Interaction method and interaction device

Abstract

The invention provides an interaction method and an interaction device.The method comprises the steps that in response to a recommendation instruction triggered by a target user, a recommendation theme associated with the target user is obtained; wherein the recommended theme is generated by a preset artificial intelligence model based on historical behavior data and a current geographic position of the target user; obtaining recommended content corresponding to the recommended theme; and displaying a recommendation page including the recommendation theme and the recommendation content thereof. According to the interaction method provided by the embodiment of the invention, personalized recommendation of themes can be carried out in combination with the historical behavior data and the current geographic position of the user, and personalized requirements of the user are met, so that the user experience is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to an interaction method and an interaction device. BACKGROUND

[0002] With the development of mobile Internet, map software has become an important tool indispensable in people's daily life. Users can search for points of interest (POI) or view the evaluation of POI by other users using the map software, so as to obtain the desired information.

[0003] At present, in order to enable users to quickly find the desired information, a plurality of recommended themes such as food, hotel, etc. are configured in the map software. After the user clicks the food theme, the user can be recommended food points of interest or food packages, etc. However, the recommended themes displayed at present are fixed and cannot meet the personalized needs of users. SUMMARY

[0004] The present application provides an interaction method and an interaction device, which can make personalized recommendation of themes in combination with historical behavior data and current geographic position of a user. The specific scheme is as follows:

[0005] In the first aspect, the embodiments of the present application provide an interaction method, comprising:

[0006] In response to a recommendation instruction triggered by a target user, a recommended theme associated with the target user is acquired; wherein the recommended theme is generated by a preset artificial intelligence model based on historical behavior data and current geographic position of the target user;

[0007] Recommended content corresponding to the recommended theme is acquired;

[0008] A recommendation page including the recommended theme and the recommended content thereof is displayed.

[0009] In the second aspect, the embodiments of the present application provide an interaction device, comprising:

[0010] A first acquisition unit is configured to acquire, in response to a recommendation instruction triggered by a target user, a recommended theme associated with the target user; wherein the recommended theme is generated by a preset artificial intelligence model based on historical behavior data and current geographic position of the target user;

[0011] A second acquisition unit is configured to acquire recommended content corresponding to the recommended theme;

[0012] A display unit is configured to display a recommendation page including the recommended theme and the recommended content thereof.

[0013] Compared with the prior art, the present application has the following advantages:

[0014] The embodiment of the present application provides an interactive method, in response to a recommendation instruction triggered by a target user, a recommendation theme associated with the target user is acquired, the recommendation theme is generated by a preset artificial intelligence model based on historical behavior data and a current geographical position of the target user; in this way, the acquired recommendation theme conforms to the historical preference and behavior habit of the target user and is associated with the current geographical position of the target user; then, recommendation content corresponding to the recommendation theme is acquired; since the recommendation theme conforms to the historical preference and behavior habit of the target user and is associated with the current geographical position of the target user, the recommendation content corresponding to the recommendation theme also conforms to the historical preference and behavior habit of the target user and is associated with the current geographical position of the target user; finally, a recommendation page including the recommendation theme and the recommendation content thereof is displayed. Therefore, the interactive method provided by the embodiment of the present application can combine the historical behavior data and the current geographical position of the user to perform personalized recommendation of a theme, meet the personalized demand of the user, and thereby improve the user experience. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 FIG. 1 is a flowchart of an interactive method provided by the embodiment of the present application.

[0016] Figure 2 FIG. 2 is a schematic diagram of an example of a recommendation page in the interactive method provided by the embodiment of the present application.

[0017] Figure 3 FIG. 3 is an interface schematic diagram of an example of generating a display area reduction instruction in the interactive method provided by the embodiment of the present application.

[0018] Figure 4 FIG. 4 is an interface schematic diagram of another example of generating a display area reduction instruction in the interactive method provided by the embodiment of the present application.

[0019] Figure 5 FIG. 5 is an interface schematic diagram of an example of a touch instruction for a thumbnail theme in the interactive method provided by the embodiment of the present application.

