A point of interest recommendation method, related method and device, and equipment

Abstract

The application discloses a point of interest recommendation method, a related method and device and equipment. The recommendation method comprises the following steps: obtaining at least one recommendation scene corresponding to a received point of interest recommendation request from a preset scene set; obtaining a first target point of interest set associated with a display area range corresponding to the recommendation request from a preset POI database according to the at least one recommendation scene; obtaining the overlying relationship between each target point of interest in the first target point of interest set, performing overlying removal processing, obtaining a second target point of interest set and performing recommendation. Through the technical scheme provided by the embodiment of the application, the problem that a traditional map cannot display points of interest according to user demand can be solved, the user is preferentially recommended the point of interest information of interest, so that dynamic display of point of interest information is realized, the display and layout of three-dimensional points of interest in the map are readjusted, and the map display is more beautiful and practical.

Description

Technical Field

[0001] This invention relates to computer technology, and more particularly to a method, related methods, apparatus, and device for recommending points of interest. Background Technology

[0002] With the development of computer technology and the widespread use of navigation applications, users' travel experience has been greatly improved. Navigation applications, designed for various travel scenarios, typically provide basic navigation functions such as destination search, route planning, voice prompts during driving, and turn diagrams at intersections to meet users' basic travel needs.

[0003] To accurately represent the real world, existing maps require comprehensive and detailed information. Therefore, Points of Interest (POIs) on maps typically correspond one-to-one with real-world POIs, allowing users to visually view all POI information. However, for map users, a large portion of the map is occupied by large or popular POIs. These POIs are not essential or frequently used by users, especially the 3D POIs, which occupy an even larger area. This forces users to sift through a vast amount of POI information to find the information they need. Summary of the Invention

[0004] The inventors of this invention have discovered that existing map technologies, which display all POI information, do not consider POIs of interest to the user and cannot display 3D points of interest according to the user's needs. Based on this, the inventors have proposed this invention to provide a point of interest recommendation method, related methods, apparatus, and devices that overcome the above-mentioned problems or at least partially solve the problems existing in the prior art, thereby making map displays more aesthetically pleasing and practical.

[0005] In a first aspect, embodiments of the present invention provide a point-of-interest recommendation method, the method comprising:

[0006] Based on the received point of interest recommendation request, at least one recommended scene corresponding to the recommendation request is obtained from a preset scene set;

[0007] According to the at least one recommendation scenario, a first set of target interest points associated with the display area range corresponding to the recommendation request is obtained from a preset POI database;

[0008] Obtain the overlap relationship between each target interest point in the first target interest point set, perform de-overlap processing, obtain the second target interest point set, and make recommendations.

[0009] In a second aspect, embodiments of the present invention provide a point-of-interest (POI) display method, applied to a terminal device, comprising:

[0010] Send a request for point-of-interest recommendations;

[0011] Receive the second target interest point set determined according to the interest point recommendation method described above;

[0012] Based on the second set of target points of interest, the model of each target POI in the second set of target points of interest is drawn and displayed.

[0013] Thirdly, embodiments of the present invention provide an interest point recommendation device, comprising:

[0014] The scene determination module is used to obtain at least one recommended scene corresponding to the received interest point recommendation request from a preset scene set;

[0015] The first acquisition module is used to acquire a first set of target interest points associated with the display area range corresponding to the recommendation request from a preset POI database according to the at least one recommendation scenario;

[0016] The second acquisition module is used to acquire the overlapping relationships between the target interest points in the first target interest point set, perform de-overlapping processing, obtain the second target interest point set, and make recommendations.

[0017] Fourthly, embodiments of the present invention provide a point-of-interest display device, applied to a terminal device, comprising:

[0018] The sending module is used to send point-of-interest recommendation requests;

[0019] The receiving module is used to receive the second target interest point set determined according to the interest point recommendation method described above;

[0020] The display module is used to draw and display the models of each target POI in the second target point of interest set.

[0021] Fifthly, embodiments of the present invention provide an electronic device, the electronic device comprising:

[0022] At least one processor; and

[0023] A memory communicatively connected to the at least one processor; wherein,

[0024] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the above-described point-of-interest recommendation method and / or the above-described point-of-interest display method.

[0025] In a sixth aspect, embodiments of the present invention provide a computer-readable storage medium storing computer instructions that cause a processor to execute the above-described point-of-interest recommendation method and / or the above-described point-of-interest display method.

[0026] The beneficial effects of the above-described solutions provided in the embodiments of the present invention include at least the following:

[0027] The technical solution of this invention solves the problem that traditional maps cannot display points of interest according to user needs by obtaining at least one recommended scene corresponding to the received point of interest recommendation request from a preset scene set; obtaining a first set of target points of interest associated with the display area range corresponding to the recommendation request from a preset POI database according to the at least one recommended scene; obtaining the overlay relationship between each target point of interest in the first set of target points of interest, performing de-overlay processing, obtaining a second set of target points of interest, and recommending it. By filtering POI information according to the user's usage scenario, the invention prioritizes recommending points of interest information that the user is interested in, so as to realize the dynamic display of points of interest information on the user's end. Furthermore, since the points of interest information displayed on the map is dynamic, the overlay processing hides some three-dimensional points of interest that the user is not interested in, which can realize the readjustment of the display layout of three-dimensional points of interest in the map, avoid interference from invalid points of interest information, improve the display effect of points of interest information that the user is interested in, and make the map display more beautiful and practical.

