CN111260172A - Information processing method and system and computer equipment - Google Patents

Information processing method and system and computer equipment Download PDF

Info

Publication number
CN111260172A
CN111260172A CN201811467869.1A CN201811467869A CN111260172A CN 111260172 A CN111260172 A CN 111260172A CN 201811467869 A CN201811467869 A CN 201811467869A CN 111260172 A CN111260172 A CN 111260172A
Authority
CN
China
Prior art keywords
order information
car
carpooling
platform
information
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
Application number
CN201811467869.1A
Other languages
Chinese (zh)
Other versions
CN111260172B (en
Inventor
刘养彪
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Didi Infinity Technology and Development Co Ltd
Original Assignee
Beijing Didi Infinity Technology and Development Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Didi Infinity Technology and Development Co Ltd filed Critical Beijing Didi Infinity Technology and Development Co Ltd
Priority to CN201811467869.1A priority Critical patent/CN111260172B/en
Publication of CN111260172A publication Critical patent/CN111260172A/en
Application granted granted Critical
Publication of CN111260172B publication Critical patent/CN111260172B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06311—Scheduling, planning or task assignment for a person or group
    • 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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Theoretical Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Educational Administration (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The embodiment of the disclosure relates to the technical field of information processing, and provides an information processing method, an information processing system, computer equipment and a computer readable storage medium, wherein the method comprises the following steps: receiving first order information to be carpooled, wherein the first order information to be carpooled comprises a carpooling starting point, a carpooling end point and a carpooling moment; acquiring the number of competing vehicles and the number of matched passengers; predicting the first platform profit when the air bus is dispatched according to the first order information to be carpooled, the number of competing vehicles and the number of matched passengers; inquiring matched car pooling order information matched with the first car pooling order information; calculating the second platform profit when dispatching the vehicle bearing the matched carpool order information; and determining the carpooling scheme of the first order information to be carpooled according to the first platform income and the second platform income. By comparing the first platform income with the second platform income, the embodiment of the disclosure can not only not influence the user experience, but also improve the utilization efficiency of the platform income and the transport vehicles.