[0020] Figure 6 FIG. 6 is an interface schematic diagram of an example of restoring a reduced recommendation page in the interactive method provided by the embodiment of the present application.

[0021] Figure 7 FIG. 7 is an interface schematic diagram of an example of displaying comparison information in the interactive method provided by the embodiment of the present application.

[0022] Figure 8 FIG. 8 is an interface schematic diagram of an example of displaying ranking information of a point of interest in the interactive method provided by the embodiment of the present application.

[0023] Figure 9 FIG. 9 is a flowchart of a data processing method provided by the embodiment of the present application.

[0024] Figure 10 This is a structural block diagram of an example of an interactive device provided in the embodiments of this application.

[0025] Figure 11 This is a structural block diagram of an example of the data processing apparatus provided in the embodiments of this application.

[0026] Figure 12 This is a structural block diagram of an example of an electronic device for interaction or data processing provided in the embodiments of this application. Detailed Implementation

[0027] Many specific details are set forth in the following description to provide a full understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of this application; therefore, this application is not limited to the specific embodiments disclosed below.

[0028] It should be noted that the terms "first," "second," "third," etc., in the claims, specification, and drawings of this application are used to distinguish similar objects and are not used to describe a specific order or sequence. Such data are interchangeable where appropriate so that the embodiments of this application described herein can be implemented in a sequence other than that shown or described herein. Furthermore, the terms "comprising," "having," and their variations are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that includes 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 these processes, methods, products, or apparatuses.

[0029] It should be understood that in the embodiments of this application, "at least one" means one or more, and "more than one" means two or more. "And / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. The character " / " generally indicates that the related objects before and after it are in an "or" relationship. "Contains A, B and / or C" means containing any one, two, or three of A, B, and C.

[0030] It should be understood that in the embodiments of this application, "B corresponding to A", "B corresponding to A", "A corresponds to B" or "B corresponds to A" means that B is associated with A, and B can be determined based on A. Determining B based on A does not mean that B is determined solely based on A; B can also be determined based on A and / or other information.

[0031] Based on the reasons mentioned in the background art, the first embodiment of this application provides an interaction method that can make personalized recommendations on topics by combining the user's historical behavior data and current geographical location. This method is applied to electronic devices, which may be desktop computers, laptops, mobile phones, tablets, smartwatches, etc., or other interactive electronic devices; this application embodiment is not specifically limited to any particular type.

[0032] It should be noted that in the embodiments of this application, the executing entity of the interaction method can be a terminal device, which can be a local terminal device or a client device in a cloud system.

[0033] The interaction method provided in this application can be applied to map navigation applications, online real estate applications, and food delivery applications. This application does not limit the application scenario. The following describes two optional application scenarios of the interaction method provided in this application.

[0034] Application Scenario 1: When a target user opens a map navigation application on an electronic device and triggers a recommendation command, a recommendation page can be displayed on the device. This page can show one or more recommended topics and corresponding content. The displayed recommended topics are generated by a preset artificial intelligence model based on the target user's historical behavior data and current geographical location. The recommended topics match the target user's historical preferences and behavioral habits and are associated with the target user's current geographical location. For example, if the target user is a mother who enjoys coffee and hot springs and is currently in region xx, then the recommended topics could include, but are not limited to, "Group purchase discounts for taking your baby to hot springs on weekends," "Delicious coffee in region xx," and "Hotels suitable for weekend family activities."

[0035] Application Scenario 2: When a target user opens an online real estate application on an electronic device to obtain housing rental and sales information, the device can display a recommendation page. This page can show one or more recommended topics and corresponding content. The recommended topics are generated by a preset artificial intelligence model based on the target user's historical behavior data and current geographical location. The recommended topics match the target user's historical preferences and behavioral habits and are associated with the target user's current geographical location. For example, if the target user has previously searched for south-facing courtyards, large terraces, garden villas, and storage rooms, and is currently located in area xx, then the recommended topics could include, but are not limited to, "apartments with south-facing courtyards that are not damp," "garden villas with large terraces in area xx," and "houses with multiple south-facing bedrooms and storage rooms."

