelligence, characterized in that: Includes steps: Establish a database based on the temperature curve of the historical temperature of each collection point in the carriage; Screen the temperature curve to remove the noise curve; Calculate the temperature change anomaly evaluation of any collection point and adjacent collection points, traverse all collection points, the collection point corresponding to the maximum value of the temperature change anomaly evaluation is the first monitoring point, and the collection point corresponding to the minimum value of the temperature change anomaly evaluation is the second monitoring point; Construct multiple temperature curve sets of the first monitoring point, each temperature curve set includes multiple temperature curves arranged in a preset order, and obtain the temperature curve set of the first monitoring point. Similarly, obtain the temperature data set of the second monitoring point; Construct multiple subsets based on the same temperature curves in the temperature curve set of the first monitoring point and the temperature curve set of the second monitoring point, all the temperature curves in each subset can form a continuous temperature change interval, and take the subset with the least number of temperature curves as the optimal temperature curve subset, and the cumulative sum of the temperature curve time periods included in the optimal temperature curve subset is the predicted adjustment time; According to the distance between the current warehouse and the remaining warehouses and the average speed of the vehicle, a set of predicted driving times is obtained. Each warehouse corresponds to a predicted driving time. The difference between the predicted driving time and the adjusted time is calculated, and the warehouse corresponding to the smallest positive number in the difference is used as the next distribution warehouse.

2. The logistics route planning method based on artificial intelligence according to claim 1 is characterized in that: According to the temperature curve of the historical temperature of each collection point in the carriage, a database is established, including: Get the temperature and cooling power level at any collection point in the car at each moment, set multiple moments as a period, build a temperature curve about the period and temperature under each cooling power level, traverse, get the temperature curves corresponding to all periods, and build a database based on all temperature curves.

3. The logistics route planning method based on artificial intelligence according to claim 1 is characterized in that: Construct multiple temperature curve sets of the first monitoring point, each temperature curve set includes multiple temperature curves arranged in a preset order, the preset order is to satisfy a first condition and a second condition, the first condition is: the temperature of the end point of the first temperature curve is the temperature of the starting point of the next temperature curve, and the temperature of the end point of the last temperature curve is a preset temperature threshold; The second condition is that the cooling power levels corresponding to each temperature curve are sorted in order from large to small or from small to large.

4. The logistics route planning method based on artificial intelligence according to claim 1 is characterized in that: Calculate the temperature change anomaly evaluation of any collection point and adjacent collection points. The calculation formula is: ,in, To evaluate the abnormal temperature change at any collection point, is the temperature value sequence of any collection point in any period of time, is the temperature data of any adjacent collection point in any period of time, is the total number of adjacent collection points of any collection point, represents the Pearson correlation coefficient.

5. The logistics route planning method based on artificial intelligence according to claim 1 is characterized in that: Screen temperature curves to remove noise curves, including: At each collection point, the temperature curves with the same cooling power and the same starting point temperature are clustered as a temperature curve, and the similarity between the temperature curves in each temperature curve cluster is calculated; Calculate the evaluation coefficient of any temperature curve; Traverse to obtain the evaluation coefficients of all temperature change curves in any temperature curve cluster, take the temperature curve with the largest evaluation coefficient as the screened temperature curve, traverse all temperature curve clusters, and obtain the screened temperature curve of each temperature curve cluster.

6. The artificial intelligence-based logistics route planning method according to claim 5, characterized in that: The similarity calculation formula is: ,in, For the Temperature curve With Temperature curve The similarity between express and The temperature value of the initial point, express and The temperature value at the end point of the curve, Indicates the time of collection.

7. The artificial intelligence-based logistics route planning method according to claim 5, characterized in that: The calculation formula of the evaluation coefficient is: ,in, For the The evaluation coefficient of the temperature curve is For the The total number of temperature curves with the same cooling power and the same starting point temperature. For the The first temperature curve has the same cooling power and the same starting point temperature. A temperature curve.

8. A logistics route planning method system based on artificial intelligence, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the artificial intelligence-based logistics route planning method according to any one of claims 1-7 is implemented.

Images