Description

Information processing method and system and computer equipment
Technical Field
The disclosed embodiments relate to the field of information processing technologies, and in particular, to an information processing method, an information processing system, a computer device, and a computer-readable storage medium.
Background
The reservation car sharing in the shared economy is a very important travel mode, and for the same order, a car booking platform may have multiple distribution modes. For example, an empty vehicle may be allocated solely at the fastest rate, an already manned vehicle may be allocated at the lowest cost (but at a longer time), and so on. If people-carried vehicles are distributed to all orders at the lowest cost, the user experience is reduced, adverse effects are caused to the platform, and long-term benefits of the platform are affected; however, when an empty car is allocated independently at the fastest speed, the benefit of the platform cannot be guaranteed, and is closely related to whether the new order is successfully assembled or not. Therefore, how to allocate orders for the platform such that the orders generate the maximum revenue for the platform is a problem that needs to be solved in the art.
Disclosure of Invention
The disclosed embodiments are directed to solving at least one of the technical problems of the related art or the related art.
To this end, a first aspect of the embodiments of the present disclosure is to provide an information processing method.
A second aspect of the embodiments of the present disclosure is to provide an information processing system.
A third aspect of the embodiments of the present disclosure is to provide a computer device.
A fourth aspect of embodiments of the present disclosure is to provide a computer-readable storage medium.
In view of this, according to a first aspect of the embodiments of the present disclosure, there is provided an information processing method including: receiving first order information to be carpooled, wherein the first order information to be carpooled comprises a carpooling starting point, a carpooling end point and a carpooling moment; acquiring the number of competing vehicles and the number of matched passengers; predicting the first platform profit when the air bus is dispatched according to the first order information to be carpooled, the number of competing vehicles and the number of matched passengers; inquiring matched car pooling order information matched with the first car pooling order information; calculating the second platform profit when dispatching the vehicle bearing the matched carpool order information; and determining the carpooling scheme of the first order information to be carpooled according to the first platform income and the second platform income.
When the information processing method provided by the embodiment of the disclosure receives the first order information to be carpooled, there are usually two carpooling schemes, one is to directly dispatch an empty car, and the other is to search for a manned car to perform carpooling. For the first scheme, the first platform profit can be predicted by combining the car sharing information and big data gathered by historical orders; for the second scheme, a matched car pooling order which can be matched with the order to be pooled is inquired in the order which is in progress, a clear travel route is generated after the matched order is inquired, and the generated revenue can be calculated according to the existing revenue calculation method to serve as the second platform revenue. By comparing the first platform benefit and the second platform benefit, the car sharing scheme most beneficial to the platform can be determined, so that the user experience is not influenced, and the platform benefits and the use efficiency of the transport vehicle are improved.
In addition, according to the information processing method in the above technical solution provided by the embodiment of the present disclosure, the following additional technical features may also be provided:
in the foregoing technical solution, preferably, the operation of acquiring the number of competing vehicles includes: receiving first order information to be carpooled, wherein the first order information to be carpooled comprises a carpooling starting point, a carpooling end point and a carpooling moment; obtaining car sharing order information of a driver end in a designated geographic area, wherein the car sharing order information comprises associated car sharing passenger information and car sharing route information, the designated geographic area is a first preset geographic area around a designated place, and the designated place is a car sharing starting point and/or any point in a journey; if the matching degree of the car pooling order information and the first order information to be subjected to car pooling is larger than or equal to a first threshold value, marking a driver end corresponding to the car pooling order information as a competitive driver end; and counting the number of the competitive driver terminals as the number of the competitive vehicles.
In the technical scheme, how to acquire the number of the competitive vehicles is specifically limited. Firstly, obtaining the car sharing order information of an operator end in a reasonable range around a car sharing starting point and/or any point in a journey according to needs, wherein the car sharing order information comprises the associated car sharing passenger information and car sharing route information, then calculating the matching degree of the car sharing order information and the first order information to be shared, specifically, determining whether people can be further loaded in quantity according to the car sharing passenger information, if yes, calculating the overlap ratio of a planned car sharing route and the journey route of the first order information to be shared, if the overlap ratio is higher, indicating that the planned car sharing route and the first order information to be shared form a competition relationship, and enabling the corresponding driver end to be a competitive operator end, and further counting the quantity of the competitive operator end to obtain the quantity of competitive vehicles. Correspondingly, the taxi sharing order information carried by the competitive driver end can be recorded as competitive taxi sharing order information.
In any of the above technical solutions, preferably, the operation of obtaining the matching passenger number includes: acquiring second order information to be carpooled sent out in a specified geographical area; if the matching degree of the second order information to be carpooled and the first order information to be carpooled is larger than or equal to a second threshold value, marking the passenger end sending the second order information to be carpooled as a matched passenger end; and counting the number of the matched passengers to serve as the number of the matched passengers.
In this solution, how to obtain the number of matching passengers is specifically defined. The method comprises the steps that first, second order information to be carpooled sent by a passenger end in a reasonable range around a carpooling starting point and/or any point in a journey is obtained according to needs, wherein the second order information to be carpooled comprises the carpooling starting point, the carpooling end point and the carpooling time, if the matching degree of the journey and the first order information to be carpooled is larger than or equal to a second threshold value, the passenger end is a potential carpooling object, the passenger end is marked as a matching passenger end, and then the number of the matching passenger ends is counted to obtain the number of the matching passengers.
In any one of the above technical solutions, preferably, after the operation of obtaining the number of competing vehicles and matching the number of passengers, the method further includes: obtaining a car sharing travel from a car sharing starting point to a car sharing terminal point; dividing the whole geographic area into a plurality of grids, and marking the grids passed by the carpooling journey as journey grids; obtaining historical order information to be carpooled, which is sent within a preset time range, has a carpooling stroke passing through a specified stroke grid and has a matching degree with the first order information to be carpooled greater than or equal to a third threshold value, and marking the historical order information to be carpooled as a reference historical order related to the corresponding stroke grid; calculating a reference spelling rate of each travel grid, wherein the reference spelling rate is the proportion of the orders with successful car spelling in the corresponding travel grid in the reference historical orders; the step of predicting the first platform profit of the dispatching empty car according to the first order information to be shared, the number of competing cars and the number of matched passengers comprises the following steps: and predicting the first platform profit according to the first order information to be shared, the number of competing vehicles, the number of matched passengers and the reference sharing rate.
In the technical scheme, the reference spelling rate is further limited to be obtained. Because whether the carpooling is successful or not has a key influence on the first platform income, the statistical information (namely the reference splicing rate) of the reference historical orders in the preset time range in the related geographic range (namely the travel grid) is obtained, so that the reference splicing rate can be combined when the first platform income is predicted, and the prediction accuracy is improved. The routes of each order to be carpooled often have more or less difference and are difficult to directly compare, and the statistical area is divided into a plurality of fixed grids, so that the grids related to the routes are only needed to be used in prediction, the carpooling condition of the historical order to be carpooled in the routes is conveniently summarized and summarized, and the prediction accuracy is improved by means of historical data. The journey of the reference historical order firstly needs to pass through a journey network, and in addition, the reference historical order needs to be highly matched with the information of the first order to be carpooled, so that the reference historical order has a reference value. The order of successful carpooling related to the reference carpooling rate is successful in carpooling in the corresponding journey network, specifically, the boarding place of the new boarding passenger is in the journey grid, so that the counting of the order of successful carpooling outside the journey grid while passing through the journey grid can be avoided, the successful carpooling result of the order cannot be realized for the order to be carpooled, the repeated counting of the same order in different journey networks is avoided, and the reference value of the reference carpooling rate is improved.
In any one of the above technical solutions, preferably, before the operation of receiving the first order information to be carpooled, the method further includes: establishing a probability prediction model and a probability profit mapping table according to historical order information, wherein training parameters of the probability prediction model comprise a car sharing starting point, a car sharing end point, car sharing time, the number of competing vehicles, the number of matched passengers and car sharing result information in the historical order information, the car sharing result information comprises car sharing success information and car sharing failure information, and target parameters of the probability prediction model are car sharing success probability; the step of predicting the first platform profit when dispatching the empty car according to the first order information to be carpooled, the number of competing vehicles, the number of matched passengers and the reference carpooling rate comprises the following steps: inputting the first order information to be carpooled, the number of competing vehicles, the number of matched passengers and the reference carpooling rate into a probability prediction model to calculate the successful carpooling probability; and searching a probability profit mapping table to obtain the first platform profit corresponding to the carpooling success probability.
In this solution, a solution for how to predict the first platform profit is specifically defined. The method comprises the steps of firstly, conducting machine learning, utilizing a car pooling starting point, a car pooling end point, car pooling time, the number of competing vehicles, the number of matched passengers and car pooling result information of historical orders as training parameters, taking car pooling success probability as a target parameter, building a probability prediction model, calculating the car pooling success probability of each historical order according to the probability prediction model, counting the relation between the car pooling success probability and first platform income to obtain a probability income mapping table, inputting the first car pooling order information, the number of competing vehicles, the number of matched passengers and reference stitching rate into the built probability prediction model during prediction to predict the car pooling success probability, and searching the probability income mapping table to obtain the corresponding first platform income. According to the scheme, the carpooling success probability is used as the middle bridge, the influence of carpooling success or failure on the first platform income is fully considered, and the prediction accuracy is improved.
In any one of the above technical solutions, preferably, before the operation of receiving the first order information to be carpooled, the method further includes: establishing a profit prediction model according to the historical order information, wherein training parameters of the profit prediction model comprise a car sharing starting point, a car sharing terminal point, car sharing time, the number of competing vehicles, the number of matched passengers and car sharing result information in the historical order information, the car sharing result information comprises car sharing success information and car sharing failure information, and target parameters of the profit prediction model are first platform profits; the step of predicting the first platform profit when dispatching the empty car according to the first order information to be carpooled, the number of competing vehicles, the number of matched passengers and the reference carpooling rate comprises the following steps: and inputting the first order information to be shared, the number of competing vehicles, the number of matched passengers and the reference sharing rate into a profit prediction model so as to calculate the first platform profit.
In this solution, another solution of how to predict the first platform gain is specifically defined. The method comprises the steps of firstly, conducting machine learning, establishing a profit prediction model by using a car pooling starting point, a car pooling end point, car pooling time, the number of competing vehicles, the number of matched passengers and car pooling result information of a historical order as training parameters and first platform profit as a target parameter, and then inputting the first car pooling order information, the number of competing vehicles, the number of matched passengers and a reference stitching rate into the established profit prediction model during prediction, so that the first platform profit can be output. According to the scheme, the successful car sharing probability is not generated specifically, the first platform profit is obtained directly according to the first order information to be shared and the related information, the calculation time can be shortened, and the operation efficiency is improved.
In any of the above technical solutions, preferably, the step of calculating the second platform profit when the vehicle carrying the matching carpool order information is dispatched includes: and when the number of the matched carpooling order information is at least one, calculating at least one platform profit when at least one vehicle bearing the matched carpooling order information is dispatched, and taking the maximum value in the at least one platform profit as a second platform profit.
According to the technical scheme, a processing scheme when at least one piece of matched carpool order information is inquired is limited. If a matching carpooling order is inquired, directly comparing the second platform income with the first platform income, wherein the specific comparison scheme can be seen in the embodiments; when at least two pieces of matched car pooling order information are inquired, corresponding car pooling strokes can be generated, and then platform benefits generated are calculated respectively.
In any of the above technical solutions, preferably, the step of calculating the second platform profit when the vehicle carrying the matching carpool order information is dispatched includes: planning at least one driving route when a vehicle bearing the matched carpool order information is dispatched; and respectively calculating at least one second platform profit when at least one driving route is adopted.
In the technical scheme, for one matched car pooling order information, the planned driving route may be one or more, and the profit of the second platform can be directly calculated when the planned driving route is one, and the specific comparison scheme can be referred to the embodiments; and when the number of the car sharing routes is multiple, calculating the second platform profit for each driving route respectively, and comparing the second platform profit with the first platform profit to select the car sharing scheme with the best profit. The maximum value of the platform gains corresponding to the plurality of driving routes is not directly used as the second platform gain, because the phenomenon that the driving routes are too long, namely excessive detour, may exist, and the user experience may be reduced.
According to a second aspect of the embodiments of the present disclosure, there is provided an information processing system including: the receiving unit is used for receiving first order information to be carpooled, and the first order information to be carpooled comprises a carpooling starting point, a carpooling end point and a carpooling moment; the acquiring unit is used for acquiring the number of competitive vehicles and the number of matched passengers; the prediction unit is used for predicting the first platform profit when the air bus is dispatched according to the first order information to be carpooled, the number of competing vehicles and the number of matched passengers; the query unit is used for querying the matched car pooling order information matched with the first order information to be pooled; the calculating unit is used for calculating the second platform profit when the vehicle bearing the matched carpooling order information is dispatched; and the decision unit is used for determining the carpooling scheme of the first order information to be carpooled according to the first platform income and the second platform income.
In the information processing system provided by the embodiment of the disclosure, when the receiving unit receives the first order information to be carpooled, there are usually two carpooling schemes, one is to directly dispatch an empty car, and the other is to search for a manned car for carpooling. For the first scheme, the prediction unit predicts the first platform profit obtained by the platform when the empty car is dispatched based on the first order information to be shared received by the receiving unit and the relevant information obtained by the obtaining unit; for the second scheme, the query unit queries matched car pooling order information which can be matched with the first car pooling order information in the ongoing order, after the matched car pooling order information is queried, a clear driving route is generated by a car pooling starting point and a car pooling ending point, and the calculation unit can calculate the generated income as the second platform income according to the conventional income calculation method. The decision-making unit can determine the car sharing scheme most favorable for the platform by comparing the first platform benefit with the second platform benefit, so that the user experience is not influenced, and the platform benefits and the use efficiency of the transport vehicle are improved.