[0036] The recommended content corresponding to the recommended topic can be identification cards corresponding to one or more points of interest associated with that recommended topic. Identification cards for points of interest can be image cards of those points of interest, or evaluation cards from other users, etc. These identification cards can guide target users to explore the corresponding application (such as a map navigation application in application scenario one or an online real estate application in application scenario two), enhancing the interactivity and stickiness between the target user and the online real estate application. The one or more points of interest associated with the displayed recommended topic can be points of interest whose distance from the target user's current location is within a preset range.

[0037] As can be seen from the two application scenarios above, the recommendation page not only displays recommended topics that match the target user's historical preferences and behavioral habits and are related to the target user's current geographical location, but also displays the recommended content corresponding to the recommended topics. In other words, personalized recommendations of topics and content are made by combining the user's historical behavioral data and current geographical location to meet the user's personalized needs and thus improve the user experience.

[0038] For ease of explanation, the following description will use the interactive method provided in the embodiments of this application applied to a map navigation application as an example. The map navigation application is a software tool that uses a Global Positioning System (GPS) and other technologies to provide route planning and navigation services. It can provide users with navigation and route planning services, and typically contains detailed map data.

[0039] The technical solution of this application will be described in detail below through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0040] The following, combined with Figures 1-8 The interaction method provided in the embodiments of this application is introduced.

[0041] like Figure 1 The diagram shown is a flowchart of the interaction method provided in the embodiment of this application, including the following steps S101 to S103.

[0042] Step S101: In response to a recommendation instruction triggered by a target user, obtain recommendation topics associated with the target user; wherein, the recommendation topics are generated by a preset artificial intelligence model based on the target user's historical behavior data and current geographical location.

[0043] This step is used to obtain recommended topics for target users that match their historical behavior data and current geographical location.

[0044] The target user can trigger recommendation commands on their electronic device while using the map navigation application. These recommendation commands can be generated through touch operations on a touch-sensitive screen, touch operations on a specified control, voice commands, etc. The touch operations can be one of clicks, presses, swipes, etc. This application does not specifically limit the method of generating recommendation commands.

[0045] In response to a recommendation instruction triggered by a target user, a recommendation request can be sent to the server. The server can then generate a related recommendation topic for the target user based on this request. Specifically, the server uses a preset artificial intelligence model to generate the recommendation topic based on the target user's user behavior data and current geographical location. Afterward, the server returns the recommendation topic to the client so that the client can access it. The method for generating the recommendation topic will be specifically described in the data processing method provided in the second embodiment of this application, and will not be repeated here.

[0046] The recommended topics can be generated by a pre-set artificial intelligence model based on the target user's historical behavior data and current geographical location. That is, different users in the same geographical location will have different recommended topics; the same user in different geographical locations will also have different recommended topics.

[0047] The preset artificial intelligence model refers to a pre-trained model for topic recommendation, which can be trained using the sample user's sample historical behavior data, the sample's current geographical location data, and the sample recommendation topic corresponding to the sample user.

[0048] The target user's historical behavior data refers to data generated from various behaviors of the target user during the use of the application, used to characterize the target user's historical preferences and behavioral habits. The target user's historical behavior data may include, but is not limited to, data such as dwell time on different pages, input of search terms, likes, favorites, shares, comments, and purchases of goods or services.

[0049] The current geographic location is the actual location of the target user, which can be obtained through GPS (Global Positioning System), Wi-Fi positioning, cellular network positioning, or other means.

[0050] For example, if target user 1 is a stay-at-home mom who enjoys coffee and hot springs and is currently located in region xx, then recommended topics related to target user 1 could include "group deals for hot springs with babies in region xx", "hotels suitable for family activities in region xx", and "good coffee in region xx". Similarly, if target user 2 enjoys fitness and is currently located in region xx, then recommended topics related to target user 2 could include "a nice gym in region xx" and "a park nearby with a running track".

