Route recommendation method and device

Abstract

The embodiment of the invention discloses a route recommendation method and device. According to the embodiment of the invention, a plurality of alternative routes are generated according to the information of a plurality of riding orders obtained by matching, then the route popularity characteristic value and the bus lane characteristic value of each alternative route are determined, and one of the alternative routes is recommended as the target route based on the route popularity characteristic value and the bus lane characteristic value. Since the characteristics of the bus lane are taken into consideration of route recommendation, the route recommendation of the online booking bus service operated by using a small bus or a large bus and the like is more adaptive to scene requirements, the accuracy of the optimal route can be improved, and the operation cost can be reduced.

Description

Technical Field

[0001] The present invention relates to the field of data recommendation, and in particular to a route recommendation method, device, electronic device and storage medium. Background Art

[0002] In urban areas, online car-hailing and carpooling services are developing rapidly. At the same time, users expect relevant travel service providers to provide services at lower prices. More and more passengers expect to enjoy a travel service similar to a bus, with several stops along the way, but with more flexible routes and stops. Under this travel service model, how to reasonably plan the driving routes for vehicles with more than 7 seats involved in the operation is a problem that needs to be solved. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides a route recommendation method, device, electronic device and storage medium, thereby improving the accuracy of recommending the optimal route and reducing operating costs.

[0004] In a first aspect, an embodiment of the present invention provides a route recommendation method, the method comprising:

[0005] Determine a plurality of ride orders according to an order set, wherein the order set includes a plurality of ride requests;

[0006] generating a predetermined number of alternative routes based on multiple ride orders;

[0007] Determine a route heat characteristic value and a bus lane characteristic value of each alternative route, wherein the route heat characteristic value is used to characterize the number of historical orders covered by the alternative route, and the bus lane characteristic value is used to characterize the proportion of bus lanes in the alternative route;

[0008] Determine a first score for each candidate route according to the route heat characteristic value and the bus lane characteristic value;

[0009] The first alternative route with the highest score is determined as the target route.

[0010] In a second aspect, an embodiment of the present invention provides a route recommendation device, the device comprising:

[0011] An order determination unit, configured to determine a plurality of ride orders according to an order set, wherein the order set includes a plurality of ride requests;

[0012] an alternative route determination unit, configured to generate a predetermined number of alternative routes according to a plurality of ride orders;

[0013] A characteristic value determination unit, used to determine a route heat characteristic value and a bus lane characteristic value of each alternative route, wherein the route heat characteristic value is used to characterize the number of historical orders covered by the alternative route, and the bus lane characteristic value is used to characterize the proportion of bus lanes in the alternative route;

[0014] A first score determination unit, configured to determine a first score for each candidate route according to the route heat characteristic value and the bus lane characteristic value;

[0015] The target route determination unit is used to determine the candidate route with the highest first score as the target route.

[0016] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer program instructions, wherein the computer program instructions implement the method described in the first aspect when executed by a processor.

[0017] In a fourth aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method described in the first aspect.

[0018] The technical solution of the embodiment of the present invention generates multiple alternative routes based on the information of multiple ride orders obtained by matching, and then determines the route heat characteristic value and the bus lane characteristic value of each alternative route, and recommends one of the alternative routes as the target route based on the route heat characteristic value and the bus lane characteristic value. Since the bus lane characteristics are taken into consideration in the route recommendation, the route recommendation of the online bus-hailing business that uses larger vehicles such as minibuses or buses is more adapted to the scenario requirements, which can improve the accuracy of the optimal route and reduce operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0020] Figure 1 It is a system block diagram of the online bus booking service system according to an embodiment of the present invention.

[0021] Figure 2 is a flow chart of a route recommendation method according to an embodiment of the present invention;

[0022] Figure 3 is a schematic diagram of an online bus booking route according to an embodiment of the present invention;

[0023] Figure 4 is a schematic diagram of a U-turn of an online-booked bus in an embodiment of the present invention;

[0024] Figure 5 is a schematic diagram of another U-turn situation of an online-booked bus in an embodiment of the present invention;

[0025] Figure 6 is a flow chart of determining a predetermined number of alternative routes according to an embodiment of the present invention;

[0026] Figure 7 is a flowchart of determining a set of optional routes according to an embodiment of the present invention;

[0027] Figure 8 is a schematic diagram of a route recommendation device according to an embodiment of the present invention;

[0028] Fig. 9 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The present application is described below based on embodiments, but the present application is not limited to these embodiments. In the detailed description of the present application below, some specific details are described in detail. It is possible for those skilled in the art to fully understand the present application without the description of these details. In order to avoid confusing the essence of the present application, known methods, processes, flows, components and circuits are not described in detail.

[0030] In addition, persons of ordinary skill in the art will appreciate that the drawings provided herein are for illustration purposes and are not necessarily drawn to scale.

[0031] Unless the context clearly requires otherwise, the words "include", "comprising" and similar words throughout the application should be interpreted as including rather than exclusive or exhaustive; that is, the meaning is "including but not limited to".

[0032] In the description of this application, it should be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of this application, unless otherwise specified, the meaning of "plurality" is two or more.

