Route recommendation information push method, device, computer equipment and storage medium

Abstract

The present application relates to a method, apparatus, computer device, and storage medium for pushing path recommendation information, and relates to the field of navigation technology. The method comprises: determining at least one moving path within a search area containing m sub-region paths; obtaining the estimated tour duration of each of the m sub-regions based on their respective regional characteristics and the user characteristics corresponding to the terminal; obtaining the estimated occupancy time of each of the at least one moving path based on the estimated tour duration of each of the m sub-regions; and pushing path recommendation information to the terminal based on the estimated occupancy time of each of the at least one moving path. Through the above method, the estimated occupancy time of the moving path can be more accurately calculated based on the user characteristics and the regional characteristics of the sub-regions during the process of pushing the path recommendation information, thereby improving the accuracy and flexibility of the path recommendation information push.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of navigation technology, and in particular to a method, apparatus, computer device, and storage medium for pushing route recommendation information. Background Art

[0002] At present, with the increasing demand for travel by people, people need to plan their itineraries before traveling.

[0003] To meet the above requirements, in related technologies, the platform will plan travel routes within a specific area in advance, such as different travel routes provided by travel agencies to users. Each travel route corresponds to a different travel area and travel duration for users to choose.

[0004] However, in the above-mentioned related technologies, the areas and occupancy time of the routes pre-planned by the platform are fixed. Users need to adjust their time plans according to the occupancy time required for the route, and the areas passed by the route cannot be intelligently changed as user needs change, which makes the flexibility of route recommendation information push low. Summary of the Invention

[0005] The present invention provides a method, apparatus, computer device, and storage medium for pushing route recommendation information, which can improve the flexibility of pushing route recommendation information. The technical solution is as follows:

[0006] In one aspect, a method for pushing route recommendation information is provided, the method comprising:

[0007] Determine at least one moving path in a path search area, wherein the path search area includes m sub-areas, and each moving path passes through n sub-areas of the m sub-areas, where m and n are positive integers and m≥n≥1;

[0008] Obtaining an estimated tour duration for each of the m sub-areas based on the respective regional characteristics of the m sub-areas and the characteristics of the user corresponding to the terminal; the estimated tour duration is the estimated tour duration of the user corresponding to the terminal in the corresponding sub-area;

[0009] Obtaining an estimated occupancy time for each of the at least one moving path according to the estimated tour durations of each of the m sub-areas;

[0010] Pushing path recommendation information to the terminal according to the estimated occupancy time of each of the at least one moving path.

[0011] In another aspect, a route recommendation information push device is provided, the device comprising:

[0012] a determination module, configured to determine at least one movement path within a path search area, wherein the path search area includes m sub-areas, and each movement path passes through n sub-areas of the m sub-areas, where m and n are positive integers and m≥n≥1;

[0013] A first acquisition module is configured to acquire an estimated tour duration of each of the m sub-areas based on regional characteristics of each of the m sub-areas and characteristics of a user corresponding to the terminal; the estimated tour duration is the estimated tour duration of the user corresponding to the terminal in the corresponding sub-area;

[0014] A second acquisition module is configured to acquire an estimated occupancy time of each of the at least one moving path according to the estimated tour time of each of the m sub-areas;

[0015] The push module is used to push path recommendation information to the terminal according to the estimated occupancy time of each of the at least one moving path.

[0016] In a possible implementation, the first acquisition module includes:

[0017] an extraction submodule, configured to extract regional features of a target subregion, where the target subregion is any one of the m subregions;

[0018] The first acquisition submodule is used to input the regional characteristics of the target sub-area and the user characteristics corresponding to the terminal into a tour duration estimation model to obtain the estimated tour duration of the target sub-area; the tour duration estimation model is trained based on the regional characteristics of the sample sub-area, the user characteristics of the sample user, and the historical tour duration of the sample user in the sample sub-area.

[0019] In a possible implementation, the tour duration estimation model is a Bayesian network model;

[0020] The first acquisition submodule includes:

[0021] A first acquisition subunit is configured to input the regional characteristics of the target sub-region and the user characteristics corresponding to the terminal into a tour duration estimation model, and obtain m sub-estimated tour durations output by the tour duration estimation model, and the probabilities corresponding to the m sub-estimated tour durations;

[0022] The first calculation subunit is configured to calculate the expected tour duration of the target sub-area according to the m expected tour durations and the probabilities corresponding to the m expected tour durations.

[0023] In a possible implementation, the second acquisition module includes:

[0024] A second acquisition submodule is configured to acquire the estimated tour duration of each of the n sub-areas passed by the at least one moving path among the m sub-areas;

[0025] The third acquisition submodule is configured to acquire the estimated occupancy time of each of the at least one moving path according to the respective estimated tour time of the n sub-areas passed by the at least one moving path.

[0026] In a possible implementation, the push module includes:

[0027] A first determining submodule is configured to determine, among the at least one moving path, each moving path whose corresponding estimated occupancy time is within a preset time range as a recommended path;

[0028] The push submodule is configured to push path recommendation information to the terminal according to each of the recommended paths.

[0029] In a possible implementation, the push submodule includes:

[0030] A second acquisition subunit is configured to acquire an estimated feedback result for each of the recommended routes based on the estimated tour duration of each of the recommended routes and the user characteristics corresponding to the terminal; the estimated feedback result is a predicted satisfaction feedback result of the user corresponding to the terminal with respect to the recommended route;

[0031] a sorting subunit, configured to sort the recommendable paths according to their respective expected feedback results;

[0032] The push subunit is configured to push recommendation information of the recommended path to the terminal according to the ranking result of each of the recommendable paths.