[0028] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0029] Figure 1 This is a flowchart of an interest point recommendation method provided in Embodiment 1 of the present invention;

[0030] Figure 2 This is a flowchart of user profile acquisition provided in Embodiment 1 of the present invention;

[0031] Figure 3 This is a flowchart illustrating the construction of the POI database provided in Embodiment 1 of the present invention;

[0032] Figure 4 This is a flowchart of the POI recommended location determination process in the POI database provided in Embodiment 1 of the present invention;

[0033] Figure 5 This is a flowchart illustrating the implementation of scene interaction provided in Embodiment 1 of the present invention;

[0034] Figure 6 This is a schematic diagram of point-of-interest display provided in Embodiment 1 of the present invention. Figure 1 ;

[0035] Figure 7 This is a schematic diagram of point-of-interest display provided in Embodiment 1 of the present invention. Figure 2 ;

[0036] Figure 8 This is a schematic diagram of point-of-interest display provided in Embodiment 1 of the present invention. Figure 3 ;

[0037] Figure 9 This is a schematic diagram of point-of-interest display provided in Embodiment 1 of the present invention. Figure 4 ;

[0038] Figure 10 This is a schematic diagram of point-of-interest display provided in Embodiment 1 of the present invention. Figure 5 ;

[0039] Figure 11 This is a flowchart illustrating the implementation process of displaying points of interest according to Embodiment 1 of the present invention.

[0040] Figure 12 This is a flowchart of a point-of-interest display method provided in Embodiment 2 of the present invention;

[0041] Figure 13 This is a schematic diagram of the structure of a point-of-interest recommendation device provided in Embodiment 3 of the present invention;

[0042] Figure 14 This is a schematic diagram of the structure of a point of interest display device provided in Embodiment 4 of the present invention;

[0043] Figure 15 This is a schematic diagram of the structure of an electronic device used to implement embodiments of the present invention. Detailed Implementation

[0044] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0045] It should be noted that the terms "first," "second," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0046] Example 1

[0047] Figure 1 This is a flowchart of an interest point recommendation method provided in Embodiment 1 of the present invention. This embodiment can be applied to the determination, recommendation, and display of 3D interest points. The method can be executed by the interest point recommendation device provided in this embodiment of the invention, which can be implemented in software and / or hardware. Figure 1 As shown, the point-of-interest recommendation method provided in this embodiment includes:

[0048] S101. Based on the received point of interest recommendation request, obtain at least one recommended scene corresponding to the recommendation request from a preset scene set.

[0049] In this embodiment, the point of interest recommendation request in step S101 can be a request initiated by the user through a terminal device. This request may include at least one of the following: request time information, vehicle status, the current location of the terminal device, and the map display area information of the terminal device. Therefore, recommended scenarios related to the current time, vehicle status, terminal device location, and / or map display area can be obtained based on this request. The preset scenario set contains at least one preset scenario. Different scenarios can be determined through preset methods in the preset scenario set. For example, the preset scenario set may include at least one scenario such as breakfast scenario, low fuel scenario, low battery scenario, holiday scenario, outing scenario, and arrival scenario.

[0050] S102. Based on the at least one recommended scenario, obtain a set of first target interest points associated with the display area range corresponding to the recommendation request from a preset POI database.

[0051] In this embodiment, the POI database includes the recommended location information and scene category for each POI model; the process of obtaining the first target interest point set in step S102 is as follows:

[0052] Based on the geographic region range information in the received point of interest recommendation request and the recommended location information of each POI model in the POI database, POI models whose recommended location information matches the geographic region range are selected from the POI database.

[0053] Based on the at least one recommended scenario, a POI model corresponding to the scenario category is matched to determine the POI model for each recommended scenario, thus obtaining a first set of target interest points. This first set of target interest points includes the first target interest points corresponding to the at least one recommended scenario. The aforementioned geographical area information constitutes the map display area of ​​the user's terminal device.

[0054] It should be noted that, in this embodiment, the POI model in the POI data is a 3D POI model.

[0055] S103. Obtain the overlap relationship between each target interest point in the first target interest point set, perform deovering processing, obtain the second target interest point set, and make recommendations.

[0056] In this embodiment, the aforementioned POI model database may include the overlay relationship between each POI model and other POI models. Therefore, after obtaining the first set of target points of interest, the overlay relationship between each target point of interest in the set can be obtained, enabling overlay processing. This hides some target points of interest in the first set, resulting in the overlaid target points of interest, which constitute the second set of target points of interest. This second set of target points of interest is then recommended to the terminal device corresponding to the point of interest recommendation request, thereby enabling the display of each target point of interest in the second set of target points of interest on the terminal device and displaying POI information of interest to the user on the map. Since the terminal device may be moving during map navigation, the information in the point of interest recommendation request is dynamically changing. Therefore, the second set of target points of interest obtained through this point of interest recommendation method is also dynamically changing, thus enabling dynamic display of POI information on the terminal device.

[0057] In this embodiment, the overlay processing rule for target interest points with overlay relationships in the first target interest point set can be as follows: first, retain target interest point POIs with higher priority according to the scene priority of the target interest points; if the scene priorities are the same, retain target interest point POIs that match the user's preferences; if both the scene priority and the user's preferences are the same, randomly select a target interest point POI.