[0051] Furthermore, the recommended topics can also be generated by a preset artificial intelligence model based on the target user's historical behavior data, current geographical location, and current time period attributes.

[0052] The current time period attribute is used to indicate the current holiday type. For example, the current time period attribute indicates that it is currently a weekend; it indicates that it is currently a weekday; it indicates that it is currently Chinese New Year, and so on. The current time period attribute can be obtained in real time while the user is using the map navigation application. Through the current time period attribute, the user's historical behavior data, and the current geographical location, recommendation topics strongly correlated with the current time period, user's historical behavior, and current geographical location can be determined. For example, if the current time period is Chinese New Year, and target user 1 enjoys shopping and is located in region xx, then the recommendation topics associated with target user 1 could include "commercial areas in region xx with a strong festive atmosphere during Chinese New Year"; or if the current time period is a weekday, and target user 1 prefers ordering takeout, then the recommendation topics associated with target user 1 could include "providing you with several quick and delicious work meals," etc.

[0053] Step S102: Obtain the recommended content corresponding to the recommended topic.

[0054] This step is used to retrieve the corresponding recommended content for each recommended topic.

[0055] While the server generates the associated recommendation topics for the target user based on the recommendation request, it can also generate corresponding recommendation content for each recommendation topic. In this way, the recommendation content corresponding to the recommendation topic can be returned to the client so that the client can obtain the recommendation content corresponding to the recommendation topic.

[0056] The recommended topics are generated based on the target user's historical behavior data and current geographical location. That is, the recommended topics conform to the target user's historical preferences and behavioral habits and are associated with the target user's current geographical location. Thus, the corresponding recommended content also conforms to the target user's historical preferences and behavioral habits and is associated with the target user's current geographical location.

[0057] The recommended content may include recommendation information corresponding to one or more points of interest associated with the recommended topic. This recommendation information may be presented in card format, text format, or video format. When presented as cards, the recommendation information may be a purchase card for goods or services offered by the points of interest associated with the recommended topic, or a review card from other users for the point of interest. This recommendation information is used to guide target users to explore the map navigation application in depth, enhancing the interactivity and stickiness between the target users and the map navigation application.

[0058] One or more points of interest associated with the displayed recommended topics can be points of interest within a preset range of distance from the target user's current geographical location. This preset range can be 1 kilometer, 3 kilometers, 5 kilometers, etc., and can be specifically set based on actual needs; this application does not impose any restrictions on this.

[0059] Step S103: Display a recommendation page including the recommended topics and their recommended content.

[0060] This step is used to present target users with recommended topics and their corresponding content that match the target users' historical preferences and behavioral habits and are associated with the target users' current geographical location.

[0061] like Figure 2 The diagram shows an example of a recommendation page in the interactive method provided in this application embodiment. The graphical user interface displays a recommendation page 20, which shows multiple recommendation topics and corresponding recommended content. The recommendation topics are: Recommendation Topic 201 "Weekend Hot Spring Getaway Deals for Babies" and Recommendation Topic 206 "Delicious Coffee in xx Area." The recommended content for Recommendation Topic 201 includes cards corresponding to points of interest associated with Recommendation Topic 201, namely cards 202 and 203. Card 202 is a purchase card for the product "xxx Family Package" offered by the point of interest "xx Hot Spring Hotel," and card 203 is a review card from other users regarding the point of interest "Japanese Hot Spring." The recommended content for Recommendation Topic 206 includes cards corresponding to points of interest associated with Recommendation Topic 206, namely cards 207 and 208. Card 207 is a purchase card for the product "xxx Latte" offered by the point of interest "xx Coffee," and card 203 is a review card from other users regarding the point of interest "xx Coffee Shop."

[0062] Therefore, by displaying recommended topics that match the target user's historical preferences and behavioral habits, along with corresponding recommended content, on the recommendation page, personalized recommendations for topics and content are achieved. This allows target users to obtain content that meets their needs and interests through the recommendation page, increasing their positive feelings, trust, and engagement with the map navigation application.