[0033] Figure 1 is a system block diagram of the online bus booking service system according to an embodiment of the present invention. Figure 1 As shown, the online bus booking service system of this embodiment includes a server 1, a passenger terminal 2, and a driver terminal 3. The server 1, the passenger terminal 2, and the driver terminal 3 are connected to each other through a network 4 to achieve information and data interaction. It should be understood that although Figure 1 Only a certain number of servers 1, passenger terminals 2 and driver terminals 3 are shown, but this does not mean that their respective numbers are limited. The system can include multiple servers, passenger terminals and driver terminals.

[0034] Server 1 should be understood as a device that provides data processing, database, and communication facilities. For example, server 1 may refer to a single physical server with related communication and data storage and database facilities, or may refer to a collection of networked or clustered processors, related networks, and storage devices, and operates software and one or more database systems and application software that supports the services provided by the server. Server 1 can be a monolithic server or a distributed server across multiple computers or computer data centers, or it can be various types of cloud servers. In some embodiments, each server may include hardware, software, or an embedded logic component or a combination of two or more such components for performing appropriate functions supported or implemented by the server.

[0035] The passenger terminal 2 and the driver terminal 3 are communication terminals capable of running computer programs. These communication terminals may be terminal devices such as mobile phones, tablet computers, PDAs, wearable devices, and vehicle-mounted terminals integrated with vehicles. Both the passenger terminal 2 and the driver terminal 3 have a communication module, which is capable of wired or wireless communication. In some embodiments, the passenger terminal 2 and the driver terminal 3 include at least one remote communication module, such as a communication circuit for WLAN, GPRS, 2G / 3G / 4G / 5G remote communication. The passenger terminal 2 and the driver terminal 3 also have a display device and an input device, and the display device may be a liquid crystal display, an LED display, or a projection device. The input device may include, for example, a touch screen, a button, a pressure sensor, etc. The passenger terminal 2 and the driver terminal 3 receive instructions from passengers through the input device, and interact with passengers or drivers through the display device.

[0036] The passenger client 21 can be run on the passenger terminal 2. The driver client 31 can be run on the driver terminal 3. At the same time, the server 1 runs the server application 11. The server 1, the passenger terminal 2 and the driver terminal 3 can communicate through the network 4. In some application scenarios, the passenger can issue a ride request by operating the passenger client 21. The server 1 receives the ride request and matches a suitable driver terminal 3 based on, for example, the location information reported by the driver terminal 3 and the location information of the ride request, and then sends the ride request to one or more matching driver terminals 3. Then, a ride order can be generated.

[0037] The online bus of this embodiment is different from the existing online car-hailing business. The existing online car-hailing business usually does not set up fixed stations, but the online car-hailing cruises in a certain area of ​​the city. The server 1 matches the corresponding ride request according to the location of the online car-hailing, and forms a ride order to send the boarding location selected by the passenger to the driver end. The driver end picks up and drops off passengers at the boarding point and drop-off point selected by the passenger according to the requirements of the ride task. In the process of carrying out this business, the boarding point and the drop-off point are selected by the passenger through the passenger client, and can be any location that the online car-hailing can reach. Such a service provides the same flexible and personalized service as a taxi, and passengers can enjoy door-to-door travel services. However, this type of online car-hailing service is the same as a taxi, and the price is relatively high. In order to reduce the price, a carpooling service has emerged, that is, multiple passengers who do not know each other send carpooling service requests to the server, and the server will match these carpooling service requests, and form a carpooling service task with multiple carpooling service requests along the way to assign it to a specific driver end of an online car-hailing vehicle. The driver end picks up and drops off multiple passengers to different locations in sequence according to the carpooling service task. Carpooling services have significantly reduced service prices and improved vehicle utilization efficiency. However, the selection and determination of the boarding and alighting locations in carpooling services are the same as those in online car-hailing services, and are still selected by the passengers. When passengers choose the boarding location, online car-hailing platforms only recommend several locations with a high number of boarding or alighting times in the area to assist passengers in making their choices.

[0038] However, there is still a demand to further reduce travel prices, as well as a demand to enjoy more flexible and convenient travel services than existing public transportation at a lower price. Based on the above needs, online bus services have emerged. Online buses have the concept of fixed stations and integrate the logic of existing carpooling services. However, it is different from the existing bus business. The existing bus business is based on different bus routes, and each route operates based on a completely unchanged driving route. On the one hand, the online bus business forms a ride order based on the user's ride request, inheriting the mechanism of online car-hailing and carpooling businesses initiated online based on user requests. On the other hand, the online bus business limits the boarding and alighting locations to fixed stations as much as possible. The advantage of setting fixed stations is that there is a greater probability of picking up and dropping off multiple passengers at a time at fixed stations, which improves efficiency. At the same time, in the case of setting fixed stations, passengers can not only initiate requests online, but also directly initiate ride requests by scanning codes at fixed stations. At the same time, the online bus service still has a high degree of flexibility. The server can match ride orders based on the location of the passenger who initiated the request and the location of the driver of the online bus with a logic similar to carpooling. Moreover, online-hailing buses do not run on fixed routes throughout the day and at all times, but instead run around areas covered by multiple different stations in urban areas, retaining the flexibility of online-hailing cars and taxis. Moreover, in certain modes, the routes of online-hailing buses can change dynamically during driving, which is highly intelligent and can meet the travel needs of passengers with extremely high efficiency.