[0058] In one specific embodiment, the aforementioned preset scene set may include the priority of each recommended scene; in step S103, obtaining the overlap relationship between each target interest point in the first target interest point set, performing de-overlap processing, obtaining the second target interest point set, and making recommendations includes:

[0059] Based on the overlap relationship between each target point of interest in the first target point of interest set, determine whether the priority of the scene to which any two target POI models with overlap relationship belong is different.

[0060] If so, retain the POI models with high priority in the relevant scene, obtain the second target interest point set, and make recommendations;

[0061] If not, based on the user profile of the user corresponding to the recommendation request, a POI model that matches the user's preference information is selected from the two target interest points with overlapping relationship, and the second target interest point set is obtained and recommended.

[0062] In this embodiment, the priority of each recommended scene in the preset scene set can be customized. For example, different priority values ​​can be assigned to different recommended scenes according to their importance. This could be that a smaller value indicates a higher priority, and a larger value indicates a lower priority, or vice versa. Based on the target interest points in the first target interest point set, if there is an overlap between the target interest points and multiple scenes exist, target interest points in scenes with higher priority are recommended first, while target interest points in scenes with lower priority are hidden, thus obtaining the second target interest point set.

[0063] In this embodiment, step S103 above, which involves filtering out POI models that match user preference information from the two target points of interest with overlapping relationships based on the obtained user profile of the user corresponding to the recommendation request, includes:

[0064] Obtain the user profile of the user corresponding to the recommendation request;

[0065] For each recommendation scenario, obtain at least one user tag from the user profile;

[0066] Based on at least one user tag in the user profile, select POI models that match at least one user tag from any two target points of interest with overlapping relationship, and obtain POI models that match user preferences.

[0067] In this embodiment of the invention, reference is made to Figure 2As shown, user tags in a user profile can include at least one of the following: basic information tags, lifestyle information tags, travel information tags, vehicle maintenance information tags, and vehicle usage information tags. Of course, in this embodiment of the invention, user tags in a user profile can be configured according to actual needs and are not limited to the above-mentioned user tags. During the execution of this solution, the relationship between recommended scenarios and user tags can be predefined, establishing a correspondence between different scenarios and user tags. For example, a breakfast scenario can be associated with lifestyle information tags; a low fuel consumption scenario can be associated with vehicle maintenance information tags and vehicle usage information tags. The POI model that matches user preferences can be a POI model that matches any user tag in the user's user profile. When two target points of interest with a coverage relationship both match user preferences, the target point of interest with a larger number of matching user tags can be selected for recommendation based on the number of user tags matched by the two target points of interest.

[0068] Reference Figure 2 As shown, user profiles can be generated by a user profile tagging system based on multiple source data obtained from various channels. The user profile tags are then segmented according to the data source information obtained through the user profile tagging system. These data sources can include user personal information data, vehicle trajectory data, vehicle navigation data, vehicle operation data, and third-party data. This third-party data could, for example, be user purchasing preference data and dietary habit data obtained from various shopping applications.

[0069] In this embodiment, the POI data in the POI database can be generated in the following way:

[0070] First, refer to Figure 3 As shown, in order to make the map display more aesthetically pleasing, this invention creates 3D POI models for different POI categories. It should be noted that in the production of 3D POI model data, not all POIs in the map are created as 3D POI models.

[0071] Next, create a "Model Classification Comparison Table", which can include information such as POI classification CODE, classification name, model storage path, model file name, and model dimensions.

[0072] The POIs in this "Model Classification Reference Table" can be classified into parent scene categories, child scene categories, and grandchild scene categories according to scene classification rules. The parent scene categories, child scene categories, and grandchild scene categories have an inclusion relationship. When processing the data, attention needs to be paid to handling the classification relationship. According to the preset POI scene classification rules, it is determined whether each POI model belongs to a grandchild scene category under the parent scene category. If so, the grandchild scene category is determined as the scene category corresponding to the POI model; if not, it is determined whether each POI model belongs to a child scene category under the parent scene category. If so, the child scene category is determined as the scene category corresponding to the POI model; if not, the parent scene category is determined as the scene category corresponding to the POI model. Wherein, refer to... Figure 3 As shown, in the preset POI scene classification rules, the parent scene category can be called the major category, the child scene category can be called the medium category, and the grandchild scene category can be called the minor category.

[0073] Next, based on the "Model Classification Comparison Table," map POI classification information (POI classifications are predefined data, primarily categorized according to different dimensions, such as transportation services, accommodation, companies, restaurants, etc., and consistent with the POI classifications in the "Model Classification Comparison Table"), and map POI information (including POI code, name, latitude and longitude, classification, etc.), the 3D POI models corresponding to the relevant classifications in the table are extracted and stored in the database, forming the POI database. (Refer to...) Figure 3 As shown in this embodiment, the POI database can also be called the POI information database.

[0074] In one specific embodiment, suppose the parent scene is food, the child scene is Chinese or Western food, and the grandchild scene is KFC or McDonald's. The specific classification method for the scene category corresponding to the POI model is as follows: first, determine whether the scene category is a grandchild scene category; if not, then determine whether the scene category is a child scene category; if not, finally determine it as the parent scene category.