In addition, according to the information processing system in the above technical solution provided by the embodiment of the present disclosure, the following additional technical features may also be provided:
in the foregoing technical solution, preferably, the obtaining unit is specifically configured to: obtaining car sharing order information of a driver end in a designated geographic area, wherein the car sharing order information comprises associated car sharing passenger information and car sharing route information, the designated geographic area is a first preset geographic area around a designated place, and the designated place is a car sharing starting point and/or any point in a journey; if the matching degree of the car pooling order information and the first order information to be subjected to car pooling is larger than or equal to a first threshold value, marking a driver end corresponding to the car pooling order information as a competitive driver end; and counting the number of the competitive driver terminals as the number of the competitive vehicles.
In this technical solution, how the acquiring unit acquires the number of competing vehicles is specifically defined. Firstly, obtaining the car sharing order information of an operator end in a reasonable range around a car sharing starting point and/or any point in a journey according to needs, wherein the car sharing order information comprises the associated car sharing passenger information and car sharing route information, then calculating the matching degree of the car sharing order information and the first order information to be shared, specifically, determining whether people can be further loaded in quantity according to the car sharing passenger information, if yes, calculating the overlap ratio of a planned car sharing route and the journey route of the first order information to be shared, if the overlap ratio is higher, indicating that the planned car sharing route and the first order information to be shared form a competition relationship, and enabling the corresponding driver end to be a competitive operator end, and further counting the quantity of the competitive operator end to obtain the quantity of competitive vehicles. Correspondingly, the taxi sharing order information carried by the competitive driver end can be recorded as competitive taxi sharing order information.
In any of the above technical solutions, preferably, the obtaining unit is further specifically configured to: acquiring second order information to be carpooled sent out in a specified geographical area; if the matching degree of the second order information to be carpooled and the first order information to be carpooled is larger than or equal to a second threshold value, marking the passenger end sending the second order information to be carpooled as a matched passenger end; and counting the number of the matched passengers to serve as the number of the matched passengers.
In this solution, it is specifically defined how the acquisition unit acquires the number of matching passengers. The method comprises the steps that first, second order information to be carpooled sent by a passenger end in a reasonable range around a carpooling starting point and/or any point in a journey is obtained according to needs, wherein the second order information to be carpooled comprises the carpooling starting point, the carpooling end point and the carpooling time, if the matching degree of the journey and the first order information to be carpooled is larger than or equal to a second threshold value, the passenger end is a potential carpooling object, the passenger end is marked as a matching passenger end, and then the number of the matching passenger ends is counted to obtain the number of the matching passengers.
In any of the above technical solutions, preferably, the obtaining unit is further configured to: obtaining a car sharing travel from a car sharing starting point to a car sharing terminal point; dividing the whole geographic area into a plurality of grids, and marking the grids passed by the carpooling journey as journey grids; obtaining historical order information to be carpooled, which is sent within a preset time range, has a carpooling stroke passing through a specified stroke grid and has a matching degree with the first order information to be carpooled greater than or equal to a third threshold value, and marking the historical order information to be carpooled as a reference historical order related to the corresponding stroke grid; calculating a reference spelling rate of each travel grid, wherein the reference spelling rate is the proportion of the orders with successful car spelling in the corresponding travel grid in the reference historical orders; the prediction unit is specifically used for predicting the first platform profit according to the first order information to be shared, the number of competing vehicles, the number of matched passengers and the reference sharing rate.
In the technical scheme, the obtaining unit is further limited to be used for obtaining the reference spelling rate. Because whether the carpooling is successful or not has a key influence on the first platform income, the statistical information (namely the reference splicing rate) of the reference historical orders in the preset time range in the related geographic range (namely the travel grid) is obtained, so that the reference splicing rate can be combined when the first platform income is predicted, and the prediction accuracy is improved. The routes of each order to be carpooled often have more or less difference and are difficult to directly compare, and the statistical area is divided into a plurality of fixed grids, so that the grids related to the routes are only needed to be used in prediction, the carpooling condition of the historical order to be carpooled in the routes is conveniently summarized and summarized, and the prediction accuracy is improved by means of historical data. The journey of the reference historical order firstly needs to pass through a journey network, and in addition, the reference historical order needs to be highly matched with the information of the first order to be carpooled, so that the reference historical order has a reference value. The order of successful carpooling related to the reference carpooling rate is successful in carpooling in the corresponding journey network, specifically, the boarding place of the new boarding passenger is in the journey grid, so that the counting of the order of successful carpooling outside the journey grid while passing through the journey grid can be avoided, the successful carpooling result of the order cannot be realized for the order to be carpooled, the repeated counting of the same order in different journey networks is avoided, and the reference value of the reference carpooling rate is improved.
In any of the above technical solutions, preferably, the method further includes: the system comprises a first model establishing unit, a second model establishing unit and a third model establishing unit, wherein the first model establishing unit is used for establishing a probability prediction model and a probability profit mapping table according to historical order information, training parameters of the probability prediction model comprise a car-sharing starting point, a car-sharing terminal point, a car-sharing time, the number of competing vehicles, the number of matched passengers and car-sharing result information in the historical order information, the car-sharing result information comprises car-sharing success information and car-sharing failure information, and target parameters of the probability prediction model are car-sharing success probability; the prediction unit is specifically configured to: inputting the first order information to be carpooled, the number of competing vehicles, the number of matched passengers and the reference carpooling rate into a probability prediction model to calculate the successful carpooling probability; and searching a probability profit mapping table to obtain the first platform profit corresponding to the carpooling success probability.
In this embodiment, a scheme for predicting the first platform benefit by the prediction unit is specifically defined. The first model building unit firstly carries out machine learning, a car pooling starting point, a car pooling end point, car pooling time, competitive car quantity, matching passenger quantity and car pooling result information of historical orders are used as training parameters, the car pooling success probability is used as a target parameter, a probability prediction model is built, the car pooling success probability of each historical order is calculated according to the probability prediction model, the relation between the car pooling success probability and first platform income is counted, a probability income mapping table is obtained, the prediction unit inputs the first car pooling order information, the competitive car quantity, the matching passenger quantity and the reference car pooling rate into the built probability prediction model, the car pooling success probability can be predicted, and the corresponding first platform income can be obtained by searching the probability income mapping table. According to the scheme, the carpooling success probability is used as the middle bridge, the influence of carpooling success or failure on the first platform income is fully considered, and the prediction accuracy is improved.
In any of the above technical solutions, preferably, the method further includes: the second model establishing unit is used for establishing a profit prediction model according to the historical order information, the training parameters of the profit prediction model comprise a car-sharing starting point, a car-sharing terminal point, a car-sharing time, the number of competing vehicles, the number of matched passengers and car-sharing result information in the historical order information, the car-sharing result information comprises car-sharing success information and car-sharing failure information, and the target parameter of the profit prediction model is the first platform profit; the prediction unit is specifically used for inputting the first order information to be shared, the number of competing vehicles, the number of matched passengers and the reference sharing rate into the profit prediction model so as to calculate the first platform profit.
In this embodiment, another scheme for predicting the first platform benefit by the prediction unit is specifically defined. The second model establishing unit firstly performs machine learning, establishes a profit prediction model by using a car pooling starting point, a car pooling end point, car pooling time, competitive vehicle quantity, matched passenger quantity and car pooling result information of a historical order as training parameters and using first platform profit as a target parameter, and inputs the first car pooling order information, the competitive vehicle quantity, the matched passenger quantity and the reference pooling rate into the established profit prediction model, so that the first platform profit can be output. According to the scheme, the successful car sharing probability is not generated specifically, the first platform profit is obtained directly according to the first order information to be shared and the related information, the calculation time can be shortened, and the operation efficiency is improved.
In any of the above technical solutions, preferably, the calculating unit is specifically configured to: and when the number of the matched carpooling order information is at least one, calculating at least one platform profit when at least one vehicle bearing the matched carpooling order information is dispatched, and taking the maximum value in the at least one platform profit as a second platform profit.
In the technical scheme, a processing scheme of the calculating unit when the inquiring unit inquires at least one piece of matched carpool order information is limited. If the inquiry unit inquires a matched car pooling order, the calculation unit directly compares the second platform profit with the first platform profit, and the specific comparison scheme of the decision unit can refer to the embodiments; when the inquiry unit inquires at least two pieces of matched car pooling order information, corresponding car pooling strokes can be generated, the calculation unit further calculates the generated platform benefits respectively, and because different pieces of matched car pooling order information are selected, the experience difference of users is not large, the maximum value of the platform benefits is directly used as the second platform benefits and is compared with the first platform benefits, so that the decision unit can select a car pooling scheme with the best benefits, namely, the decision unit can select which car to dispatch the first car pooling order information to be dispatched.
In any of the above technical solutions, preferably, the calculating unit is specifically configured to: planning at least one driving route when a vehicle bearing the matched carpool order information is dispatched; and respectively calculating at least one second platform profit when at least one driving route is adopted.
In the technical scheme, for one piece of matching car pooling order information inquired by the inquiry unit, the planned driving route may be one or multiple, the calculation unit can directly calculate the profit of the second platform when the driving route is one, and the specific comparison scheme of the decision unit can be referred to the embodiments; the calculation unit needs to calculate the second platform profit for each driving route respectively, and the decision unit compares the second platform profit with the first platform profit to select the carpooling scheme with the best profit. The reason why the maximum value of the platform gains corresponding to the plurality of driving routes is not directly used as the second platform gain by the calculating unit is that the driving routes are too long, that is, the phenomenon of excessive detour may occur, and the user experience may be reduced.
According to a third aspect of the embodiments of the present disclosure, there is provided a computer device, including a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of the above-mentioned technical solutions when executing the computer program.
In the computer device provided in the embodiment of the present disclosure, when the processor executes the computer program stored in the memory, the steps of the method in any of the above technical solutions can be implemented, so that all the beneficial technical effects of the information processing method are achieved, and no further description is given here.
According to a fourth aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of the above-mentioned claims.
In the computer-readable storage medium provided in the embodiment of the present disclosure, when being executed by a processor, a computer program stored thereon can implement the steps of the method in any of the above technical solutions, so that all the beneficial technical effects of the information processing method are achieved, and details are not described herein again.
Additional aspects and advantages of the disclosed embodiments will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the disclosed embodiments.
Drawings
The above and/or additional aspects and advantages of the embodiments of the present disclosure will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 shows a schematic flow chart of an information processing method according to a first embodiment of the present disclosure;
FIG. 2 shows a schematic flow chart diagram of an information processing method according to a second embodiment of the present disclosure;
fig. 3 shows a schematic flow chart of an information processing method according to a third embodiment of the present disclosure;
fig. 4 shows a schematic flow chart of an information processing method according to a fourth embodiment of the present disclosure;
fig. 5 shows a schematic flow chart of an information processing method according to a fifth embodiment of the present disclosure;
fig. 6 shows a schematic flow chart of an information processing method according to a sixth embodiment of the present disclosure;
fig. 7 shows a schematic flow chart of an information processing method according to a seventh embodiment of the present disclosure;
fig. 8 shows a schematic flowchart of an information processing method according to an eighth embodiment of the present disclosure;
FIG. 9 shows a schematic block diagram of an information handling system according to a first embodiment of the present disclosure;
FIG. 10 shows a schematic block diagram of an information handling system according to a second embodiment of the present disclosure;
FIG. 11 shows a schematic block diagram of an information handling system according to a third embodiment of the present disclosure;
FIG. 12 shows a schematic structural diagram of a computer device according to one embodiment of the present disclosure.
Detailed Description
In order that the above objects, features and advantages of the embodiments of the present disclosure can be more clearly understood, embodiments of the present disclosure will be described in further detail below with reference to the accompanying drawings and detailed description. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure, however, the embodiments of the disclosure may be practiced in other ways than those described herein, and therefore the scope of the embodiments of the disclosure is not limited by the specific embodiments disclosed below.
An embodiment of a first aspect of an embodiment of the present disclosure provides an information processing method.
Fig. 1 shows a schematic flow chart of an information processing method according to a first embodiment of the embodiments of the present disclosure.
As shown in fig. 1, an information processing method according to a first embodiment of the present disclosure includes:
s102, receiving first order information to be carpooled, wherein the first order information to be carpooled comprises a carpooling starting point, a carpooling end point and a carpooling moment;
s104, acquiring the number of competing vehicles and the number of matched passengers;
s106, predicting first platform income when the air bus is dispatched according to the first order information to be carpooled, the number of competing vehicles and the number of matched passengers;
s108, inquiring matched car sharing order information matched with the first order information to be shared;
s110, calculating the second platform profit when the vehicle bearing the matched carpooling order information is dispatched;
and S112, determining the carpooling scheme of the first order information to be carpooled according to the first platform income and the second platform income.
When the information processing method provided by the embodiment of the disclosure receives the first order information to be carpooled, there are usually two carpooling schemes, one is to directly dispatch an empty car, and the other is to search for a manned car to perform carpooling. For the first scheme, predicting the first platform profit obtained by the platform when the empty car is dispatched based on the currently received first order information to be shared and the related information thereof; for the second scheme, matching car sharing order information which can be matched with the first car sharing order information is inquired in the ongoing order, after the matching car sharing order information is inquired, a clear driving route is generated by a car sharing starting point and a car sharing terminal point, and the generated benefit can be calculated according to the existing benefit calculation method to serve as the second platform benefit. By comparing the first platform benefit and the second platform benefit, the car sharing scheme most beneficial to the platform can be determined, so that the user experience is not influenced, and the platform benefits and the use efficiency of the transport vehicle are improved. Optionally, a carpooling scheme corresponding to the party with more profit in the first platform profit and the second platform profit can be selected; the empty vehicles can be selected to be dispatched only when the profit of the first platform is higher than a certain value of the profit of the second platform, namely, the second scheme is preferred, the vehicles carrying people can be preferably spliced into a new order, and the splicing rate is ensured; the vehicle sharing with the manned vehicle can be selected when the first platform profit is lower than the second platform profit by a certain value, that is, the first scheme is preferred to ensure the user experience, and the first scheme and the second scheme belong to the protection scope of the embodiment of the disclosure as long as the first scheme and the second scheme do not depart from the design concept of the embodiment of the disclosure. Specifically, for the second scheme, when the matched car pool order information is not queried, the second scheme may wait for a predetermined time period and query again or keep querying until the query is successful, or directly jump to the first situation or jump to the first scheme when the matched car pool order information is not queried after the predetermined time period, that is, dispatch empty cars, so as to ensure user experience.
