CN111598307A - Optimization method and equipment of bus taking order scheduling system - Google Patents
Optimization method and equipment of bus taking order scheduling system Download PDFInfo
- Publication number
- CN111598307A CN111598307A CN202010333881.4A CN202010333881A CN111598307A CN 111598307 A CN111598307 A CN 111598307A CN 202010333881 A CN202010333881 A CN 202010333881A CN 111598307 A CN111598307 A CN 111598307A
- Authority
- CN
- China
- Prior art keywords
- order
- user
- scheduling system
- evaluation
- predicted
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000005457 optimization Methods 0.000 title claims abstract description 45
- 238000011156 evaluation Methods 0.000 claims abstract description 136
- 230000014759 maintenance of location Effects 0.000 claims abstract description 29
- 238000012549 training Methods 0.000 claims description 13
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000013461 design Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 238000012216 screening Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013398 bayesian method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/067—Enterprise or organisation modelling
-
- 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)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Educational Administration (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 invention provides an optimization method and equipment of a bus taking order scheduling system, wherein the method comprises the steps of obtaining order characteristics of a bus taking order of a user; inputting the order features into a stay time model to obtain the predicted stay time of the user in an order evaluation interface; if the predicted retention time is larger than a preset threshold value, pushing the order evaluation interface to the user; and receiving evaluation information input by the user in the order evaluation interface, and optimizing a scheduling system according to the evaluation information. The embodiment of the invention can effectively screen the user, obtain more real and valuable evaluation information and find the problem of the current scheduling system based on the evaluation information, thereby realizing the effective optimization of the scheduling system.
Description
Technical Field
The embodiment of the invention relates to the technical field of intelligent traffic, in particular to an optimization method and equipment of a bus taking order scheduling system.
Background
With the improvement of the environmental protection consciousness of people and the more serious parking difficulty problem, more users select the on-line car booking travel mode. In a specific car booking process, after receiving a riding order sent by a user terminal, a scheduling system of an operator background plans a route for a user and allocates vehicles to be taken according to the riding order and the conditions of online vehicles. Therefore, the riding experience of the user and the efficiency of vehicle scheduling are directly influenced by the rationality of the scheduling strategy of the scheduling system. Therefore, the scheduling system needs to be optimized to meet the user requirements.
In the prior art, engineers select features which may meet the user psychology according to their understanding of services, and build a scoring model to score a riding order for the riding experience of the user. And determining the problem of the scheduling system based on the grading result, and optimizing the scheduling system.
However, a gap often exists between data guessing of engineers and the real psychology of users, so that problems cannot be found quickly and accurately, the optimization efficiency of the scheduling system is low, the requirements of the users cannot be met, and the riding experience of the users is influenced.
Disclosure of Invention
The embodiment of the invention provides a method and equipment for optimizing a bus taking order scheduling system, which are used for improving the effective optimization of the scheduling system, meeting the requirements of users and improving the bus taking experience of the users.
In a first aspect, an embodiment of the present invention provides an optimization method for a bus taking order scheduling system, including:
obtaining order features of a riding order of a user;
inputting the order features into a stay time model to obtain the predicted stay time of the user in an order evaluation interface;
if the predicted retention time is larger than a preset threshold value, pushing the order evaluation interface to the user;
and receiving evaluation information input by the user in the order evaluation interface, and optimizing a scheduling system according to the evaluation information.
In one possible design, the order characteristics include at least one of: ordering time, departure time, peak hours of the location, weather conditions, riding time and travel distance.
In one possible design, before the inputting the order characteristics into the dwell time model, the method further includes:
obtaining user characteristics of the user, wherein the user characteristics comprise at least one of the following: route preference, travel time preference and accumulated order placing times;
the inputting the order characteristics into a dwell time model comprises:
inputting the order characteristics and the user characteristics to the dwell time model.
In a possible design, before pushing the order evaluation interface to the user, the method further includes:
inputting the riding order into a dispatching scoring model to obtain a predicted dispatching score;
the pushing the order evaluation interface to the user includes:
and if the predicted order dispatching score is lower than a preset score, pushing the order evaluation interface to the user.
In one possible design, the order evaluation interface includes: a text input box for the user to input information and an item box to be checked for the user to select the evaluation result.
In one possible design, before the inputting the order characteristics into the dwell time model, the method further includes:
the method comprises the steps of obtaining order features of a plurality of orders to be trained and labels corresponding to the order features of the orders to be trained; the label is used for indicating the stay time of a user corresponding to the order to be trained in the corresponding order evaluation interface;
and training the retention time model to be trained according to the order features of the orders to be trained and the labels corresponding to the order features of the orders to be trained to obtain the trained retention time model.
