CN117610694A - Multi-tenant order distribution method, device, equipment and storage medium - Google Patents
Multi-tenant order distribution method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117610694A CN117610694A CN202410090000.9A CN202410090000A CN117610694A CN 117610694 A CN117610694 A CN 117610694A CN 202410090000 A CN202410090000 A CN 202410090000A CN 117610694 A CN117610694 A CN 117610694A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- order
- passenger
- network
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000013135 deep learning Methods 0.000 claims description 25
- 238000012545 processing Methods 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 10
- 238000010219 correlation analysis Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 210000002569 neuron Anatomy 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 5
- 230000004044 response Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000026676 system process Effects 0.000 description 1
- 230000029305 taxis Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/02—Reservations, e.g. for tickets, services or events
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Resources & Organizations (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method, a device, equipment and a storage medium for distributing orders of multiple tenants, which relate to the field of order distribution of a technical network vehicle-booking platform and specifically comprise the following steps: s1, allocating a digital identifier to a network about vehicle capable of receiving a bill, wherein the digital identifier is network about vehicle historical data, and the network about vehicle historical data comprise a departure position of a passenger in each historical order, a destination of the passenger, a distance from the departure position of the passenger to the destination, a used time and scoring data; s2, collecting vehicle parameters of the net appointment vehicle capable of being checked. According to the invention, the vehicle parameters are monitored in real time, and the real-time position information and the priority level of the tenant are combined, so that the order recommendation coefficient can be dynamically adjusted, the passengers can be optimally distributed in different time and different places, the real will of the passengers is met, and the riding experience of the passengers and the service level of network taxi drivers are improved.
Description
Technical Field
The invention relates to the technical field of order distribution of network about vehicle platforms, in particular to a method, a device, equipment and a storage medium for distributing orders of multiple tenants.
Background
Network booking vehicles refer to vehicle services subscribed to and used by an online platform or application. Such services allow passengers to subscribe to vehicles, such as riding private cars, taxis, or other vehicles, using smart phone applications or websites without having to call the car or wait in line on site. Generally, the network taxi service provides a real-time positioning, transparent price, convenient payment and an evaluation system between passengers and drivers to provide a safer and more convenient trip experience.
In the prior art, an order is generally allocated to a network vehicle platform according to the distance from an ordered passenger, the closer the network vehicle platform is to the passenger, the higher the priority of the order taking is, the higher the probability of acquiring the order is, the farther the network vehicle platform is from the passenger, the lower the priority of the order taking is, the probability of acquiring the order is lower, but the distance can only indicate whether the areas where the vehicle and the passenger are located are in the same range, and cannot indicate the condition of vehicle time rate, the number of times of vehicle violations and the satisfaction of the vehicle of the intranet vehicle in the past for a period of time, which is possibly slightly far from the passenger, but is better than the vehicle slightly near the passenger, the passenger wants to select the vehicle slightly far from the passenger but is slightly better than the other conditions, if the platform only considers the distance to allocate the vehicle, the intangible with the passenger, the passengers experience of the riding is reduced, and the service level of the network vehicle driver is gradually reduced if the vehicle is not allocated according to the vehicle attribute and the priority of the position.
The above information disclosed in the background section is only for enhancement of understanding of the background of the disclosure and therefore it may include information that does not form the prior art that is already known to a person of ordinary skill in the art.
Disclosure of Invention
The invention aims to provide a method, a device, equipment and a storage medium for distributing orders of multiple tenants, so as to solve the problems in the prior art.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a method for distributing orders of multiple tenants, as shown in fig. 1, specifically includes the steps of:
s1, allocating a digital identifier to a network about vehicle capable of receiving a bill, wherein the digital identifier is network about vehicle historical data, and the network about vehicle historical data comprise a departure position of a passenger in each historical order, a destination of the passenger, a distance from the departure position of the passenger to the destination, a used time and scoring data;
s2, acquiring vehicle parameters of a network-bound vehicle capable of receiving orders, wherein the vehicle parameters comprise the proportion of vehicles reaching the position of a passenger on time in a T time period in a historical order, the total number of violations of the vehicles and the average satisfaction degree of the vehicles, acquiring the real-time position of the network-bound vehicle, and acquiring order data in an order to be distributed, wherein the order data comprises the departure position of the passenger, the destination of the passenger and the expected time of reaching the destination in the order;
s3, distributing service areas of the network appointment vehicles into 3 areas according to real-time positions of passengers and real-time positions of the network appointment vehicles in an order to be distributed, setting order receiving priority levels according to whether the real-time positions of the network appointment vehicles and the passengers belong to the same area, wherein the network appointment vehicles of the network appointment vehicles and the real-time positions of the passengers in the same area are set to be highest priority, the network appointment vehicles of adjacent areas are second highest priority, the network appointment vehicles of the separated areas are lowest priority, and priority coefficients are distributed according to the priority levels;
s4, performing non-dimensionalization processing on the collected vehicle parameters and the priority coefficient of the vehicle, and performing correlation analysis to generate a vehicle comprehensive index;
s5, constructing a deep learning network, taking the departure position of a passenger, the destination of the passenger, the distance between the departure position of the passenger and the destination and the time used in the digital identifier of the network vehicle as a training set, taking the scoring data of the corresponding historical order as a label, and inputting the scoring data into the deep learning network for training;
s6, inputting the departure position of the passenger, the destination of the passenger, the distance from the departure position of the passenger to the destination and the estimated time of the passenger to the destination in the existing data of the order to be distributed into a trained deep learning network, and acquiring estimated scoring data of the current order;
s7, analyzing and data processing the estimated score data and the vehicle comprehensive index of each vehicle, generating an order recommendation coefficient of each vehicle, and distributing the order to the vehicle with the highest order recommendation coefficient.