Further, the order information to be carpooled also comprises the carpooling time, the order information to be carpooled is directly sent out, the carpooling time is the current time, and when the carpooling is reserved, the carpooling time is the reserved time, so that the order taking driver can conveniently take the passengers according to the reserved time. The first platform profit and the second platform profit are calculated based on the car sharing time so as to improve the calculation accuracy.
Specifically, when matching the car pool order information is queried, vehicles that can further carry passengers (i.e., vehicles that already carry passengers and have a passenger number that does not reach the upper limit) around the car pool starting point and the car pool order information carried by the vehicles can be obtained first, and then whether the routes planned for the vehicles are matched with the routes of the first car pool order information to be matched is analyzed, and if so, the currently analyzed car pool order information is defined as the matching car pool order information. The specific matching algorithm is not within the limited range of the embodiments of the present disclosure, and reference may be made to related technologies in the art, which are not described herein again.
In addition, the car booking platform usually performs a certain elimination after obtaining the car booking order information, the value (such as the billing ratio) that the eliminated order can contribute to the platform can be calculated by the method for calculating the profit of the first platform in the information processing method provided by the embodiment of the disclosure, and when the calculated value is greater than a predetermined threshold value, the eliminated order can be retrieved for performing the car pooling service again, so that the user demand is met, and the platform profit and the use efficiency of the transport vehicle are improved.
Fig. 2 shows a schematic flow chart of an information processing method according to a second embodiment of the embodiments of the present disclosure.
As shown in fig. 2, an information processing method according to a second embodiment of the present disclosure includes:
s202, receiving first order information to be carpooled, wherein the first order information to be carpooled comprises a carpooling starting point, a carpooling end point and a carpooling moment;
s204, obtaining car sharing order information of a driver end in a designated geographic area, wherein the car sharing order information comprises associated car sharing passenger information and car sharing route information, the designated geographic area is a first preset geographic area around a designated place, and the designated place is a car sharing starting point and/or any point in a journey;
s206, if the matching degree of the car pooling order information and the first order information to be car pooling is larger than or equal to a first threshold value, marking a driver end corresponding to the car pooling order information as a competitive driver end;
s208, counting the number of competitive driver terminals as the number of competitive vehicles;
s210, acquiring the number of matched passengers;
s212, predicting first platform benefits when the air bus is dispatched according to the first order information to be carpooled, the number of competing vehicles and the number of matched passengers;
s214, inquiring matched car pooling order information matched with the first order information to be car pooling;
s216, calculating second platform benefits when the vehicle bearing the matched carpooling order information is dispatched;
s218, determining the carpooling scheme of the first order information to be carpooled according to the first platform income and the second platform income.
In this embodiment, how to acquire the number of competing vehicles is specifically defined. Firstly, obtaining the car sharing order information of an operator end in a reasonable range around a car sharing starting point and/or any point in a journey according to needs, wherein the car sharing order information comprises the associated car sharing passenger information and car sharing route information, then calculating the matching degree of the car sharing order information and the first order information to be shared, specifically, determining whether people can be further loaded in quantity according to the car sharing passenger information, if yes, calculating the overlap ratio of a planned car sharing route and the journey route of the first order information to be shared, if the overlap ratio is higher, indicating that the planned car sharing route and the first order information to be shared form a competition relationship, and enabling the corresponding driver end to be a competitive operator end, and further counting the quantity of the competitive operator end to obtain the quantity of competitive vehicles. Correspondingly, the taxi sharing order information carried by the competitive driver end can be recorded as competitive taxi sharing order information.
It can be appreciated that the main difference between the competitive ride share order information and the matching ride share order information involved in calculating the second platform revenue is that the former is for order information within a specified geographic area, the latter is for order information that can reach the start of ride share at the ride share time (or within a certain time range around the ride share time), and the vehicle bearing the matching ride share order information belongs to the matching vehicle.
Specifically, the competitive car sharing order information may be defined in many ways, for example, the competitive car sharing order information may be car sharing order information whose travel coincidence degree of the first car sharing order information exceeds a threshold value, or the competitive car sharing order information may be car sharing orders whose car sharing end point is adjacent to the car sharing end point of the first car sharing order information. When the quantity of the competitive car sharing order information is obtained, all the car sharing order information sent in the appointed geographic area can be obtained firstly, then whether the car sharing order information is the competitive car sharing order information or not is analyzed, and finally the quantity of the competitive car sharing order information in the car sharing order information is counted.
The method comprises the steps that for a designated geographic area, the area obtained by radiating a preset radius with a designated place as a center is used, the more the number of the designated places is, the larger the area of the designated geographic area is, the larger the acquired information amount is, the more accurate the prediction is, and when the designated place comprises a plurality of continuous points in a journey, the designated geographic area is approximately corresponding to a curve which is formed by overlapping a plurality of continuous circular areas and has a certain width. When the appointed place is the starting point of the carpooling, corresponding to the situation that the carpooling is successful at the starting point of the carpooling after an empty car is dispatched, the probability that the carpooling of the order to be carpooled is successful in the whole process can be obtained by obtaining the number of competitive carpooling orders and the number of matched cars in the appointed geographic area corresponding to all points in the starting point of the carpooling and the travel (the current order to be carpooled is not recorded under the situation that the carpooling is successful at the end point of the carpooling), and the accuracy of prediction is improved.
Fig. 3 shows a schematic flow chart of an information processing method according to a third embodiment of the embodiments of the present disclosure.
As shown in fig. 3, an information processing method according to a third embodiment of the present disclosure includes:
s302, receiving first order information to be carpooled, wherein the first order information to be carpooled comprises a carpooling starting point, a carpooling end point and a carpooling moment;
s304, obtaining car sharing order information of a driver side in a designated geographic area, wherein the car sharing order information comprises associated car sharing passenger information and car sharing route information, the designated geographic area is a first preset geographic area around a designated place, and the designated place is a car sharing starting point and/or any point in a journey;
s306, if the matching degree of the car pooling order information and the first order information to be car pooling is larger than or equal to a first threshold value, marking a driver end corresponding to the car pooling order information as a competitive driver end;
s308, counting the number of competitive driver terminals as the number of competitive vehicles;
s310, acquiring second order information to be carpooled sent out in a specified geographic area;
s312, if the matching degree of the second order information to be carpooled and the first order information to be carpooled is larger than or equal to a second threshold value, marking the passenger end sending the second order information to be carpooled as a matched passenger end;
s314, counting the number of the matched passenger terminals to serve as the number of the matched passengers;
s316, predicting the first platform profit when the air bus is dispatched according to the first order information to be carpooled, the number of competing vehicles and the number of matched passengers;
s318, inquiring matched car sharing order information matched with the first order information to be shared;
s320, calculating the second platform income when the vehicle bearing the matched carpooling order information is dispatched;
s322, determining the carpooling scheme of the first order information to be carpooled according to the first platform income and the second platform income.
In this embodiment, how to obtain the matching passenger number is specifically defined. The method comprises the steps that first, second order information to be carpooled sent by a passenger end in a reasonable range around a carpooling starting point and/or any point in a journey is obtained according to needs, wherein the second order information to be carpooled comprises the carpooling starting point, the carpooling end point and the carpooling time, if the matching degree of the journey and the first order information to be carpooled is larger than or equal to a second threshold value, the passenger end is a potential carpooling object, the passenger end is marked as a matching passenger end, and then the number of the matching passenger ends is counted to obtain the number of the matching passengers.
Fig. 4 shows a schematic flow chart of an information processing method according to a fourth embodiment of the present disclosure.
As shown in fig. 4, an information processing method according to a fourth embodiment of the present disclosure includes:
s402, receiving first order information to be carpooled, wherein the first order information to be carpooled comprises a carpooling starting point, a carpooling end point and a carpooling moment;
s404, acquiring the number of competitive vehicles and the number of matched passengers;
s406, obtaining a car sharing travel from the car sharing starting point to the car sharing terminal point;
s408, dividing the whole geographic area into a plurality of grids, and marking the grids where the carpooling journey passes as journey grids;
s410, obtaining historical order information to be carpooled, which is sent within a preset time range, has a carpooling stroke passing through a specified stroke grid and has a matching degree with the first order information to be carpooled larger than or equal to a third threshold value, and marking the historical order information to be carpooled as a reference historical order related to the corresponding stroke grid;
s412, calculating a reference spelling rate of each travel grid, wherein the reference spelling rate is the proportion of the orders with successful car spelling in the corresponding travel grid in the reference historical orders;
s414, predicting the first platform profit according to the first order information to be shared, the number of competing vehicles, the number of matched passengers and the reference sharing rate;
s416, inquiring matched car sharing order information matched with the first order information to be shared;
s418, calculating the second platform profit when the vehicle bearing the matched carpooling order information is dispatched;
and S420, determining a carpooling scheme of the first order information to be carpooled according to the first platform income and the second platform income.
In this embodiment, obtaining the reference spelling rate is further defined. Because whether the carpooling is successful or not has a key influence on the first platform income, the statistical information (namely the reference splicing rate) of the reference historical orders in the preset time range in the related geographic range (namely the travel grid) is obtained, so that the reference splicing rate can be combined when the first platform income is predicted, and the prediction accuracy is improved. The routes of each order to be carpooled often have more or less difference and are difficult to directly compare, and the statistical area is divided into a plurality of fixed grids, so that the grids related to the routes are only needed to be used in prediction, the carpooling condition of the historical order to be carpooled in the routes is conveniently summarized and summarized, and the prediction accuracy is improved by means of historical data. Optionally, the statistical region (e.g., the entire city) is divided into a 600m grid. The journey of the reference historical order firstly needs to pass through a journey network, and in addition, the reference historical order needs to be highly matched with the information of the first order to be carpooled, so that the reference historical order has a reference value. Optionally, the third threshold is equal to the second threshold. The order of successful carpooling related to the reference carpooling rate is successful in carpooling in the corresponding journey network, specifically, the boarding place of the new boarding passenger is in the journey grid, so that the counting of the order of successful carpooling outside the journey grid while passing through the journey grid can be avoided, the successful carpooling result of the order cannot be realized for the order to be carpooled, the repeated counting of the same order in different journey networks is avoided, and the reference value of the reference carpooling rate is improved.
Optionally, setting a preset time range as the previous day or the previous week of the car sharing time in the first order information to be shared, so that the reference sharing rate changes correspondingly with the advance of time, and the latest historical data is fully referred to; further, the 24 hours in the day are divided into different time periods, one time period can be divided at fixed time intervals, and the time periods can also be divided into peak time periods and ordinary time periods, for example, the early peak time period is from 7 to 9 am, the late peak time period is from 5 to 8 pm, the rest time periods are ordinary time periods, and the preset time range is set as the same time period of the previous day or the previous week.
Fig. 5 shows a schematic flowchart of an information processing method according to a fifth embodiment of the present disclosure.
As shown in fig. 5, the information processing method of the fifth embodiment of the present disclosure includes:
s502, a probability prediction model and a probability profit mapping table are established according to historical order information, training parameters of the prediction model comprise a car-sharing starting point, a car-sharing end point, car-sharing time, the number of competing vehicles, the number of matched passengers and car-sharing result information in the historical order information, the car-sharing result information comprises car-sharing success information and car-sharing failure information, and target parameters of the probability prediction model are car-sharing success probability;
s504, receiving first order information to be carpooled, wherein the first order information to be carpooled comprises a carpooling starting point, a carpooling end point and a carpooling moment;
s506, acquiring the number of competing vehicles and the number of matched passengers;
s508, obtaining a car sharing travel from the car sharing starting point to the car sharing terminal point;
s510, dividing the whole geographic area into a plurality of grids, and marking the grids where the carpooling journey passes as journey grids;
s512, acquiring historical order information to be carpooled, which is sent within a preset time range, has a carpooling stroke passing through a specified stroke grid and has a matching degree with the first order information to be carpooled greater than or equal to a third threshold value, and marking the historical order information to be carpooled as a reference historical order related to the corresponding stroke grid;
s514, calculating a reference spelling rate of each travel grid, wherein the reference spelling rate is the proportion of the orders with successful car spelling in the corresponding travel grid in the reference historical orders;
s516, inputting the first order information to be carpooled, the number of competing vehicles, the number of matched passengers and the reference carpooling rate into a probability prediction model to calculate the successful carpooling probability;
s518, searching a probability profit mapping table to obtain a first platform profit corresponding to the carpooling success probability;
s520, inquiring matched car sharing order information matched with the first order information to be shared;
s522, calculating the second platform profit when the vehicle bearing the matched carpooling order information is dispatched;
and S524, determining the carpooling scheme of the first order information to be carpooled according to the first platform income and the second platform income.
In this embodiment, one scheme of how to predict the first platform gain is specifically defined. The method comprises the steps of firstly, conducting machine learning, utilizing a car pooling starting point, a car pooling end point, car pooling time, the number of competing vehicles, the number of matched passengers and car pooling result information of historical orders as training parameters, taking car pooling success probability as a target parameter, building a probability prediction model, calculating the car pooling success probability of each historical order according to the probability prediction model, counting the relation between the car pooling success probability and first platform income to obtain a probability income mapping table, inputting the first car pooling order information, the number of competing vehicles, the number of matched passengers and reference stitching rate into the built probability prediction model during prediction to predict the car pooling success probability, and searching the probability income mapping table to obtain the corresponding first platform income. According to the scheme, the carpooling success probability is used as the middle bridge, the influence of carpooling success or failure on the first platform income is fully considered, and the prediction accuracy is improved.