[0075] In this embodiment, since a POI in a 2D map is just a point, it does not overlap with roads. When a 3D POI model is added, a point becomes an object with length, width, and height. The original POI display location (including latitude and longitude information) may overlap with roads after adding length, width, and height. Therefore, the inventors propose to determine the placement of the POI model on the map through POI location data production, obtain recommended location information for the POI model, and store it in the POI database. POI location data production repositions the 3D POIs to suitable map locations, and provides a possible scaling ratio when placement is not possible. During POI location production, it is required that the POI model does not overlap with roads and that overlap between POI models is minimized.

[0076] Specifically, the recommended location information of the POI model can be obtained through the following methods:

[0077] Based on the original geographic location information of the POI model, determine the location information of the POI model in the original map;

[0078] Based on the 3D shape of the POI model, determine the bounding rectangle of the POI model, and determine whether the bounding rectangle of the POI model overlaps the road in the corresponding background display surface of the original map;

[0079] If so, perform position offset processing on the POI model to obtain the recommended position information of the POI model;

[0080] If not, the location information of the POI model in the original map shall be used as the recommended location information of the POI model.

[0081] Finally, the recommended location information from the POI model is updated in the POI database.

[0082] Among them, reference Figure 4 As shown, the 3D shape of the POI model is obtained from the POI model information read from the POI database;

[0083] The original geographic location information of the POI model is the location information of the POI point corresponding to the POI model in the original map, which is determined by reading the road network information from the map road network data.

[0084] For example, taking the background display surface as a reference object, when there are 3 POI models in the background display surface, namely POI model 1, POI model 2 and POI model 3, when POI model 1 overlaps with the road, and POI model 2 and POI model 3 do not overlap with the road, then POI model 1 is offset. When offsetting, POI model 1 is moved in a preset direction, and its movement range is ensured not to exceed the preset range.

[0085] The POI model is moved in a preset direction, with each move taking a certain distance at a preset step size, and it is continuously checked whether it overlaps with the road. When it moves to a position that does not overlap the road, or when the difference between the total distance moved by the POI model and the preset moving distance threshold is less than the preset step size, the movement operation is stopped, and the recommended position of the POI model is obtained.

[0086] By determining whether the bounding rectangle of the POI model overlaps with the road, and if so, an offset method is used to solve the problem of POI model overlapping with the road, the recommended position of the POI model is determined. For POI models that have not undergone offset processing, the determined position of the POI model in the original map is used as the recommended position of the POI model.

[0087] In this embodiment, after obtaining the recommended location information of the POI model, the recommended size information of the POI model can be obtained in the following way:

[0088] If, when the recommended position of the POI model is reached, the bounding rectangle of the POI model still overlaps the road on the corresponding background display surface in the map, then the POI model is proportionally compressed based on the obtained original size information of the POI model to obtain the recommended size information of the POI model.

[0089] If, when the POI model is placed at its recommended location, the circumscribed rectangle of the POI model does not cover the road on the corresponding background display surface in the map, then the original size information of the POI model will be used as the recommended size information of the POI model.

[0090] The original size information of the POI model can be the length, width and height information of the initially obtained POI model.

[0091] After moving POI model 1 a preset distance in a preset direction, if POI model 1 still overlaps with the road, then POI model 1 is shrunk until it no longer overlaps with the road, thus obtaining the recommended size information for the POI model. By using the shrunk POI model, the problem of the POI model still overlapping with the road after movement is solved.

[0092] In this embodiment, after obtaining the recommended size information of the POI model, the capping relationship information between the POI model and other POI models can be obtained in the following way:

[0093] Based on the recommended location and size information of each POI model, determine whether there is overlap between the POI models;

[0094] If so, adjust the recommended position of the POI model in the preset direction and determine the adjusted position information of the POI model;

[0095] Based on the adjusted location information and the recommended location information of each POI model, determine whether the adjustment distance of the POI model exceeds the preset distance;

[0096] If so, record the overlay relationship information between each POI model and other POI models;

[0097] No, the adjusted location information of the POI model will be used as the recommended location information of the updated POI model.

[0098] In the POI database, overlap can occur not only between POI models and roads, but also between POI models themselves. If a POI model overlaps with other POI models, it can be offset.

[0099] If the POI model is located in the lower left of the background display surface, and other POI models are located in the upper right of the background display surface, when the POI model overlaps with other POI models, the overlapping area is the upper right area of ​​POI model 1. The POI model is adjusted according to a preset direction, where the preset direction adjustment of the POI model can be at least one of the following: down, lower left, and left. The adjusted position information of the POI model can be obtained.

[0100] If the POI model is located in the upper left of the background display surface, and other POI models are located in the lower right of the background display surface, when the POI model overlaps with other POI models, the overlap area is the lower right area of ​​the POI model. The POI model is adjusted according to a preset direction, where the preset direction adjustment of the POI model can be at least one of left, upper left, and top, so that the adjusted position information of the POI model can be obtained.

[0101] If the POI model is located in the upper right of the background display surface, and other POI models are located in the lower left of the background display surface, and if the POI model overlaps with other POI models, the overlapped area is the lower left area of ​​the POI model. Adjust the POI model according to the preset direction, where the preset direction adjustment of the POI model can be at least one of right, upper right, and top, so as to obtain the adjusted position information of the POI model.