Further, the time range of the T time period is as followsWherein->The expected arrival time is represented, and the range of values for the T time period is: 10 min-20 min.
Further, the coefficient of the highest priority is set to 0.5, the coefficient of the next highest priority is set to 0.3, and the coefficient of the lowest priority is set to 0.1.
Further, the collected vehicle parameters and the priority coefficient of the vehicle are processed in a non-dimensionality mode, correlation analysis is carried out, and a vehicle comprehensive index is generatedThe formula according to is as follows:
wherein,for the proportion of the time of the vehicle reaching the passenger position in the period T, +.>For the total number of violations of the vehicle in the period T, < > for the period T>For the average satisfaction of the vehicle during time T, < >>For the priority factor of the vehicle, +.>The factor of the proportion of the time of arrival of the vehicle at the passenger position in the period T is 0.2 +.>≤0.4,/>Is a factor coefficient of the total number of violations of the vehicle in the T time period, and is 0.2 +.>≤0.4,/>Is a factor of the average satisfaction of the vehicle in the T period, 0.2 +.>≤0.4,/>Is a constant correction coefficient.
Further, the deep learning network is formed by a deep neural network based on a multi-layer perceptron, the deep neural network of the multi-layer perceptron comprises an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer, and the first hidden layer, the second hidden layer and the third hidden layer are provided with at least two neurons and all adopt ReLU as an activation function.
Further, analyzing and data processing the predicted scoring data and the comprehensive index of the vehicle of each vehicle to generate an order recommendation coefficient of each vehicleThe formula according to is as follows:
wherein,for predictive scoring data, ++>Factor coefficient of predicted scoring data, 0.2. Ltoreq.o ≡>≤0.4,/>Factor coefficient of vehicle comprehensive index for each vehicle is 0.2 +.>≤0.4,/>Is a constant correction coefficient.
An apparatus for multi-tenant order allocation, comprising:
the network appointment vehicle history data comprises a departure position of a passenger in each history order, a passenger destination, a distance from the departure position of the passenger to the destination, a used time and scoring data;
the system comprises a data acquisition module, a data acquisition module and a control module, wherein the data acquisition module is used for acquiring vehicle parameters of an order-available network vehicle, the vehicle parameters comprise the proportion of vehicles reaching the position of a passenger on time in a T time period in a historical order, the total number of violations of the vehicles and the average satisfaction degree of the vehicles, acquiring the real-time position of the network vehicle, and acquiring order data in an order to be distributed, wherein the order data comprise the departure position of the passenger, the destination of the passenger and the expected arrival time in the order;
the priority setting module is used for distributing service areas of the network appointment vehicles into 3 areas according to real-time positions of passengers and real-time positions of the network appointment vehicles in an order to be distributed, setting order receiving priority levels according to whether the real-time positions of the network appointment vehicles and the passengers belong to the same area, wherein the network appointment vehicles of the network appointment vehicles and the real-time positions of the passengers in the same area are set to be highest priority, the network appointment vehicles of adjacent areas are second highest priority, the network appointment vehicles of the separated areas are lowest priority, and priority coefficients are distributed according to the priority levels;
the data processing module is used for carrying out non-dimensionalization processing on the collected vehicle parameters and the priority coefficient of the vehicle, carrying out correlation analysis and generating a vehicle comprehensive index;
the deep learning network construction module is used for constructing a deep learning network, taking the departure position of a passenger of a historical order, the destination of the passenger, the distance between the departure position of the passenger and the destination and the time used in the digital identifier of the network appointment vehicle as a training set, taking the scoring data of the corresponding historical order as a label, and inputting the scoring data into the deep learning network for training;
the scoring data acquisition module is used for inputting the departure position of the passenger, the destination of the passenger, the distance from the departure position of the passenger to the destination and the estimated time from the passenger to the destination in the existing data of the order to be distributed into the trained deep learning network to acquire the estimated scoring data of the current order;
and the order distribution module is used for analyzing and data processing the estimated score data and the vehicle comprehensive index of each vehicle, generating an order recommendation coefficient of each vehicle and distributing the order to the vehicle with the highest order recommendation coefficient.
An apparatus, comprising:
a memory for storing a computer program;
a processor for executing the computer program to implement the method of multi-tenant order allocation as described above.