[0039] exist Figure 1 In the online bus booking service system shown, in a typical example, the passenger terminal 2 can initiate a ride request to the server 1 through the passenger client 21, and the ride request can contain the boarding station and the alighting station (both fixed stations) selected by the passenger. The server 1 can match and send the corresponding ride task according to the driver terminal 3 of the online bus running around the boarding station to the vicinity of the alighting station, and form a ride order. The driver terminal 3 guides the online bus to the boarding station through the driver client 31, and passes through multiple fixed stations along the predetermined driving route to send the passengers to the alighting station. In this process, the driver terminal 3 of the online bus is still in the order-taking state, and can continuously match new ride requests, and pick up passengers at the corresponding boarding station and send them to the alighting station. The server 1 can plan the route of the online bus in real time according to the actual distribution of the received ride requests, so that the online bus runs between different stations to pick up passengers according to the planned route.

[0040] In the online-hailing bus business system, when assigning ride tasks to an empty online-hailing bus, a group of ride orders obtained through matching are usually assigned to the online-hailing bus, and a route is planned for the online-hailing bus to complete this group of ride orders. When the online-hailing bus is a larger vehicle, how to adapt to this business model and dynamically recommend a suitable route passing through several stations for the vehicle becomes a problem that needs to be solved.

[0041] Figure 2 FIG. 1 is a flow chart of a route recommendation method according to an embodiment of the present invention, wherein the route recommendation method is applied to a server. Figure 2 As shown, the route recommendation method includes the following steps:

[0042] Step S100: determine a plurality of ride orders according to an order set, wherein the order set includes a plurality of ride requests.

[0043] The order set is the ride order sent by the passenger terminal and received by the server. In this step, multiple ride orders are determined in the order set, and the ride orders can be matched by using a pre-trained order matching model. Specifically, the split order matching model is trained to match orders based on the standard of avoiding U-turn routes as much as possible. This is because the fewer U-turn routes, the higher the safety and stability of the online bus driving, and it can save time.

[0044] Specifically, the passenger initiates a ride request in the passenger terminal, wherein the ride request includes user information and ride information. The user information may be the user ID of the passenger. The ride information may include starting point information and end point information. The passenger terminal is a terminal device held by the passenger.

[0045] It should be noted that in actual application scenarios, in addition to matching multiple ride orders before departure, similar to online car-hailing, during the travel of the online bus, the server can also assign newly received orders to the online bus. After determining to assign a new order to the online bus, the multiple ride orders need to add new orders on the basis of the original ones. At this time, due to changes in the route, it may be necessary to make new route recommendations.

[0046] It should be noted that when the distance between the driver and the passenger is relatively close, for example, when the passenger is within the preset range of the driver, the order should be avoided from being assigned to the online-hailing bus to avoid traffic accidents caused by sudden braking.

[0047] Step S200: Generate a predetermined number of alternative routes based on multiple ride orders.

[0048] After multiple ride orders are determined, alternative routes need to be generated based on these ride orders, and the alternative routes are routes that pass through the starting points or end points of these ride orders. For each alternative route, when the online-booked bus passes through the alternative route, multiple passengers corresponding to multiple ride orders can get on the bus from the starting point and get off at the end point.

[0049] Due to the difference between online-hailing buses and ordinary cars, in the process of generating alternative routes, it is necessary to consider the impassable sections of online-hailing buses, and generate alternative routes after removing these impassable sections. Since the size of online-hailing buses is quite different from that of small passenger cars with less than seven seats, there are some sections with relatively low height and width limits that online-hailing buses cannot pass. In addition, due to the influence of traffic regulations, there will also be some routes that online-hailing buses cannot pass, such as small passenger car lanes. Therefore, in the scenario of online-hailing buses, in the process of generating alternative routes, you can first remove these impassable sections from all routes in the road network, generate alternative routes on the remaining sections, or remove routes with impassable sections after generating routes.

[0050] Figure 3 Schematic diagram of online bus route planning according to an embodiment of the present invention. Figure 3 As shown, the route includes multiple stations A, B, C, and D. It should be noted that the stations can be bus stops or stations suitable for online bus operations that are mined through driving data analysis of online bus services. It should be understood that there are multiple routes between different stations, and the embodiment of the present invention only schematically shows two routes between two stations. In this embodiment, a road section refers to a basic component unit in a road network, that is, a road section between two nodes (intersections or intersections). Each road section can represent a specific road entity such as a street, a part of a highway, a bridge, a tunnel, etc. Each road section has its own attributes. When planning a route, the route from one location to another can be determined based on the attributes of the road section. Specifically, Figure 3As shown, it should be noted that the dotted lines and solid lines in the figure both represent road sections, and the use of different forms of lines is only to distinguish different road sections in the same route. Specifically, there are two routes 31 and 32 between station A and station B, wherein route 31 includes road section 31a and road section 31b, and route 32 includes road section 32a and road section 32b. There are two routes 33 and 34 between station B and station C, wherein route 33 includes road section 33a and road section 33b, and route 34 includes road section 34a, road section 34b and road section 34c. There are two routes 37 and 38 between station C and station D, wherein route 37 includes road section 37a, road section 37b and road section 37c, and route 38 includes road section 38a, road section 38b and road section 38c. There are two routes 35 and 36 between station A and station D, wherein route 35 includes road section 35a and road section 35b, and route 36 includes road section 36a and road section 36b. For example, when the starting point is station A and the end point is station C, an optional route may be composed of the following road sections: road section 32a, road section 32b, road section 33a, and road section 33b.