[0063] In one optional implementation, before displaying the recommendation page including the recommended topic and its recommended content, the recommendation reason and at least one generative question corresponding to the recommended topic can also be obtained; wherein the recommendation reason and the generative question are generated by the artificial intelligence model based on the target user's historical behavior data.

[0064] In this embodiment, while the server generates the associated recommendation topic for the target user based on the recommendation request, the artificial intelligence model can generate the recommendation reason and at least one generative question corresponding to the recommendation topic based on the target user's historical behavior data. Then, the server returns the recommendation reason and at least one generative question to the client, enabling the client to obtain the recommendation reason and at least one generative question for the recommendation topic and display a recommendation page including the recommendation topic and its recommendation reason, recommendation content, and at least one generative question.

[0065] The generative questions can reflect the user's potential needs and intentions, thereby enhancing the intelligent experience. For example, if the target user is a mother, the corresponding generative question could be "Are there any restaurants nearby that offer baby meals?"; or if the target user travels by car, the corresponding generative question could be "Is parking convenient nearby?"; and so on. The presentation formats of the generative questions include, but are not limited to, text, cards, and videos.

[0066] The recommendation reasons are generated for the target user and are consistent with their historical preferences and behavioral habits. For example, the recommendation topic "Group purchase discounts for taking your baby to hot springs on weekends" corresponds to 8 related points of interest, and its recommendation reason could be "Based on your inquiry about group purchase discounts, we have selected 8 family-friendly hotels for you"; another example is the recommendation topic "Delicious coffee in xx area, try this one" which corresponds to 6 related points of interest, and its recommendation reason could be "Based on your daily coffee drinking habits, we have recommended 6 coffee shops for you".

[0067] Combined with appendix Figure 2For recommended topic 201, the following explanation is provided: "Based on your inquiry about group-buying discounts, we have selected 8 family-friendly hotels for you." Also included are generated questions 204 and 205: "Is there parking nearby?" and "Are there hotels nearby that offer baby meals?". For recommended topic 206, the following explanation is provided: "Based on your daily coffee-drinking habits, we recommend 6 coffee shops." Also included are generated questions 209 and 210: "Are there shopping malls nearby?" and "Is there parking nearby?".

[0068] Thus, displaying the recommendation reasons and generative questions corresponding to the recommended topics on the recommendation page serves several purposes. First, by providing targeted users with generative questions that meet their needs, the time spent by users manually editing and inputting their questions can be reduced. Second, since the displayed generative questions can reflect the potential needs and intentions of the target users, they feel that their needs are valued, thus increasing their positive perception of the map navigation application. Third, the displayed recommendation reasons allow target users to intuitively understand the recommendation logic of the recommended topics, increasing their trust in the recommended topics and content, thereby helping them make decisions more quickly among a large amount of content.

[0069] Optionally, while obtaining the recommended topics associated with the target user, or after obtaining the recommended topics associated with the target user, a shortened topic corresponding to the recommended topic can be obtained; wherein, the shortened topic of the recommended topic has the same semantics as the recommended topic and its text length is shorter than that of the recommended topic. Accordingly, while displaying the recommendation page including the recommended topic and its recommended content, or after displaying the recommendation page including the recommended topic and its recommended content, the shortened topic corresponding to the recommended topic is displayed.

[0070] While generating the recommended topic on the server side, a corresponding abbreviated topic can also be generated and returned to the client so that the client can obtain the abbreviated topic and present it.

[0071] The abbreviated title of the recommended topic has the same semantic meaning as the recommended topic but is shorter in length. For example, the recommended topic "Weekend hot spring group purchase discounts for taking your baby" has 14 characters, and its corresponding abbreviated title "Take your baby to hot springs" has 6 characters; another example is the recommended topic "Delicious coffee in xx region, drink this cup" which has 11 characters, and its corresponding abbreviated title "Delicious coffee" has 4 characters.

[0072] After obtaining the abbreviated topic corresponding to the recommended topic, the abbreviated topic corresponding to the recommended topic can be displayed.