Further, when matching car sharing order information is not inquired, decision can be made according to the car sharing success probability, if the car sharing success probability exceeds a preset value, empty cars are dispatched and waiting for car sharing, otherwise, the inquiry is carried out again after waiting for a preset time, the inquiry can be kept until the inquiry is successful, the car sharing success probability can be continuously predicted while the inquiry is carried out, and the empty cars are dispatched when the car sharing success probability exceeds the preset value.
In addition, for a car booking order, the current platform is often matched on two platforms of car pooling and car booking (such as express cars) at the same time, and the car pooling is expected to be realized as far as possible because the transportation capacity can be better utilized by the car pooling. When the carpooling is carried out, the two schemes can be generated, wherein the first scheme and the express bus are both used for dispatching an empty bus, if the subsequent carpooling is unsuccessful under the first scheme, and the charge is lower than that of the express bus, the loss of the platform income can be caused, at the moment, the platform can calculate the successful probability of carpooling by using the information processing method provided by the embodiment of the disclosure according to the carpooling information of the order to be carpooled, and when the successful probability of carpooling is larger than a preset value, the order is preferentially taken as the order to be carpooled for matching.
Fig. 6 shows a schematic flowchart of an information processing method according to a sixth embodiment of the present disclosure.
As shown in fig. 6, an information processing method of a sixth embodiment of the present disclosure includes:
s602, establishing a profit prediction model according to the historical order information, wherein training parameters of the profit prediction model comprise a car-sharing starting point, a car-sharing terminal point, car-sharing time, the number of competing vehicles, the number of matched passengers and car-sharing result information in the historical order information, the car-sharing result information comprises car-sharing success information and car-sharing failure information, and target parameters of the profit prediction model are first platform profits;
s604, receiving first order information to be carpooled, wherein the first order information to be carpooled comprises a carpooling starting point, a carpooling end point and a carpooling moment;
s606, obtaining the number of competing vehicles and the number of matched passengers;
s608, obtaining a car sharing travel from the car sharing starting point to the car sharing terminal point;
s610, dividing the whole geographic area into a plurality of grids, and marking the grids where the carpooling journey passes as journey grids;
s612, acquiring historical order information to be carpooled, which is sent within a preset time range, has a carpooling stroke passing through a specified stroke grid and has a matching degree with the first order information to be carpooled greater than or equal to a third threshold value, and marking the historical order information to be carpooled as a reference historical order related to the corresponding stroke grid;
s614, calculating the reference spelling rate of each travel grid, wherein the reference spelling rate is the proportion of the orders with successful car spelling in the corresponding travel grid in the reference historical orders;
s616, inputting the first order information to be carpeted, the number of competitive vehicles, the number of matched passengers and the reference carpeted rate into a profit prediction model to calculate the first platform profit;
s618, inquiring matched car pooling order information matched with the first order information to be car pooling;
s620, calculating the second platform profit when the vehicle bearing the matched carpooling order information is dispatched;
and S622, determining the carpooling scheme of the first order information to be carpooled according to the first platform income and the second platform income.
In this embodiment, another scheme of how to predict the first platform gain is specifically defined. The method comprises the steps of firstly, conducting machine learning, establishing a profit prediction model by using a car pooling starting point, a car pooling end point, car pooling time, the number of competing vehicles, the number of matched passengers and car pooling result information of a historical order as training parameters and first platform profit as a target parameter, and then inputting the first car pooling order information, the number of competing vehicles, the number of matched passengers and a reference stitching rate into the established profit prediction model during prediction, so that the first platform profit can be output. According to the scheme, the successful car sharing probability is not generated specifically, the first platform profit is obtained directly according to the first order information to be shared and the related information, the calculation time can be shortened, and the operation efficiency is improved.
Fig. 7 shows a schematic flowchart of an information processing method according to a seventh embodiment of the present disclosure.
As shown in fig. 7, the information processing method of the seventh embodiment of the present disclosure includes:
s702, receiving first order information to be carpooled, wherein the first order information to be carpooled comprises a carpooling starting point, a carpooling end point and a carpooling moment;
s704, acquiring the number of competing vehicles and the number of matched passengers;
s706, predicting the first platform income when the air bus is dispatched according to the first order information to be carpooled, the number of competing vehicles and the number of matched passengers;
s708, inquiring at least one piece of matching car sharing order information matched with the first order information to be shared;
s710, calculating at least one platform benefit when at least one vehicle bearing matched carpooling order information is dispatched, and taking the maximum value of the at least one platform benefit as a second platform benefit;
and S712, determining the carpooling scheme of the first order information to be carpooled according to the first platform income and the second platform income.
In this embodiment, a processing scheme when at least one matching car pool order information is queried is defined. If a matching carpooling order is inquired, directly comparing the second platform income with the first platform income, wherein the specific comparison scheme can be seen in the embodiments; when at least two pieces of matched car pooling order information are inquired, corresponding car pooling strokes can be generated, and then platform benefits generated are calculated respectively.
Fig. 8 shows a schematic flowchart of an information processing method according to an eighth embodiment of the present disclosure.
As shown in fig. 8, the information processing method of the eighth embodiment of the present disclosure includes:
s802, receiving first order information to be carpooled, wherein the first order information to be carpooled comprises a carpooling starting point, a carpooling end point and a carpooling moment;
s804, obtaining the number of competitive vehicles and the number of matched passengers;
s806, predicting first platform benefits in dispatching the empty cars according to the first order information to be shared, the number of competing cars and the number of matched passengers;
s808, inquiring matched car pooling order information matched with the first order information to be car pooling;
s810, planning at least one driving route when a vehicle bearing matched carpool order information is dispatched;
s812, respectively calculating at least one second platform benefit when at least one driving route is adopted;
s814, determining the carpooling scheme of the first order information to be carpooled according to the first platform income and the second platform income.
In this embodiment, for one piece of matching car pooling order information, the planned driving route may be one or more, and the profit of the second platform may be directly calculated when the planned driving route is one, and the specific comparison scheme thereof may be referred to in the foregoing embodiments; and when the number of the car sharing routes is multiple, calculating the second platform profit for each driving route respectively, and comparing the second platform profit with the first platform profit to select the car sharing scheme with the best profit. The maximum value of the platform gains corresponding to the plurality of driving routes is not directly used as the second platform gain, because the phenomenon that the driving routes are too long, namely excessive detour, may exist, and the user experience may be reduced. For this purpose, optionally, the plurality of driving routes are sorted according to the driving time length from short to long, several driving routes with shorter driving time lengths (for example, the driving routes arranged in the front 70% or the driving routes corresponding to the plurality of driving time lengths with the difference value not greater than a set value) are reserved to ensure the user experience, and then the largest second platform benefit is selected to be further compared with the first platform benefit. The protection scope of the embodiments of the present disclosure is within the design concept of the embodiments of the present disclosure.
Further, for a particular order, the platform may generate multiple matching schemes, including different driver-side (i.e. vehicle) and different driving routes for each driver-side, so that this embodiment may be combined with the seventh embodiment to estimate the revenue generated by the platform according to the driving route of each matching scheme, so as to select the matching scheme with the best revenue.
An embodiment of a second aspect of an embodiment of the present disclosure provides an information processing system.
Fig. 9 shows a schematic block diagram of an information processing system according to a first embodiment of the present disclosure.
As shown in fig. 9, an information processing system 100 of a first embodiment of the present disclosure includes:
the receiving unit 102 is configured to receive first order information to be carpooled, where the first order information to be carpooled includes a carpooling start point, a carpooling end point, and a carpooling time;
an acquisition unit 104 for acquiring the number of competing vehicles and the number of matching passengers;
the prediction unit 106 is used for predicting the first platform profit when the air bus is dispatched according to the first order information to be carpooled, the number of competing vehicles and the number of matched passengers;
the query unit 108 is used for querying the matching carpooling order information matched with the first order information to be carpooled;
a calculating unit 110, configured to calculate a second platform profit when a vehicle bearing the matched carpool order information is dispatched;
and the decision unit 112 is configured to determine a carpooling scheme of the first order information to be carpooled according to the first platform benefit and the second platform benefit.
In the information processing system 100 provided by the embodiment of the present disclosure, when receiving the first order information to be carpooled, the receiving unit 102 generally has two carpooling schemes, one is to directly dispatch an empty car, and the other is to search for a manned car for carpooling. For the first solution, the predicting unit 106 predicts the first platform profit obtained by the platform when the empty car is dispatched, based on the first order information to be carpeted received by the receiving unit 102 and the related information obtained by the obtaining unit 104; for the second scheme, the query unit 108 queries matching car pooling order information that can be matched with the first to-be-car pooling order information in the ongoing order, and after the matching car pooling order information is queried, a clear driving route is generated by the car pooling starting point and the car pooling ending point, and the calculation unit 110 can calculate the generated revenue as the second platform revenue according to the existing revenue calculation method. The decision unit 112 can determine the carpooling scheme most favorable for the platform by comparing the first platform benefit and the second platform benefit, so that the user experience is not influenced, and the platform benefits and the use efficiency of the transport vehicle are improved. Optionally, the decision unit 112 may select a carpooling scheme corresponding to the party with the higher profit from the first platform profit and the second platform profit; the empty vehicles can be selected to be dispatched only when the profit of the first platform is higher than a certain value of the profit of the second platform, namely, the second scheme is preferred, the vehicles carrying people can be preferably spliced into a new order, and the splicing rate is ensured; the vehicle sharing with the manned vehicle can be selected when the first platform profit is lower than the second platform profit by a certain value, that is, the first scheme is preferred to ensure the user experience, and the first scheme and the second scheme belong to the protection scope of the embodiment of the disclosure as long as the first scheme and the second scheme do not depart from the design concept of the embodiment of the disclosure. Specifically, for the second scheme, when the query unit 108 does not query the matched car pool order information, the query unit may wait for a predetermined time period and query again or keep querying until the query is successful, and the decision unit 112 may also directly jump to the first case or jump to the first scheme when the matched car pool order information is not queried after the predetermined time period, that is, dispatch empty cars, so as to ensure the user experience.
Further, the order information to be carpooled also comprises the carpooling time, the order information to be carpooled is directly sent out, the carpooling time is the current time, and when the carpooling is reserved, the carpooling time is the reserved time, so that the order taking driver can conveniently take the passengers according to the reserved time. The first platform profit and the second platform profit are calculated based on the car sharing time so as to improve the calculation accuracy.
Specifically, when the query unit 108 queries and matches the car pooling order information, it may first obtain cars that can further carry passengers (i.e. cars that have carried passengers and whose number of passengers does not reach the upper limit) around the car pooling starting point and the car pooling order information carried by the cars, and further analyze whether the routes planned for the cars are matched with the routes of the first car pooling order information, and if so, plan the currently analyzed car pooling order information as the matched car pooling order information. The specific matching algorithm is not within the limited range of the embodiments of the present disclosure, and reference may be made to related technologies in the art, which are not described herein again.
In addition, the car booking platform usually performs a certain elimination after obtaining the car booking order information, the value (for example, the billing ratio) that the eliminated order can contribute to the platform can be calculated by the method for calculating the first platform profit through the prediction unit 106 provided by the embodiment of the present disclosure, and when the calculated value is greater than the predetermined threshold value, the eliminated order can be retrieved, and the car pooling service is performed again, so that the user demand is met, and the platform profit and the use efficiency of the transport vehicle are improved.
In an embodiment of the present disclosure, preferably, the obtaining unit 104 is specifically configured to: obtaining car sharing order information of a driver end in a designated geographic area, wherein the car sharing order information comprises associated car sharing passenger information and car sharing route information, the designated geographic area is a first preset geographic area around a designated place, and the designated place is a car sharing starting point and/or any point in a journey; if the matching degree of the car pooling order information and the first order information to be subjected to car pooling is larger than or equal to a first threshold value, marking a driver end corresponding to the car pooling order information as a competitive driver end; and counting the number of the competitive driver terminals as the number of the competitive vehicles.
In this embodiment, how the acquisition unit 104 acquires the number of competing vehicles is specifically defined. Firstly, obtaining the car sharing order information of an operator end in a reasonable range around a car sharing starting point and/or any point in a journey according to needs, wherein the car sharing order information comprises the associated car sharing passenger information and car sharing route information, then calculating the matching degree of the car sharing order information and the first order information to be shared, specifically, determining whether people can be further loaded in quantity according to the car sharing passenger information, if yes, calculating the overlap ratio of a planned car sharing route and the journey route of the first order information to be shared, if the overlap ratio is higher, indicating that the planned car sharing route and the first order information to be shared form a competition relationship, and enabling the corresponding driver end to be a competitive operator end, and further counting the quantity of the competitive operator end to obtain the quantity of competitive vehicles. Correspondingly, the taxi sharing order information carried by the competitive driver end can be recorded as competitive taxi sharing order information.
It can be appreciated that the main difference between the competitive ride share order information and the matching ride share order information involved in calculating the second platform revenue is that the former is for order information within a specified geographic area, the latter is for order information that can reach the start of ride share at the ride share time (or within a certain time range around the ride share time), and the vehicle bearing the matching ride share order information belongs to the matching vehicle.
Specifically, the competitive car sharing order information may be defined in many ways, for example, the competitive car sharing order information may be car sharing order information whose travel coincidence degree of the first car sharing order information exceeds a threshold value, or the competitive car sharing order information may be car sharing orders whose car sharing end point is adjacent to the car sharing end point of the first car sharing order information. When the quantity of the competitive car sharing order information is obtained, all the car sharing order information sent in the appointed geographic area can be obtained firstly, then whether the car sharing order information is the competitive car sharing order information or not is analyzed, and finally the quantity of the competitive car sharing order information in the car sharing order information is counted.
The method comprises the steps that for a designated geographic area, the area obtained by radiating a preset radius with a designated place as a center is used, the more the number of the designated places is, the larger the area of the designated geographic area is, the larger the acquired information amount is, the more accurate the prediction is, and when the designated place comprises a plurality of continuous points in a journey, the designated geographic area is approximately corresponding to a curve which is formed by overlapping a plurality of continuous circular areas and has a certain width. When the appointed place is the starting point of the carpooling, corresponding to the situation that the carpooling is successful at the starting point of the carpooling after an empty car is dispatched, the probability that the carpooling of the order to be carpooled is successful in the whole process can be obtained by obtaining the number of competitive carpooling orders and the number of matched cars in the appointed geographic area corresponding to all points in the starting point of the carpooling and the travel (the current order to be carpooled is not recorded under the situation that the carpooling is successful at the end point of the carpooling), and the accuracy of prediction is improved.