[0033] In one possible implementation, the second acquisition sub-unit is used to input the estimated tour duration of the target recommended path and the user characteristics corresponding to the terminal into a feedback result prediction model to obtain the estimated feedback result of the target recommended path; the target recommended path is any one of the recommended paths; the feedback result prediction model is trained based on the estimated tour duration of the sample path, the user characteristics of the sample user, and the satisfaction feedback results of the sample user on the sample path.

[0034] In a possible implementation, the feedback result prediction model is a Bayesian network model;

[0035] The second acquisition sub-unit is configured to input the estimated tour duration of the target recommended route and the user characteristics corresponding to the terminal into a feedback result estimation model, and obtain m sub-estimated feedback results output by the feedback result estimation model, and the probabilities corresponding to the m sub-estimated feedback results;

[0036] The expected feedback result of the target recommended path is calculated according to the m expected sub-feedback results and the probabilities corresponding to the m expected sub-feedback results.

[0037] In a possible implementation, before determining at least one moving path within the path search area, the apparatus further includes:

[0038] A third acquisition module is used to obtain the starting point and the ending point of the user corresponding to the terminal;

[0039] A construction module is used to construct the path search area according to the starting point and the end point.

[0040] On the other hand, a computer device is provided, which includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set, or an instruction set, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the path recommendation information push method provided in the various optional implementations described above.

[0041] On the other hand, a computer-readable storage medium is provided, which stores at least one instruction, at least one program, code set or instruction set, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by a processor to implement the path recommendation information push method provided in the various optional implementations mentioned above.

[0042] In another aspect, a computer program product or program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the route recommendation information push method provided in the various optional implementations described above.

[0043] The technical solution provided by this application may have the following beneficial effects:

[0044] By determining at least one moving path containing at least one sub-area in the path search area, and estimating the user's sightseeing time in each sub-area based on the regional characteristics of each sub-area and the user characteristics corresponding to the terminal, the estimated occupancy time corresponding to each moving path is determined, and path recommendation information is pushed to the terminal based on the estimated occupancy time corresponding to each moving path. In the process of pushing the path recommendation information, the estimated occupancy time of the moving path can be more accurately calculated based on the user characteristics and the regional characteristics of the sub-area, thereby improving the accuracy and flexibility of pushing the path recommendation information.

[0045] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0047] Figure 1 A schematic diagram of a Bayesian network shown in an exemplary embodiment of the present application is shown;

[0048] Figure 2 A schematic diagram showing the relationship between nodes shown in an exemplary embodiment of the present application is shown;

[0049] Figure 3 A diagram showing a route planning system configuration according to an exemplary embodiment of the present application is shown;

[0050] Figure 4 A flowchart of a method for pushing route recommendation information provided by an exemplary embodiment of the present application is shown;

[0051] Figure 5 A schematic diagram of a path search area range shown in an exemplary embodiment of the present application is shown;

[0052] Figure 6 A flowchart of a method for pushing route recommendation information provided by an exemplary embodiment of the present application is shown;

[0053] Figure 7 A schematic diagram of the operation of a tour duration estimation model according to an exemplary embodiment of the present application is shown;

[0054] Figure 8 A schematic diagram of the operation of a feedback result prediction model shown in an exemplary embodiment of the present application is shown;

[0055] Figure 9 A block diagram of a route recommendation information pushing device provided by an exemplary embodiment of the present application is shown;

[0056] Figure 10 is a structural block diagram of a computer device according to an exemplary embodiment;

[0057] Figure 11 It is a structural block diagram of a computer device according to an exemplary embodiment. DETAILED DESCRIPTION

[0058] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0059] It should be understood that the term "several" in this document refers to one or more, and "multiple" refers to two or more. "And / or" describes the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exists simultaneously, or B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0060] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0061] First, a brief introduction to the terms involved in the embodiments of this application is given:

[0062] Bayesian Network

[0063] Bayesian network, also known as belief network or directed acyclic graph model, is a typical probabilistic graphical model. It is an uncertainty processing model that simulates the causal relationship in the process of internal reasoning. Its network topology is a directed acyclic graph, and the overall joint distribution of the network is calculated as the product of the conditional distribution defined by each node in the framework. Please refer to Figure 1 , which shows a schematic diagram of a Bayesian network shown in an exemplary embodiment of the present application, such as Figure 1 As shown in the figure, there are several nodes in the directed acyclic graph of the Bayesian network, and the nodes in the directed acyclic graph represent random variables {X1, X2, ..., Xn}, they are observable variables, or hidden variables, position parameters, etc. Variables or propositions that are considered to have causal relationships (or non-conditional independence) are connected by arrows. If two nodes are connected by a single arrow, it means that one node is the "cause (parents)" and the other is the "effect (children)," and the two nodes will produce a conditional probability value. For example, please refer to Figure 2 , which shows a schematic diagram of the relationship between nodes shown in an exemplary embodiment of the present application, such as Figure 2 As shown, assuming that node E directly affects node H, that is, E→H, then a directed arc (E, H) is established from node E to node H using an arrow pointing from E to H, and the weight (i.e., connection strength) is represented by the conditional probability P(H|E). In other words, by plotting the random variables involved in a certain research system in a directed graph based on whether they are conditionally independent, a Bayesian network is formed. It is mainly used to describe the conditional dependencies between random variables, with circles representing random variables and arrows representing conditional dependencies. In addition, for any random variable, its joint probability can be obtained by multiplying their respective local conditional probability distributions:

[0064] P(x1,...,x k )=P(x k |x1,...,x k -1)...P(x2|x1)P(x1)

[0065] Please refer to Figure 3 , which shows a diagram of a route planning system structure shown in an exemplary embodiment of the present application, such as Figure 3 As shown, the system includes a terminal 310 and a server 320 .

[0066] The terminal 310 can be a mobile phone, a tablet computer, an e-book reader, smart glasses, a smart watch, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 player (Moving Picture Experts Group Audio Layer IV), etc.

[0067] The terminals 310 may communicate with each other via short-range wireless communication technology. For example, the terminals 310 may communicate with each other via at least one short-range wireless communication technology selected from Wi-Fi technology, Bluetooth technology, and NFC technology.

[0068] The terminal 310 may be installed with an application program that supports route planning. Accordingly, the server 320 may be a server corresponding to the application program that supports route planning.

[0069] The terminal 310 is connected to the server 320 via a communication network. Optionally, the communication network is a wired network or a wireless network.

[0070] The server 320 is a server, or is composed of several servers, or is a virtualization platform, or is a cloud computing service center.

[0071] Optionally, the above-mentioned wireless network or wired network uses standard communication technologies and / or protocols. The network is typically the Internet, but can also be any network, including but not limited to a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a private network or any combination of a virtual private network). In some embodiments, technologies and / or formats including Hyper Text Mark-up Language (HTML), Extensible Markup Language (XML), etc. are used to represent data exchanged over the network. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPsec), etc. can be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above-mentioned data communication technologies.

[0072] Please refer to Figure 4 , which shows a flowchart of a method for pushing route recommendation information provided by an exemplary embodiment of the present application. The method for pushing route recommendation information can be executed by a computer device, which can be a server or a terminal, wherein the terminal can be Figure 3 The terminal shown in , the server can be Figure 3 The server shown in . Figure 4 As shown, the route recommendation information push method includes the following steps:

[0073] Step 410 : Determine at least one moving path in a path search area. The path search area includes m sub-areas. Each moving path passes through n sub-areas of the m sub-areas. m and n are positive integers, and m≥n≥1.

[0074] In one possible implementation, the path search area is a two-dimensional plane range, for example, the path search area is a certain floor of a building, the plane layout of a scenic spot, etc.; or, the path search area is a three-dimensional range, such as each floor of a commercial building, etc.

[0075] In the embodiment of the present application, the route recommendation information push method provided by the present application is described by taking the route search area as a two-dimensional plane range as an example.

[0076] In a possible implementation, the path search area includes m sub-areas. Based on the different sub-areas passed during the movement, at least one movement path is determined within the path search area. For example, please refer to Figure 5 , which shows a schematic diagram of the path search area range shown in an exemplary embodiment of the present application, such as Figure 5 As shown, within the path search area 510, the user's movement route can be S→A→E→F→G→O, or S→A→B→C→D→O, or S→A→E→C→G→O, etc. Different movement routes can be formed by permutations and combinations between different sub-areas.

[0077] Step 420: Obtain the estimated tour duration of each of the m sub-areas based on the respective regional characteristics of the m sub-areas and the user characteristics corresponding to the terminal; the estimated tour duration is the estimated tour duration of the user corresponding to the terminal in the corresponding sub-area.

[0078] In one possible implementation, the user characteristics corresponding to the terminal include the user's basic information and the user's additional demand information, wherein the user's basic information includes basic user portrait information such as the user's age and gender, and the user's additional demand information includes the user's available time, the number of companions, the form of companions, and other information.

[0079] In one possible implementation, the user's basic information is extracted by a computer device from a user information database, or is input by the user into the computer device when the user has a need to push route recommendation information; the user's additional demand information is actively input by the user into the computer device, or is predicted by the computer device based on the user's historical behavior habits, or is the default additional demand information pre-set by the computer device.

[0080] In one possible implementation, the terminal corresponds to at least two user profiles. Different numbers and types of user profiles can have different impacts on the estimated duration of a visit within the same sub-area. For example, the estimated duration of a meal in a dining area might be shorter for one person than for four people. Alternatively, the estimated duration of a game area might be longer for a user with children than for a user without children.

[0081] In one possible implementation, different sub-areas have different regional characteristics, such as floor levels, floor area, related facilities, and regional attributes. Regional attributes may include different functions such as education, catering, shopping, and entertainment. These different regional characteristics will affect the duration of a user's visit to each sub-area. For example, a user's visit to an area with catering functions may last 1 to 2 hours, while a visit to an area with shopping functions may last 10 to 30 minutes. Another example is that different floor areas have different effects on user visit duration. Generally speaking, users' visit duration is shorter in sub-areas with smaller floor areas, while users' visit duration is longer in sub-areas with larger floor areas.

[0082] Step 430 : Obtain the estimated occupancy time of each of at least one moving path based on the estimated tour time of each of the m sub-areas.

[0083] Step 440: Push path recommendation information to the terminal based on the estimated occupancy time of at least one moving path.

[0084] In one possible implementation, the computer device pushes path recommendation information to the terminal based on the estimated occupancy time of at least one moving path, including: the sub-areas passed by the pushed moving path, the user's estimated tour time in each sub-area, an introduction to the activity projects in each sub-area, historical user evaluations in each sub-area, and other information.

[0085] To summarize, the path recommendation information push method provided in the embodiment of the present application determines at least one moving path containing at least one sub-area within the path search area, and estimates the user's tour time in each sub-area based on the regional characteristics of each sub-area and the user characteristics corresponding to the terminal, thereby determining the estimated occupancy time corresponding to each moving path, and pushing the path recommendation information to the terminal based on the estimated occupancy time corresponding to each moving path. In the process of pushing the path recommendation information, the estimated occupancy time of the moving path can be more accurately calculated based on the user characteristics and the regional characteristics of the sub-area, thereby improving the accuracy and flexibility of the path recommendation information push.

[0086] Please refer to Figure 6 , which shows a flowchart of a method for pushing route recommendation information provided by an exemplary embodiment of the present application. The method for pushing route recommendation information can be executed by a computer device, which can be a server or a terminal, wherein the terminal can be Figure 3 The terminal shown in , the server can be Figure 3 The server shown in . Figure 6 As shown, the route recommendation information push method may include the following steps:

[0087] Step 610: Determine at least one moving path in a path search area, where the path search area includes m sub-areas, and each moving path passes through n sub-areas of the m sub-areas, where m and n are positive integers, and m≥n≥1.

[0088] In one possible implementation, the path search area is constructed based on the user's determined starting and ending points. Therefore, before determining at least one movement path within the path search area, the path search area needs to be constructed. This process may include:

[0089] Get the starting and ending points of the user corresponding to the terminal;

[0090] Based on the start and end points, a path search area is constructed.

[0091] In one possible implementation, the starting point of the user corresponding to the terminal is the user's desired starting point input into the computer device when the user has a need to push route recommendation information, or the current location of the user corresponding to the terminal obtained by the computer device through positioning; and the end point of the user corresponding to the terminal is the user's desired end point input into the computer device when the user has a need to push route recommendation information, or the location determined by the computer device based on the user's historical movement information.

[0092] After determining the user's starting point and end point, a path search area is determined based on the user's starting point and end point. In one possible implementation, a search step is set to construct a path search area based on the starting point and end point. The search step indicates the distance between the edge of the search area and the line connecting the starting point and the end point. Figure 5 As shown, the line between the starting point and the end point is taken as the center line, and the area formed by extending the preset search step on both sides of the center line is the path search area, where the length of the line between the starting point S and the end point O is the length, 2x is the width, x is the preset search step, and the line between the starting point S and the end point O is the center line.

[0093] In a possible implementation, the path search area is a circular search area having a line connecting the start point and the end point as a diameter and a midpoint of the line connecting the start point and the end point as a center.

[0094] It should be noted that the above method of constructing a path search area using the user's starting point and end point is only exemplary, and this application does not limit the method of constructing the scope of the path search area.

[0095] Step 620: extracting regional features of a target sub-region, where the target sub-region is any one of the m sub-regions.

[0096] In one possible implementation, the same sub-region corresponds to different regional features. For example, for a Chinese restaurant on the second floor of a shopping mall, "shopping mall", "second floor", "restaurant", and "Chinese food" are different regional features belonging to the restaurant.

[0097] Generally speaking, the regional characteristics of the same sub-region remain unchanged, while the user characteristics can change according to different user needs. For example, the first time a user travels, it is a company dinner occasion, and the second time the user travels, it is a couple's date occasion. In the above two occasions, there are differences in the number of people traveling together and the form of travel.

[0098] Step 630 : Input the regional characteristics of the target sub-region and the user characteristics corresponding to the terminal into a tour duration estimation model to obtain an estimated tour duration of the target sub-region.

[0099] In a possible implementation, the tour duration estimation model is trained based on regional characteristics of the sample sub-region, user characteristics of the sample users, and historical tour durations of the sample users in the sample sub-region.

[0100] Please refer to Figure 7 , which shows a working diagram of a tour duration estimation model shown in an exemplary embodiment of the present application, such as Figure 7 As shown, when it is necessary to calculate the expected tour duration of a sub-area, the regional characteristics 710 corresponding to the sub-area and the user characteristics 720 of the terminal in the current case need to be input into the tour duration estimation model 730 to obtain the expected tour duration of the sub-area.

[0101] In a possible implementation, the tour duration estimation model is a Bayesian network model.

[0102] When the preview duration prediction model is a Bayesian network model, the output of the preview duration prediction model is composed of multiple possible tour durations and probabilities, that is,

[0103] The regional features of the target sub-region and the user features corresponding to the terminal are input into the tour duration estimation model to obtain m sub-estimated tour durations output by the tour duration estimation model and the probabilities corresponding to the m sub-estimated tour durations.

[0104] For example, for sub-region A, the output predicted by the preview duration estimation model is:

[0105] Estimated duration of visit Probability 0 minutes 0 0-20 minutes 40％ 20-40 minutes 50％ 40-60 minutes 10％ … 0

[0106] That is to say, under the current user characteristics of the terminal, the estimated visiting time of the user in sub-area A is: there is a 40% probability that the user's visiting time in sub-area A is 0 to 20 minutes; there is a 50% probability that the user's visiting time in sub-area A is 20 to 40 minutes; there is a 10% probability that the user's visiting time in sub-area A is 40 to 60 minutes.

[0107] According to the m sub-area expected tour durations and the probabilities corresponding to the m sub-area expected tour durations, the expected tour duration of the target sub-area is calculated.

[0108] In a possible implementation, the estimated tour duration with the highest probability among the sub-estimated tour durations is obtained as the estimated tour duration of the target sub-area. For example, the estimated tour duration of the sub-area A is obtained as 20 to 40 minutes with a probability of 50%.

[0109] Alternatively, in another possible implementation, a weighted average is taken for each of the m sub-estimated tour durations, with the weights being the probabilities corresponding to the m sub-estimated tour durations. The weighted averages of the m sub-estimated tour durations are accumulated, and the accumulated result is obtained as the estimated tour duration of the target sub-area. For example, for the above sub-area A, its estimated tour duration T is:

[0110] T=[0,20]×40%+[20,40]×50%+[40,60]×10%=[14,34]

[0111] That is, the estimated tour duration of sub-area A is 14 to 34 minutes.

[0112] Step 640 : Obtain the estimated occupancy time of each of at least one moving path based on the estimated tour time of each of the m sub-areas.

[0113] In one possible implementation, the above steps are implemented as follows:

[0114] Get the estimated tour duration of each of the n sub-areas that at least one moving path passes through among the m sub-areas.

[0115] According to the respective estimated tour durations of the n sub-areas passed by the at least one moving path, the respective estimated occupancy duration of the at least one moving path is obtained.

[0116] Based on the estimated durations for each of the m sub-areas within the path search area, the estimated duration for a path passing through some of these m sub-areas is calculated by summing the estimated durations for each sub-area passed by the path. For example, if path A passes through sub-areas A, C, and D, the estimated duration for path A is the sum of the estimated durations A, B, and C for sub-areas A, C, and D, respectively.

[0117] In step 650 , each moving path whose corresponding estimated occupancy time is within a preset time range among the at least one moving path is determined as a recommendable path.

[0118] In one possible implementation, the preset time range is determined based on a user-entered desired duration, with the tolerance period being shortened based on the user's desired duration or extended based on the user's desired duration. For example, if the user enters a desired duration of 4 hours and a tolerance period of 30 minutes, the preset time range is 3 hours and 30 minutes to 4 hours and 30 minutes. Routes with an estimated occupancy time within this preset time range are recommended routes, and at least one of these recommended routes exists in the at least one travel route.

[0119] Step 660: Push path recommendation information to the terminal based on each recommended path.

[0120] In a possible implementation, the above process can be implemented as follows:

[0121] Step 661: Obtain an estimated feedback result for each recommended route based on the estimated tour duration of each recommended route and the user characteristics corresponding to the terminal. The estimated feedback result is the predicted satisfaction feedback result of the user corresponding to the terminal with the recommended route.

[0122] In one possible scenario, the process of obtaining the expected feedback results can be implemented as follows:

[0123] The estimated tour duration of the target recommended path and the user characteristics corresponding to the terminal are input into the feedback result estimation model to obtain the estimated feedback result of the target recommended path; the target recommended path is any one of the recommended paths; the feedback result estimation model is trained based on the estimated tour duration of the sample path, the user characteristics of the sample user, and the satisfaction feedback results of the sample user on the sample path.

[0124] The satisfaction feedback results reflect the rationality of the sample path and the user's satisfaction with the sample path.

[0125] Please refer to Figure 8 , which shows a working diagram of a feedback result prediction model shown in an exemplary embodiment of the present application, such as Figure 8 As shown, when it is necessary to predict the expected feedback result of a certain recommended path, it is necessary to input the estimated occupancy time 810 corresponding to the recommended path and the user characteristics 820 of the terminal in the current situation into the feedback result prediction model 830 to obtain the expected feedback result of the recommended path.

[0126] In a possible implementation, the feedback result prediction model is a Bayesian network model.

[0127] When the feedback result prediction model is a Bayesian network model, the output result of the feedback result prediction model is composed of multiple possible feedback results and probabilities, that is,

[0128] The estimated tour duration of the target recommended path and the user characteristics corresponding to the terminal are input into the feedback result prediction model to obtain m sub-estimated feedback results output by the feedback result prediction model and the probabilities corresponding to the m sub-estimated feedback results.

[0129] In one possible case, the expected feedback result of the target recommended path is expressed as a user rating. For example, for recommended path A, the output result predicted by the feedback result estimation model is:

[0130]

[0131]

[0132] That is to say, under the current user characteristics of the terminal, the expected feedback results of the user for the recommended path A are: there is a 2% chance that the user's feedback result for the recommended path A is 0 points; there is a 10% chance that the user's feedback result for the recommended path A is 1 point; there is a 30% chance that the user's feedback result for the recommended path A is 2 points; there is a 40% chance that the user's feedback result for the recommended path A is 3 points; there is a 10% chance that the user's feedback result for the recommended path A is 4 points; there is an 8% chance that the user's feedback result for the recommended path A is 5 points.

[0133] According to the m sub-estimated feedback results and the probabilities corresponding to the m sub-estimated feedback results, the expected feedback result of the target recommended path is calculated.

[0134] In a possible implementation, the one with the highest probability among the sub-estimated feedback results is obtained as the estimated feedback result of the target recommended path. For example, the estimated feedback result of the recommended path A is 3 points with a probability of 40%.

[0135] Alternatively, in another possible implementation, a weighted average is taken for each of the m sub-estimated feedback results, with the weights being the probabilities corresponding to the m sub-estimated feedback results. The weighted average of the m sub-estimated feedback results is accumulated, and the accumulated result is obtained as the expected feedback result for the target recommended path. For example, for the recommended path A above, its expected feedback result Z is:

[0136] Z=0×2%+1×10%+2×30%+3×40%+4×10%+5×8%=2.7

[0137] That is to say, the expected feedback result of the recommended path A is 2.7 points.

[0138] Step 662: sort the recommended paths according to their respective expected feedback results.

[0139] In a possible implementation, the recommendable paths are sorted in descending order of their expected feedback results.

[0140] Step 663: Push recommendation information of the recommended path to the terminal according to the ranking result of each recommendable path.

[0141] In one possible case, after ranking the recommendable paths, the top n recommendable paths are selected as recommended paths, and recommendation information of the recommended paths is pushed to the terminal, where n is a positive integer.

[0142] In one possible case, the value of n is preset by the computer device, or the value of n is set by the user.

[0143] In one possible case, after the recommended paths are sorted, a recommended path with an expected feedback result greater than a feedback result threshold is selected as a recommended path, and recommendation information of the recommended path is pushed to the terminal.

[0144] In one possible case, the feedback result threshold is preset by the computer device, or the feedback result threshold is set by the user.

[0145] sorting the recommended paths according to the expected feedback result of each of the at least one recommended path;

[0146] The first n recommended paths are determined as recommended paths, and recommendation information of the recommended paths is pushed to the terminal, where n is a positive integer.

[0147] To summarize, the path recommendation information push method provided in the embodiment of the present application determines at least one moving path containing at least one sub-area within the path search area, and estimates the user's tour time in each sub-area based on the regional characteristics of each sub-area and the user characteristics corresponding to the terminal, thereby determining the estimated occupancy time corresponding to each moving path, and pushing the path recommendation information to the terminal based on the estimated occupancy time corresponding to each moving path. In the process of pushing the path recommendation information, the estimated occupancy time of the moving path can be more accurately calculated based on the user characteristics and the regional characteristics of the sub-area, thereby improving the accuracy and flexibility of the path recommendation information push.

[0148] Please refer to Figure 9 , which shows a block diagram of a route recommendation information push device provided by an exemplary embodiment of the present application. The route recommendation information push device can be applied to a computer device, which can be a server or a terminal, wherein the terminal can be Figure 3 The terminal shown in , the server can be Figure 3 The server shown in . Figure 9 As shown, the route recommendation information push device includes:

[0149] A determination module 910 is configured to determine at least one movement path within a path search area, wherein the path search area includes m sub-areas, and each movement path passes through n sub-areas of the m sub-areas, where m and n are positive integers and m≥n≥1;

[0150] The first acquisition module 920 is configured to acquire an estimated tour duration for each of the m sub-areas based on the respective regional characteristics of the m sub-areas and the characteristics of the user corresponding to the terminal; the estimated tour duration is the estimated tour duration of the user corresponding to the terminal in the corresponding sub-area;

[0151] The second acquisition module 930 is configured to acquire an estimated occupancy time of each of at least one moving path according to the estimated tour time of each of the m sub-areas;

[0152] The push module 940 is configured to push path recommendation information to the terminal based on the estimated occupancy time of at least one moving path.

[0153] In a possible implementation, the first obtaining module 920 includes:

[0154] An extraction submodule, configured to extract regional features of a target subregion, where the target subregion is any one of the m subregions;

[0155] The first acquisition submodule is used to input the regional characteristics of the target sub-area and the user characteristics corresponding to the terminal into a tour duration estimation model to obtain the estimated tour duration of the target sub-area; the tour duration estimation model is trained based on the regional characteristics of the sample sub-area, the user characteristics of the sample user, and the historical tour duration of the sample user in the sample sub-area.

[0156] In a possible implementation, the tour duration estimation model is a Bayesian network model;

[0157] The first acquisition submodule includes:

[0158] The first acquisition sub-unit is used to input the regional characteristics of the target sub-region and the user characteristics corresponding to the terminal into the tour duration estimation model, and obtain m sub-estimated tour durations output by the tour duration estimation model, and the probabilities corresponding to the m sub-estimated tour durations;

[0159] The first calculation subunit is configured to calculate an estimated tour duration of a target sub-area according to the m estimated tour durations and the probabilities corresponding to the m estimated tour durations.

[0160] In a possible implementation, the second acquisition module 930 includes:

[0161] The second acquisition submodule is used to obtain the estimated tour duration of each of the n sub-areas passed by at least one moving path among the m sub-areas;

[0162] The third acquisition submodule is configured to acquire the estimated occupancy time of each of the at least one moving path according to the estimated tour times of each of the n sub-areas that the at least one moving path passes through.

[0163] In a possible implementation, the push module 940 includes:

[0164] A first determining submodule is configured to determine, among at least one moving path, each moving path whose corresponding estimated occupancy time is within a preset time range as a recommended path;

[0165] The push submodule is used to push path recommendation information to the terminal based on each recommendable path.

[0166] In a possible implementation, the push submodule includes:

[0167] The second acquisition subunit is configured to acquire an estimated feedback result for each recommended route based on the estimated tour duration of each recommended route and the user characteristics corresponding to the terminal; the estimated feedback result is a predicted satisfaction feedback result of the user corresponding to the terminal for the recommended route;

[0168] A sorting subunit, configured to sort each of the recommended paths according to the expected feedback results of each of the recommended paths;

[0169] The push subunit is used to push recommendation information of the recommended path to the terminal according to the ranking result of each recommendable path.

[0170] In one possible implementation, the second acquisition sub-unit is used to input the estimated tour duration of the target recommended path and the user characteristics corresponding to the terminal into a feedback result prediction model to obtain the estimated feedback result of the target recommended path; the target recommended path is any one of the recommendable paths; the feedback result prediction model is trained based on the estimated tour duration of the sample path, the user characteristics of the sample user, and the satisfaction feedback results of the sample user on the sample path.

[0171] In a possible implementation, the feedback result prediction model is a Bayesian network model;

[0172] The second acquisition sub-unit is configured to input the estimated tour duration of the target recommended route and the user characteristics corresponding to the terminal into the feedback result estimation model, and obtain m sub-estimated feedback results output by the feedback result estimation model, and the probabilities corresponding to the m sub-estimated feedback results;

[0173] According to the m sub-estimated feedback results and the probabilities corresponding to the m sub-estimated feedback results, the expected feedback result of the target recommended path is calculated.

[0174] In a possible implementation, before determining at least one moving path within the path search area, the apparatus further includes:

[0175] The third acquisition module is used to obtain the starting point and end point of the user corresponding to the terminal;

[0176] The construction module is used to construct a path search area based on the starting point and the end point.

[0177] In summary, the path recommendation information push device provided in the embodiment of the present application is applied in a computer device. It determines at least one moving path containing at least one sub-area in the path search area, and estimates the user's tour time in each sub-area based on the regional characteristics of each sub-area and the user characteristics corresponding to the terminal, and then determines the estimated occupancy time corresponding to each moving path. Based on the estimated occupancy time corresponding to each moving path, the path recommendation information is pushed to the terminal. In the process of pushing the path recommendation information, the estimated occupancy time of the moving path can be more accurately calculated based on the user characteristics and the regional characteristics of the sub-area, thereby improving the accuracy and flexibility of the path recommendation information push.

[0178] Figure 10 1 is a block diagram illustrating the structure of a computer device 1000 according to an exemplary embodiment. The computer device 1000 may be a terminal, such as a smartphone, a tablet computer, or a desktop computer. The computer device 1000 may also be referred to as a user device, a portable terminal, a laptop terminal, a desktop terminal, or other names.

[0179] Typically, the computer device 1000 includes a processor 1001 and a memory 1002 .

[0180] In some embodiments, the non-transitory computer-readable storage medium in the memory 1002 is used to store at least one instruction, which is used to be executed by the processor 1001 to implement the method provided in the method embodiment of the present application.

[0181] In some embodiments, computer device 1000 may optionally include a peripheral device interface 1003 and at least one peripheral device. Processor 1001, memory 1002, and peripheral device interface 1003 may be connected via a bus or signal lines. Each peripheral device may be connected to peripheral device interface 1003 via a bus, signal lines, or circuit boards. Specifically, the peripheral device may include at least one of a radio frequency circuit 1004, a touchscreen display 1005, a camera 1006, an audio circuit 1007, a positioning component 1008, and a power supply 1009.

[0182] In some embodiments, the computer device 1000 further includes one or more sensors 1010 , including but not limited to: an acceleration sensor 1011 , a gyroscope sensor 1015 , a pressure sensor 1013 , a fingerprint sensor 1014 , an optical sensor 1015 , and a proximity sensor 1016 .

[0183] Those skilled in the art will understand that Figure 10 The structure shown in the figure does not constitute a limitation on the computer device 1000, and the computer device 1000 may include more or fewer components than shown in the figure, or combine some components, or adopt a different component arrangement.

[0184] Figure 111 is a block diagram of a computer device 1100 according to an exemplary embodiment. The computer device 1100 can be implemented as the server in the above-mentioned solution. The computer device 1100 includes a central processing unit (CPU) 1101, a system memory 1104 including a random access memory (RAM) 1102 and a read-only memory (ROM) 1103, and a system bus 1105 connecting the system memory 1104 and the central processing unit 1101. The computer device 1100 also includes a basic input / output system (I / O system) 1106 that helps transfer information between various components within the computer, and a mass storage device 1107 for storing an operating system 1113, application programs 1114, and other program modules 1115.

[0185] The basic input / output system 1106 includes a display 1108 for displaying information and an input device 1109 such as a mouse and keyboard for user input. The display 1108 and the input device 1109 are both connected to the central processing unit 1101 via an input / output controller 1110 connected to the system bus 1105. The basic input / output system 1106 may also include an input / output controller 1110 for receiving and processing input from a variety of other devices such as a keyboard, mouse, or electronic stylus. Similarly, the input / output controller 1110 also provides output to a display screen, printer, or other types of output devices.

[0186] The mass storage device 1107 is connected to the central processing unit 1101 via a mass storage controller (not shown) connected to the system bus 1105. The mass storage device 1107 and its associated computer-readable media provide non-volatile storage for the computer device 1100. In other words, the mass storage device 1107 may include a computer-readable medium (not shown) such as a hard disk or a compact disc read-only memory (CD-ROM) drive.

[0187] Without loss of generality, the computer-readable medium may include computer storage media and communication media. Computer storage media include volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information such as computer-readable instructions, data structures, program modules or other data. Computer storage media include RAM, ROM, Erasable Programmable Read Only Memory (EPROM), Electronically Erasable Programmable Read-Only Memory (EEPROM), flash memory or other solid-state storage technologies, CD-ROM, Digital Versatile Disc (DVD) or other optical storage, tape cassettes, magnetic tape, disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that the computer storage media are not limited to the above-mentioned ones. The above-mentioned system memory 1104 and mass storage device 1107 can be collectively referred to as memory.

[0188] According to various embodiments of the present application, the computer device 1100 may also be connected to a remote computer on a network such as the Internet for operation. That is, the computer device 1100 may be connected to a network 1112 via a network interface unit 1111 connected to the system bus 1105. Alternatively, the network interface unit 1111 may be used to connect to other types of networks or remote computer systems (not shown).

[0189] The memory also includes one or more programs, which are stored in the memory. The CPU 1101 executes the one or more programs to implement Figure 4 or Figure 6 All or part of the steps of the method shown.

[0190] Those skilled in the art will appreciate that in one or more of the above examples, the functions described in the embodiments of the present application can be implemented using hardware, software, firmware, or any combination thereof. When implemented using software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any media that facilitates the transmission of computer programs from one place to another. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0191] The present application also provides a computer-readable storage medium for storing at least one instruction, at least one program, code set, or instruction set, which is loaded and executed by a processor to implement the above-described route recommendation information push method. For example, the computer-readable storage medium may be ROM, RAM, magnetic tape, floppy disk, or optical data storage device.

[0192] Embodiments of the present application also provide a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform all or part of the steps of the method for pushing route recommendation information described in the various embodiments above.

[0193] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0194] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for pushing route recommendation information, characterized in that: The method comprises: Get the starting and ending points of the user corresponding to the terminal; Setting a search step size, combining the starting point and the end point to construct a path search area, wherein the search step size indicates the distance between the edge of the search area and the line connecting the starting point and the end point; Determine at least one moving path in the path search area, wherein the path search area includes m sub-areas, and each moving path passes through n sub-areas of the m sub-areas, where m and n are positive integers and m≥n≥1; Obtaining an estimated tour duration for each of the m sub-areas based on the respective regional characteristics of the m sub-areas and the characteristics of the user corresponding to the terminal; the estimated tour duration is the estimated tour duration of the user corresponding to the terminal in the corresponding sub-area; Obtaining an estimated occupancy time for each of the at least one moving path according to the estimated tour durations of each of the m sub-areas; Determining, among the at least one moving path, each moving path whose corresponding estimated occupancy duration is within a preset time range as a recommended path, the preset time range being determined based on a desired duration input by a user, and shortening a fault tolerance period based on the desired duration input by the user to a time range in which the fault tolerance period is extended based on the desired duration input by the user; According to each of the recommended paths, path recommendation information is pushed to the terminal.

2. The method according to claim 1, characterized in that The obtaining of the estimated tour duration of each of the m sub-areas according to the respective regional characteristics of the m sub-areas and the user characteristics corresponding to the terminal includes: Extracting regional features of a target subregion, where the target subregion is any one of the m subregions; The regional characteristics of the target sub-area and the user characteristics corresponding to the terminal are input into a tour duration estimation model to obtain an estimated tour duration of the target sub-area; the tour duration estimation model is trained based on the regional characteristics of the sample sub-area, the user characteristics of the sample user, and the historical tour duration of the sample user in the sample sub-area.

3. The method according to claim 2, characterized in that The tour duration estimation model is a Bayesian network model; The step of inputting the regional characteristics of the target sub-region and the user characteristics corresponding to the terminal into a tour duration estimation model to obtain an estimated tour duration of the target sub-region includes: Inputting the regional characteristics of the target sub-region and the user characteristics corresponding to the terminal into a tour duration estimation model, obtaining m sub-estimated tour durations output by the tour duration estimation model and the probabilities corresponding to the m sub-estimated tour durations; The expected tour duration of the target sub-area is calculated according to the m sub-areas expected tour durations and the probabilities corresponding to the m sub-areas expected tour durations.

4. The method according to claim 1, wherein The obtaining of the estimated occupancy time of each of the at least one moving path according to the estimated tour time of each of the m sub-areas includes: Obtain the estimated tour duration of each of the n sub-areas passed by the at least one moving path among the m sub-areas; According to the respective expected tour durations of the n sub-areas passed by the at least one moving path, the estimated occupancy duration of each of the at least one moving path is obtained.

5. The method according to claim 1, wherein The pushing path recommendation information to the terminal according to each of the recommended paths includes: Obtaining, based on the estimated tour duration of each of the recommended routes and the user characteristics corresponding to the terminal, an estimated feedback result for each of the recommended routes; the estimated feedback result is a predicted satisfaction feedback result of the user corresponding to the terminal with respect to the recommended route; sorting the recommended paths according to their respective expected feedback results; According to the ranking result of each of the recommendable paths, recommendation information of the recommended path is pushed to the terminal.

6. The method according to claim 5, characterized in that The obtaining of the estimated feedback result of each of the recommended routes according to the estimated tour duration of each of the recommended routes and the user characteristics corresponding to the terminal includes: The estimated tour duration of the target recommended path and the user characteristics corresponding to the terminal are input into a feedback result prediction model to obtain an estimated feedback result of the target recommended path; the target recommended path is any one of the recommended paths; the feedback result prediction model is trained based on the estimated tour duration of the sample path, the user characteristics of the sample user, and the satisfaction feedback results of the sample user on the sample path.

7. The method according to claim 6, characterized in that The feedback result estimation model is a Bayesian network model; The step of inputting the estimated tour duration of the target recommended route and the user characteristics corresponding to the terminal into the feedback result estimation model to obtain the estimated feedback result of the target recommended route includes: Inputting the estimated tour duration of the target recommended route and the user characteristics corresponding to the terminal into a feedback result prediction model, obtaining m sub-estimated feedback results output by the feedback result prediction model and the probabilities corresponding to the m sub-estimated feedback results; The expected feedback result of the target recommended path is calculated according to the m expected sub-feedback results and the probabilities corresponding to the m expected sub-feedback results.

8. A route recommendation information push device, characterized in that: The device comprises: The third acquisition module is used to obtain the starting point and end point of the user corresponding to the terminal; a construction module, configured to set a search step length, and construct a path search area in combination with the starting point and the end point, wherein the search step length indicates the distance between the edge of the search area and the line connecting the starting point and the end point; A determination module, configured to determine at least one movement path within the path search area, wherein the path search area includes m sub-areas, and each movement path passes through n sub-areas of the m sub-areas, where m and n are positive integers and m≥n≥1; A first acquisition module is configured to acquire an estimated tour duration of each of the m sub-areas based on regional characteristics of each of the m sub-areas and characteristics of a user corresponding to the terminal; the estimated tour duration is the estimated tour duration of the user corresponding to the terminal in the corresponding sub-area; The second module is configured to obtain an estimated occupancy time of each of the at least one moving path according to the estimated tour time of each of the m sub-areas; The push module is used to determine, among the at least one moving path, each moving path whose corresponding estimated occupancy time is within a preset time range as a recommended path, where the preset time range is determined based on an expected time input by a user, and to shorten the fault tolerance time based on the expected time input by the user to a time range in which the fault tolerance time is extended based on the expected time input by the user; and push path recommendation information to the terminal based on each of the recommended paths.

9. A computer device, characterized in that: The computer device includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set, or an instruction set, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the path recommendation information push method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The storage medium stores at least one instruction, at least one program, a code set, or an instruction set, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the path recommendation information push method as described in any one of claims 1 to 7.

Images