In one possible design, the dwell time model is a regression model or a neural network model.
In a second aspect, an embodiment of the present invention provides an optimization device for a bus taking order scheduling system, including:
the obtaining module is used for obtaining the order characteristics of the riding order of the user;
the input module is used for inputting the order characteristics into a stay time model to obtain the predicted stay time of the user in an order evaluation interface;
the pushing module is used for pushing the order evaluation interface to the user if the predicted retention time is larger than a preset threshold value;
and the receiving module is used for receiving the evaluation information input by the user in the order evaluation interface and optimizing the scheduling system according to the evaluation information.
In a third aspect, an embodiment of the present invention provides an optimization device for a bus taking order scheduling system, including: at least one processor and memory;
the memory stores computer-executable instructions;
the at least one processor executes computer-executable instructions stored by the memory to cause the at least one processor to perform the method as set forth in the first aspect above and in various possible designs of the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, in which computer-executable instructions are stored, and when a processor executes the computer-executable instructions, the method according to the first aspect and various possible designs of the first aspect are implemented.
The method comprises the steps of obtaining order characteristics of a riding order of a user; inputting the order features into a stay time model to obtain the predicted stay time of the user in an order evaluation interface; if the predicted retention time is larger than a preset threshold value, pushing the order evaluation interface to the user; and receiving evaluation information input by the user in the order evaluation interface, and optimizing a scheduling system according to the evaluation information. According to the optimization method provided by the embodiment, the predicted stay time of the user on the order evaluation interface is obtained through the stay time model according to the order characteristics of the riding order of the user, the user who can seriously treat the order evaluation is screened out according to the predicted stay time, the evaluation information of the user is collected by pushing the order evaluation interface to the user, the evaluation information can reflect the user opinion more truly, the problem of the current scheduling system can be captured more accurately by analyzing the evaluation information of the user, and therefore the effective optimization of the scheduling system is achieved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic view of an application scenario provided in an embodiment of the present invention;
FIG. 2 is a flow chart of a residence time model acquisition process provided by yet another embodiment of the present invention;
fig. 3 is a schematic flow chart of an optimization method of a ride order scheduling system according to another embodiment of the present invention;
FIG. 4 is a schematic diagram of an order evaluation interface according to another embodiment of the present invention;
fig. 5 is a schematic flow chart illustrating an optimization method of a ride order scheduling system according to another embodiment of the present invention;
fig. 6 is a schematic flow chart illustrating an optimization method of a ride order scheduling system according to another embodiment of the present invention;
fig. 7 is a schematic structural diagram of an optimization device of a bus order scheduling system according to an embodiment of the present invention;
fig. 8 is a schematic hardware structure diagram of an optimization device of a bus order scheduling system according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic view of an application scenario provided in an embodiment of the present invention. As shown in fig. 1, a server 101 loaded with a scheduling system is communicatively connected with a client terminal 102 held by a user and an in-vehicle terminal 103 of a vehicle to be borne. The client terminal 102 may be a mobile terminal such as a mobile phone or a tablet, and optionally, the client terminal is loaded with an APP for calling and placing an order. The vehicle-mounted terminal 103 may be a system platform mounted on a vehicle, and may also be a handheld terminal of a driver of the vehicle to be carried, such as a mobile phone, a tablet, and the like.
In a specific taxi taking scene, a user places a taxi through the client terminal 102, an operator receives a taxi through the scheduling system of the server 101, selects a vehicle to be taken according to order information and the condition of an online vehicle, and pushes an order to the vehicle to be taken. And after the vehicle to be taken over takes over the order, executing the order, and sending the user from the departure place to the destination to complete the order.
Therefore, the riding experience of the user and the vehicle scheduling efficiency are directly influenced by the rationality of the scheduling strategy of the scheduling system. There is a need to optimize the scheduling system. In the prior art, an engineer usually obtains a user order, performs data analysis on the order to determine a delivery score corresponding to the user order, selects an order with a delivery score lower than a preset value from a large number of user orders, performs problem extraction, and optimizes a scheduling system according to the extracted problem. However, the score determination of the user order from the perspective of the engineer is too subjective, and the data guess of the engineer is often different from the true psychology of the user, so that the true opinion of the user cannot be obtained. The problem cannot be found quickly and accurately, so that the optimization efficiency of the dispatching system is low, the requirements of users cannot be met, and the riding experience of the users is influenced. Based on the above, the embodiment of the invention provides an optimization method of a bus order scheduling system, so as to improve the effectiveness of optimization of the bus order scheduling system.