A readable storage medium storing the computer program which when executed by a processor implements a method of multi-tenant order allocation as described above.
Compared with the prior art, the invention has the beneficial effects that:
the invention distributes a digital identifier to a network about vehicle capable of receiving orders, wherein the digital identifier is network about vehicle historical data, the network about vehicle historical data comprises a departure position of a passenger in each historical order, a destination of the passenger, a distance from the departure position of the passenger to the destination, used time and scoring data, a service area of the network about vehicle is distributed into 3 areas according to a real-time position of the passenger in an order to be distributed and a real-time position of the network about vehicle, a priority coefficient of receiving orders is set according to the distance between the tenant of the network about vehicle and the real-time position of the passenger, vehicle parameters and the priority coefficient of the tenant are processed to generate a vehicle comprehensive index, a deep learning network is constructed, the predicted scoring data of the current order is obtained, the predicted scoring data and the vehicle comprehensive index of each vehicle are analyzed and processed to generate an order recommendation coefficient of each vehicle, and the order is distributed to the vehicle with the highest order recommendation coefficient. Therefore, the vehicle parameters are monitored in real time, and the real-time position information and the priority level of the tenant are combined, so that the order recommendation coefficient can be dynamically adjusted, passengers can be optimally distributed in different time and different places, the real will of the passengers is met, and the riding experience of the passengers and the service level of network taxi drivers are improved.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention;
FIG. 2 is a block diagram of the modular components of the present invention;
fig. 3 is a schematic diagram of the priority of the network bus in different areas according to the present invention.
Detailed Description
The present invention will be further described in detail with reference to specific embodiments in order to make the objects, technical solutions and advantages of the present invention more apparent.
It is to be noted that unless otherwise defined, technical or scientific terms used herein should be taken in a general sense as understood by one of ordinary skill in the art to which the present invention belongs. The terms "first," "second," and the like, as used herein, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "up", "down", "left", "right" and the like are used only to indicate a relative positional relationship, and when the absolute position of the object to be described is changed, the relative positional relationship may be changed accordingly.
Examples:
referring to fig. 1 to 3, the present invention provides a technical solution:
a method for distributing orders of multiple tenants, as shown in fig. 1, specifically includes the steps of:
s1, allocating a digital identifier to a network about vehicle capable of receiving a bill, wherein the digital identifier is network about vehicle historical data, and the network about vehicle historical data comprise a departure position of a passenger in each historical order, a destination of the passenger, a distance from the departure position of the passenger to the destination, a used time and scoring data;
s2, acquiring vehicle parameters of a network-bound vehicle capable of receiving orders, wherein the vehicle parameters comprise the proportion of vehicles reaching the position of a passenger on time in a T time period in a historical order, the total number of violations of the vehicles and the average satisfaction degree of the vehicles, acquiring the real-time position of the network-bound vehicle, and acquiring order data in an order to be distributed, wherein the order data comprises the departure position of the passenger, the destination of the passenger and the expected time of reaching the destination in the order;
s3, distributing service areas of the network appointment vehicles into 3 areas according to real-time positions of passengers and real-time positions of the network appointment vehicles in an order to be distributed, setting order receiving priority levels according to whether the real-time positions of the network appointment vehicles and the passengers belong to the same area, wherein the network appointment vehicles of the network appointment vehicles and the real-time positions of the passengers in the same area are set to be highest priority, the network appointment vehicles of adjacent areas are second highest priority, the network appointment vehicles of the separated areas are lowest priority, and priority coefficients are distributed according to the priority levels;
s4, performing non-dimensionalization processing on the collected vehicle parameters and the priority coefficient of the vehicle, and performing correlation analysis to generate a vehicle comprehensive index;
s5, constructing a deep learning network, taking the departure position of a passenger, the destination of the passenger, the distance between the departure position of the passenger and the destination and the time used in the digital identifier of the network vehicle as a training set, taking the scoring data of the corresponding historical order as a label, and inputting the scoring data into the deep learning network for training;
s6, inputting the departure position of the passenger, the destination of the passenger, the distance from the departure position of the passenger to the destination and the estimated time of the passenger to the destination in the existing data of the order to be distributed into a trained deep learning network, and acquiring estimated scoring data of the current order;
s7, analyzing and data processing the estimated score data and the vehicle comprehensive index of each vehicle, generating an order recommendation coefficient of each vehicle, and distributing the order to the vehicle with the highest order recommendation coefficient.
When the proportion of vehicles reaching the passenger position on time in the T time period is different, the allocation modes of the orders of multiple tenants are different, and the following specific reasons are as follows:
high punctual rate: if the vehicle is on a high punctual rate during the T period, i.e. most vehicles are able to arrive at the passenger location on time. In such a case, the system may be more inclined to employ an efficiency-oriented allocation strategy, such as shortest path or minimum cost, to ensure that orders are rapidly satisfied.