In an embodiment of the present disclosure, preferably, the obtaining unit 104 is further configured to: obtaining car sharing order information of a driver end in a designated geographic area, wherein the car sharing order information comprises associated car sharing passenger information and car sharing route information, the designated geographic area is a first preset geographic area around a designated place, and the designated place is a car sharing starting point and/or any point in a journey; if the matching degree of the car pooling order information and the first order information to be subjected to car pooling is larger than or equal to a first threshold value, marking a driver end corresponding to the car pooling order information as a competitive driver end; and counting the number of the competitive driver terminals as the number of the competitive vehicles.
In this embodiment, how the acquisition unit 104 acquires the matching passenger number is specifically defined. The method comprises the steps that first, second order information to be carpooled sent by a passenger end in a reasonable range around a carpooling starting point and/or any point in a journey is obtained according to needs, wherein the second order information to be carpooled comprises the carpooling starting point, the carpooling end point and the carpooling time, if the matching degree of the journey and the first order information to be carpooled is larger than or equal to a second threshold value, the passenger end is a potential carpooling object, the passenger end is marked as a matching passenger end, and then the number of the matching passenger ends is counted to obtain the number of the matching passengers.
In an embodiment of the present disclosure, preferably, the obtaining unit 104 is further configured to: obtaining a car sharing travel from a car sharing starting point to a car sharing terminal point; dividing the whole geographic area into a plurality of grids, and marking the grids passed by the carpooling journey as journey grids; obtaining historical order information to be carpooled, which is sent within a preset time range, has a carpooling stroke passing through a specified stroke grid and has a matching degree with the first order information to be carpooled greater than or equal to a third threshold value, and marking the historical order information to be carpooled as a reference historical order related to the corresponding stroke grid; calculating a reference spelling rate of each travel grid, wherein the reference spelling rate is the proportion of the orders with successful car spelling in the corresponding travel grid in the reference historical orders; the prediction unit 106 is specifically configured to predict the first platform profit according to the first order information to be carpooled, the number of competing vehicles, the number of matching passengers, and the reference carpooling rate.
In this embodiment, the obtaining unit 104 is further defined to obtain the reference spelling rate. Because whether the carpooling is successful or not has a key influence on the first platform income, the statistical information (namely the reference splicing rate) of the reference historical orders in the preset time range in the related geographic range (namely the travel grid) is obtained, so that the reference splicing rate can be combined when the first platform income is predicted, and the prediction accuracy is improved. The routes of each order to be carpooled often have more or less difference and are difficult to directly compare, and the statistical area is divided into a plurality of fixed grids, so that the grids related to the routes are only needed to be used in prediction, the carpooling condition of the historical order to be carpooled in the routes is conveniently summarized and summarized, and the prediction accuracy is improved by means of historical data. Optionally, the statistical region (e.g., the entire city) is divided into a 600m grid. The journey of the reference historical order firstly needs to pass through a journey network, and in addition, the reference historical order needs to be highly matched with the information of the first order to be carpooled, so that the reference historical order has a reference value. Optionally, the third threshold is equal to the second threshold. The order of successful carpooling related to the reference carpooling rate is successful in carpooling in the corresponding journey network, specifically, the boarding place of the new boarding passenger is in the journey grid, so that the counting of the order of successful carpooling outside the journey grid while passing through the journey grid can be avoided, the successful carpooling result of the order cannot be realized for the order to be carpooled, the repeated counting of the same order in different journey networks is avoided, and the reference value of the reference carpooling rate is improved.
Optionally, setting a preset time range as the previous day or the previous week of the car sharing time in the first order information to be shared, so that the reference sharing rate changes correspondingly with the advance of time, and the latest historical data is fully referred to; further, the 24 hours in the day are divided into different time periods, one time period can be divided at fixed time intervals, and the time periods can also be divided into peak time periods and ordinary time periods, for example, the early peak time period is from 7 to 9 am, the late peak time period is from 5 to 8 pm, the rest time periods are ordinary time periods, and the preset time range is set as the same time period of the previous day or the previous week.
Fig. 10 shows a schematic block diagram of an information processing system according to a second embodiment of the present disclosure.
As shown in fig. 10, an information processing system 200 of a second embodiment of the present disclosure includes:
the first model establishing unit 202 is used for establishing a probability prediction model and a probability profit mapping table according to the historical order information, wherein training parameters of the prediction model comprise a car-sharing starting point, a car-sharing terminal point, a car-sharing time, the number of competing vehicles, the number of matched passengers and car-sharing result information in the historical order information, the car-sharing result information comprises car-sharing success information and car-sharing failure information, and a target parameter of the probability prediction model is the car-sharing success probability;
the receiving unit 204 is configured to receive first order information to be carpooled, where the first order information to be carpooled includes a carpooling start point, a carpooling end point, and a carpooling time;
an acquisition unit 206 for acquiring the number of competing vehicles and the number of matching passengers;
the prediction unit 208 is used for inputting the first order information to be carpooled, the number of competing vehicles, the number of matched passengers and the reference carpooling rate into the probability prediction model so as to calculate the carpooling success probability; searching a probability profit mapping table to obtain first platform profits corresponding to the carpooling success probability;
the query unit 210 is configured to query matching car pooling order information matched with the first to-be-car pooling order information;
a calculating unit 212, configured to calculate a second platform benefit when a vehicle bearing the matching carpool order information is dispatched;
and the decision unit 214 is configured to determine a carpooling scheme of the first order information to be carpooled according to the first platform benefit and the second platform benefit.
In this embodiment, a scheme for predicting the first platform profit by the prediction unit 208 is specifically defined. The first model establishing unit 202 first performs machine learning, establishes a probability prediction model by using the car-pooling starting point, the car-pooling end point, the car-pooling time, the number of competing vehicles, the number of matched passengers and the car-pooling result information of the historical orders as training parameters and the car-pooling success probability as a target parameter, calculates the car-pooling success probability of each historical order according to the probability prediction model, calculates the relation between the car-pooling success probability and the first platform profit to obtain a probability profit mapping table, and the predicting unit 208 inputs the first car-pooling order information, the number of competing vehicles, the number of matched passengers and the reference car-pooling rate into the established probability prediction model to predict the car-pooling success probability and searches the probability profit mapping table to obtain the corresponding first platform profit. According to the scheme, the carpooling success probability is used as the middle bridge, the influence of carpooling success or failure on the first platform income is fully considered, and the prediction accuracy is improved.
Further, when matching car sharing order information is not inquired, decision can be made according to the car sharing success probability, if the car sharing success probability exceeds a preset value, empty cars are dispatched and waiting for car sharing, otherwise, the inquiry is carried out again after waiting for a preset time, the inquiry can be kept until the inquiry is successful, the car sharing success probability can be continuously predicted while the inquiry is carried out, and the empty cars are dispatched when the car sharing success probability exceeds the preset value.
In addition, for a car booking order, the current platform is often matched on two platforms of car pooling and car booking (such as express cars) at the same time, and the car pooling is expected to be realized as far as possible because the transportation capacity can be better utilized by the car pooling. When the carpooling is performed, the two schemes are adopted, wherein the first scheme and the express bus are both used for dispatching an empty car, if the subsequent carpooling is unsuccessful under the first scheme, and the charge is lower than that of the express bus, the loss of the platform yield is caused, at the moment, the platform can calculate the successful probability of carpooling by using the prediction unit 208 provided by the embodiment of the disclosure according to the carpooling information of the order to be carpooled, and when the successful probability of carpooling is greater than a preset value, the order is preferentially taken as the order to be carpooled for matching.
Fig. 11 shows a schematic block diagram of an information processing system according to a third embodiment of the present disclosure.
As shown in fig. 11, an information processing system 300 of a third embodiment of the present disclosure includes:
a second model establishing unit 302, configured to establish a profit prediction model according to the historical order information, where training parameters of the profit prediction model include a car-pooling starting point, a car-pooling ending point, a car-pooling time, a number of competing vehicles, a number of matched passengers, and car-pooling result information in the historical order information, the car-pooling result information includes car-pooling success information and car-pooling failure information, and a target parameter of the profit prediction model is a first platform profit;
the receiving unit 304 is configured to receive first order information to be carpooled, where the first order information to be carpooled includes a carpooling start point, a carpooling end point, and a carpooling time;
an obtaining unit 306 for obtaining the number of competing vehicles and the number of matching passengers;
the prediction unit 308 is used for inputting the first order information to be carpooled, the number of competing vehicles, the number of matched passengers and the reference carpooling rate into the profit prediction model so as to calculate the first platform profit;
the query unit 310 is used for querying the matching car pooling order information matched with the first order information to be pooled;
a calculating unit 312, configured to calculate a second platform profit when a vehicle bearing the matched carpool order information is dispatched;
and the decision unit 314 is configured to determine a car pooling scheme of the first order information to be car pooled according to the first platform benefit and the second platform benefit.
In this embodiment, a scheme for predicting the first platform profit by the prediction unit 308 is specifically defined. The second model establishing unit 302 first performs machine learning, establishes a profit prediction model using the starting point of car pooling, the ending point of car pooling, the time of car pooling, the number of competing vehicles, the number of matched passengers and the information of car pooling results of the historical orders as training parameters and the first platform profit as a target parameter, and the predicting unit 308 then inputs the information of the first order to be car pooled and the number of competing vehicles, the number of matched passengers and the reference rate of pooling thereof into the established profit prediction model, i.e., outputs the first platform profit. According to the scheme, the successful car sharing probability is not generated specifically, the first platform profit is obtained directly according to the first order information to be shared and the related information, the calculation time can be shortened, and the operation efficiency is improved.
In an embodiment of the present disclosure, preferably, the computing unit is specifically configured to: and when the number of the matched carpooling order information is at least one, calculating at least one platform profit when at least one vehicle bearing the matched carpooling order information is dispatched, and taking the maximum value in the at least one platform profit as a second platform profit.
In this embodiment, a processing scheme of the calculation unit when the query unit queries at least one piece of matching carpool order information is defined. If the inquiry unit inquires a matched car pooling order, the calculation unit directly compares the second platform profit with the first platform profit, and the specific comparison scheme of the decision unit can refer to the embodiments; when the inquiry unit inquires at least two pieces of matched car pooling order information, corresponding car pooling strokes can be generated, the calculation unit further calculates the generated platform benefits respectively, and because different pieces of matched car pooling order information are selected, the experience difference of users is not large, the maximum value of the platform benefits is directly used as the second platform benefits and is compared with the first platform benefits, so that the decision unit can select a car pooling scheme with the best benefits, namely, the decision unit can select which car to dispatch the first car pooling order information to be dispatched.
In an embodiment of the present disclosure, preferably, the computing unit is specifically configured to: planning at least one driving route when a vehicle bearing the matched carpool order information is dispatched; and respectively calculating at least one second platform profit when at least one driving route is adopted.
In this embodiment, for one piece of matching car pooling order information queried by the query unit, the planned driving route may be one or multiple, the calculation unit may directly calculate the second platform profit for one piece, and the specific comparison scheme of the decision unit may refer to the foregoing embodiments; the calculation unit needs to calculate the second platform profit for each driving route respectively, and the decision unit compares the second platform profit with the first platform profit to select the carpooling scheme with the best profit. The reason why the maximum value of the platform gains corresponding to the plurality of driving routes is not directly used as the second platform gain by the calculating unit is that the driving routes are too long, that is, the phenomenon of excessive detour may occur, and the user experience may be reduced. For this purpose, optionally, the calculating unit sorts the driving routes according to the driving time length from short to long, firstly reserves a few driving routes with shorter driving time length (for example, the driving routes ranked in the first 70% or the driving routes corresponding to a plurality of driving time lengths with a difference value not greater than a set value) to ensure the user experience, and then selects the largest second platform benefit to further compare with the first platform benefit. The protection scope of the embodiments of the present disclosure is within the design concept of the embodiments of the present disclosure.
Further, for a specific order, the platform may generate a plurality of matching schemes, including different driver sides (i.e. vehicles) and different driving routes for each driver side, so that this embodiment may be combined with the seventh embodiment, and the calculating unit may estimate the revenue generated by the platform according to the driving routes for each matching scheme, respectively, to select the matching scheme with the best revenue.
The "unit" defined by the embodiments of the present disclosure is a functional unit, and may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, are programs or code segments that perform the required tasks. The program or code segments can be stored in a computer readable storage medium or transmitted by data signals carried in a carrier wave over transmission media or communication links. "computer-readable storage media" may include any medium that can store or transfer information. Examples of computer readable storage media include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
An embodiment of the third aspect of the embodiments of the present disclosure provides a computer device, as shown in fig. 12, the computer device 4 includes a memory 42, a processor 44, and a computer program stored on the memory 42 and executable on the processor 44, and when the processor 44 executes the computer program, the steps of the method according to any one of the embodiments described above are implemented.
In the computer device 4 provided in the embodiment of the present disclosure, when the processor 44 executes the computer program stored in the memory 42, the steps of the method described in any of the embodiments above may be implemented, so that all the beneficial technical effects of the information processing method described above are achieved, and details are not described herein again.
An embodiment of a fourth aspect of the embodiments of the present disclosure provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the steps of the method according to any of the embodiments described above.
In the computer-readable storage medium provided in the embodiments of the present disclosure, when being executed by a processor, a computer program stored thereon may implement the steps of the method in any of the embodiments, so that all the advantageous technical effects of the information processing method are achieved, and details are not described herein again.
The technical scheme of the embodiment of the disclosure is described in detail with reference to the accompanying drawings, the embodiment of the disclosure provides an information processing scheme, the problem that platform benefits under different car sharing schemes are difficult to judge is solved, a prediction model is established by machine learning and combining big data formed by historical orders, so that order information to be shared is led into the prediction model to predict first platform benefits corresponding to the order information, second platform benefits generated by shared cars with people are calculated, and the first platform benefits and the second platform benefits are compared to determine the car sharing scheme most beneficial to a platform, so that user experience is not influenced, and the platform benefits and the use efficiency of transport vehicles are improved.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the disclosed embodiments should be included in the scope of protection of the disclosed embodiments.