In this embodiment, in order to obtain the true opinions of the users, users who are willing to evaluate and seriously evaluated can be screened out from a large number of users according to the stay time of the users in the order evaluation interface, and the evaluation interface is pushed. And then according to the reply content input by the user, analyzing the problems of the scheduling system, and optimizing the scheduling system based on the analyzed problems, so that the effectiveness of the optimization of the scheduling system can be improved, the user requirements can be met, and the user experience can be improved.
The following is a detailed description of the training model and the usage model, respectively.
Fig. 2 is a flowchart of a residence time model obtaining method according to another embodiment of the present invention. As shown in fig. 2, the method includes:
201. the method comprises the steps of obtaining order features of a plurality of orders to be trained and labels corresponding to the order features of the orders to be trained; the label is used for indicating the stay time of the user corresponding to the order to be trained in the corresponding order evaluation interface.
In a specific implementation process, historical orders of a user can be collected to be used as orders to be trained.
And after the orders to be trained are collected, extracting the order characteristics of each order. The order characteristics include at least one of: ordering time, departure time, peak hours of the location, weather conditions, riding time and travel distance.
In this embodiment, the order features extracted from the order to be trained may be obtained from a big data warehouse, specifically, the required feature data may be obtained at the corresponding interface position by setting data embedding points on an online system, for example, for weather conditions, data embedding may be performed on a weather data interface to obtain, and for features such as geographic environment and road conditions, data embedding may be performed on a data interface of a map department with map surveying right to extract.
After the order characteristics of each order are obtained, determining a label corresponding to each order characteristic, wherein the label is used for indicating the time of a user evaluating the order to be trained, namely the stay time between the time of receiving the evaluation interface corresponding to the order to be trained and the time of submitting the order evaluation interface after the order evaluation is completed.
202. And training the retention time model to be trained according to the order features of the orders to be trained and the labels corresponding to the order features of the orders to be trained to obtain the trained retention time model.
After the order features of the order to be trained and the labels corresponding to the order features are obtained, the stay time model to be trained is trained, and the stay time model after training is obtained.
In this embodiment, the dwell time model may be a conventional machine learning model, such as: regression algorithms, decision tree learning, bayesian methods, and also neural network models, such as convolutional neural network models.
According to the method, the obtained stay time model is trained, the influence of different order features on the stay time is fully considered by the training data of the stay time model, and the stay time of the user on the order evaluation interface can be accurately predicted.
Optionally, in a specific embodiment, in order to improve the prediction accuracy of the dwell time model, the user characteristics of the user may be also taken into consideration, and specifically, the training method further includes:
step 203, obtaining user characteristics of users corresponding to a plurality of orders to be trained and labels corresponding to the user characteristics; the label is used for indicating the stay time of the user corresponding to the order to be trained in the corresponding order evaluation interface.
Optionally, the user characteristics comprise at least one of: route preference, travel time preference, and accumulated order placement times.
Accordingly, step 202 includes: and training the retention time model to be trained according to the order features of the orders to be trained and the labels corresponding to the order features of the orders to be trained, the user features of the users corresponding to the orders to be trained and the labels corresponding to the user features to obtain the trained retention time model.
According to the training method of the stay time model provided by the embodiment, the order characteristics of the order to be trained and the user characteristics of the user corresponding to the order to be trained are taken into consideration simultaneously, so that the stay time model with higher prediction accuracy can be obtained through training, and therefore, the method is beneficial to accurately screening the user suitable for order evaluation, so that evaluation information capable of truly reflecting the problems of the scheduling system can be obtained, and the scheduling system can be effectively optimized.
The following describes a method for optimizing a bus taking order scheduling system by using a trained stay time model according to an embodiment of the present invention.
Fig. 3 is a flowchart illustrating an optimization method of a bus taking order scheduling system according to another embodiment of the present invention. As shown in fig. 3, the method includes:
301. and acquiring the order characteristics of the riding order of the user.
The execution subject of this embodiment may be the client terminal or the server shown in fig. 1.
Optionally, the order characteristics include at least one of: ordering time, departure time, peak hours of the location, weather conditions, riding time, travel distance and road conditions.
In this embodiment, the manner of extracting the order features from the riding order of the user may be to set data embedding points in an online system, and obtain the required feature data at the corresponding interface position, for example, for weather conditions, data embedding points may be performed on a weather data interface to obtain, and for features such as geographic environment and road conditions, data embedding points may be performed on a data interface of a map department with map surveying right to extract.