[0051] Specifically, when generating alternative routes, it is necessary to minimize at least one of the number of U-turn routes, the estimated route time or the route length, and generate a predetermined number of alternative routes passing through the starting point and end point of each ride order based on the set of impassable road sections and the multiple ride orders.

[0052] Figure 4 is a schematic diagram of a U-turn of an online-booked bus in an embodiment of the present invention, such as Figure 4 As shown, the online-hailing bus needs to make a U-turn on the road section. Since the length of the online-hailing bus is relatively long, a U-turn cannot be achieved on this road section. In other words, although the relevant road section can be used for the online-hailing bus to pass through, it cannot be used for the online-hailing bus to make a U-turn. If the route includes such a road section and a U-turn route is planned at the location of the road section, it may result in the inability to drive according to the route or a lot of time will be spent on U-turning.

[0053] Therefore, for an online-hailing bus with a fixed length and width, the minimum width required for its U-turn is fixed, and the wider the road section when making a U-turn, the safer the U-turn is.

[0054] Figure 5 is a schematic diagram of another U-turn situation of an online-booked bus in an embodiment of the present invention. Figure 5 The road segments shown are compared to Figure 4 The road section is relatively wide, so the online-hailing bus can make a U-turn on this road section. Therefore, the route including the U-turn can be used as an alternative route. Figure 4 The route with a U-turn as shown is not an alternative route.

[0055] Figure 6 is a flow chart of determining a predetermined number of alternative routes according to an embodiment of the present invention, such as Figure 6 As shown, the step of determining a predetermined number of alternative routes includes the following steps:

[0056] Step S210: Generate a set of optional routes consisting of optional routes that pass through the starting point and end point of each ride order and do not include the impassable road sections in the impassable road section set.

[0057] In an optional implementation, after the impassable road sections are determined, the road sections in the impassable road section set are removed from the total road section set composed of all road sections, and the resulting road section set is the impassable road section set. It should be noted that since online-hailing buses can travel on bus lanes compared to ordinary cars, bus lanes need to be added when determining the set composed of all road sections.

[0058] After determining the set of passable road sections, a set of optional routes passing through the starting point and the end point of each ride order is generated according to the set of passable road sections. Specifically, the optional routes can be obtained by a pre-trained route generation model, wherein the route generation model is pre-trained to generate routes without impassable road sections and / or without U-turn widths that do not meet predetermined requirements.

[0059] In addition to directly obtaining routes that meet the predetermined requirements through the pre-trained route generation model, you can also generate all routes first, and then filter out routes that meet the requirements from all routes. Figure 7 As shown, Figure 7 is a flowchart of determining a set of optional routes according to an embodiment of the present invention, wherein determining the optional routes may include the following steps:

[0060] Step S211: Generate an initial set of optional routes, wherein the initial set of optional routes includes initial optional routes passing through the starting point and the end point of each ride order.

[0061] Specifically, all initial optional routes including the starting point and the end point of each ride order are generated. It should be noted that in the initial optional routes, it must be ensured that for any ride order, the end point is after the starting point.

[0062] Step S212: Remove routes with impassable sections and / or routes with U-turns and whose road widths at U-turn locations do not meet predetermined requirements from the initial set of optional routes to determine the set of optional routes.

[0063] Specifically, after all the initial optional routes are determined, the routes that do not meet the requirements need to be removed from the initial optional routes. In the embodiment of the present invention, when the initial optional routes include impassable sections or routes whose U-turn widths do not meet the predetermined requirements, they need to be removed. Figure 3 Take the route shown as an example for explanation. If a certain optional route includes route 33, and section 33a in route 33 is an impassable section, then the initial optional route is removed from the initial optional route set. If a certain initial optional route needs to make a U-turn at a certain position of section 36a in route 36, and the width of section 36a at the U-turn is less than the minimum width required for the online bus to make a U-turn, then the initial optional route is removed from the initial optional route set.

[0064] Through step S211 and step S212, the optional routes are obtained, so as to reduce the sample size and facilitate the subsequent calculation of the second score.

[0065] Step S220: Determine a second score for each optional route in the optional route set.

[0066] The second score is determined according to at least one of the number of U-turn routes, the estimated route time, or the route length. Specifically, the fewer the number of U-turn routes of the optional route, the shorter the estimated route time, the shorter the route length, the higher the driving efficiency in the route, and the higher the second score of the optional route.

[0067] In an optional implementation, the second score is determined according to the number of U-turn routes, and a deduction system with a full score of 100 points and a lower limit of 0 points is used for explanation. For each U-turn route, the first predetermined score is deducted. In an optional implementation, the first predetermined score is 10 points. For example, when there are 5 U-turn routes on a certain route, 50 points are deducted from the second score, and the second score is 50 points. It should be noted that the deduction value of the U-turn route may not be a fixed value, and may be specifically determined according to the width of the road section where the U-turn route is located. When the width of the road section is wider, the deducted score may be reduced accordingly.