Claims (18)

1. An information processing method characterized by comprising:
receiving first order information to be carpooled, wherein the first order information to be carpooled comprises a carpooling starting point, a carpooling end point and a carpooling moment;
acquiring the number of competing vehicles and the number of matched passengers;
predicting first platform benefits when the air vehicles are dispatched according to the first order information to be carpooled, the number of the competitive vehicles and the number of the matched passengers;
inquiring matched car pooling order information matched with the first car pooling order information;
calculating the second platform profit when the vehicle bearing the matched carpooling order information is dispatched;
and determining the carpooling scheme of the order to be carpooled according to the first platform income and the second platform income.
2. The information processing method according to claim 1, wherein the operation of acquiring the number of competing vehicles includes:
obtaining car sharing order information of a driver end in a designated geographic area, wherein the car sharing order information comprises associated car sharing passenger information and car sharing route information, the designated geographic area is a first preset geographic area around a designated place, and the designated place is a starting point of car sharing and/or any point in a journey;
if the matching degree of the car pooling order information and the first order information to be car pooling is larger than or equal to a first threshold value, marking the driver end corresponding to the car pooling order information as a competitive driver end;
and counting the number of the competitive driver terminals as the number of the competitive vehicles.
3. The information processing method according to claim 2, wherein the operation of obtaining the matching passenger number includes:
acquiring second order information to be carpooled sent out in the designated geographic area;
if the matching degree of the second order information to be carpooled and the first order information to be carpooled is larger than or equal to a second threshold value, marking a passenger end sending the second order information to be carpooled as a matched passenger end;
and counting the number of the matched passenger terminals to serve as the number of the matched passengers.
4. The information processing method according to claim 1,
after the operation of acquiring the number of competing vehicles and matching the number of passengers, the method further comprises the following steps:
obtaining a carpooling travel from the carpooling starting point to the carpooling terminal point;
dividing the whole geographic area into a plurality of grids, wherein the grids passed by the carpool journey are marked as journey grids;
obtaining historical order information to be carpooled, which is sent within a preset time range, has a carpooling route passing through the specified route grid and has a matching degree with the first order information to be carpooled greater than or equal to a third threshold value, and marking the historical order information to be carpooled as a reference historical order related to the corresponding route grid;
calculating a reference spelling rate of each travel grid, wherein the reference spelling rate is a proportion of orders which are successfully carpooled in the corresponding travel grid in the reference historical orders;
the step of predicting the first platform profit when dispatching the empty car according to the first order information to be carpooled, the number of competing vehicles and the number of matched passengers comprises the following steps:
and predicting the first platform profit according to the first order information to be shared, the number of competing vehicles, the number of matched passengers and the reference sharing rate.
5. The information processing method according to claim 4,
before the operation of receiving the first order information to be carpooled, the method further comprises the following steps:
establishing a probability prediction model and a probability profit mapping table according to historical order information, wherein training parameters of the probability prediction model comprise the car-sharing starting point, the car-sharing end point, the car-sharing time, the number of competing vehicles, the number of matched passengers and car-sharing result information in the historical order information, the car-sharing result information comprises car-sharing success information and car-sharing failure information, and target parameters of the probability prediction model are car-sharing success probability;
the step of predicting the first platform profit when dispatching the air bus according to the first order information to be carpooled, the number of competing vehicles, the number of matched passengers and the reference carpooling rate comprises the following steps:
inputting the first order information to be carpooled, the number of competing vehicles, the number of matched passengers and the reference carpooling rate into the probability prediction model to calculate the carpooling success probability;
and searching the probability profit mapping table to obtain the first platform profit corresponding to the carpooling success probability.
6. The information processing method according to claim 4, further comprising, before the operation of receiving the first to-be-carpooled order information:
establishing the profit prediction model according to historical order information, wherein training parameters of the profit prediction model comprise the car-sharing starting point, the car-sharing ending point, the car-sharing time, the number of competitive vehicles, the number of matched passengers and car-sharing result information in the historical order information, the car-sharing result information comprises car-sharing success information and car-sharing failure information, and target parameters of the profit prediction model are the first platform profit;
the step of predicting the first platform profit when dispatching the air bus according to the first order information to be carpooled, the number of competing vehicles, the number of matched passengers and the reference carpooling rate comprises the following steps:
inputting the first order information to be shared, the number of competing vehicles, the number of matched passengers and the reference sharing rate into the profit forecasting model to calculate the first platform profit.
7. The information processing method according to any one of claims 1 to 6, wherein the step of calculating a second platform profit when dispatching the vehicle carrying the matching carpool order information includes:
when the number of the matched carpool order information is one, calculating the second platform profit when the vehicle bearing the matched carpool order information is dispatched;
and when the number of the matched carpooling order information is multiple, respectively calculating multiple platform benefits when distributing a plurality of vehicles bearing the matched carpooling order information, and taking the maximum value of the multiple platform benefits as the second platform benefit.
8. The information processing method according to any one of claims 1 to 6, wherein the step of calculating a second platform profit when dispatching the vehicle carrying the matching carpool order information includes:
planning at least one driving route when the vehicle bearing the matched carpool order information is dispatched;
and respectively calculating at least one second platform profit when the at least one driving route is adopted.
9. An information processing system, comprising:
the system comprises a receiving unit, a judging unit and a display unit, wherein the receiving unit is used for receiving first order information to be carpooled, and the first order information to be carpooled comprises a carpooling starting point, a carpooling end point and a carpooling moment;
the acquiring unit is used for acquiring the number of competitive vehicles and the number of matched passengers;
the prediction unit is used for predicting the first platform profit when the air bus is dispatched according to the first order information to be carpooled, the number of competitive vehicles and the number of matched passengers;
the query unit is used for querying the matched car pooling order information matched with the first order information to be pooled;
the calculating unit is used for calculating the second platform profit when the vehicle bearing the matched carpooling order information is dispatched;
and the decision unit is used for determining the carpooling scheme of the first order information to be carpooled according to the first platform income and the second platform income.
10. The information processing system of claim 9, wherein the obtaining unit is specifically configured to:
obtaining car sharing order information of a driver end in a designated geographic area, wherein the car sharing order information comprises associated car sharing passenger information and car sharing route information, the designated geographic area is a first preset geographic area around a designated place, and the designated place is a starting point of car sharing and/or any point in a journey;
if the matching degree of the car pooling order information and the first order information to be car pooling is larger than or equal to a first threshold value, marking the driver end corresponding to the car pooling order information as a competitive driver end;
and counting the number of the competitive driver terminals as the number of the competitive vehicles.
11. The information processing system of claim 10, wherein the obtaining unit is further specifically configured to:
acquiring second order information to be carpooled sent out in the designated geographic area;
if the matching degree of the second order information to be carpooled and the first order information to be carpooled is larger than or equal to a second threshold value, marking a passenger end sending the second order information to be carpooled as a matched passenger end;
and counting the number of the matched passenger terminals to serve as the number of the matched passengers.
12. The information processing system of claim 9, wherein the obtaining unit is further configured to:
obtaining a carpooling travel from the carpooling starting point to the carpooling terminal point;
dividing the whole geographic area into a plurality of grids, wherein the grids passed by the carpool journey are marked as journey grids;
obtaining historical order information to be carpooled, which is sent within a preset time range, has a carpooling route passing through the specified route grid and has a matching degree with the first order information to be carpooled greater than or equal to a third threshold value, and marking the historical order information to be carpooled as a reference historical order related to the corresponding route grid;
calculating a reference spelling rate of each travel grid, wherein the reference spelling rate is a proportion of orders which are successfully carpooled in the corresponding travel grid in the reference historical orders;
the prediction unit is specifically configured to predict the first platform profit according to the first order information to be shared, the number of competing vehicles, the number of matching passengers, and the reference sharing rate.
13. The information processing system of claim 12, further comprising:
the system comprises a first model establishing unit, a second model establishing unit and a third model establishing unit, wherein the first model establishing unit is used for establishing a probability prediction model and a probability profit mapping table according to historical order information, training parameters of the probability prediction model comprise the car-sharing starting point, the car-sharing terminal point, the car-sharing time, the number of competitive vehicles, the number of matched passengers and car-sharing result information in the historical order information, the car-sharing result information comprises car-sharing success information and car-sharing failure information, and target parameters of the probability prediction model are car-sharing success probability;
the prediction unit is specifically configured to:
inputting the first order information to be carpooled, the number of competing vehicles, the number of matched passengers and the reference carpooling rate into the probability prediction model to calculate the carpooling success probability;
and searching the probability profit mapping table to obtain the first platform profit corresponding to the carpooling success probability.
14. The information processing system of claim 12, further comprising:
a second model establishing unit, configured to establish a profit prediction model according to historical order information, where training parameters of the profit prediction model include the car-pooling starting point, the car-pooling ending point, the car-pooling time, the number of competing vehicles, the number of matched passengers, and car-pooling result information in the historical order information, the car-pooling result information includes car-pooling success information and car-pooling failure information, and a target parameter of the profit prediction model is the first platform profit;
the prediction unit is specifically configured to input the first order information to be shared, the number of competing vehicles, the number of matching passengers, and the reference sharing rate into the profit prediction model to calculate the first platform profit.
15. The information processing system according to any one of claims 9 to 14, wherein the computing unit is specifically configured to:
when the number of the matched carpool order information is one, calculating the second platform profit when the vehicle bearing the matched carpool order information is dispatched;
and when the number of the matched carpooling order information is multiple, respectively calculating multiple platform benefits when distributing a plurality of vehicles bearing the matched carpooling order information, and taking the maximum value of the multiple platform benefits as the second platform benefit.
16. The information processing system according to any one of claims 9 to 14, wherein the computing unit is specifically configured to:
planning at least one driving route when the vehicle bearing the matched carpool order information is dispatched;
and respectively calculating at least one second platform profit when the at least one driving route is adopted.
17. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 8 when executing the computer program.
18. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 8.
CN201811467869.1A 2018-12-03 2018-12-03 Information processing method and system and computer equipment Active CN111260172B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811467869.1A CN111260172B (en) 2018-12-03 2018-12-03 Information processing method and system and computer equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811467869.1A CN111260172B (en) 2018-12-03 2018-12-03 Information processing method and system and computer equipment