Medium time rate: if the vehicle punctual rate during the T period is of a medium level, i.e. part of the vehicles can arrive on time. In this case, the system may trade off efficiency and fairness, employing an allocation strategy that is intermediate between efficiency and fairness to ensure that orders are fairly allocated to a certain extent while remaining as efficient as possible.
Low time rate: if the vehicle is on a low punctual level during the T period, most vehicles often delay reaching the passenger position. In this case, the system may be more focused on fairness and passenger experience, employing a strategy that can distribute orders more evenly, reducing latency, to increase overall service levels.
Therefore, monitoring the proportion of vehicles reaching the passenger position on time in the T time period through the background or the background server is particularly important for monitoring the multi-tenant order distribution mode, for example, the following effects can be produced:
optimizing allocation strategy: by monitoring the arrival of vehicles at the passenger location in real time, the platform can analyze the punctuality of different vehicles and drivers. This data can be used to optimize the order allocation strategy to allocate orders to drivers that are more likely to arrive on time, thereby improving overall quality of service.
Passenger satisfaction is improved: ensuring that the vehicle arrives at the passenger location on time can enhance the passenger experience. By monitoring the punctuality of the driver, the platform can ensure that more passengers can obtain the on-time driving receiving service, and the satisfaction degree of the passengers on the service is enhanced.
Latency is reduced: by analyzing the on-time arrival rate of vehicles, the platform can identify and exclude factors that often cause delays and adjust the order allocation to reduce passenger waiting time.
Optimizing route planning: the sensors monitor the driving conditions of the vehicle and help to analyze traffic conditions and driver behavior. These data can be used to improve route planning and suggest the driver's best travel path, improving punctuality.
When the total number of violations of the vehicle exceeds a set threshold value in the period of T, the allocation modes of the orders of the multiple tenants are different, and the following specific reasons are as follows:
safety considerations: vehicle violations may increase the safety risk to passengers and drivers. To ensure the safety of passengers and drivers, the platform may adjust the order distribution, and make the orders more prone to drivers who observe traffic regulations and drive safely, so as to reduce the occurrence probability of accidents and emergencies.
Regulatory compliance: multi-tenant platforms are often required to adhere to local regulations and traffic rules. The platform may be subjected to legal liabilities if the vehicle frequently violates regulations. To maintain compliance, the platform may take steps such as limiting the receipt of orders by drivers whose number of violations exceeds a threshold to ensure legitimacy of the business.
Passenger trust: the violation of the vehicle may negatively affect passengers, affecting their confidence in the platform. To maintain the trust of the passenger, the platform may adjust the order distribution to ensure that the passenger is able to select drivers with better safety records.
The insurance cost is as follows: frequent violations may result in increased insurance costs for the driver. The platform may consider this factor and adjust the order distribution based on the number of violations to reduce the risk of insurance for the platform and the driver.
Therefore, detecting the total number of violations of the vehicle in the T period by the traffic monitoring camera is particularly important for monitoring the allocation mode of orders for multiple tenants, for example, the following effects can be achieved:
improving the compliance of drivers: monitoring the number of violations may encourage drivers to more adhere to traffic regulations to avoid affecting order allocation due to violations. This helps to improve compliance and safety of the driver.
The safety of passengers is improved: by reducing the number of violations, the platform can increase the passenger's sense of trust in the service. Passengers tend to choose drivers that are safer to drive on the road, thereby improving overall passenger safety.
When the average satisfaction of the vehicles is different, the allocation modes of the orders of the multiple tenants are different, and the following specific reasons are as follows:
and (3) improving service quality: if the satisfaction of a vehicle is high, the platform may be more inclined to distribute orders to the vehicle to provide high quality service. This helps to promote the overall user experience, increasing the user's sense of trust in the platform.
Passenger preference matching: the platform may be matched according to the satisfaction of the vehicle and the preferences of the passengers. If the passenger prefers to select vehicles with good public praise and high satisfaction, the platform may prioritize the allocation of orders to those vehicles to meet the user's expectations.
Maintaining the image of a platform: high satisfaction vehicles represent a good image of the platform. To maintain the reputation and brand image of the platform, the platform may adjust the order allocation to ensure that the user is able to enjoy a high level of service.
Therefore, the average satisfaction degree of the vehicle is obtained through the user feedback and evaluation system, which is particularly important for monitoring the multi-tenant order distribution mode, for example, the following effects can be produced:
accurate passenger demand that matches: knowing the satisfaction of the vehicle helps to better match the expectations of the passengers. The platform may adjust the order allocation policy based on user feedback so that passengers are more likely to be allocated to vehicles they approve, improving passenger satisfaction.
When the priority coefficients of tenants are different, the order allocation modes of the tenants are different, and the following specific reasons are as follows:
urgency and importance: different tenants may have different needs for urgency and importance. Higher priority orders may require faster response and shorter waiting times, and thus the system may prioritize resources to fulfill these orders.
Therefore, detecting the priority coefficient of the tenant through the global positioning system is particularly important for monitoring the order allocation mode of the multi-tenant, for example, the following effects can be produced:
flexible resource allocation: the order distribution system may more flexibly distribute resources according to the priority of the tenant. A high priority order may be supported by more resources, ensuring timely response and high quality service.