In this embodiment, the timing for extracting the order features of the riding order may be to extract the order features in a unified manner after the riding order is completed, or may extract the order features that can be formed only after the riding order is completed according to the characteristics of the order features, and in order to improve the operation efficiency, the features that can be obtained when the order is not completed need not be extracted after the order is completed.
302. And inputting the order features into a stay time model to obtain the predicted stay time of the user in an order evaluation interface.
303. And judging whether the predicted retention time is greater than a predicted threshold value, and if the predicted retention time is greater than a preset threshold value, executing step 304.
304. And pushing the order evaluation interface to the user, receiving evaluation information input by the user on the order evaluation interface, and optimizing a scheduling system according to the evaluation information.
In practical application, after the carrying vehicle sends the user to the destination and informs the background server of the arrival at the destination, the server or the client terminal can predict the stay time through the stay time model according to the order characteristics of the current riding order to obtain the predicted stay time of the user in the order evaluation interface, if the obtained predicted stay time of the user is greater than a preset threshold value, the user is indicated to have the tendency of seriously evaluating the order, the order evaluation interface is pushed to the user, so that the user inputs evaluation information about the completion condition of the current order in the order evaluation interface.
Optionally, the order evaluation interface includes: a text input box for the user to input information and an item box to be checked for the user to select the evaluation result. For example, fig. 4 is a schematic diagram of an order evaluation interface according to another embodiment of the present invention, and as shown in fig. 4, a questionnaire provided for a user in the order evaluation interface includes two questions, a first question is an objective question, a plurality of options are set below the questions, and each option is configured with a check box, so that the user can check in the corresponding box according to an actual riding situation. The second question is a subjective question, and a text box is arranged below the question so that a user can input character information or picture information in the text box. In order to know the riding condition of the user in more detail, a plurality of topics can be set in the order evaluation interface, and each page can be selected to display one topic or a plurality of topics. In order to save the user time and fully utilize the attention of the user, a smaller number of titles may be set, for example, 3 to titles may be set. In the embodiment, the user can input characters by setting the subjective questions, so that the user can clearly and completely describe the concerned problems. The situation that the problem concerned by the user cannot be covered due to the limited coverage range of the objective question is avoided.
According to the optimization method of the bus taking order scheduling system, the predicted stay time of the user on the order evaluation interface is obtained through the stay time model according to the order characteristics of the bus taking order of the user, the user who can seriously treat the order evaluation is screened according to the predicted stay time, the evaluation information of the user is collected by pushing the order evaluation interface to the user, the evaluation information can reflect the user opinion more truly, the problem of the current scheduling system can be captured more accurately by analyzing the evaluation information of the user, and therefore effective optimization of the scheduling system is achieved.
Optionally, after step 303, further comprising:
Fig. 5 is a flowchart illustrating an optimization method of a bus order scheduling system according to another embodiment of the present invention. On the basis of the above-mentioned embodiment, for example, on the basis of the embodiment shown in fig. 3, the identification of the user characteristics is added in the present embodiment, so that the stay time of the user can be accurately predicted according to the order characteristics and the user characteristics at the same time. As shown in fig. 5, the method includes:
501. obtaining order characteristics of a riding order of a user and user characteristics of the user, wherein the user characteristics comprise at least one of the following items: route preference, travel time preference, and accumulated order placement times.
For obtaining the order characteristics in step 501 in this embodiment, reference may be made to the description of step 301 in the above embodiment, and details are not repeated here.
In this embodiment, the user characteristics of the user refer to characteristics related to personal riding preferences or habits of the user, such as route preferences, travel time preferences, and accumulated number of orders.
502. And inputting the order characteristics and the user characteristics into a stay time model to obtain the predicted stay time of the user in an order evaluation interface.
503. And judging whether the predicted retention time is greater than a predicted threshold value, if so, executing step 504, and if not, executing step 505.
504. And pushing the order evaluation interface to the user, receiving evaluation information input by the user on the order evaluation interface, and optimizing a scheduling system according to the evaluation information.
505. And pushing a notification message of the order completion to the user.
In practical application, after the carrying vehicle sends the user to the destination and informs the background server of the arrival at the destination, the server or the client terminal can predict the stay time of the user in the order evaluation interface according to the order characteristics of the current riding order and the user characteristics of the user through the stay time model to obtain the predicted stay time of the user in the order evaluation interface, if the obtained predicted stay time of the user is larger than a preset threshold, the user is indicated to have the tendency of seriously evaluating the order, and the order evaluation interface is pushed to the user so that the user inputs evaluation information about the completion condition of the current order in the order evaluation interface.