Publications (2)

Publication Number Publication Date
CN111260172A true CN111260172A (en) 2020-06-09
CN111260172B CN111260172B (en) 2022-08-23

Family

ID=70950637

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811467869.1A Active CN111260172B (en) 2018-12-03 2018-12-03 Information processing method and system and computer equipment

Country Status (1)

Country Link
CN (1) CN111260172B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111882093A (en) * 2020-06-16 2020-11-03 北京嘀嘀无限科技发展有限公司 Carpooling method and system
CN111882312A (en) * 2020-07-27 2020-11-03 北京嘀嘀无限科技发展有限公司 Method, device, electronic equipment and storage medium for managing vehicle service travel
CN113642761A (en) * 2021-06-25 2021-11-12 东风汽车集团股份有限公司 Robotaxi automatic driving shared network car booking resource allocation method
WO2022073444A1 (en) * 2020-10-07 2022-04-14 Beijing Didi Infinity Technology And Development Co., Ltd. Systems and methods for dispatching shared rides through ride-hailing platform
CN116644942A (en) * 2023-07-24 2023-08-25 山东车拖车网络科技有限公司 Automatic trailer service matching method

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040236668A1 (en) * 2003-03-25 2004-11-25 Toffey James Warden Method and system for effecting straight-through-processing of trades of various financial instruments
CN107798403A (en) * 2016-09-07 2018-03-13 北京嘀嘀无限科技发展有限公司 A kind of share-car order processing method, server, terminal device and system
CN108416559A (en) * 2018-04-18 2018-08-17 江苏富力物流科技有限公司 A kind of shipping platform car owner maximum revenue intelligence share-car matching process
CN108734489A (en) * 2017-04-18 2018-11-02 北京嘀嘀无限科技发展有限公司 Share-car discount determines method and device
CN108734361A (en) * 2017-04-18 2018-11-02 北京嘀嘀无限科技发展有限公司 Share-car order processing method and apparatus
CN108876156A (en) * 2018-06-25 2018-11-23 清华大学 Share-car and user's order processing method, system and the equipment being applicable in

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040236668A1 (en) * 2003-03-25 2004-11-25 Toffey James Warden Method and system for effecting straight-through-processing of trades of various financial instruments
CN107798403A (en) * 2016-09-07 2018-03-13 北京嘀嘀无限科技发展有限公司 A kind of share-car order processing method, server, terminal device and system
CN108734489A (en) * 2017-04-18 2018-11-02 北京嘀嘀无限科技发展有限公司 Share-car discount determines method and device
CN108734361A (en) * 2017-04-18 2018-11-02 北京嘀嘀无限科技发展有限公司 Share-car order processing method and apparatus
CN108416559A (en) * 2018-04-18 2018-08-17 江苏富力物流科技有限公司 A kind of shipping platform car owner maximum revenue intelligence share-car matching process
CN108876156A (en) * 2018-06-25 2018-11-23 清华大学 Share-car and user's order processing method, system and the equipment being applicable in

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
金宇明 等: "《高峰时间出租车合乘计费策略研究》", 《交通运输研究》 *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111882093A (en) * 2020-06-16 2020-11-03 北京嘀嘀无限科技发展有限公司 Carpooling method and system
CN111882312A (en) * 2020-07-27 2020-11-03 北京嘀嘀无限科技发展有限公司 Method, device, electronic equipment and storage medium for managing vehicle service travel
WO2022073444A1 (en) * 2020-10-07 2022-04-14 Beijing Didi Infinity Technology And Development Co., Ltd. Systems and methods for dispatching shared rides through ride-hailing platform
US11626021B2 (en) 2020-10-07 2023-04-11 Beijing Didi Infinity Technology And Development Co., Ltd. Systems and methods for dispatching shared rides through ride-hailing platform
CN113642761A (en) * 2021-06-25 2021-11-12 东风汽车集团股份有限公司 Robotaxi automatic driving shared network car booking resource allocation method
CN116644942A (en) * 2023-07-24 2023-08-25 山东车拖车网络科技有限公司 Automatic trailer service matching method
CN116644942B (en) * 2023-07-24 2023-10-24 山东车拖车网络科技有限公司 Automatic trailer service matching method

Also Published As

Publication number Publication date
CN111260172B (en) 2022-08-23

Similar Documents

Publication Publication Date Title
CN111260172B (en) Information processing method and system and computer equipment
US10160321B2 (en) Methods, circuits, devices, systems and associated computer executable code for driver decision support
CN106875066B (en) Vehicle travel behavior prediction method, device, server and storage medium
WO2016034209A1 (en) Method and system for providing a dynamic ride sharing service
CN110245377B (en) Travel scheme recommendation method and recommendation system
JP6890069B2 (en) Information processing equipment, information processing methods and computer programs
EP3514738A1 (en) Demand prediction apparatus, redistribution plan generation apparatus, user model generation apparatus
CN113253722B (en) Method, device and system for planning charging path of electric vehicle
JP2018206225A (en) Distribution device, distribution method, distribution program, and model
CN113379159B (en) Taxi driver passenger searching route recommendation method based on gray model and Markov decision process
CN115164922A (en) Path planning method, system, equipment and storage medium
CN115060278A (en) Intelligent vehicle battery replacement navigation method and system based on multi-target genetic algorithm
CN111582527A (en) Travel time estimation method and device, electronic equipment and storage medium
CN112819394B (en) Waybill processing method and device, computer-readable storage medium and electronic equipment
CN114169813A (en) Transportation scheduling method and device, electronic equipment and storage medium
CN109682387B (en) Method and device for determining navigation position point
CN110610284A (en) Information processing method and information processing apparatus
CN116681197B (en) Logistics line searching method and system based on big data
CN116558521B (en) Track positioning method, track positioning device and computer readable storage medium
CN110347937B (en) Intelligent passenger searching method for taxi
US11733051B2 (en) Communications server apparatus, method and communications system for managing request for transport-related services
CN114817376B (en) Intelligent analysis system for running data of electric automobile based on Internet of things
CN113902427B (en) Method, device and equipment for determining estimated arrival time and storage medium
CN109034494A (en) Bus dispatching method
KR102459756B1 (en) A hierarchical route recommendation method and system considering inter-node accessibility using multimodes

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