[0068] In an optional implementation, the second score is determined based on the estimated time of the route. The longer the estimated time of the route, the lower the second score. In an optional implementation, when the estimated time of the route is less than the standard time, or the difference with the standard time is within a predetermined time period, the second score is 100 points, and the second predetermined score is deducted for each predetermined time period that the estimated time of the route exceeds the standard time. It should be noted that since the number and content of the orders are different, the standard time needs to be determined according to the actual situation. In an optional implementation, the estimated time of the shortest optional route among the optional routes is used as the standard time. The following is an example of a predetermined time period of 5 minutes and a second predetermined score of 5 points. When the estimated time of the route is 62 minutes, since the difference between the estimated time of the route and the standard time is within 5 minutes, the second score of the route is 100 points. When the estimated time of the route is 92 minutes, since it exceeds the standard time by 6 predetermined time periods, 30 points are deducted, and the second score is 70 points. In addition, the second score can also be determined based on the correspondence between the preset route estimated time and the second score. For example, when the route estimated time is less than 40 minutes, the second score is 100 points, when the route estimated time is 40-60 minutes, the second score is 80 points, when the route estimated time is 60-90 minutes, the second score is 70 points, and when the route estimated time is more than 90 minutes, the second score is 50 points. Therefore, after determining the route estimated time of the optional route, the second score of the optional route is determined according to the interval in which the route estimated time is located. For example, when the route estimated time is 75 minutes, the second score is determined to be 70 points.

[0069] In an optional implementation, the second score is determined based on the length of the route. The longer the route length, the lower the second score. In an optional implementation, similar to the estimated route time, when the route length is less than the standard length, or the difference with the standard length is within a predetermined distance, the second score is 100 points, and the third predetermined score is deducted for each predetermined distance that the route length exceeds the standard time. It should be noted that due to the different number and content of orders, the standard length needs to be determined based on actual conditions. For example, the length of the shortest optional route among the optional routes is used as the standard length. Take the standard length of 3km, the predetermined distance of 200m, and the third predetermined score of 5 points as an example. When the route length is 3.7km, 15 points are deducted because it exceeds the standard length by three predetermined distances, and the second score is 85 points.

[0070] In an optional implementation, the second score is determined according to at least two criteria, and the optional routes are deducted according to the two criteria, and the final score is used as the target score. For example, the second score is determined according to the number of U-turn routes and the route length. When the first predetermined score is 10 points, the third predetermined score is 5 points, the number of U-turn routes is 2, the predetermined distance is 200m, the standard length is 2km, and the standard route length is 2.5km, 20 points need to be deducted according to the number of U-turn routes, and 10 points need to be deducted according to the standard route length, so the second score of the optional route is 70 points.

[0071] It should be noted that when the second score is determined according to at least two criteria, the degree of deduction for each criterion needs to be adjusted accordingly according to the impact on actual traffic. For example, if the U-turn route has a greater impact on actual traffic, when the second score is determined according to the number of U-turn routes, the estimated route time and the route length, the first predetermined score is set higher, for example, the first predetermined score is set to 25 points, and the second predetermined score and the third predetermined score are set to 5 points, so as to increase the impact of the number of U-turn routes.

[0072] In addition, when the second score is determined based on at least two criteria, it is also possible to score each criterion separately, and use the lowest score / highest score as the final second score. For example, if the lowest score is used as the final second score, the score based on the number of U-turn routes is 80 points, and the score based on the estimated route time is 75 points, then the second score is determined to be 75 points. In this way, the characteristics of the route can be more clearly highlighted from the score.

[0073] In addition to the preset scoring criteria, the second score can also be determined by a pre-trained second score determination model. Specifically, the second score determination model is trained to have the ability to score based on at least one of the number of U-turn routes, the estimated route time, and the route length. In an optional implementation, the second score determination model is trained using the historical routes that the online-hailing bus has traveled as samples, and the sample is specifically the frequency of the historical route being adopted, and the frequency of being adopted is specifically the frequency of being screened as an alternative route when the route appears in the optional route, and the label is the number of U-turn routes, the estimated route time, and the route length. Scoring through the second score determination model can perform preliminary screening among a relatively large number of optional routes to reduce the amount of calculation for the subsequent first score.

[0074] Step S230: Determine a predetermined number of optional routes with the second highest scores in the optional route set as the alternative routes.

[0075] Specifically, after determining the second score of each optional route in the optional route set, it is necessary to select a predetermined number of optional routes with high second scores from each optional route as alternative routes, so as to subsequently select the best route from each alternative route. For example, the optional route set includes 10 optional routes, whose second scores are 95, 90, 85, 80, 80, 75, 60, 50, 20, and 20, respectively. Assuming that the predetermined number is 3, the alternative routes are routes with second scores of 95, 90, and 85.

[0076] It should be noted that in the embodiment of the present invention, it is not necessary to strictly screen the alternative routes with high second scores according to the predetermined number. In an optional implementation method, some routes with too low scores can be screened out by setting a benchmark. For example, the scores of the 10 optional routes are 95, 80, 75, 50, 40, 45, 30, 20, 20, and 10 respectively. Assuming that the predetermined number is 5, the alternative routes are 95, 80, 75, 50, and 40 with second scores. However, the scores of the routes with scores of 50 and 40 are too low and the quality is relatively poor. Therefore, these two routes can be screened out by setting a benchmark with a second score of at least 60 points. The benchmark is set according to the actual situation. In this way, some routes with poor traffic quality can be screened out to reduce the calculation amount of the subsequent route heat characteristic value and the bus lane characteristic value.