According to the optimization method of the bus taking order scheduling system, the predicted residence time can be obtained more accurately by comprehensively considering the order characteristics of the bus taking orders and the user characteristics of the bus taking users, the users can be accurately screened, the users who can seriously treat order evaluation can be found out, more valuable information can be collected from the users, the problems of the current scheduling system can be analyzed according to the information fed back by the users, and the current scheduling system can be optimized.
Fig. 6 is a flowchart illustrating an optimization method of a bus order scheduling system according to another embodiment of the present invention. On the basis of the above-mentioned embodiment, for example, on the basis of the embodiment shown in fig. 5, in this embodiment, a further user screening condition based on a menu score is added to improve the accuracy of user screening, as shown in fig. 6, the method includes:
601. the method comprises the steps of obtaining order characteristics of a riding order of a user and user characteristics of the user.
602. And inputting the order characteristics and the user characteristics into a stay time model to obtain the predicted stay time of the user in an order evaluation interface.
Step 601 and step 602 in this embodiment are similar to step 501 and step 502 in the above embodiment, and are not described again here.
603. And inputting the riding orders into a dispatching scoring model to obtain a predicted dispatching score.
In this embodiment, the dispatch scoring model may be a model obtained by analyzing, selecting and training features, of an engineer, according to a data situation of a riding order of a user, and the dispatch scoring model is used to output a dispatch score of the riding order according to an input riding order, that is, an experience score of the user for the riding situation.
604. And judging whether the predicted retention time is larger than a prediction threshold value or not and whether the dispatch score is lower than a preset score or not. If the predicted retention time is greater than the prediction threshold and the dispatch score is lower than the preset score, go to step 605, and if the predicted retention time is less than or equal to the prediction threshold or the dispatch score is higher than the preset score, go to step 606.
In order to further reduce the calculation amount, the target user is locked more accurately to collect order evaluation information. In the embodiment, the residence time of the user in the order evaluation interface is predicted, the taking order grade of the user is predicted through the order grade model, the obtained predicted residence time and the obtained order grade are judged, and when the predicted residence time and the obtained order grade meet preset conditions, the user is indicated as a target user for pushing the order evaluation interface. Specifically, the fact that the predicted retention time is larger than the predicted threshold value indicates that the user can seriously treat the evaluation, and the fact that the order dispatching score is lower than the preset score indicates that the order has a higher possibility of having a scheduling problem. Based on the above, the evaluation information provided by the user and obtained by screening according to the situations of the predicted residence time and the dispatch score is more helpful for finding the problems of the dispatching system.
605. And pushing the order evaluation interface to the user, receiving evaluation information input by the user on the order evaluation interface, and optimizing a scheduling system according to the evaluation information.
606. And pushing a notification message of the order completion to the user.
In practical application, after the carrying vehicle sends the user to the destination and informs the background server of the arrival at the destination, the server or the client terminal can predict the stay time of the user in the order evaluation interface according to the order characteristics of the current riding order and the user characteristics of the user through the stay time model to obtain the predicted stay time of the user in the order evaluation interface, and can predict the order dispatching score of the current riding order through the order dispatching score model, if the obtained predicted stay time of the user is greater than a preset threshold value and the order dispatching score is lower than a preset score, the user has a tendency of seriously evaluating the order, and if the order dispatching score is lower than the preset score, the user has a higher possibility of scheduling the current order. And then, when the predicted stopping time of the riding order of the user is greater than a preset threshold value and the dispatching score is lower than a preset score value, an order evaluation interface is pushed to the user, so that the user inputs evaluation information about the order completion condition at the order evaluation interface.
According to the optimization method of the bus taking order scheduling system, the conditions of the predicted stopping time and the dispatching order grading of the bus taking orders are considered at the same time, users capable of finishing order evaluation with high quality can be screened more accurately, the problems of the scheduling system are analyzed according to the evaluation information provided by the users, and the scheduling system is optimized effectively.
Fig. 7 is a schematic structural diagram of an optimization device of a bus order scheduling system according to an embodiment of the present invention. As shown in fig. 7, the optimization apparatus 70 of the ride order scheduling system includes: the device comprises an acquisition module 701, an input module 702, a push module 703 and a receiving module 704.
An obtaining module 701, configured to obtain order features of a riding order of a user;
an input module 702, configured to input the order characteristics into a retention time model, and obtain a predicted retention time of the user in an order evaluation interface;
a pushing module 703, configured to push the order evaluation interface to the user if the predicted retention time is greater than a preset threshold;
a receiving module 704, configured to receive evaluation information input by the user in the order evaluation interface, and optimize a scheduling system according to the evaluation information.