Emergency order processing: orders for high priority tenants may be related to urgency. The system may ensure that emergency orders are prioritized to meet tenant expectations for quick response.
Efficiency is improved: knowing the priority level may help the system process orders more efficiently. The system can focus on tasks with high priority, improves the overall operation efficiency and reduces the resource waste.
Customer satisfaction improves: providing personalized services that meet tenant expectations may improve customer satisfaction. The tenant feels the attention of the order distribution system to the demands of the tenant, and the trust feeling of the service is enhanced.
In summary, the proportion of the vehicle reaching the passenger position on time, the total number of violations of the vehicle, the average satisfaction of the vehicle and the priority level of the tenant in the T period are collected, which plays an extremely important role in order allocation of multiple tenants.
On the basis of the above embodiment, the time range of the T period isWherein->The expected arrival time is represented, and the range of values for the T time period is: 10 min-20 min.
On the basis of the above embodiment, as shown in fig. 3, the highest priority is that the passenger and the net car are located in the same area, the area is assumed to be square with 5KM, the coefficient of the highest priority is set to 0.5, the next highest priority is that the passenger and the net car are located in adjacent areas, the area is 15KM square with the middle 5KM square removed, the coefficient of the next highest priority is set to 0.3, the lowest priority is that the passenger and the net car are located in separate areas, the area is 25KM square with the middle 15KM square removed, and the coefficient of the lowest priority is set to 0.1.
The collected vehicle parameters and the priority coefficient of the vehicle are processed in a non-dimensionality mode, correlation analysis is carried out, and a vehicle comprehensive index is generatedThe formula according to is as follows:
wherein,for the proportion of the time of the vehicle reaching the passenger position in the period T, +.>For the total number of violations of the vehicle in the period T, < > for the period T>For the average satisfaction of the vehicle during time T, < >>For the priority factor of the vehicle, +.>The factor of the proportion of the time of arrival of the vehicle at the passenger position in the period T is 0.2 +.>≤0.4,/>Is a factor coefficient of the total number of violations of the vehicle in the T time period, and is 0.2 +.>≤0.4,/>Is a factor of the average satisfaction of the vehicle in the T period, 0.2 +.>≤0.4,/>Is a constant correction coefficient.
As can be seen from the above formula, whenThe higher the vehicle combination index->The higher the->The higher the vehicle combination index->The lower the->The higher the vehicle combination index->The higher the->The higher the vehicle combination index->The higher, indicate +.>、/>、And->In positive correlation with->And->And in the formula, the factor coefficients are used for balancing the duty ratio of each item of data in the formula so as to promote the accuracy of a calculation result.
On the basis of the embodiment, the deep learning network is formed by a deep neural network based on a multi-layer perceptron, the deep neural network of the multi-layer perceptron comprises an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer, and the first hidden layer, the second hidden layer and the third hidden layer are provided with at least two neurons and all adopt ReLU as an activation function.
In this embodiment, the input features of the deep neural network of the multi-layer sensor include: passenger departure location (longitude and latitude): 2 features, passenger destination (longitude and latitude): 2 characteristics, distance of passenger departure location from destination: 1 feature, time used (e.g., travel time): 1 feature.
The deep neural network structure of the multilayer perceptron is as follows:
input layer ×: receiving an input of 6 features;
first hidden layer: having 64 neurons, using ReLU as an activation function;
second hidden layer: having 128 neurons, again using the ReLU activation function;
third hidden layer: having 64 neurons, using a ReLU activation function;
output layer: with a single neuron, a predicted scoring value is output.
On the basis of the embodiment, the predicted score data and the comprehensive vehicle index of each vehicle are analyzed and processed to generate an order recommendation coefficient of each vehicleThe formula according to is as follows:
wherein,for predictive scoring data, ++>Factor coefficient of predicted scoring data, 0.2. Ltoreq.o ≡>≤0.4,/>Factor coefficient of vehicle comprehensive index for each vehicle is 0.2 +.>≤0.4,/>Is a constant correction coefficient.
As can be seen from the above formula, whenThe higher the order recommendation coefficient for each vehicle +.>The higher the->The higher the order recommendation coefficient for each vehicle +.>The higher, indicate +.>、/>And->And in the positive correlation, the factor coefficient in the formula is used for balancing the duty ratio of each item of data in the formula, so that the accuracy of a calculation result is promoted.
In the formula、/>、/>、/>And->The specific value of (2) is generally determined by a person skilled in the art according to the actual situation, the formula is essentially a weighted sum for comprehensive analysis, a person skilled in the art collects a plurality of groups of sample data, and sets a corresponding preset proportionality coefficient for each group of sample data to be setSubstituting preset proportional coefficients and collected sample data into a formula, observing the accuracy of model output and the rationality of results through repeated experiments and parameter adjustment, gradually adjusting the factor coefficients, comparing the performance and effects of the model under different parameter settings, finding out the optimal coefficient combination, screening and averaging the calculated factor coefficients to obtain +.>、/>、/>、/>And->Is a value of (a).