[0077] Through steps S210 to S230, the acquisition of alternative routes with higher second scores corresponding to multiple ride orders is determined, thereby reducing the number of routes that need to be calculated subsequently, and further facilitating the calculation of the first score.

[0078] Step S300: determine the route heat characteristic value and bus lane characteristic value of each alternative route, wherein the route heat characteristic value is used to characterize the number of historical orders covered by the alternative route, and the bus lane characteristic value is used to characterize the proportion of bus lanes in the alternative route.

[0079] The route heat characteristic value is used to characterize the number of historical orders covered by the alternative route. Specifically, when all or part of the alternative route covers the travel path of a historical order, the route heat characteristic value of the alternative route will increase. It can be concluded that the higher the route heat characteristic value of an alternative route, the more times the stations in the alternative route have been used in history, indicating that the route may be more suitable for adoption.

[0080] It should be noted that the historical orders covered by the alternative route may be the same historical orders as the alternative route, or may be historical orders included in the alternative route, that is, the route corresponding to the historical order may be a sub-route of the alternative route. Figure 3Take the route shown as an example. If the routes corresponding to the historical order include route 31 and route 34, and the alternative routes include route 31, route 34 and route 37, then the historical order will increase the popularity of the alternative routes. If the historical order and the alternative routes have overlapping parts, the historical order will also increase the popularity of the alternative routes. For example, the routes corresponding to the historical order include route 31, route 34 and route 37, and the alternative routes include route 34, route 37 and route 35, the historical order will also increase the popularity of the alternative routes.

[0081] Specifically, the route heat can be calculated based on the overlap between historical orders and alternative routes. In an optional implementation, the heat of the alternative route is increased based on the proportion of the overlap between historical orders and alternative routes to the alternative route. For example, if the overlap between a historical order accounts for 30% of the alternative route and the heat added to the alternative route by the historical order that is the same as the alternative route is 100, then the heat added to the alternative route by the historical order is 30.

[0082] The bus lane characteristic value is used to characterize the proportion of bus lanes in the alternative route, wherein the higher the proportion of bus lanes, the more suitable the route is for online bus-hailing. In an optional implementation, the bus lane characteristic value is proportional to the proportion of the length of the bus lane. Taking the bus lane characteristic value between 0 and 1 as an example, specifically, when the bus lane characteristic value is 0, it indicates that there is no bus lane in the alternative route, and when the bus lane characteristic value is 1, it indicates that the sections in the alternative route are all bus lanes. When there are both bus lanes and non-bus lanes in the alternative route, the ratio of the length of the bus lane to the length of the alternative route is used as. When the length of the alternative route is 5km and the length of the bus lane is 4km, the bus lane characteristic value is 0.8. In addition to determining the bus lane characteristic value based on the proportion of the length of the bus lane, the bus lane characteristic value can also be determined by the proportion of the travel time of the bus lane in the estimated time.

[0083] Step S400: determining a first score for each candidate route according to the route heat characteristic value and the bus lane characteristic value.

[0084] Specifically, after obtaining a predetermined number of alternative routes through the second scoring screening, these alternative routes need to be further screened using route popularity and bus lanes, two factors that are more relevant to the online bus-hailing business, as screening conditions to obtain a target route that is more suitable for online bus travel.

[0085] After calculating the route heat characteristic value and the bus lane characteristic value, it is necessary to determine a first score based on the route heat characteristic value and the bus lane characteristic value, wherein the first score represents the pros and cons of the alternative route. In some embodiments, the first score is positively correlated with the route heat characteristic value, and the first score is positively correlated with the bus lane characteristic value. That is, the larger the route heat characteristic value and the bus lane characteristic value, the lower the first score.

[0086] In an optional implementation, the first score is obtained by deducting points twice based on the route heat characteristic value and the bus lane. Taking the full score as 100 as an example, the deduction system with a lower limit of 0 points is explained. Specifically, the score is determined based on the relationship between the preset route heat characteristic value / bus lane and the deduction point. For example, when the route heat characteristic value is above 0.8, no points are deducted, when the route heat characteristic value is 0.6-0.8, 10 points are deducted, when the route heat characteristic value is 0.5-0.6, 30 points are deducted, and when the route heat characteristic value is below 0.5, 50 points are deducted; when the bus lane characteristic value is above 0.6, no points are deducted, when the bus lane characteristic value is 0.4-0.6, 10 points are deducted, and when the bus lane characteristic value is below 0.4, 30 points are deducted. At this time, if the route heat characteristic value of an alternative route is 0.7 and the bus lane characteristic value is 0.5, the first score of the alternative route is 80 points.

[0087] In another optional implementation, the first score is obtained by weighted summing the score corresponding to the route heat feature value and the score corresponding to the bus lane feature value. Taking the full score as 100, assume that the weight of the route heat feature value is 0.2 and the weight of the bus lane feature value is 0.8. First, determine the score corresponding to the route heat feature and the score corresponding to the bus lane feature value based on the route heat feature value and the bus lane feature value, and then weight the two scores. For example, the score corresponding to the route heat feature value of an alternative route is 70 points, and the score corresponding to the bus lane feature value is 90 points, then the weighted score is 86 points.