According to the optimization equipment of the bus taking order scheduling system provided by the embodiment of the invention, an obtaining module 701 obtains the order characteristics of a bus taking order of a user; the input module 702 inputs the order characteristics into a stay time model to obtain the predicted stay time of the user in an order evaluation interface; the pushing module 703 pushes the order evaluation interface to the user when the predicted retention time is greater than a preset threshold; the receiving module 704 receives evaluation information input by the user on the order evaluation interface, and optimizes the scheduling system according to the evaluation information. The optimization device provided by the embodiment screens out users who can seriously treat order evaluation according to the predicted stay time of the users on the order evaluation interface, which is obtained according to the order characteristics of the riding orders of the users through the stay time model, and further collects evaluation information of the users by pushing the order evaluation interface to the users, wherein the evaluation information can reflect user opinions more truly, and the problem of the current scheduling system can be captured more accurately by analyzing the evaluation information of the users, so that the scheduling system can be optimized effectively.
Optionally, the order characteristics include at least one of: ordering time, departure time, peak hours of the location, weather conditions, riding time and travel distance.
Optionally, the obtaining module is further configured to:
obtaining user characteristics of the user, wherein the user characteristics comprise at least one of the following: route preference, travel time preference and accumulated order placing times;
the input module is specifically configured to input the order characteristics and the user characteristics to the dwell time model.
Optionally, the apparatus further comprises: the determining module 705 is used for inputting the riding orders into a dispatching score model to obtain a predicted dispatching score;
the pushing module 703 is specifically configured to push the order evaluation interface to the user when the predicted retention time is greater than the threshold and the predicted dispatch score is lower than a preset score.
Optionally, the order evaluation interface includes: a text input box for the user to input information and an item box to be checked for the user to select the evaluation result.
Optionally, the apparatus further includes a training module 706, configured to obtain order features of multiple orders to be trained and a label corresponding to the order feature of each order to be trained; the label is used for indicating the stay time of a user corresponding to the order to be trained in the corresponding order evaluation interface;
and training the retention time model to be trained according to the order features of the orders to be trained and the labels corresponding to the order features of the orders to be trained to obtain the trained retention time model.
Optionally, the residence time model is a regression model or a neural network model.
The optimization device of the bus taking order scheduling system provided by the embodiment of the invention can be used for executing the method embodiment, the implementation principle and the technical effect are similar, and the details are not repeated here.
Fig. 8 is a schematic hardware structure diagram of an optimization device of a bus order scheduling system according to an embodiment of the present invention. As shown in fig. 8, the optimization device 80 of the bus order scheduling system provided in this embodiment includes: at least one processor 801 and a memory 802. The optimization device 80 of the ride order dispatching system further comprises a communication component 803. The processor 801, the memory 802, and the communication unit 803 are connected by a bus 804.
In a specific implementation, the at least one processor 801 executes the computer executable instructions stored in the memory 802, so that the at least one processor 801 executes the optimization method of the ride order scheduling system as executed by the optimization device 80 of the ride order scheduling system. Specifically, after the host vehicle sends the user to the destination and informs the background server of the arrival at the destination, the processor 801 of the optimization device 80 may predict the staying time of the user in the order evaluation interface according to the order characteristics of the current riding order through the staying time model, and obtain the predicted staying time of the user in the order evaluation interface, and if the obtained predicted staying time of the user is greater than a preset threshold, it indicates that the user has a tendency to seriously evaluate the order, the order evaluation interface is pushed to the user, so that the user inputs evaluation information about the completion condition of the current order in the order evaluation interface.
When some of the steps of this embodiment are performed by the server, the communication component 803 may send relevant data to the server, for example, if the obtaining of the predicted parking time needs to be performed by the server, the order characteristics of the ride order or the ride order may be sent to the server through the communication component 803.
For a specific implementation process of the processor 801, reference may be made to the above method embodiments, which have similar implementation principles and technical effects, and details of this embodiment are not described herein again.
In the embodiment shown in fig. 8, it should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose processors, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.
The memory may comprise high speed RAM memory and may also include non-volatile storage NVM, such as at least one disk memory.
The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present application are not limited to only one bus or one type of bus.
The application also provides a computer-readable storage medium, wherein computer-executable instructions are stored in the computer-readable storage medium, and when a processor executes the computer-executable instructions, the optimization method of the bus taking order dispatching system, which is executed by the optimization equipment of the bus taking order dispatching system, is realized.