[0102] If the POI model is located in the lower right of the background display surface, and other POI models are located in the upper left of the background display surface, and if the POI model overlaps with other POI models, the overlapped area is the upper left area of ​​the POI model. Adjust the POI model according to the preset direction, where the preset direction adjustment of the POI model can be at least one of the following: down, lower right, and right, and the adjusted position information of the POI model can be obtained.

[0103] The following method can be used to determine whether the adjustment distance of the POI model exceeds the preset distance: when the POI models are adjusted to not overlap, the distance between the adjusted position information and the original position information is calculated; if the distance exceeds the preset distance threshold, the adjusted position information is discarded, the original position information is saved, and the overlap relationship information between the POI model and other POI models is recorded to avoid the adjusted POI model position information from differing too much from the actual position, thereby improving the accuracy of POI model position information determination.

[0104] In this embodiment, the above-mentioned method of obtaining at least one recommended scene corresponding to the received interest point recommendation request from a preset scene set specifically includes:

[0105] Based on the recommendation request, environmental perception information is obtained, and at least one recommended scene is obtained from a preset scene set based on the environmental perception information.

[0106] In this embodiment, the preset scenario set can be determined by preset methods to define different scenarios. For example, the preset scenario set may include breakfast scenario, low fuel scenario, low battery scenario, holiday scenario, outing scenario, arrival scenario, etc. The preset breakfast scenario can be the morning time from 04:00 to 09:00, which can be preset as breakfast when the user is driving. The low fuel scenario can be preset as low fuel scenario based on the fuel tank signal, when the fuel level is lower than a certain value.

[0107] In this embodiment, refer to Figure 5 As shown, the preset scene set includes recognition rules for each recommended scene; the above-mentioned obtaining environmental perception information based on the recommendation request, and obtaining at least one recommended scene from the preset scene set based on the environmental perception information, includes:

[0108] Obtain environmental perception information based on the recommendation request;

[0109] Obtain at least one recommended scene from a preset scene set that corresponds to the recognition rule and the environmental perception information.

[0110] Based on the above method, scene recognition is achieved through environmental perception information, resulting in at least one recommended scene.

[0111] The environmental perception information includes at least one of the following: environmental information, travel information, entertainment information, vehicle use information, vehicle maintenance information, lifestyle information, system information, and vehicle body information. This environmental perception information includes various environmental perception signals. For example, environmental information can be obtained from third parties, such as date, time, weather conditions, and real-time traffic information; travel information can be determined by predicting the user's home and company locations based on their driving trajectory and commuting times; entertainment information can be collected from the user's search and navigation information, such as searching for cinemas and navigating to specific entertainment venues; vehicle usage information can be specific to the vehicle type (personal or commercial) and usage frequency; vehicle maintenance information can be determined through 4S store maintenance records and mileage; lifestyle information can be determined by combining user profiles and user tags to determine user brand preferences, such as refueling between 92-octane and 95-octane fuel; and system information can be determined through vehicle system information, such as real-time vehicle location, user operation information, low fuel signal, low battery signal, fatigue driving signal, and fault signal.

[0112] In this embodiment, refer to Figure 5 As shown, to make it easier for users to find POI information of interest, POI models that match user preferences can be filtered from the second set of target points of interest based on the user profile, and then prioritized for display and recommendation. Thus, the terminal device can prioritize displaying POI models that match user preferences during map drawing, achieving an intelligent recommendation process.

[0113] Specifically, after receiving the second set of points of interest recommended according to this technical solution, the terminal device highlights the POI models in the second set that match the user's preferences, while displaying other POIs normally. When a POI model in the second set that matches the user's preferences overlaps with other normally displayed POIs, the overlapping normally displayed POIs are hidden, and the POI model in the second set that matches the user's preferences is highlighted.

[0114] During the highlighting process, in the same scenario, different users will see different brands and different service content at the same location on the map. For example:

[0115] For midday scenarios (11:00-13:00), food-related POIs will be displayed first.

[0116] For evening scenes (time: 17:00-21:00), cinema-related POIs will be displayed first.

[0117] For example, refer to Figure 6 and Figure 7 As shown, if user A's user tags are: Luckin Coffee, McDonald's, PetroChina, 92-octane gasoline, and user B's user tags are: Starbucks, KFC, PetroChina, 95-octane gasoline, then in the same scenario, such as lunchtime, user A will have Luckin Coffee and McDonald's highlighted on the map, while PetroChina will be displayed normally. Similarly, user B will have Starbucks and KFC highlighted on the map, while PetroChina will be displayed normally. Regarding user tags, in the same scenario, different user preferences will result in different displayed brands. For example, user A will have Luckin Coffee and McDonald's highlighted, while user B will have Starbucks and KFC highlighted. Furthermore, in the same scenario, since both user A and user B have the same brand preference ("PetroChina"), but require different octane ratings, user A will have "92# price" highlighted on the map, while user B will have "95# price" highlighted.

[0118] During the highlighting process, different users will see different brands and services at the same location on the map in different scenarios. For example:

[0119] In the midday and evening scenes, refer to Figure 7 and Figure 8 As shown, user B will see different recommended content in the same location. For example, user B sees Starbucks and KFC in the midday scene and Wanda Cinema in the evening scene. It should be noted that in the map data, the 3D POI models of Starbucks and KFC and Wanda Cinema have an overlapping relationship.