[0088] In another optional implementation, the first score can also be obtained by a pre-trained first score determination model. Specifically, the first score determination model is trained to have the ability to score the route by integrating the bus lane feature value and the route heat feature value. In some embodiments, in addition to the route heat feature and the bus lane feature, the first score can also be affected by the estimated time of the bus lane. Specifically, the estimated time of the alternative route with the bus lane is calculated by the pre-trained time prediction model, and then the first score of each alternative route is determined according to the route heat feature, the lane feature and the estimated time of the lane. Specifically, the longer the estimated time of the lane, the higher the first score. Specifically, since the traffic rules and road conditions of the bus lane are different from those of ordinary sections, for example, the bus lane only allows buses to travel, and does not allow small passenger cars to pass, so the traffic speed of the bus lane is relatively stable. In addition, the speed limit of the bus lane is also different from that of the ordinary lane. Therefore, the driving conditions of the bus lane are completely different from those of the ordinary lane, and the prediction by the ordinary time prediction model is not accurate enough, and it is necessary to predict by the pre-trained time prediction model. The time prediction model is trained to determine the time to pass each road section according to the type of each road section, wherein the type of each road section includes a dedicated lane and a non-dedicated lane.

[0089] Specifically, the time prediction model is trained by using samples with the travel time of the bus lane, where the samples are historical routes and the labels are time. By pre-training the time prediction model to calculate the estimated time, a more accurate prediction of the time can be made.

[0090] The route recommendation method in the embodiment of the present invention involves two scorings. Specifically, all the alternative routes that meet the requirements are preliminarily screened through the second scoring to obtain a predetermined number of alternative routes, and then the best route is selected from the predetermined number of alternative routes based on the first score determined by the bus lane characteristic value and the route heat characteristic value. The purpose of screening through the second score is to perform a preliminary screening first to reduce the amount of calculation when calculating the first score later. By incorporating the bus lane characteristic value into the calculation of the first score, it is because the routes with a high proportion of bus lanes are only used by buses, so they are relatively open, and the road conditions for online-booked buses are better.

[0091] In an optional implementation, a predetermined number of alternative routes corresponding to the second score can be obtained by reusing an existing route scoring model for online car-hailing. After obtaining the alternative routes that meet the predetermined conditions, the bus lane characteristic values ​​and route heat characteristic values ​​are used to further select from the pre-screened predetermined number of alternative routes.

[0092] Step S500: Determine the candidate route with the highest first score as the target route.

[0093] After the first scores of the candidate routes are determined, the candidate route with the highest first score is determined as the target route.

[0094] The embodiment of the present invention generates multiple alternative routes based on the information of multiple ride orders obtained by matching, and then determines the route heat characteristic value and the bus lane characteristic value of each alternative route, and recommends one of the alternative routes as the target route based on the route heat characteristic value and the bus lane characteristic value. Since the bus lane characteristics are taken into consideration in the route recommendation, the route recommendation of the online bus-hailing business that uses larger vehicles such as minibuses or buses is more adapted to the scenario requirements, which can improve the accuracy of the optimal route and reduce operating costs.

[0095] Figure 8 is a schematic diagram of a route recommendation device according to an embodiment of the present invention. Figure 8 As shown, the route recommendation device includes an order determination unit 81, an alternative route determination unit 82, a characteristic value determination unit 83, a first score determination unit 84 and a target route determination unit 85. Among them, the order determination unit 81 is used to determine multiple ride orders according to an order set, and the order set includes multiple ride requests. The alternative route determination unit 82 is used to generate a predetermined number of alternative routes according to multiple ride orders. The characteristic value determination unit 83 is used to determine the route heat characteristic value and the bus lane characteristic value of each alternative route, the route heat value characteristic value is used to characterize the number of historical orders covered by the alternative route, and the bus lane characteristic value is used to characterize the proportion of bus lanes in the alternative route. The first score determination unit 84 is used to determine the first score of each alternative route according to the route heat characteristic value and the bus lane characteristic value. The target route determination unit 85 is used to determine the alternative route with the highest first score as the target route.

[0096] The embodiment of the present invention generates multiple alternative routes based on the information of multiple ride orders obtained by matching, and then determines the route heat characteristic value and the bus lane characteristic value of each alternative route, and recommends one of the alternative routes as the target route based on the route heat characteristic value and the bus lane characteristic value. Since the bus lane characteristics are taken into consideration in the route recommendation, the route recommendation of the online bus-hailing business that uses larger vehicles such as minibuses or buses is more adapted to the scenario requirements, which can improve the accuracy of the optimal route and reduce operating costs.

[0097] Fig. 9 Schematic diagram of an electronic device according to an embodiment of the present invention. Fig. 9 As shown, Fig. 9The electronic device shown is a general data processing device, which includes a general computer hardware structure, which includes at least a processor 91 and a memory 92. The processor 91 and the memory 92 are connected via a bus 93. The memory 92 is suitable for storing instructions or programs executable by the processor 91. The processor 91 can be an independent microprocessor or a collection of one or more microprocessors. Thus, the processor 91 executes the instructions stored in the memory 92, thereby executing the method flow of the embodiment of the present invention as described above to realize the processing of data and the control of other devices. The bus 93 connects the above-mentioned multiple components together, and at the same time connects the above-mentioned components to the display controller 94 and the display device and the input / output (I / O) device 95. The input / output (I / O) device 95 can be a mouse, a keyboard, a modem, a network interface, a touch input device, a somatosensory input device, a printer, and other devices known in the art. Typically, the input / output device 95 is connected to the system via an input / output (I / O) controller 96.