In addition, the size of the preset factor coefficient is a specific numerical value obtained by quantizing each parameter, so that the size of the coefficient depends on the number of sample data and the corresponding preset scaling factor preliminarily set by a person skilled in the art, and is not unique, so long as the scaling relation between the parameter and the quantized numerical value is not affected.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation.
An apparatus for multi-tenant order allocation, as shown in fig. 2, comprises:
the network appointment vehicle history data comprises a departure position of a passenger in each history order, a passenger destination, a distance from the departure position of the passenger to the destination, a used time and scoring data;
the system comprises a data acquisition module, a data acquisition module and a control module, wherein the data acquisition module is used for acquiring vehicle parameters of an order-available network vehicle, the vehicle parameters comprise the proportion of vehicles reaching the position of a passenger on time in a T time period in a historical order, the total number of violations of the vehicles and the average satisfaction degree of the vehicles, acquiring the real-time position of the network vehicle, and acquiring order data in an order to be distributed, wherein the order data comprise the departure position of the passenger, the destination of the passenger and the expected arrival time in the order;
the priority setting module is used for distributing service areas of the network appointment vehicles into 3 areas according to real-time positions of passengers and real-time positions of the network appointment vehicles in an order to be distributed, setting order receiving priority levels according to whether the real-time positions of the network appointment vehicles and the passengers belong to the same area, wherein the network appointment vehicles of the network appointment vehicles and the real-time positions of the passengers in the same area are set to be highest priority, the network appointment vehicles of adjacent areas are second highest priority, the network appointment vehicles of the separated areas are lowest priority, and priority coefficients are distributed according to the priority levels;
the data processing module is used for carrying out non-dimensionalization processing on the collected vehicle parameters and the priority coefficient of the vehicle, carrying out correlation analysis and generating a vehicle comprehensive index;
the deep learning network construction module is used for constructing a deep learning network, taking the departure position of a passenger of a historical order, the destination of the passenger, the distance between the departure position of the passenger and the destination and the time used in the digital identifier of the network appointment vehicle as a training set, taking the scoring data of the corresponding historical order as a label, and inputting the scoring data into the deep learning network for training;
the scoring data acquisition module is used for inputting the departure position of the passenger, the destination of the passenger, the distance from the departure position of the passenger to the destination and the estimated time from the passenger to the destination in the existing data of the order to be distributed into the trained deep learning network to acquire the estimated scoring data of the current order;
and the order distribution module is used for analyzing and data processing the estimated score data and the vehicle comprehensive index of each vehicle, generating an order recommendation coefficient of each vehicle and distributing the order to the vehicle with the highest order recommendation coefficient.
An apparatus, comprising:
a memory for storing a computer program;
a processor for executing a computer program to implement the method of multi-tenant order allocation as claimed in any one of the preceding claims.
A readable storage medium storing a computer program which when executed by a processor performs a method of multi-tenant order allocation as claimed in any one of the preceding claims.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. Those of skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application.
Claims (9)
1. A method for multi-tenant order distribution, comprising the specific steps of:
s1, allocating a digital identifier to a network about vehicle capable of receiving a bill, wherein the digital identifier is network about vehicle historical data, and the network about vehicle historical data comprise a departure position of a passenger in each historical order, a destination of the passenger, a distance from the departure position of the passenger to the destination, a used time and scoring data;
s2, acquiring vehicle parameters of a network-bound vehicle capable of receiving orders, wherein the vehicle parameters comprise the proportion of vehicles reaching the position of a passenger on time in a T time period in a historical order, the total number of violations of the vehicles and the average satisfaction degree of the vehicles, acquiring the real-time position of the network-bound vehicle, and acquiring order data in an order to be distributed, wherein the order data comprises the departure position of the passenger, the destination of the passenger and the expected time of reaching the destination in the order;
s3, distributing service areas of the network appointment vehicles into 3 areas according to real-time positions of passengers and real-time positions of the network appointment vehicles in an order to be distributed, setting order receiving priority levels according to whether the real-time positions of the network appointment vehicles and the passengers belong to the same area, wherein the network appointment vehicles of the network appointment vehicles and the real-time positions of the passengers in the same area are set to be highest priority, the network appointment vehicles of adjacent areas are second highest priority, the network appointment vehicles of the separated areas are lowest priority, and priority coefficients are distributed according to the priority levels;
s4, performing non-dimensionalization processing on the collected vehicle parameters and the priority coefficient of the vehicle, and performing correlation analysis to generate a vehicle comprehensive index;
s5, constructing a deep learning network, taking the departure position of a passenger, the destination of the passenger, the distance between the departure position of the passenger and the destination and the time used in the digital identifier of the network vehicle as a training set, taking the scoring data of the corresponding historical order as a label, and inputting the scoring data into the deep learning network for training;
s6, inputting the departure position of the passenger, the destination of the passenger, the distance from the departure position of the passenger to the destination and the estimated time of the passenger to the destination in the existing data of the order to be distributed into a trained deep learning network, and acquiring estimated scoring data of the current order;
s7, analyzing and data processing the estimated score data and the vehicle comprehensive index of each vehicle, generating an order recommendation coefficient of each vehicle, and distributing the order to the vehicle with the highest order recommendation coefficient.