The application also provides a computer-readable storage medium, wherein computer-executable instructions are stored in the computer-readable storage medium, and when a processor executes the computer-executable instructions, the optimization method of the bus taking order dispatching system, which is executed by the optimization equipment of the bus taking order dispatching system, is realized.
The computer-readable storage medium may be implemented by any type of volatile or non-volatile memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk. Readable storage media can be any available media that can be accessed by a general purpose or special purpose computer.
An exemplary readable storage medium is coupled to the processor such the processor can read information from, and write information to, the readable storage medium. Of course, the readable storage medium may also be an integral part of the processor. The processor and the readable storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the readable storage medium may also reside as discrete components in the apparatus.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for optimizing a bus order dispatching system is characterized by comprising the following steps:
obtaining order features of a riding order of a user;
inputting the order features into a stay time model to obtain the predicted stay time of the user in an order evaluation interface;
if the predicted retention time is larger than a preset threshold value, pushing the order evaluation interface to the user;
and receiving evaluation information input by the user in the order evaluation interface, and optimizing a scheduling system according to the evaluation information.
2. The method of claim 1, wherein the order characteristics comprise at least one of: ordering time, departure time, peak hours of the location, weather conditions, riding time and travel distance.
3. The method of claim 2, wherein prior to entering the order characteristics into a dwell time model, further comprising:
obtaining user characteristics of the user, wherein the user characteristics comprise at least one of the following: route preference, travel time preference and accumulated order placing times;
the inputting the order characteristics into a dwell time model comprises:
inputting the order characteristics and the user characteristics to the dwell time model.
4. The method of claim 1, wherein before pushing the order evaluation interface to the user, further comprising:
inputting the riding order into a dispatching scoring model to obtain a predicted dispatching score;
the pushing the order evaluation interface to the user includes:
and if the predicted order dispatching score is lower than a preset score, pushing the order evaluation interface to the user.
5. The method according to any one of claims 1 to 4,
the order evaluation interface comprises: a text input box for the user to input information and an item box to be checked for the user to select the evaluation result.
6. The method of any of claims 1-4, wherein prior to entering the order characteristics into the dwell time model, further comprising:
the method comprises the steps of obtaining order features of a plurality of orders to be trained and labels corresponding to the order features of the orders to be trained; the label is used for indicating the stay time of a user corresponding to the order to be trained in the corresponding order evaluation interface;
and training the retention time model to be trained according to the order features of the orders to be trained and the labels corresponding to the order features of the orders to be trained to obtain the trained retention time model.
7. The method of any one of claims 1-4, wherein the residence time model is a regression model or a neural network model.
8. An optimization device for a ride order scheduling system, comprising:
the obtaining module is used for obtaining the order characteristics of the riding order of the user;
the input module is used for inputting the order characteristics into a stay time model to obtain the predicted stay time of the user in an order evaluation interface;
the pushing module is used for pushing the order evaluation interface to the user if the predicted retention time is larger than a preset threshold value;
and the receiving module is used for receiving the evaluation information input by the user in the order evaluation interface and optimizing the scheduling system according to the evaluation information.
9. An optimization device for a ride order scheduling system, comprising: at least one processor and memory;
the memory stores computer-executable instructions;
the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform a method of optimizing a ride order scheduling system according to any of claims 1 to 7.