[0120] During the highlighting process, multiple scenes occur simultaneously, with the scene with the highest priority being displayed first.

[0121] For example, in the breakfast scenario: time: 04:00-09:00, prioritize displaying POIs related to breakfast, coffee, and convenience stores.

[0122] Low fuel level scenario: Low fuel level is identified by fuel tank signal, and gas stations are recommended. Low fuel level scenario is given higher priority than breakfast scenario.

[0123] Assume user A's user tags are: Luckin Coffee, McDonald's, PetroChina, and 92-octane gasoline. (Refer to...) Figure 9 As shown, in the breakfast scenario, user A sees Luckin Coffee, McDonald's, and an Easy Joy convenience store inside a PetroChina gas station highlighted on the map. (Refer to...) Figure 10 As shown, when the breakfast scenario and the low battery scenario occur simultaneously, user A highlights PetroChina gas stations, Luckin Coffee, and McDonald's on the map.

[0124] In one specific embodiment, refer to Figure 5 As shown, the above method also includes:

[0125] Based on the target POI models in the second target interest point set, the corresponding dynamic information is obtained and pushed to realize scene interaction with the user.

[0126] In this embodiment of the invention, when recommending points of interest (POIs), dynamic information corresponding to all POI models can be obtained based on third-party data, and corresponding dynamic information can be distributed according to each target POI model in the second target POI set. The aforementioned dynamic information may include: parking lot occupancy status, gas station prices and discounts, airport flight information, cinema screening information, shopping mall discount information, and short video information, etc.

[0127] In one specific embodiment, the aforementioned preset scenario set may include the recommendation frequency and recommendation method for each recommendation scenario, and the method further includes:

[0128] Based on the recommendation frequency and recommendation method of at least one recommendation scenario corresponding to the recommendation request, the second set of target interest points is recommended.

[0129] The recommendation frequency can be defined according to needs, such as continuous recommendation, recommendation only once, or recommendation at preset intervals. The recommendation frequency for different scenarios can be determined based on the current time; for example, during breakfast time, breakfast scenarios would be continuously recommended.

[0130] The recommendation methods can include strong recommendations and weak recommendations. Weak recommendations can include special display processing of POI models, such as adding an icon around the POI model or applying special highlighting or flowing light effects to the POI model's polarity; weak recommendations can also include overlaying dynamic pop-up messages when displaying POI models, such as displaying a recommendation message after arriving at a preset location within a scene.

[0131] The inventors discovered that in existing technologies, map drawing is typically performed on the server side, and the drawing data is pre-made. This pre-drawn data is then directly sent to the terminal device for display. In the technical solution provided by this invention, the inventors propose recommending a second set of target points of interest (POIs) to the terminal device. The terminal device then draws the models of each POI in the second set and further displays them on the user's terminal device using highlighting. Based on the user's profile and usage scenario, the POI information in the map is dynamically displayed, highlighting the POIs of interest the user is currently interested in for easy searching. Furthermore, this reduces the computational load on the server side and improves the efficiency of map drawing. Based on this, referring to... Figure 11As shown in this embodiment, the process of displaying points of interest through interaction between the terminal device and the server includes the following steps:

[0132] The terminal requests map information for its local area, that is, it sends a point of interest recommendation request to the cloud server;

[0133] The cloud server receives the request, and the scene engine service queries the POI results in the current scene based on the area information, thus obtaining the first target interest point set;

[0134] Next, the cloud server requests a user profile from the user profiling service, filters the POI results based on the user profile, and determines the target interest points in the first target interest point set that match the user's preferences.

[0135] Next, the cloud server performs POI de-covering processing based on the overlapping relationship between POI models in the POI information database and other POI models. First, it retains the target interest point POIs with higher priority according to the scene priority of the target interest point. If the scene priorities are the same, it retains the target interest point POIs that match the user's preferences. If both the scene priority and the user's preferences are the same, it randomly selects a target interest point POI to obtain the second target interest point set.

[0136] Next, the cloud server sends the POI information within the requested area to the terminal, which is the set of second target points of interest;

[0137] Finally, the terminal draws a map based on the content sent by the cloud server, namely the set of second target points of interest, and displays the POI model.

[0138] The technical solution of this invention solves the problem that traditional maps cannot display points of interest according to user needs by obtaining at least one recommended scene corresponding to the received point of interest recommendation request from a preset scene set; obtaining a first set of target points of interest associated with the display area range corresponding to the recommendation request from a preset POI database according to the at least one recommended scene; obtaining the overlay relationship between each target point of interest in the first set of target points of interest, performing de-overlay processing, obtaining a second set of target points of interest, and recommending it. By filtering POI information according to the user's usage scenario, the invention prioritizes recommending points of interest information that the user is interested in, so as to realize the dynamic display of points of interest information on the user's end. Furthermore, since the points of interest information displayed on the map is dynamic, the overlay processing hides some three-dimensional points of interest that the user is not interested in, which can realize the readjustment of the display layout of three-dimensional points of interest in the map, avoid interference from invalid points of interest information, improve the display effect of points of interest information that the user is interested in, and make the map display more beautiful and practical.

[0139] Example 2

[0140] Figure 12 This is a flowchart of a point-of-interest (POI) display method provided in Embodiment 2 of the present invention. This embodiment is applicable to drawing and displaying target POI models from a second set of target POIs. The method is executed by a user terminal device, specifically, by a point-of-interest display device configured in the user terminal device, which is implemented in software and / or hardware. The method specifically includes the following steps:

[0141] S201, Send a point of interest recommendation request;

[0142] The sending object is sent by the user terminal device, and the point of interest is the point of interest that the user terminal device needs to display on the screen within that area.

[0143] The process of sending a point of interest recommendation request can be that the user terminal device initiates a request to the server, and the content of the request is a recommendation of points of interest for the user terminal device within the area.

[0144] S202, Receive the second target interest point set determined according to the interest point recommendation method in Embodiment 1;

[0145] The receiving object is a user terminal device, and the determined second set of target points of interest is obtained through a server. The receiving process may involve the user terminal device receiving data from the server regarding the point of interest recommendation request, which is the determined second set of target points of interest.

[0146] S203. Based on the second target point of interest set, draw and display the target POI model in the second target point of interest set.

[0147] The process of depicting and displaying the target POI models in the second set of target points of interest can be achieved by the user terminal device performing 3D depiction based on the acquired target POI models in the second set of target points of interest and displaying the results on the user terminal device. The result displayed by the user terminal device is that it presents all 3D POIs within the area where the user terminal device is located, within the screen area of ​​the user terminal device.

[0148] In this embodiment of the invention, the specific implementation process of the point of interest display method can be referred to the detailed description in Embodiment 1 above, and will not be repeated here.

[0149] The technical solution of this invention, by receiving a second set of target points of interest (POIs), depicting and displaying the models of each POI in the second set of target POIs, solves the problem that traditional maps cannot display POIs according to user needs. By filtering POI information based on the user's usage scenario, it prioritizes recommending POI information of interest to the user, realizing the dynamic display of POI information on the user's end. Since the POI information displayed on the map is dynamic, by overlaying some 3D POIs that the user does not care about, it is possible to readjust the display layout of 3D POIs on the map, avoid interference from invalid POI information, improve the display effect of POI information of interest to the user, and make the map display more beautiful and practical.

[0150] Example 3

[0151] Figure 13 This is a schematic diagram of an interest point recommendation device provided in Embodiment 3 of the present invention. This device can be implemented in hardware and / or software, and can execute an interest point recommendation method provided in any embodiment of the present invention, possessing the corresponding functional modules and beneficial effects of the method. Figure 13 As shown, the device includes:

[0152] The scene determination module 1010 is used to obtain at least one recommended scene corresponding to the received interest point recommendation request from a preset scene set;

[0153] The first acquisition module 1020 is used to acquire a first set of target interest points associated with the display area range corresponding to the recommendation request from a preset POI database according to the at least one recommendation scenario;

[0154] The second acquisition module 1030 is used to acquire the overlapping relationship between each target interest point in the first target interest point set, perform de-overlapping processing, obtain the second target interest point set, and make recommendations.

[0155] Example 4

[0156] Figure 14 This is a schematic diagram of a point-of-interest (POI) display device according to Embodiment 3 of the present invention. This device can be implemented in hardware and / or software, and can execute a POI display method provided in any embodiment of the present invention, possessing the corresponding functional modules and beneficial effects of the method. Figure 14 As shown, the device includes:

[0157] The sending module 2010 is used to send point-of-interest recommendation requests;

[0158] The receiving module 2020 is used to receive the second target interest point set determined according to the interest point recommendation method described in Embodiment 1;

[0159] Display module 2030 is used to draw and display the model of each target POI in the second target point of interest set.

[0160] Example 5

[0161] Figure 15 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0162] like Figure 15 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0163] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0164] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as point-of-interest (POI) recommendation methods and / or POI display methods.

[0165] In some embodiments, the point-of-interest (POI) recommendation method and / or POI display method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the POI recommendation method and / or POI display method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the POI recommendation method and / or POI display method by any other suitable means (e.g., by means of firmware).

[0166] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0167] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0168] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0169] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0170] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0171] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0172] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0173] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An interest point recommendation method, applied to a server, characterized in that, include: Based on the received point of interest recommendation request, at least one recommended scene corresponding to the recommendation request is obtained from a preset scene set; According to the at least one recommendation scenario, a first set of target interest points associated with the display area range corresponding to the recommendation request is obtained from a preset POI database; Obtain the overlap relationship between each target interest point in the first target interest point set, perform de-overlap processing to obtain the second target interest point set, and then recommend it, including: Based on the overlap relationship between each target point of interest in the first target point of interest set, determine whether the priority of the scene to which any two target POI models with overlap relationship belong is different. If so, retain the POI models with high priority in the relevant scene, obtain the second target interest point set, and make recommendations; If not, based on the user profile of the user corresponding to the recommendation request, a POI model that matches the user's preference information is selected from the two target interest points with overlapping relationship, and the second target interest point set is obtained and recommended.

2. The method according to claim 1, characterized in that, The step of obtaining at least one recommended scene corresponding to the received point of interest recommendation request from a preset scene set includes: Based on the recommendation request, environmental perception information is obtained, and at least one recommended scene is obtained from a preset scene set based on the environmental perception information.

3. The method according to claim 2, characterized in that, The preset scene set includes the recognition rules for each recommended scene; The step of obtaining environmental perception information based on the recommendation request, and obtaining at least one recommended scene from a preset scene set based on the environmental perception information, includes: Obtain environmental perception information based on the recommendation request; Obtain at least one recommended scene from a preset scene set that corresponds to the recognition rule and the environmental perception information.

4. The method according to claim 1, characterized in that, The POI database includes recommended location information and scene category for each POI model; The step of retrieving a first set of target interest points associated with the display area range corresponding to the recommendation request from a preset POI database based on the at least one recommendation scenario includes: Based on the geographic region range information in the received point of interest recommendation request and the recommended location information of each POI model in the POI database, POI models whose recommended location information matches the geographic region range are selected from the POI database. Based on the at least one recommended scenario, match the POI model corresponding to the scenario category, determine the POI model under each recommended scenario, and obtain the first target interest point set.

5. The method according to claim 4, characterized in that, The recommended location information of the POI model is obtained in the following way: Based on the original geographic location information of the POI model, determine the location information of the POI model in the original map; Based on the 3D shape of the POI model, determine the bounding rectangle of the POI model, and determine whether the bounding rectangle of the POI model overlaps the road in the corresponding background display surface of the original map; If so, perform position offset processing on the POI model to obtain the recommended position information of the POI model; If not, the location information of the POI model in the original map shall be used as the recommended location information of the POI model.

6. The method according to claim 5, characterized in that, Also includes: The recommended size information for the POI model is obtained through the following method: If, at the recommended location, the bounding rectangle of the POI model still overlaps the road on the corresponding background display surface of the map, then the POI model is proportionally compressed based on the obtained original size information of the POI model to obtain the recommended size information of the POI model. If, at the recommended location, the circumscribed rectangle of the POI model does not cover the road corresponding to the background display surface in the map, then the original size information of the POI model will be used as the recommended size information of the POI model.

7. The method according to claim 6, characterized in that, The overlay relationship information between the POI model and other POI models in the POI database is obtained in the following way: Based on the recommended location and size information of each POI model, determine whether there is overlap between the POI models; If so, adjust the recommended position of the POI model in the preset direction and determine the adjusted position information of the POI model; Based on the adjusted location information and the recommended location information of each POI model, determine whether the adjustment distance of the POI model exceeds the preset distance; If so, record the overlay relationship information between each POI model and other POI models; If not, the adjusted location information of the POI model will be used as the recommended location information of the updated POI model.

8. The method according to claim 4, characterized in that, The scene categories of POI models in the POI database are determined in the following way: According to the preset POI scene classification rules, determine whether each POI model belongs to a grandchild scene category under the parent scene category. If so, determine the grandchild scene category as the scene category corresponding to the POI model. If not, determine whether each POI model belongs to a sub-scene category under the parent scene category; if so, determine the sub-scene category as the scene category corresponding to the POI model. If not, determine that the parent scene category is the scene category corresponding to the POI model; wherein, the preset POI scene classification rule includes the parent scene category, and the parent scene category includes the child scene category and the grandchild scene category.

9. The method according to claim 1, characterized in that, The step of selecting a POI model that matches user preference information from two target points of interest with overlapping relationships based on the obtained user profile of the user corresponding to the recommendation request includes: The user profile of the user corresponding to the recommendation request is obtained; For each recommendation scenario, obtain at least one user tag from the user profile; Based on at least one user tag in the user profile, select POI models that match at least one user tag from any two target points of interest with overlapping relationship, and obtain POI models that match user preferences.

10. A method for displaying points of interest, applied to a terminal device, characterized in that, include: Send a request for point-of-interest recommendations; Receive the second target set of interest points determined by the interest point recommendation method according to any one of claims 1-9; Based on the second set of target points of interest, the model of each target POI in the second set of target points of interest is drawn and displayed.

11. An interest point recommendation device, characterized in that, include: The scene determination module is used to obtain at least one recommended scene corresponding to the received interest point recommendation request from a preset scene set; The first acquisition module is used to acquire a first set of target interest points associated with the display area range corresponding to the recommendation request from a preset POI database according to the at least one recommendation scenario; The second acquisition module is used to acquire the overlap relationship between each target interest point in the first target interest point set, perform de-overlap processing, obtain the second target interest point set, and make recommendations, including: Based on the overlap relationship between each target point of interest in the first target point of interest set, determine whether the priority of the scene to which any two target POI models with overlap relationship belong is different. If so, retain the POI models with high priority in the relevant scene, obtain the second target interest point set, and make recommendations; If not, based on the user profile of the user corresponding to the recommendation request, a POI model that matches the user's preference information is selected from the two target interest points with overlapping relationship, and the second target interest point set is obtained and recommended.

12. A point-of-interest display device, applied to a terminal device, characterized in that, include: The sending module is used to send point-of-interest recommendation requests; The receiving module is configured to receive the second target interest point set determined by the interest point recommendation method according to any one of claims 1-9; The display module is used to draw and display the models of each target POI in the second target point of interest set.

13. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the point of interest recommendation method of any one of claims 1-9, or the point of interest display method of claim 10.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the point-of-interest recommendation method as described in any one of claims 1-9, or the point-of-interest display method as described in claim 10.

Images