2. The method of multi-tenant order distribution of claim 1, wherein the time range of the T time period, />The expected arrival time is represented, and the range of values for the T time period is: 10 min-20 min.
3. The method of claim 1, wherein the highest priority factor is set to 0.5, the next highest priority factor is set to 0.3, and the lowest priority factor is set to 0.1.
4. A method of multi-tenant order allocation according to claim 3, wherein the collected vehicle parameters and priority coefficients of the vehicle are processed nondimensionally and subjected to correlation analysis to generate a vehicle comprehensive indexThe formula according to is as follows:
wherein (1)>For the proportion of the time of the vehicle reaching the passenger position in the period T, +.>For the total number of violations of the vehicle in the period T, < > for the period T>For the average satisfaction of the vehicle during time T, < >>For the priority factor of the vehicle, +.>The factor of the proportion of the time of arrival of the vehicle at the passenger position in the period T is 0.2 +.>≤0.4,/>Is a factor coefficient of the total number of violations of the vehicle in the T time period, and is 0.2 +.>≤0.4,/>Is a factor of the average satisfaction of the vehicle in the T period, 0.2 +.>≤0.4,/>Is a constant correction coefficient.
5. The method of claim 1, wherein the deep learning network is configured with a multi-layer perceptron-based deep neural network comprising an input layer, a first hidden layer, a second hidden layer, a third hidden layer, and an output layer, wherein the first, second, and third hidden layers each have at least two neurons, and wherein each uses ReLU as an activation function.
6. The method of multi-tenant order distribution of claim 4 wherein the predictive scoring data and the vehicle combination index for each vehicle are analyzed and data processed to generate order recommendation coefficients for each vehicleThe formula according to is as follows:
wherein (1)>For predictive scoring data, ++>Factor coefficient of predicted scoring data, 0.2. Ltoreq.o ≡>≤0.4,/>Factor coefficient of vehicle comprehensive index for each vehicle is 0.2 +.>≤0.4,/>Is a constant correction coefficient.
7. An apparatus for multi-tenant order distribution, comprising:
the network appointment vehicle history data comprises a departure position of a passenger in each history order, a passenger destination, a distance from the departure position of the passenger to the destination, a used time and scoring data;
the system comprises a data acquisition module, a data acquisition module and a control module, wherein the data acquisition module is used for acquiring vehicle parameters of an order-available network vehicle, the vehicle parameters comprise the proportion of vehicles reaching the position of a passenger on time in a T time period in a historical order, the total number of violations of the vehicles and the average satisfaction degree of the vehicles, acquiring the real-time position of the network vehicle, and acquiring order data in an order to be distributed, wherein the order data comprise the departure position of the passenger, the destination of the passenger and the expected arrival time in the order;
the priority setting module is used for distributing service areas of the network appointment vehicles into 3 areas according to real-time positions of passengers and real-time positions of the network appointment vehicles in an order to be distributed, setting order receiving priority levels according to whether the real-time positions of the network appointment vehicles and the passengers belong to the same area, wherein the network appointment vehicles of the network appointment vehicles and the real-time positions of the passengers in the same area are set to be highest priority, the network appointment vehicles of adjacent areas are second highest priority, the network appointment vehicles of the separated areas are lowest priority, and priority coefficients are distributed according to the priority levels;
the data processing module is used for carrying out non-dimensionalization processing on the collected vehicle parameters and the priority coefficient of the vehicle, carrying out correlation analysis and generating a vehicle comprehensive index;
the deep learning network construction module is used for constructing a deep learning network, taking the departure position of a passenger of a historical order, the destination of the passenger, the distance between the departure position of the passenger and the destination and the time used in the digital identifier of the network appointment vehicle as a training set, taking the scoring data of the corresponding historical order as a label, and inputting the scoring data into the deep learning network for training;
the scoring data acquisition module is used for inputting the departure position of the passenger, the destination of the passenger, the distance from the departure position of the passenger to the destination and the estimated time from the passenger to the destination in the existing data of the order to be distributed into the trained deep learning network to acquire the estimated scoring data of the current order;
and the order distribution module is used for analyzing and data processing the estimated score data and the vehicle comprehensive index of each vehicle, generating an order recommendation coefficient of each vehicle and distributing the order to the vehicle with the highest order recommendation coefficient.
8. An apparatus, comprising:
a memory for storing a computer program;
a processor for executing the computer program to implement the method of multi-tenant order allocation as claimed in any one of claims 1 to 6.