10. A computer readable storage medium having computer executable instructions stored thereon which, when executed by a processor, implement a method of optimizing a ride order scheduling system according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010333881.4A CN111598307A (en) | 2020-04-24 | 2020-04-24 | Optimization method and equipment of bus taking order scheduling system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010333881.4A CN111598307A (en) | 2020-04-24 | 2020-04-24 | Optimization method and equipment of bus taking order scheduling system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111598307A true CN111598307A (en) | 2020-08-28 |
Family
ID=72190571
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010333881.4A Pending CN111598307A (en) | 2020-04-24 | 2020-04-24 | Optimization method and equipment of bus taking order scheduling system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111598307A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112581146A (en) * | 2020-12-24 | 2021-03-30 | 北京嘀嘀无限科技发展有限公司 | Feedback method of travel problems, user request terminal and service evaluation feedback system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140136458A1 (en) * | 2011-05-17 | 2014-05-15 | The John Hopkins University | Hospital unit demand forecasting tool |
| CN105489001A (en) * | 2015-12-11 | 2016-04-13 | 惠州Tcl移动通信有限公司 | Taxi scheduling optimization method and system |
| CN107093120A (en) * | 2016-09-28 | 2017-08-25 | 北京小度信息科技有限公司 | Service strategy method for pushing and device |
| CN107918884A (en) * | 2017-11-21 | 2018-04-17 | 上海亿动信息技术有限公司 | A kind of control method, apparatus and system that advertisement pushing is realized based on user behavior |
| CN110209794A (en) * | 2018-02-12 | 2019-09-06 | 北京嘀嘀无限科技发展有限公司 | Processing method, device and the storage medium of evaluation information |
| CN110363551A (en) * | 2018-04-02 | 2019-10-22 | 北京嘀嘀无限科技发展有限公司 | A kind of method, system and computer equipment for predicting user satisfaction |
| CN110910180A (en) * | 2019-12-02 | 2020-03-24 | 北京嘀嘀无限科技发展有限公司 | Information pushing method and device, electronic equipment and storage medium |
-
2020
- 2020-04-24 CN CN202010333881.4A patent/CN111598307A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140136458A1 (en) * | 2011-05-17 | 2014-05-15 | The John Hopkins University | Hospital unit demand forecasting tool |
| CN105489001A (en) * | 2015-12-11 | 2016-04-13 | 惠州Tcl移动通信有限公司 | Taxi scheduling optimization method and system |
| CN107093120A (en) * | 2016-09-28 | 2017-08-25 | 北京小度信息科技有限公司 | Service strategy method for pushing and device |
| CN107918884A (en) * | 2017-11-21 | 2018-04-17 | 上海亿动信息技术有限公司 | A kind of control method, apparatus and system that advertisement pushing is realized based on user behavior |
| CN110209794A (en) * | 2018-02-12 | 2019-09-06 | 北京嘀嘀无限科技发展有限公司 | Processing method, device and the storage medium of evaluation information |
| CN110363551A (en) * | 2018-04-02 | 2019-10-22 | 北京嘀嘀无限科技发展有限公司 | A kind of method, system and computer equipment for predicting user satisfaction |
| CN110910180A (en) * | 2019-12-02 | 2020-03-24 | 北京嘀嘀无限科技发展有限公司 | Information pushing method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 刘译文: "基于分布式计算智能的城市出租车最优化调度算法" * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112581146A (en) * | 2020-12-24 | 2021-03-30 | 北京嘀嘀无限科技发展有限公司 | Feedback method of travel problems, user request terminal and service evaluation feedback system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12012109B2 (en) | System and methods for determining owner's preferences based on vehicle owners telematics data | |
| US20170262770A1 (en) | Cascaded boosted predictive models | |
| CN110826006B (en) | Abnormal collection behavior identification method and device based on privacy data protection | |
| US11836748B2 (en) | System and methods for predicting rental vehicle use preferences | |
| CN112884224A (en) | Method and device for selecting address of entity object, computing equipment and computer storage medium | |
| CN112509317B (en) | Bus real-time arrival prediction method, device and equipment based on machine learning algorithm | |
| EP3262831A1 (en) | Telephone call placement | |
| CN111582605A (en) | Method and device for predicting destination site, electronic equipment and storage medium | |
| CN112488806A (en) | Method and device for predicting order willingness, computer equipment and computer-readable storage medium | |
| CN111353094A (en) | Information pushing method and device | |
| CN110363611B (en) | Network appointment vehicle user matching method, device, server and storage medium | |
| CN111652639A (en) | Service recommendation method and system | |
| CN111832872A (en) | Vehicle scheduling method and device, electronic equipment and storage medium | |
| CN111598307A (en) | Optimization method and equipment of bus taking order scheduling system | |
| CN111754261B (en) | Method and device for evaluating taxi willingness and terminal equipment | |
| CN112989188A (en) | Determination method and device of recommended order and server | |
| CN112559858A (en) | Service information pushing method and device, computer readable medium and electronic equipment | |
| CN112488430A (en) | Modeling method and device for predicting order cancellation, computer equipment and computer readable storage medium | |
| CN114743384B (en) | Alarm method and device | |
| CN111327661A (en) | Pushing method, pushing device, server and computer readable storage medium | |
| CN111835730B (en) | Service account processing method and device, electronic equipment and readable storage medium | |
| CN115662400A (en) | Processing method, device and equipment for voice interaction data of vehicle machine and storage medium | |
| CN111833595B (en) | Shared automobile auxiliary vehicle configuration method, electronic device and storage medium | |
| CN111695919B (en) | Evaluation data processing method, device, electronic equipment and storage medium | |
| CN111507753A (en) | Information pushing method and device and electronic equipment |
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 |