[0098] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, devices (equipment) or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may adopt a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0099] The present application is described with reference to flowcharts of methods, apparatuses (devices) and computer program products according to embodiments of the present application. It should be understood that each process in the flowchart can be implemented by computer program instructions.

[0100] These computer program instructions may be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device that implements the process Figure 1 A function specified in a process or multiple processes.

[0101] These computer program instructions may also be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce the instructions for implementing the process Figure 1 A device that specifies functions in a process or multiple processes.

[0102] Another embodiment of the present invention relates to a non-volatile storage medium for storing a computer-readable program, wherein the computer-readable program is used for a computer to execute part or all of the above method embodiments.

[0103] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by specifying relevant hardware through a program, and the program is stored in a storage medium, including several instructions for a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0104] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A route recommendation method, characterized in that: The method comprises: Determine a plurality of ride orders according to an order set, wherein the order set includes a plurality of ride requests; generating a predetermined number of alternative routes based on multiple ride orders; Determine a route heat characteristic value and a bus lane characteristic value of each alternative route, wherein the route heat characteristic value is used to characterize the number of historical orders covered by the alternative route, and the bus lane characteristic value is used to characterize the proportion of bus lanes in the alternative route; Determine a first score for each candidate route according to the route heat characteristic value and the bus lane characteristic value; The first alternative route with the highest score is determined as the target route.

2. The method according to claim 1, characterized in that Generating a predetermined number of alternative routes according to a plurality of ride orders comprises: Determine an impassable road section set, where the impassable road section set is a road section where buses are not allowed to pass; The alternative route is determined according to the set of impassable road segments and the multiple ride orders.

3. The method according to claim 2, characterized in that Determining the alternative route according to the impassable road segment set and the plurality of ride orders comprises: With the goal of minimizing at least one of the number of U-turn routes, the estimated route time or the route length, a predetermined number of alternative routes passing through the starting point and the end point of each ride order are generated based on the set of impassable road sections and the multiple ride orders.

4. The method according to claim 3, characterized in that With the goal of minimizing at least one of the number of U-turn routes, the estimated route time, or the route length, generating a predetermined number of alternative routes passing through the start points and end points of the plurality of ride orders according to the set of impassable road sections and the plurality of ride orders includes: Generate a set of optional routes consisting of optional routes that pass through the starting point and the end point of each ride order and do not include the impassable road sections in the impassable road section set; Determining a second score for each optional route in the set of optional routes; Determining a predetermined number of optional routes with the second highest scores in the optional route set as the alternative routes; The second score is determined according to at least one of the number of U-turn routes, the estimated route time or the route length.

5. The method according to claim 4, characterized in that The optional route set consisting of optional routes passing through the starting point and the end point of each ride order and not including the impassable road sections in the impassable road section set includes: Generate an initial set of optional routes, wherein the initial set of optional routes includes initial optional routes passing through the starting point and the end point of each ride order; The optional route set is determined by removing routes with impassable road sections and / or routes with U-turns and roads at U-turn locations that do not meet predetermined requirements.

6. The method according to claim 4, characterized in that The optional route set consisting of the optional routes that pass through the starting point and the end point of each ride order and do not include the impassable road sections in the impassable road section set includes: The set of optional routes is determined by a pre-trained route generation model, wherein the route generation model is pre-trained to generate routes without impassable sections and / or without U-turn widths that do not meet predetermined requirements.

7. The method according to claim 5 or 6, characterized in that: The first score of each candidate route is determined according to the route popularity feature and the bus lane feature as follows: Determine the travel time of each alternative route according to a time prediction model, wherein the time prediction model is trained based on historical data with travel time of bus lanes; A first score for each candidate route is determined according to the route popularity feature, the bus lane feature, and the estimated time of the bus lane.

8. The method according to claim 1, characterized in that The first score is positively correlated with the route heat characteristic value, and the first score is positively correlated with the bus lane characteristic value.

9. A route recommendation device, characterized in that: The device comprises: An order determination unit, configured to determine a plurality of ride orders according to an order set, wherein the order set includes a plurality of ride requests; an alternative route determination unit, configured to generate a predetermined number of alternative routes according to a plurality of ride orders; A characteristic value determination unit, used to determine a route heat characteristic value and a bus lane characteristic value of each alternative route, wherein the route heat characteristic value is used to characterize the number of historical orders covered by the alternative route, and the bus lane characteristic value is used to characterize the proportion of bus lanes in the alternative route; A first score determination unit, configured to determine a first score for each candidate route according to the route heat characteristic value and the bus lane characteristic value; The target route determination unit is used to determine the candidate route with the highest first score as the target route.

10. A computer-readable storage medium storing computer program instructions, characterized in that: The computer program instructions implement the method according to any one of claims 1 to 8 when executed by a processor.

11. An electronic device comprising a memory and a processor, characterized in that: The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method according to any one of claims 1 to 8.

Images