9. A readable storage medium for storing a computer program which when executed by a processor implements the method of multi-tenant order allocation of any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410090000.9A CN117610694B (en) | 2024-01-23 | 2024-01-23 | Multi-tenant order distribution method, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410090000.9A CN117610694B (en) | 2024-01-23 | 2024-01-23 | Multi-tenant order distribution method, device, equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117610694A true CN117610694A (en) | 2024-02-27 |
CN117610694B CN117610694B (en) | 2024-04-09 |
Family
ID=89960192
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410090000.9A Active CN117610694B (en) | 2024-01-23 | 2024-01-23 | Multi-tenant order distribution method, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117610694B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180060992A1 (en) * | 2015-02-24 | 2018-03-01 | Addison Lee Limited | Systems and Methods for Allocating Networked Vehicle Resources in Priority Environments |
WO2019183844A1 (en) * | 2018-03-28 | 2019-10-03 | Beijing Didi Infinity Technology And Development Co., Ltd. | System and method for determining passenger-seeking ride-sourcing vehicle navigation |
CN112052973A (en) * | 2020-09-25 | 2020-12-08 | 广州宸祺出行科技有限公司 | Efficient network appointment vehicle-taking order matching method and system |
CN112561104A (en) * | 2020-12-10 | 2021-03-26 | 武汉科技大学 | Vehicle sharing service order dispatching method and system based on reinforcement learning |
CN112700049A (en) * | 2020-12-30 | 2021-04-23 | 北京邮电大学 | Order distribution method and device |
CN114723125A (en) * | 2022-04-01 | 2022-07-08 | 华侨大学 | Intercity vehicle order allocation method combining deep learning and multi-task optimization |
CN115222204A (en) * | 2022-06-09 | 2022-10-21 | 浙江吉利控股集团有限公司 | Order processing method and device and computer storage medium |
-
2024
- 2024-01-23 CN CN202410090000.9A patent/CN117610694B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180060992A1 (en) * | 2015-02-24 | 2018-03-01 | Addison Lee Limited | Systems and Methods for Allocating Networked Vehicle Resources in Priority Environments |
WO2019183844A1 (en) * | 2018-03-28 | 2019-10-03 | Beijing Didi Infinity Technology And Development Co., Ltd. | System and method for determining passenger-seeking ride-sourcing vehicle navigation |
CN112052973A (en) * | 2020-09-25 | 2020-12-08 | 广州宸祺出行科技有限公司 | Efficient network appointment vehicle-taking order matching method and system |
CN112561104A (en) * | 2020-12-10 | 2021-03-26 | 武汉科技大学 | Vehicle sharing service order dispatching method and system based on reinforcement learning |
CN112700049A (en) * | 2020-12-30 | 2021-04-23 | 北京邮电大学 | Order distribution method and device |
CN114723125A (en) * | 2022-04-01 | 2022-07-08 | 华侨大学 | Intercity vehicle order allocation method combining deep learning and multi-task optimization |
CN115222204A (en) * | 2022-06-09 | 2022-10-21 | 浙江吉利控股集团有限公司 | Order processing method and device and computer storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN117610694B (en) | 2024-04-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11416795B2 (en) | Systems and methods for vehicle resource management | |
US11062415B2 (en) | Systems and methods for allocating networked vehicle resources in priority environments | |
US11386359B2 (en) | Systems and methods for managing a vehicle sharing facility | |
Ghannadpour et al. | A multi-objective dynamic vehicle routing problem with fuzzy time windows: Model, solution and application | |
US20170169366A1 (en) | Systems and Methods for Adjusting Ride-Sharing Schedules and Routes | |
US11392861B2 (en) | Systems and methods for managing a vehicle sharing facility | |
CN108140202A (en) | Credit system in shared platform by bus | |
US20170227370A1 (en) | Reducing wait time of providers of ride services using zone scoring | |
CN110400015A (en) | A kind of Time Estimation Method and its device, equipment | |
CN108106622A (en) | A kind of riding route method and system for planning | |
US20180075566A1 (en) | System and method of calculating a price for a vehicle journey | |
US20160247096A1 (en) | Systems and Methods for Managing Networked Vehicle Resources | |
Thodi et al. | An analytical approach to real-time bus signal priority system for isolated intersections | |
CN112906980A (en) | Order processing method, device and system and readable storage medium | |
CN117592638B (en) | Scenic spot passenger flow analysis and control method and system | |
CN111652471B (en) | List distribution control method and device, electronic equipment and storage medium | |
CN117610694B (en) | Multi-tenant order distribution method, device, equipment and storage medium | |
CN111798283A (en) | Order distribution method and device, electronic equipment and computer readable storage medium | |
CN114923497A (en) | Method, device, equipment and storage medium for planning railway trip path | |
CA3014011C (en) | Selecting a route to a destination based on zones | |
CN112801750B (en) | Order allocation method and device | |
CN117078216A (en) | Block chain-based decentralized crowdsourcing system and task allocation method thereof | |
WO2020075164A1 (en) | System, method and computer program product providing intelligent transportation services | |
CN117576943A (en) | Intelligent analysis management system for vehicle information of parking lot | |
CN118691003A (en) | Network vehicle-booking system based on individual travel demands of users and operation method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |