Road book generation method, device, computer equipment and storage medium

Abstract

The present application relates to a road book generation method, device, computer equipment and storage medium. The method comprises: selecting non-starting points of interest related to the starting point of interest of this iteration process from at least one candidate point of interest that matches the road book portrait data; wherein the first starting point of interest is preset; for each non-starting point of interest corresponding to this iteration process, determining the target recommendation probability of the non-starting point of interest according to the recommendation influence data of the non-starting point of interest; determining the starting point of interest of the next iteration process from each non-starting point of interest according to the target recommendation probability of each non-starting point of interest, and returning to perform the non-starting point of interest selection operation; generating a target road book according to the starting point of interest under each iteration process when the travel restriction conditions in the road book portrait data are met. The use of this method can make the generated road book more objective, avoid the influence of human subjective factors, and thus improve the rationality and universality of road book generation.

Description

Technical Field

[0001] The present application relates to the field of map technology, and in particular to a road book generation method, device, computer equipment and storage medium. Background Art

[0002] With the increasing number of people traveling every year, a variety of travel planning methods have emerged. People can look up road books on the Internet to assist in their travels. Therefore, the rationality and universality of the generated road books are crucial.

[0003] In traditional technology, when generating a road book, road book planners usually collect relevant travel data through the Internet, travel agencies and other institutions, and then plan and generate the road book based on the travel data and their own experience. However, due to the strong subjectivity in the process of generating the road book, the rationality and universality of the generated road book are poor. Summary of the invention

[0004] Based on this, it is necessary to provide a road book generation method, device, computer equipment and storage medium that can improve the rationality and universality of road book generation in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for generating a road book, comprising:

[0006] Selecting non-starting points of interest related to the starting point of interest of this iteration process from at least one candidate point of interest that matches the road book portrait data; wherein the first starting point of interest is preset;

[0007] For each non-starting point of interest corresponding to this iteration process, determine the target recommendation probability of the non-starting point of interest according to the recommendation influence data of the non-starting point of interest;

[0008] According to the target recommendation probability of each non-starting interest point, determine the starting interest point of the next iteration process from each non-starting interest point, and return to perform the non-starting interest point selection operation;

[0009] When the travel restriction conditions in the road book portrait data are met, the target road book is generated according to the starting points of interest in each iterative process.

[0010] In one of the embodiments, the target recommendation probability of the non-starting interest point is determined based on the recommendation influence data of the non-starting interest point, including: determining the mutation probability of this iteration process; updating the recommendation influence data of the non-starting interest point according to the mutation probability of this iteration process; and determining the target recommendation probability of the non-starting interest point according to the updated recommendation influence data corresponding to the non-starting interest point.

[0011] In one embodiment, determining the mutation probability of the current iteration process includes: lowering the mutation probability of the previous iteration process to obtain the mutation probability of the current iteration process.

[0012] In one of the embodiments, the first starting point of interest is determined in the following manner: according to the density of the points of interest in the area where the candidate points of interest are located, one of the candidate points of interest is selected as the starting point of interest for the first iteration process.

[0013] In one of the embodiments, based on the density of interest points in the area where each candidate interest point is located, one of the candidate interest points is selected as the starting interest point of the first iterative process, including: gridding the area where at least one candidate interest point is located to obtain at least one grid area; based on the number of interest points of the candidate interest points contained in each grid area, selecting a target grid area from at least one grid area; and selecting one of the candidate interest points in the target grid area as the starting interest point of the first iterative process.

[0014] In one of the embodiments, a target road book is generated according to the starting points of interest in each iterative process, including: grouping the starting points of interest according to the administrative regions to which the starting points of interest in each iterative process belong to obtain at least one point of interest group; for each point of interest group, selecting a starting point within the group from the starting points of the point of interest group; constructing a travel route within the point of interest group based on the shortest path planning algorithm according to the starting points within the group; and generating a target road book according to the travel routes within each point of interest group.

[0015] In one of the embodiments, a starting point within the interest point group is selected from each starting point of interest in the interest point group, including: sorting the interest point groups based on traffic reference data between the administrative regions to which each interest point group belongs, with the interest point group where the preset travel starting point is located as the first interest point group; for the first interest point group, using the preset travel starting point as the starting point within the group; for each non-first interest point group, determining the starting point within the group of this interest point group based on the tail interest point of the route appearing in the corresponding group of the previous interest point group.

[0016] In one of the embodiments, if the road book portrait data corresponds to at least two travel time periods, the method further includes: determining the selection probability of each travel theme in each travel time period according to the matching between the road book portrait data and different travel themes; accordingly, selecting various non-starting interest points related to the starting interest point of this iteration process from at least one candidate interest point that matches the road book portrait data, including: for each travel time period, determining at least one candidate interest point in the travel time period according to the selection probability of each travel theme in the travel time period, and selecting various non-starting interest points related to the starting interest point of this iteration process from at least one candidate interest point in the travel time period; accordingly, generating a target road book according to the starting interest point in each iteration process when the travel restriction conditions in the road book portrait data are met, including: constructing a target travel route in the travel time period according to the starting interest point in each iteration process when the travel restriction conditions in the travel time period are met; generating a target road book according to the target travel route in each travel time period.

[0017] In a second aspect, the present application further provides a road book generating device, comprising:

[0018] A selection module, used to select non-starting interest points related to the starting interest point of this iteration process from at least one candidate interest point that matches the road book portrait data; wherein the first starting interest point is preset;

[0019] A first determination module is used to determine, for each non-starting point of interest corresponding to this iteration process, a target recommendation probability of the non-starting point of interest according to the recommendation influence data of the non-starting point of interest;

[0020] A second determination module is used to determine the starting point of interest of the next iteration process from each non-starting point of interest according to the target recommendation probability of each non-starting point of interest, and return to perform the non-starting point of interest selection operation;

[0021] The construction module is used to generate a target road book according to the starting points of interest in each iterative process while satisfying the travel restriction conditions in the road book portrait data.

[0022] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0023] Selecting non-starting points of interest related to the starting point of interest of this iteration process from at least one candidate point of interest that matches the road book portrait data; wherein the first starting point of interest is preset;

[0024] For each non-starting point of interest corresponding to this iteration process, determine the target recommendation probability of the non-starting point of interest according to the recommendation influence data of the non-starting point of interest;

[0025] According to the target recommendation probability of each non-starting interest point, determine the starting interest point of the next iteration process from each non-starting interest point, and return to perform the non-starting interest point selection operation;

[0026] When the travel restriction conditions in the road book portrait data are met, the target road book is generated according to the starting points of interest in each iterative process.

[0027] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0028] Selecting non-starting points of interest related to the starting point of interest of this iteration process from at least one candidate point of interest that matches the road book portrait data; wherein the first starting point of interest is preset;

[0029] For each non-starting point of interest corresponding to this iteration process, determine the target recommendation probability of the non-starting point of interest according to the recommendation influence data of the non-starting point of interest;

[0030] According to the target recommendation probability of each non-starting interest point, determine the starting interest point of the next iteration process from each non-starting interest point, and return to perform the non-starting interest point selection operation;

[0031] When the travel restriction conditions in the road book portrait data are met, the target road book is generated according to the starting points of interest in each iterative process.

[0032] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0033] Selecting non-starting points of interest related to the starting point of interest of this iteration process from at least one candidate point of interest that matches the road book portrait data; wherein the first starting point of interest is preset;

[0034] For each non-starting point of interest corresponding to this iteration process, determine the target recommendation probability of the non-starting point of interest according to the recommendation influence data of the non-starting point of interest;

[0035] According to the target recommendation probability of each non-starting interest point, determine the starting interest point of the next iteration process from each non-starting interest point, and return to perform the non-starting interest point selection operation;

[0036] When the travel restriction conditions in the road book portrait data are met, the target road book is generated according to the starting points of interest in each iterative process.

[0037] The above-mentioned road book generation method, device, computer equipment and storage medium select non-starting points of interest related to the starting point of interest of this iteration process from at least one candidate point of interest matching the road book portrait data; wherein the first starting point of interest is preset; for each non-starting point of interest corresponding to this iteration process, the target recommendation probability of the non-starting point of interest is determined according to the recommendation influence data of the non-starting point of interest; according to the target recommendation probability of each non-starting point of interest, the starting point of interest of the next iteration process is determined from each non-starting point of interest, and the non-starting point of interest selection operation is returned to be performed; when the travel restriction conditions in the road book portrait data are met, the target road book is generated according to the starting point of interest under each iteration process. In the above-mentioned technical scheme, the road book image data is used as the selection criterion, the correlation between the non-starting point of interest and the starting point of interest is increased, and the accuracy of the selection of the non-starting point of interest is improved. At the same time, the target recommendation probability affected by the recommendation influence data is used as the selection criterion of the starting point of interest of the next iteration process, which improves the diversity of the selection of the starting point of interest in each iteration process, thereby making the generated road book more objective, avoiding the influence of human subjective factors, and improving the rationality and universality of the road book generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. 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 paying creative work.

[0039] Figure 1 A schematic diagram of a process flow of a method for generating a road book in an embodiment;

[0040] Figure 2 A schematic diagram of a flow chart of a target recommendation probability determination step in one embodiment;

[0041] Figure 3 A schematic diagram of the results of a greedy infection algorithm in one embodiment;

[0042] Figure 4 A schematic diagram of a flow chart of a first starting point of interest determination step in one embodiment;

[0043] Figure 5 A schematic diagram of a grid area division process in one embodiment;

[0044] Figure 6A schematic diagram of a flow chart of a target route book determination step in an embodiment;

[0045] Figure 7 A schematic flow chart of a step of determining a starting point within a group in one embodiment;

[0046] Figure 8 A schematic diagram of a target route book generation process in an embodiment;

[0047] Fig. 9 A schematic diagram of a road book rendering layer in an embodiment;

[0048] Fig.10 A schematic diagram of a travel data collection process in an embodiment;

[0049] Fig.11 It is a structural block diagram of a road book generating device in an embodiment;

[0050] Fig.12 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0052] In an exemplary embodiment, Figure 1 As shown, a method for generating a road book is provided. This embodiment uses the method applied to a terminal as an example for illustration. It is understandable that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. This application does not impose any limitation on this. In this embodiment, the method includes the following steps:

[0053] S110, selecting non-starting interest points related to the starting interest point of this iteration process from at least one candidate interest point that matches the road book portrait data; wherein the first starting interest point is preset.

[0054] Among them, the road book portrait data can be understood as the portrait data corresponding to the user's travel needs, and the road book portrait data may include time data, environmental data, traffic data, and regional data. Exemplarily, the road book portrait data may specifically include but is not limited to gender, travel mode ("special forces", "city roaming", "tanking", etc.), travel weather (sunny, rainy, snowy), travel duration (1 day, 2 days, 3 days, 4 days, 5 days), place of origin (locals, outsiders), transportation methods (self-driving, public transportation, taxis), travel attributes (self-driving tours, landing tours) and regional attributes (coastal, inland, desert, forest, plateau) and other data. It is worth noting that the user corresponding to the road book portrait data does not specifically refer to a single user individual, but generally refers to a group of users.

[0055] Among them, the candidate points of interest can be scenic spots that match the user's corresponding travel needs selected from the preset area. The starting point of interest can be understood as the scenic spot used as a reference point in each iteration process. The non-starting points of interest can be understood as other candidate points of interest that have a certain association with the starting point of interest among the candidate points of interest. Among them, the above association can be characterized by at least one of the level of scenic spots, the distance between scenic spots, and the way of travel between scenic spots.

[0056] In an optional embodiment, the area where each candidate point of interest is located can be gridded to obtain at least one network area, and the network area corresponding to the starting point of interest in this iterative process is determined, and other points of interest in the network area except the starting point of interest are regarded as non-starting points of interest.

[0057] In another optional embodiment, if the road book portrait data corresponds to at least two travel time periods, the selection probability of each travel theme in each travel time period can also be determined based on the matching between the road book portrait data and different travel themes. Accordingly, from at least one candidate interest point that matches the road book portrait data, select the non-starting interest points related to the starting interest point of this iteration process, including: for each travel time period, according to the selection probability of each travel theme in the travel time period, determine at least one candidate interest point in the travel time period, and select the non-starting interest points related to the starting interest point of this iteration process from at least one candidate interest point in the travel time period.

[0058] The travel theme can be understood as the theme of travel preference corresponding to the road book portrait data, and the travel theme includes the main travel theme, auxiliary travel theme, free travel theme, and food travel theme, etc. The travel period can be in days, and this application does not impose any restrictions on this.

[0059] Exemplarily, determine the degree of match between the road book portrait data and each travel theme; select the travel theme with the highest degree of match as the main travel theme, select the non-food travel theme with the second highest degree of match as the auxiliary travel theme, and use the remaining non-food travel themes as free travel themes; determine the travel theme corresponding to the first travel period according to the preset selection weights, main travel theme and food travel theme; determine the travel theme corresponding to the second travel period according to the preset selection weights, main auxiliary theme and food travel theme; determine the travel theme corresponding to the third travel period according to the preset selection weights, free travel theme and food travel theme. The advantage of this setting is that it avoids the problem that the travel theme corresponding to each travel period is the same, resulting in a poor travel experience for users, and further improves the diversity of travel theme selection.

[0060] For example, assuming that the travel theme with the highest matching degree corresponding to the road book portrait data is "family travel", then the travel theme "family travel" is the main travel theme M, and the travel theme similar to "family travel" is used as the auxiliary travel theme A, and the remaining travel themes are used as free travel themes Z, and the food travel theme F is set. If the travel duration is set to X days, the probability of selecting the travel theme on the first day is M*Mx (selection weight) + F* (1-Mx), the probability of selecting the travel theme on the second day is A*Mx+F* (1-Mx), and the probability of selecting the travel theme from the third day to the Xth day is Z*Mx+F* (1-Mx).

[0061] It should be noted that this embodiment can adjust the selection weights based on user feedback (such as likes and favorites on the travel theme arrangements corresponding to the target road book). That is, if the user is satisfied, the fixed selection weights will be strengthened; if the user is not satisfied, the selection weight values ​​will be dynamically adjusted in the subsequent production of new target road books.

[0062] Exemplarily, for each travel period, the candidate points of interest corresponding to the travel theme with the highest selection probability are determined according to the selection probability of each travel theme in the travel period; the area where each candidate point of interest is located is grid-divided to obtain at least one network area; the network area corresponding to the starting point of interest of this iterative process is determined, and the other points of interest in the network area except the starting point of interest are regarded as non-starting points of interest.

[0063] Optionally, the first starting point of interest is determined in the following manner: according to the density of the points of interest in the area where the candidate points of interest are located, one of the candidate points of interest is selected as the starting point of interest for the first iteration process. Exemplarily, the density of the points of interest in the area where the candidate points of interest are located is determined; an area with a high (e.g., the highest) density of the points of interest is selected, and a candidate point of interest is randomly selected or selected according to the heat from the candidate points of interest in the selected area as the starting point of interest for the first iteration process.

[0064] S120, for each non-starting point of interest corresponding to the current iteration process, determining a target recommendation probability of the non-starting point of interest according to the recommendation influence data of the non-starting point of interest.

[0065] Among them, the recommendation influence data may be data used to influence the probability of a non-starting point of interest being recommended. Optionally, the recommendation influence data may include negative influence data such as the distance between the starting point of interest and the non-starting point of interest. Optionally, the recommendation influence data may include positive influence data such as the level of the point of interest of the non-starting point of interest. The so-called negative influence data is the influence data with a larger value corresponding to a lower recommendation probability; the positive influence data is the influence data with a larger value corresponding to a higher recommendation probability. Among them, the target recommendation probability may be the probability of selecting a non-starting point of interest as a point of interest in the target road book.

[0066] In an optional embodiment, the target recommendation probability of the non-starting interest point can be determined from each candidate interest point according to the recommendation influence data of the non-starting interest point in the following manner: according to the recommendation influence data of the non-starting interest point, the positive weighted sum value between the positive influence data in the recommendation influence data and the preset positive influence weight, and the negative weighted sum value between the negative influence data in the recommendation influence data and the preset negative influence weight are determined; the difference between the positive weighted sum value and the negative weighted sum value is determined as the target recommendation probability of the non-starting interest point. It is worth noting that the positive influence weights corresponding to different positive influence data can be the same or at least partially different; the negative influence weights corresponding to different negative influence data can be the same or at least partially different. Among them, the specific values ​​of each positive influence weight and each negative influence weight can be set by the technician according to needs or experience, or determined through a large number of experiments, and this application does not impose any limitation on this.

[0067] S130, determining the starting point of interest for the next iteration process from the non-starting points of interest according to the target recommendation probability of the non-starting points of interest, and returning to perform the non-starting point of interest selection operation.

[0068] In an optional embodiment, the starting point of interest for the next iteration process can be determined from the non-starting points of interest based on the target recommendation probability of each non-starting point of interest, and the operation of selecting the non-starting point of interest can be returned to: the target recommendation probability of each non-starting point of interest is determined, and the non-starting point of interest with the largest target recommendation probability is selected, and the non-starting point of interest is determined as the starting point of interest for the next iteration process, and the operation of selecting the non-starting point of interest is returned to.

[0069] S140, generating a target road book according to the starting points of interest in each iterative process when the travel restriction conditions in the road book portrait data are met.

[0070] Among them, the travel restriction condition may be at least one of the time conditions and regional conditions that restrict the user's travel, and this application does not impose any limitation on this.

[0071] In an optional embodiment, a target road book can be generated based on the starting points of interest in each iterative process while satisfying the travel restriction conditions in the road book portrait data: when a candidate point of interest that matches the road book portrait data cannot be selected, it proves that the travel restriction conditions in the road book portrait data have been satisfied at this time; based on the starting points of interest in each iterative process, travel routes are planned for the starting points of interest in each iterative process through the route planning logic, and a target road book is generated based on the travel route planning results.

[0072] Optionally, if the road book portrait data corresponds to at least two travel time periods, then when the travel restrictions in the road book portrait data are met, a target road book is generated based on the starting points of interest under each iterative process, including: when the travel restrictions under the travel time period are met, travel routes under the travel time period are constructed based on the starting points of interest under each iterative process; and a target road book is generated based on the travel routes under each travel time period.

[0073] Exemplarily, constructing a target travel route in a travel period according to the starting points of interest in each iteration process may include: determining the travel time between the two starting points of interest and the travel reference time of each starting point of interest according to the starting points of interest in each iteration process when the travel restriction conditions in the travel period are met, and determining the travel reference time of each starting point of interest and the sum of the travel time between the two points in the order of each starting point of interest; when the sum is in the current travel period, constructing a travel route in the travel period, and then connecting the travel routes in each travel period. For example, assuming that attractions 1-6 are distributed in cities A and B, where city A includes attractions 1-4, and city B includes attractions 5 and 6, and planning attraction 4 in city A as the last attraction in the current travel period, if the planned completion time of attraction 4 plus the travel time from attraction 4 to attraction 5 in city B exceeds the time threshold M at night, attraction 5 will not be planned in the current day. Among them, the time threshold M is related to the travel mode corresponding to the time data in the road book portrait data. For example, a "special forces" type of trip may allow for a wider and later end time on the day, so there is a possibility of allocating scenic spot 5 to the current travel period. Furthermore, the business hours of scenic spot 5 itself can also be considered. If the arrival time is no longer within the business hours, scenic spot 5 will not be planned into the current travel period.

[0074] The embodiment of the present application selects non-starting points of interest related to the starting point of interest of this iteration process from at least one candidate point of interest that matches the road book portrait data; wherein the first starting point of interest is preset; for each non-starting point of interest corresponding to this iteration process, the target recommendation probability of the non-starting point of interest is determined according to the recommendation influence data of the non-starting point of interest; according to the target recommendation probability of each non-starting point of interest, the starting point of interest of the next iteration process is determined from each non-starting point of interest, and the non-starting point of interest selection operation is returned to be performed; and when the travel restriction conditions in the road book portrait data are met, the target road book is generated according to the starting point of interest under each iteration process. In the above technical solution, the road book image data is used as the selection criterion, the correlation between the non-starting point of interest and the starting point of interest is increased, and the accuracy of the selection of the non-starting point of interest is improved. At the same time, the target recommendation probability affected by the recommendation influence data is used as the selection criterion of the starting point of interest of the next iteration process, which improves the diversity of the selection of the starting point of interest in each iteration process, thereby making the generated road book more objective, avoiding the influence of human subjective factors, and improving the rationality and universality of the road book generation.

[0075] Based on the technical solutions of the above embodiments, the present application also provides an optional embodiment. In this optional embodiment, based on the greedy contagion algorithm, the target recommendation probability determination step in S120 is refined.

[0076] See also Figure 2 The target recommendation probability determination steps shown include:

[0077] S210, determining the mutation probability of this iteration process.

[0078] Among them, the mutation probability is the random probability that affects the level of the scenic spot during this iteration.

[0079] In an optional embodiment, the mutation probability of this iteration process may be determined by random number generation.

[0080] In another optional embodiment, the mutation probability of the current iteration process may be determined in combination with the mutation probability of the previous iteration process. For example, the mutation probability of the previous iteration process may be lowered to obtain the mutation probability of the current iteration process. Exemplarily, the mutation probability of the current iteration process may be determined by halving the mutation probability of the previous iteration process.

[0081] S220: Update the recommendation influence data of the non-starting points of interest according to the mutation probability of this iteration process.

[0082] Exemplarily, taking the update of the interest point level of the positive influence data in the recommended influence data by the mutation probability as an example, according to the mutation probability of this iteration process, the product value between the mutation probability and the interest point level in the previous iteration process is determined, and the product value is used as the interest point level in this iteration process to update the recommended influence data of non-starting interest points.

[0083] S230: Determine the target recommendation probability of the non-starting interest point according to the updated recommendation influence data corresponding to the non-starting interest point.

[0084] Exemplarily, the method of determining the target recommendation probability is described by taking the case where the positive influence data includes the level of the point of interest and the corresponding positive influence weight includes the level influence, and the case where the negative influence data includes the distance of the point of interest and the corresponding negative influence weight includes the distance influence weight. Accordingly, the distance weighted sum value between the distance of the point of interest in the recommendation influence data and the preset distance influence weight, and the level weighted sum value between the level of the point of interest in the recommendation influence data and the preset level influence weight can be determined based on the updated recommendation influence data corresponding to the non-starting point of interest; the difference between the distance weighted sum value and the level weighted sum value is determined as the target recommendation probability of the non-starting point of interest.

[0085] For example, Figure 3 The schematic diagram of the greedy contagion algorithm result is shown in the figure. The starting and ending points shown in the figure are the first starting points of interest. At this time, for the first iteration process with the starting and ending points as the starting points of interest, based on Figure 2 The greedy contagion algorithm processing process shown in the figure determines the target recommendation probability of each non-starting interest point in the first iteration process; selects the non-starting interest point e with the largest target recommendation probability as the starting interest point in the next iteration process; takes the scenic spot e as the starting interest point of the next iteration process, determines each non-starting interest point corresponding to the starting interest point, and determines the target recommendation probability of each non-starting interest point in this iteration process based on the greedy contagion algorithm; selects the non-starting interest point a with the largest target recommendation probability as the starting interest point in the next iteration process, ..., and so on, until the travel restriction conditions in the road book portrait data are met, and the iteration process is stopped. Based on the above process, the starting interest points under different iteration processes are determined from the candidate interest points, including: starting and ending points, scenic spot e, scenic spot a, scenic spot b, scenic spot d, scenic spot c, scenic spot f, scenic spot g, scenic spot h and scenic spot i.

[0086] The embodiment of the present application updates the recommendation influence data of non-starting points of interest through the mutation probability of this iterative process, and then determines the target recommendation probability of non-starting points of interest based on the updated recommendation influence data, thereby increasing the randomness of selecting the starting points of interest in the next iterative process, thereby increasing the diversity of selecting the starting points of interest in different iterative processes.

[0087] Based on the technical solutions of the above embodiments, the present application also provides an optional embodiment. In this optional embodiment, the step of determining the first starting point of interest in S110 is refined.

[0088] See also Figure 4 The first step of determining the starting point of interest shown includes:

[0089] S310, gridding an area where at least one candidate point of interest is located to obtain at least one grid area.

[0090] Specifically, for each candidate interest point area, define the grid width w and grid height h, determine the maximum enclosing rectangle of at least one candidate interest point area, and obtain the rectangle width W and rectangle height H of the maximum enclosing rectangle; take the quotient between the rectangle width and the grid width as the number of grid divisions Wx, and take the quotient between the rectangle height and the grid height as the number of grid divisions Hy, and obtain the grid area of ​​the candidate interest point area.

[0091] S320: Select a target grid area from at least one grid area according to the number of the candidate points of interest included in each grid area.

[0092] Exemplarily, all candidate interest points in the area are normalized into each grid area, and the number of candidate interest points in each grid area is determined; the grid area with the number of candidate interest points greater than or equal to a preset number threshold (such as 3) is determined as the target grid area; or, each grid area with the largest number of candidate interest points is selected as the target grid area. The preset number threshold can be set by technicians based on experience or determined through a large number of experiments, and this application does not impose any limitation on this.

[0093] S330: Select one of the candidate interest points in the target grid area as the starting interest point of the first iteration process.

[0094] In an optional embodiment, a candidate interest point may be selected from the target grid area according to a preset selection strategy, such as random selection, as the starting interest point of the first iteration process.

[0095] For example, Figure 5 Schematic diagram of the grid area division process. The squares represent the grid areas. Grid area (1,1), grid area (2,1), grid area (1,3), grid area (2,3), grid area (3,2), grid area (4,4), and grid area (5,5) each contain only one scenic spot. Grid area (3,3) contains three scenic spots. Grid area (3,4) contains four scenic spots.

[0096] Optionally, assuming that the preset number threshold is 3, the network areas with the number of scenic spots greater than or equal to 3 are selected as the target grid areas, namely, grid area (3, 3) and grid area (3, 4), and then a candidate point of interest is randomly selected from the scenic spots corresponding to grid area (3, 3) and grid area (3,4) as the starting point of interest for the first iteration process.

[0097] Alternatively, a candidate interest point is randomly selected from each grid area (3, 4) containing the most scenic spots as the starting interest point of the first iteration process.

[0098] The embodiment of the present application determines the grid area where the candidate interest points are located, and determines the target grid area from the number of interest points contained in each grid area, and then selects a candidate interest point from the target grid area as the starting interest point of the first iterative process, so that there are more other interest points around the selected starting interest point, thereby improving the rationality of the starting interest point determined in subsequent different iterative processes.

[0099] Based on the technical solutions of the above embodiments, the present application also provides an optional embodiment. In this optional embodiment, the target road book determination step in S140 is refined.

[0100] See also Figure 6 The target route book determination steps shown include:

[0101] S410, grouping the starting points of interest according to the administrative divisions to which the starting points of interest in each iteration process belong, to obtain at least one point of interest group.

[0102] Exemplarily, the administrative division to which the starting points of interest belong in each iteration process is determined, and the starting points of interest belonging to the same administrative division are grouped into one group to obtain at least one point of interest group. In a specific implementation, the administrative division may be a city.

[0103] S420: For each interest point group, select a starting point within the interest point group from each starting interest point of the interest point group.

[0104] Exemplarily, for each interest point group, a starting interest point is randomly selected from each starting interest point of the interest point group, and the starting interest point is used as the intra-group starting point of the interest point group.

[0105] S430: constructing a travel route within the group of interest points according to the group starting point of the group of interest points based on a shortest path planning algorithm.

[0106] Exemplarily, according to the starting point in the group of interest points, all the starting interest points in the group of interest points are traversed by the shortest path planning algorithm to obtain the travel route in the group with the shortest path.

[0107] In an optional embodiment, based on a preset shortest path planning algorithm, route planning within the interest group can be performed according to at least one attribute dimension of time data, environmental data, traffic data, and regional data of each interest point in the interest point group, combined with preset weights for the above attribute dimensions, to obtain a travel route within the group.

[0108] Exemplarily, the number of points of interest (i.e., attractions) selected in the point of interest group can be determined based on the travel duration and the journey time (obtained directly by calling the preset online route calculation access interface). For example, assuming that the travel reference time of the attraction SA is SAt (e.g., 2 hours), and the distance from the hotel to the attraction SA is R1 (e.g., 30 minutes). Among them, the travel mode T (e.g., the corresponding attribute weight of the travel mode T is T=1) is used as the planning attribute, and the travel duration in the morning period is 4 hours. At this time, it can be known that R1+Sat≤4*T (i.e., 2.5 hours≤4 hours), so new attractions can continue to be arranged. It should be noted that the travel mode T is a variable coefficient, and different travel modes correspond to different attribute weights. For example, the travel mode T is "special forces" T1, and the attribute weight corresponding to special forces T1 is larger, that is to say, the planning attribute of special forces T1 can select more attractions in the same time; on the contrary, the travel mode T is "city roaming" T2, and the attribute weight corresponding to city roaming T2 is smaller, that is to say, the planning attribute of city roaming T2 will shorten the travel time, that is, select fewer attractions in the same time to avoid a tight itinerary.

[0109] Exemplarily, the selection probability corresponding to each point of interest in the point of interest group is determined based on environmental data (including travel weather) and the attribute weight corresponding to the environmental data: assuming that the user selects travel weather E as rainy day E1 (such as the attribute weight corresponding to rainy day E1 is E1=0.6), then determine whether all attractions in the preset area are suitable for visiting on rainy days, select all attractions suitable for visiting on rainy days, and set the selection probability of these attractions to E1.

[0110] Exemplarily, the travel time is adjusted according to the traffic data (including the traffic mode) and the corresponding attribute weights: Assuming that the traffic mode F is self-driving F1, F1 is used to predict the impact of uncontrollable time such as walking and finding a car on the actual time. Therefore, the time from scenic spot A to scenic spot B is determined to be (1+F1)*actual time, where 1+F1 is the expanded time. Preferably, different traffic modes F correspond to different attribute weights, such as the attribute weight corresponding to self-driving F1 is F1=0.1, the attribute weight corresponding to public transportation F2 is F2=0.3, and the attribute weight corresponding to taxi F3 is F3=0.15, etc.

[0111] Exemplarily, the regional data includes regional attributes. Different regional attributes will lead to different traffic conditions (such as convenient or inconvenient traffic), which in turn affect the factors of the play time. Therefore, the attribute weight of the coastal region can be set to be smaller than the attribute weight of the inland region, and the attribute weight of the inland region can be set to be smaller than the attribute weight of the desert region.

[0112] It can be understood that by comprehensively considering the above factors and combining the shortest path planning algorithm to plan the intra-group travel route, the planned intra-group route of the point of interest is made more reasonable, which helps to improve the rationality of the subsequently generated target road book.

[0113] S440: Generate a target road book based on the travel routes within each POI group.

[0114] In an optional embodiment, according to the directions of the journey corresponding to each interest point group (the starting point and the end point of the direction), the end point of the travel route can be selected from the interest point group corresponding to the starting point of the direction, and the starting point of the travel route can be selected from the interest point group corresponding to the end point of the direction; the end point of the previous interest point group and the starting point of the next interest point group are connected to complete the connection of the two interest point groups, and so on, all interest point groups are connected to obtain the target travel route; according to the interest point description data of the target travel route and each starting interest point, a target road book is generated.

[0115] The embodiment of the present application groups the starting points of interest according to administrative divisions to obtain at least one point of interest group, and then determines the starting point within the group from within the point of interest group. Finally, based on the starting point within the group and based on the shortest path planning algorithm, a travel route within the point of interest group is constructed to ensure that the shortest travel route within the group is determined, thereby improving the accuracy of target road book generation.

[0116] Based on the technical solutions of the above embodiments, the present application also provides an optional embodiment. In this optional embodiment, the step of determining the starting point within the group in S420 is refined.

[0117] See also Figure 7 The steps for determining the starting point within the group shown include:

[0118] S510, sorting the interest groups according to the traffic reference data between the administrative divisions to which the interest groups belong, with the interest group at the preset travel starting point as the first interest group.

[0119] Among them, the traffic reference data includes distance reference data, time reference data, weather reference data, etc.

[0120] Exemplarily, the POI group where the preset travel starting point is located is selected as the first POI group, and starting from the first POI group, for each POI group, each POI group is sorted according to the traffic reference data between the administrative divisions to which the POI groups belong.

[0121] S520: For the first POI group, the preset travel starting point is used as the starting point in the group.

[0122] Exemplarily, for the first interest point group, a preset travel starting point is found in the first interest point group, and the preset travel starting point is used as the starting point in the group.

[0123] S530: For each non-first POI group, determine the starting point of the current POI group according to the tail POI of the route in the corresponding group of the previous POI group.

[0124] Exemplarily, for each non-first interest point group, determine that the current interest point group corresponds to the previous interest point group, and determine the tail interest point of the route appearing in the previous interest point group; determine the distance between the tail interest point and each starting interest point in the current interest point group, and determine the starting interest point corresponding to the shortest distance as the starting point in the current interest point group.

[0125] The embodiment of the present application uses the preset travel starting point as the starting point within the first interest point group, and determines the starting point within the current interest point group based on the tail interest point of the route appearing in the corresponding group of the previous interest point group, so that the travel distance between the two adjacent interest point groups is the shortest, thereby improving the rationality of subsequent target road book generation.

[0126] For example, Figure 8The schematic diagram of the target road book generation process shown in the figure, where each starting point of interest includes scenic spots a to 9; scenic spots 1 to 4 are distributed in city A, scenic spots 5 and 6 are distributed in city B, and scenic spots 7 to 9 are distributed in city C. Accordingly, a point of interest group A including scenic spots 1 to 4, a point of interest group B including scenic spots 5 to 6, and a point of interest group C including scenic spots 7 to 9 can be constructed. Among them, the preset starting point of the trip is scenic spot 1. Therefore, point of interest group A is the first point of interest group. Accordingly, the point of interest groups are sorted to obtain the sorting result of "point of interest group A-point of interest group B-point of interest group C". For point of interest group A, based on the shortest path algorithm, the shortest path from attraction 1 to attraction 4 in city A is determined, and the travel route of "attraction 1-attraction 2-attraction 3-attraction 4" is obtained as the travel route A within the group; for point of interest group B, "attraction 5" which is closer to "attraction 4" is used as the starting point within the group of point of interest group B, and through the same route planning logic, the travel route "attraction 5-attraction 6" in point of interest group B is determined as the travel route B within the group; for point of interest group C, "attraction 7" which is closer to "attraction 6" is used as the starting point within the group of point of interest group C, and through the same route planning logic, the travel route "attraction 7-attraction 8-attraction 9" in point of interest group C is determined as the travel route C within the group. Accordingly, a connection is established between the end point of city A corresponding to scenic spot 4 and the starting point of city B corresponding to scenic spot 5, and the travel route between city A and city B is obtained as "Scenic spot 4-Scenic spot 5". The travel route between city B and city C is obtained as "Scenic spot 6-Scenic spot 7", and the travel route between city C and city A is obtained as "Scenic spot 9-Scenic spot 1". Using the above method, the target travel route corresponding to the target road book of this trip is determined to be "Scenic spot 1-Scenic spot 2-Scenic spot 3-Scenic spot 4-Scenic spot 5-Scenic spot 6-Scenic spot 7-Scenic spot 8-Scenic spot 9". It should be noted that if there is a return trip planning logic, the target travel route corresponding to the target road book of this trip is "Scenic spot 1-Scenic spot 2-Scenic spot 3-Scenic spot 4-Scenic spot 5-Scenic spot 6-Scenic spot 7-Scenic spot 8-Scenic spot 9-Scenic spot 1".

[0127] Exemplarily, on the basis of the target travel route, description information of each point of interest in the target travel route may be added to generate a target road book.

[0128] Furthermore, further route analysis can be performed based on the generated target road book to discover in-depth information on the path, including but not limited to: accommodation, gas stations, charging stations, sharp turns, dangerous sections and special foods, etc., and added to the target road book to generate a more content-rich boutique road book.

[0129] Exemplarily, for special food, this embodiment can select the special food of all cities above the prefecture level in the country for preliminary marking, and then select a preset number (such as 20) of special food places with high scores in the current area from the preliminary marked special food, determine the straight-line distance from the special food place to the target road book, and add the special food places with a straight-line distance less than the first distance threshold to the target road book; if there is no special food place with a straight-line distance less than the first distance threshold, then add the special food place with a straight-line distance less than the second distance threshold to the target road book; if there is no special food place with a straight-line distance less than the second distance threshold, then no special food place recommendation is made. Among them, the first distance threshold is less than the second distance threshold, and the second distance threshold is twice the first distance threshold. Among them, the first distance threshold and the second distance threshold can be set by technical personnel according to needs or experience, or determined through a large number of experiments, and this application does not impose any restrictions on this.

[0130] For example, for accommodation analysis, you can select accommodation around the last scenic spot corresponding to the current travel period, or you can select accommodation along the route (such as from city A to city B). Figure 8 , assuming that the end time of the last scenic spot corresponding to the current travel period is TT, if TT is before 3 pm, then the "stay 1" hotel can be recommended in the target route, and if TT is after 3 pm, then the "stay 2" hotel can be recommended in the target route. At the same time, this embodiment can combine third-party information sources to classify accommodation into three types of "economical", "comfortable" and "luxury" for recommendation.

[0131] For example, this embodiment can also display sharp turns and dangerous sections of the road in the target road book by obtaining warning signs provided by the navigation software. This embodiment can also perform segmented surrounding search through the track point data of the target road book, thereby realizing the surrounding search of the track, so as to find gas stations and charging stations around the target road book and display them in the target road book.

[0132] See also Fig. 9 The schematic diagram of the road book rendering layer, based on the technical solutions of the above embodiments, the present application can also render the target road book.

[0133] For example, the rendering feature data in the target road book can be extracted, and layer management and division can be performed according to the rendering feature data. The rendering feature data includes: point of interest data (including point location, point classification, point name), point of interest area data (including area location, area name) and travel route data (including trajectory data and schedule overview data for each travel period).

[0134] Among them, the base map layer is used to render the background image selected by the user through the interface; the track layer is used to render the track data; the information point layer can include the area data of the point of interest, etc. All data can be moved directly on the layer; the text content layer can include the itinerary summary, title, etc. The lower the layer, the higher the priority (the priority from high to low is base map layer-track layer-information point layer-text content layer), and the earlier it is rendered, the effect achieved is that the layer with priority rendering will be covered by the previous layer. It is worth noting that the rendering method uses different rendering engine libraries on different system platforms, which will not be elaborated in this application.

[0135] In an optional embodiment, a target route book can be constructed based on the travel data and the aforementioned target travel route. Fig.10 The travel data collection process diagram shown in FIG. 1 can be used to collect travel data in the following ways: One optional implementation method is to recognize and process the travel data in the form of video, that is, to convert the audio information in the video into text information through speech recognition technology (ASR) technology (or to directly recognize and process the travel data in the form of text), and then to recognize the scenic spots, food, and hotel nouns in the text information through large language model (LLM) technology. The identified scenic spots, food, and hotels are determined by querying the proprietary knowledge base to determine the specific data classification and data popularity information, and finally generate a travel data list (the data list may include the scenic spots, food recommendations, and accommodation recommendations for each day's itinerary mined from the article). Another optional implementation method is to recognize and process the travel data in the form of pictures and texts, that is, to use mature optical character recognition (OCR) technology to recognize all the text in the pictures and texts and convert them into text information. The subsequent processing flow refers to the subsequent logic of video processing and text processing, and finally generates a travel data list.

[0136] It should be noted that this application can also perform data cleaning on the travel data list, including: analyzing the validity of the data in the travel data list through LLM, and determining whether the data in the travel data list belongs to attractions, hotels or food; if the analysis result is that it does not belong to the relevant classification, it will be marked for reminder processing, and then secondary correction and filtering will be performed through manual review. This application can also perform sensitive word cleaning on the travel data list, including: accessing the sensitive word library through a compliant online API, and determining whether there are non-compliant sensitive words flowing into the travel data list through fuzzy and precise query methods, and completing sensitive word cleaning.

[0137] This application can also use the Levenshtein distance (Levenshtein distance, Levenshtein) algorithm to confirm whether the travel data meets the identification requirements by combining character similarity and geographical location similarity. For example, assuming that there are internal database A and external database B, it is now necessary to compare the untrusted external database B with the attractions in the internal database A, so that the attractions in the external database B are clearly identified as real attractions, and if the attractions in the external database B are not clear in the internal database A, whether they can be used as real attractions in the internal database A. First, it is necessary to confirm the city and location of the attractions in the external database B, which are used to narrow the scope of use in the comparison process with the attractions in the internal database A. Assuming that the text information currently analyzed is a travel guide, the city must be confirmed first. Exemplarily, a map data retrieval engine can be used to extract the location information in the text information. The attraction B1 of the external database B can be provided to the map retrieval engine, and the result with the highest similarity retrieved based on the map retrieval engine is returned. It is assumed that the returned result is the description data of the attraction B2, including the attraction name and attraction location. Because the attraction names in the external database B are all reviewed through the compliance process, the attraction names are all standardized and real. Furthermore, the name of the scenic spot B2 is used to match the scenic spots in the internal database A using the Levenshtein algorithm.

[0138] It should be noted that when matching characters through the Levenshtein algorithm, data processing is required to remove interfering character strings. If the description data of the acquired scenic spot B2 includes special characters, it is necessary to remove the special characters. Taking the name of scenic spot B2 as an example, after removing the special characters, it is changed to B2N, and B2N is compared with all scenic spot data in the internal database A through the Levenshtein algorithm to obtain the similarity of the scenic spot; if there is a scenic spot A1 in the internal database A with a similarity greater than 90% with the scenic spot corresponding to the scenic spot B2, then according to the distance difference between the location information of the scenic spot B2 and the scenic spot A1; if the distance difference is less than the preset distance threshold (such as 200 meters), it is considered that the scenic spot B2 is the same as the scenic spot A at this time, and then the content of the scenic spot B2 is considered to be identified. Further, if the scenic spot B2 is found to have no matching results in the internal database A, it is necessary to manually access and analyze whether it is a scenic spot missing in the internal database A. If so, it is necessary to add the scenic spot B2 to the internal database A.

[0139] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0140] Based on the same inventive concept, the embodiment of the present application also provides a road book generating device for implementing the road book generating method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more road book generating device embodiments provided below can refer to the limitations of the road book generating method above, and will not be repeated here.

[0141] In an exemplary embodiment, Fig.11 As shown, a road book generating device is provided, including: a selection module 710, a first determination module 720, a second determination module 730 and a construction module 740, wherein:

[0142] A selection module 710 is used to select non-starting interest points related to the starting interest point of this iteration process from at least one candidate interest point that matches the road book portrait data; wherein the first starting interest point is preset;

[0143] A first determination module 720 is used to determine, for each non-starting point of interest corresponding to this iteration process, a target recommendation probability of the non-starting point of interest according to the recommendation influence data of the non-starting point of interest;

[0144] The second determination module 730 is used to determine the starting point of interest for the next iteration process from the non-starting points of interest according to the target recommendation probability of each non-starting point of interest, and return to perform the non-starting point of interest selection operation;

[0145] The construction module 740 is used to generate a target road book according to the starting points of interest in each iterative process when the travel restriction conditions in the road book portrait data are met.

[0146] In one embodiment, the first determination module 720 includes: a mutation determination unit, used to determine the mutation probability of this iteration process; a data update unit, used to update the recommendation influence data of non-starting interest points according to the mutation probability of this iteration process; a probability determination unit, used to determine the target recommendation probability of non-starting interest points according to the updated recommendation influence data corresponding to the non-starting interest points.

[0147] In one embodiment, the mutation determination unit is further used to lower the mutation probability of the previous iteration process to obtain the mutation probability of the current iteration process.

[0148] In one embodiment, the selection module 710 includes: a first starting interest point determination unit, configured to select one of the candidate interest points as the starting interest point of the first iteration process according to the density of interest points in the area where the candidate interest points are located.

[0149] In one of the embodiments, the first starting point of interest determination unit is further used to grid the area where at least one candidate point of interest is located to obtain at least one grid area; select a target grid area from at least one grid area according to the number of candidate points of interest contained in each grid area; and select one of the candidate points of interest in the target grid area as the starting point of interest for the first iteration process.

[0150] In one embodiment, the construction module 740 includes: a point grouping unit, which is used to group the starting interest points in each iterative process according to the administrative division to which the starting interest points belong, so as to obtain at least one interest point group; a point selection unit, which is used to select the starting point within the interest point group from the starting interest points of the interest point group for each interest point group; a route planning unit, which is used to construct an intra-group travel route of the interest point group based on the shortest path planning algorithm according to the intra-group starting point of the interest point group; and a road book generation unit, which is used to generate a target road book according to the intra-group travel route of each interest point group.

[0151] In one of the embodiments, the point selection unit is further used to sort the interest point groups according to the traffic reference data between the administrative divisions to which the interest point groups belong, with the interest point group where the preset travel starting point is located as the first interest point group; for the first interest point group, the preset travel starting point is used as the starting point within the group; for each non-first interest point group, the starting point within the group of this interest point group is determined according to the tail interest point of the route appearing in the corresponding group of the previous interest point group.

[0152] In one embodiment, the selection module 710 is also used to determine the selection probability of each travel theme in each travel period according to the matching between the road book portrait data and different travel themes; accordingly, from at least one candidate interest point that matches the road book portrait data, various non-starting interest points related to the starting interest point of this iteration process are selected, including: for each travel period, according to the selection probability of each travel theme in the travel period, at least one candidate interest point in the travel period is determined, and from at least one candidate interest point in the travel period, various non-starting interest points related to the starting interest point of this iteration process are selected; accordingly, when the travel restriction conditions in the road book portrait data are met, according to the starting interest points in each iteration process, a target road book is generated, including: when the travel restriction conditions in the travel period are met, according to the starting interest points in each iteration process, a target travel route in the travel period is constructed; according to the target travel route in each travel period, a target road book is generated.

[0153] Each module in the road book generating device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0154] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Fig.12As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for generating a road book is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0155] Those skilled in the art will understand that Fig.12 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0156] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0157] Selecting non-starting points of interest related to the starting point of interest of this iteration process from at least one candidate point of interest that matches the road book portrait data; wherein the first starting point of interest is preset;

[0158] For each non-starting point of interest corresponding to this iteration process, determine the target recommendation probability of the non-starting point of interest according to the recommendation influence data of the non-starting point of interest;

[0159] According to the target recommendation probability of each non-starting interest point, determine the starting interest point of the next iteration process from each non-starting interest point, and return to perform the non-starting interest point selection operation;

[0160] When the travel restriction conditions in the road book portrait data are met, the target road book is generated according to the starting points of interest in each iterative process.

[0161] In one embodiment, when the processor executes the computer program, the following steps are also implemented: determining the mutation probability of this iteration process; updating the recommendation influence data of non-starting interest points based on the mutation probability of this iteration process; and determining the target recommendation probability of non-starting interest points based on the updated recommendation influence data corresponding to the non-starting interest points.

[0162] In one embodiment, when the processor executes the computer program, the following steps are further implemented: lowering the mutation probability of the previous iteration process to obtain the mutation probability of the current iteration process.

[0163] In one embodiment, when the processor executes the computer program, the following steps are further implemented: according to the density of interest points in the area where each candidate interest point is located, one of the candidate interest points is selected as the starting interest point of the first iteration process.

[0164] In one embodiment, when the processor executes the computer program, the following steps are also implemented: gridding the area where at least one candidate point of interest is located to obtain at least one grid area; selecting a target grid area from at least one grid area based on the number of candidate points of interest contained in each grid area; and selecting one of the candidate points of interest in the target grid area as the starting point of interest for the first iteration process.

[0165] In one embodiment, when the processor executes the computer program, the following steps are also implemented: grouping the starting points of interest according to the administrative regions to which the starting points of interest in each iterative process belong to obtain at least one point of interest group; for each point of interest group, selecting the starting point within the group of the point of interest group from the starting points of the point of interest group; constructing the intra-group travel routes of the point of interest group based on the shortest path planning algorithm according to the intra-group starting points of the point of interest group; generating a target road book based on the intra-group travel routes of each point of interest group.

[0166] In one embodiment, the processor further implements the following steps when executing the computer program: sorting the interest point groups based on the traffic reference data between the administrative divisions to which each interest point group belongs, with the interest point group where the preset travel starting point is located as the first interest point group; for the first interest point group, using the preset travel starting point as the starting point within the group; for each non-first interest point group, determining the starting point within the group of this interest point group based on the tail interest point of the route that appears in the corresponding group of the previous interest point group.

[0167] In one embodiment, the processor also implements the following steps when executing the computer program: determining the selection probability of each travel theme in each travel period according to the matching between the road book portrait data and different travel themes; correspondingly, selecting various non-starting points of interest related to the starting point of interest of this iteration process from at least one candidate point of interest matching the road book portrait data, including: for each travel period, determining at least one candidate point of interest in the travel period according to the selection probability of each travel theme in the travel period, and selecting various non-starting points of interest related to the starting point of interest of this iteration process from at least one candidate point of interest in the travel period; correspondingly, generating a target road book according to the starting point of interest in each iteration process when the travel restriction conditions in the road book portrait data are met, including: constructing a target travel route in the travel period according to the starting point of interest in each iteration process when the travel restriction conditions in the travel period are met; generating a target road book according to the target travel route in each travel period.

[0168] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0169] Selecting non-starting points of interest related to the starting point of interest of this iteration process from at least one candidate point of interest that matches the road book portrait data; wherein the first starting point of interest is preset;

[0170] For each non-starting point of interest corresponding to this iteration process, determine the target recommendation probability of the non-starting point of interest according to the recommendation influence data of the non-starting point of interest;

[0171] According to the target recommendation probability of each non-starting interest point, determine the starting interest point of the next iteration process from each non-starting interest point, and return to perform the non-starting interest point selection operation;

[0172] When the travel restriction conditions in the road book portrait data are met, the target road book is generated according to the starting points of interest in each iterative process.

[0173] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: determining the mutation probability of this iteration process; updating the recommendation influence data of non-starting interest points based on the mutation probability of this iteration process; and determining the target recommendation probability of non-starting interest points based on the updated recommendation influence data corresponding to the non-starting interest points.

[0174] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: lowering the mutation probability of the previous iteration process to obtain the mutation probability of the current iteration process.

[0175] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: according to the density of interest points in the area where each candidate interest point is located, one of the candidate interest points is selected as the starting interest point of the first iteration process.

[0176] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: gridding the area where at least one candidate point of interest is located to obtain at least one grid area; selecting a target grid area from at least one grid area based on the number of interest points of the candidate points of interest contained in each grid area; and selecting one of the candidate points of interest in the target grid area as the starting point of interest for the first iteration process.

[0177] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: grouping the starting points of interest according to the administrative regions to which the starting points of interest belong in each iterative process to obtain at least one point of interest group; for each point of interest group, selecting the starting point within the group from the starting points of interest in the point of interest group; constructing the travel routes within the point of interest group based on the shortest path planning algorithm according to the starting points within the group; and generating a target road book based on the travel routes within each point of interest group.

[0178] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the traffic reference data between the administrative divisions to which each interest point group belongs, the interest point group where the preset travel starting point is located is used as the first interest point group, and the interest point groups are sorted; for the first interest point group, the preset travel starting point is used as the starting point within the group; for each non-first interest point group, the starting point within the group of this interest point group is determined based on the tail interest point of the route that appears in the corresponding group of the previous interest point group.

[0179] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: according to the matching between the road book portrait data and different travel themes, the selection probability of each travel theme in each travel period is determined; accordingly, from at least one candidate interest point that matches the road book portrait data, various non-starting interest points related to the starting interest point of this iteration process are selected, including: for each travel period, according to the selection probability of each travel theme in the travel period, at least one candidate interest point in the travel period is determined, and from at least one candidate interest point in the travel period, various non-starting interest points related to the starting interest point of this iteration process are selected; accordingly, under the condition that the travel restriction conditions in the road book portrait data are met, according to the starting interest point in each iteration process, a target road book is generated, including: under the condition that the travel restriction conditions in the travel period are met, according to the starting interest point in each iteration process, a target travel route in the travel period is constructed; according to the target travel route in each travel period, a target road book is generated.

[0180] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0181] Selecting non-starting points of interest related to the starting point of interest of this iteration process from at least one candidate point of interest that matches the road book portrait data; wherein the first starting point of interest is preset;

[0182] For each non-starting point of interest corresponding to this iteration process, determine the target recommendation probability of the non-starting point of interest according to the recommendation influence data of the non-starting point of interest;

[0183] According to the target recommendation probability of each non-starting interest point, determine the starting interest point of the next iteration process from each non-starting interest point, and return to perform the non-starting interest point selection operation;

[0184] When the travel restriction conditions in the road book portrait data are met, the target road book is generated according to the starting points of interest in each iterative process.

[0185] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: determining the mutation probability of this iteration process; updating the recommendation influence data of non-starting interest points based on the mutation probability of this iteration process; and determining the target recommendation probability of non-starting interest points based on the updated recommendation influence data corresponding to the non-starting interest points.

[0186] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: lowering the mutation probability of the previous iteration process to obtain the mutation probability of the current iteration process.

[0187] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: according to the density of interest points in the area where each candidate interest point is located, one of the candidate interest points is selected as the starting interest point of the first iteration process.

[0188] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: gridding the area where at least one candidate point of interest is located to obtain at least one grid area; selecting a target grid area from at least one grid area based on the number of interest points of the candidate points of interest contained in each grid area; and selecting one of the candidate points of interest in the target grid area as the starting point of interest for the first iteration process.

[0189] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: grouping the starting points of interest according to the administrative regions to which the starting points of interest belong in each iterative process to obtain at least one point of interest group; for each point of interest group, selecting the starting point within the group from the starting points of interest in the point of interest group; constructing the travel routes within the point of interest group based on the shortest path planning algorithm according to the starting points within the group; and generating a target road book based on the travel routes within each point of interest group.

[0190] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the traffic reference data between the administrative divisions to which each interest point group belongs, the interest point group where the preset travel starting point is located is used as the first interest point group, and the interest point groups are sorted; for the first interest point group, the preset travel starting point is used as the starting point within the group; for each non-first interest point group, the starting point within the group of this interest point group is determined based on the tail interest point of the route that appears in the corresponding group of the previous interest point group.

[0191] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: according to the matching between the road book portrait data and different travel themes, the selection probability of each travel theme in each travel period is determined; accordingly, from at least one candidate interest point that matches the road book portrait data, various non-starting interest points related to the starting interest point of this iteration process are selected, including: for each travel period, according to the selection probability of each travel theme in the travel period, at least one candidate interest point in the travel period is determined, and from at least one candidate interest point in the travel period, various non-starting interest points related to the starting interest point of this iteration process are selected; accordingly, under the condition that the travel restriction conditions in the road book portrait data are met, according to the starting interest point in each iteration process, a target road book is generated, including: under the condition that the travel restriction conditions in the travel period are met, according to the starting interest point in each iteration process, a target travel route in the travel period is constructed; according to the target travel route in each travel period, a target road book is generated.

[0192] It should be noted that the data involved in this application (including but not limited to data used for analysis, stored data, displayed data, etc.) are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0193] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0194] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0195] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for generating a road book, It is characterized in that The method comprises: According to the matching between the road book portrait data and different travel themes, the selection probability of each travel theme in at least each travel period is determined; the road book portrait data corresponds to at least two travel periods; For each travel period, at least one candidate point of interest in the travel period is determined according to the selection probability of each travel theme in the travel period, and non-starting points of interest related to the starting point of interest of this iteration process are selected from the at least one candidate point of interest in the travel period; wherein the first starting point of interest is preset; For each non-starting point of interest corresponding to the current iteration process, determine the mutation probability of the current iteration process; update the recommendation influence data of the non-starting point of interest according to the mutation probability of the current iteration process; determine the target recommendation probability of the non-starting point of interest according to the updated recommendation influence data corresponding to the non-starting point of interest; According to the target recommendation probability of each of the non-starting interest points, determine the starting interest point of the next iteration process from each of the non-starting interest points, and return to perform the non-starting interest point selection operation; When the travel restriction conditions in the road book portrait data are met, a target road book is generated according to the starting points of interest in each iterative process.

2. The method according to claim 1, It is characterized in that Determining the mutation probability of this iteration process includes: Lower the mutation probability of the previous iteration process to obtain the mutation probability of this iteration process.

3. The method according to any one of claims 1 to 2, It is characterized in that The first starting point of interest is determined as follows: According to the density of interest points in the area where each of the candidate interest points is located, one of the candidate interest points is selected as the starting interest point of the first iteration process.

4. The method according to claim 3, It is characterized in that The step of selecting one of the candidate interest points as the starting interest point of the first iteration process according to the density of the interest points in the area where the candidate interest points are located includes: Dividing the area where the at least one candidate point of interest is located into grids to obtain at least one grid area; Selecting a target grid area from the at least one grid area according to the number of interest points of the candidate interest points contained in each of the grid areas; One of the candidate interest points in the target grid area is selected as the starting interest point of the first iteration process.

5. The method according to any one of claims 1 to 2, It is characterized in that The step of generating a target road book according to the starting points of interest in each iteration process includes: According to the administrative divisions to which the starting points of interest in each iteration process belong, grouping the starting points of interest to obtain at least one point of interest group; For each interest point group, selecting a starting point within the interest point group from each starting interest point of the interest point group; According to the starting point within the group of interest points, based on the shortest path planning algorithm, construct a travel route within the group of interest points; The target road book is generated according to the travel routes within each of the interest point groups.

6. The method according to claim 5, It is characterized in that The selecting, from the starting points of interest in the group of points of interest, a starting point within the group of points of interest comprises: According to the traffic reference data between the administrative divisions to which each point of interest group belongs, the point of interest group where the preset travel starting point is located is used as the first point of interest group, and the said point of interest groups are sorted; For the first POI group, the preset travel starting point is used as the starting point in the group; For each non-first POI group, the starting point of the current POI group is determined according to the tail POI of the route that appears in the corresponding group of the previous POI group.

7. The method according to any one of claims 1 to 2, It is characterized in that The method of generating a target road book according to the starting points of interest in each iterative process when the travel restriction conditions in the road book portrait data are met includes: Under the condition that the travel restriction conditions in the travel period are met, a target travel route in the travel period is constructed according to the starting points of interest in each iterative process; The target route book is generated according to the target travel route under each travel time period.

8. A road book generating device, It is characterized in that include: The selection module is used to determine the selection probability of each travel theme in each of the two travel periods according to the matching between the road book portrait data and different travel themes; The road book portrait data corresponds to at least two travel periods; For each travel period, at least one candidate point of interest in the travel period is determined according to the selection probability of each travel theme in the travel period, and non-starting points of interest related to the starting point of interest of this iteration process are selected from the at least one candidate point of interest in the travel period; wherein the first starting point of interest is preset; The first determination module is used to determine the mutation probability of the current iteration process for each non-starting interest point corresponding to the current iteration process; update the recommendation influence data of the non-starting interest point according to the mutation probability of the current iteration process; and determine the target recommendation probability of the non-starting interest point according to the updated recommendation influence data corresponding to the non-starting interest point; A second determination module is used to determine the starting point of interest of the next iteration process from each of the non-starting points of interest according to the target recommendation probability of each of the non-starting points of interest, and return to perform the non-starting point of interest selection operation; A construction module is used to generate a target road book according to the starting points of interest in each iterative process when the travel restriction conditions in the road book portrait data are met.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images