[0073] In one optional implementation, in response to a command to shrink the display area of ​​the recommendation page, a thumbnail of the recommended topic can be displayed at the top or bottom of the shrunk recommendation page.

[0074] A target user can trigger a display area shrinking command on the recommended page. The display area shrinking command is used to shrink the displayed recommended page. In response to the display area shrinking command on the recommended page, a thumbnail of the recommended topic can be displayed at the top or bottom of the shrunk recommended page. In one optional implementation, the graphical user interface can provide a target control through which the display area shrinking command can be triggered; that is, in response to a triggering operation on the target control, a display area shrinking command for the recommended page is generated. In another optional implementation, the display area shrinking command can be triggered by a swipe operation on the recommended page; that is, in response to a swipe operation on the recommended page, when the swipe distance reaches a preset distance (e.g., 3 cm, 5 cm, or 6 cm), a display area shrinking command for the recommended page is generated.

[0075] The following is passed Figure 3 and Figure 4 This application describes the method for generating the command to shrink the display area of ​​the recommendation page in the interaction method provided in the embodiments:

[0076] like Figure 3 The diagram shown is an example of an interface diagram illustrating the generation of a display area zoom-out instruction in the interactive method provided in this application embodiment. It includes interface (3-a) and interface (3-b). Interface (3-a) displays a recommended page 20, and provides a target control 211 for exploring the map. After the target user clicks the target control 211, as shown in interface (3-b), the recommended page 20 changes to a zoomed-out recommended page 21. A thumbnail of the recommended topic is displayed at the top of the zoomed-out recommended page 21. The themes are: recommended theme 201 "Group purchase discounts for taking your baby to hot springs on weekends" (abbreviated as theme 213 "Taking your baby to hot springs"); recommended theme 206 "Delicious coffee in xx area" (abbreviated as theme 214 "Delicious coffee"); recommended theme 206 "Hotels suitable for weekend family activities" (abbreviated as theme 215 "Weekend family activities"); and recommended theme 206 "Family playgrounds suitable for children on weekends" (abbreviated as theme 216 "Children's play") (abbreviated as theme 216 "Children's play").

[0077] like Figure 4The diagram shows another example of the interface diagram for generating a display area shrinking instruction in the interaction method provided in this application embodiment, including interface (4-a) and interface (3-b). Interface (4-a) displays a recommendation page 20. When the target user performs a sliding operation as shown in trajectory 217, and the sliding distance of the sliding operation is greater than a preset distance, as shown in interface (3-b), the recommendation page 20 changes to a shrunken recommendation page 21. At the top of the shrunken recommendation page 21, the abbreviated themes corresponding to the recommended topics are displayed. The abbreviated themes are: abbreviated theme 213 "Take your baby to a hot spring" corresponding to recommendation theme 201 "Group purchase discount for taking your baby to a hot spring on the weekend", abbreviated theme 214 "Delicious coffee" corresponding to recommendation theme 206 "Drink this cup of coffee in xx area", abbreviated theme 215 "Weekend parent-child activities" corresponding to recommendation theme "Hotels suitable for weekend parent-child activities" which is not displayed in interface (4-a), and abbreviated theme 216 "Children's play" corresponding to recommendation theme "Parent-child playgrounds suitable for children on the weekend" which is not displayed in interface (4-a).

[0078] It should be noted that the appendix Figure 3 and attached Figure 4 The example shown is based on the thumbnail topic being displayed at the top of the zoomed-out recommendation page and is not intended to limit this application.

[0079] Thus, when the number of recommended topics that can be displayed on the shrunk recommendation page is less than the number of recommended topics that can be displayed on the full recommendation page, displaying the corresponding abbreviated topics at the top or bottom of the shrunk recommendation page can, on the one hand, inform users of the recommended topics, and on the other hand, reduce the amount of screen space occupied by the abbreviated topics because their text length is shorter than that of the recommended topics, thereby avoiding obscuring key information on the screen and improving the user-friendliness of the interface.

[0080] In one optional implementation, after displaying the thumbnail themes corresponding to the recommended themes, the following steps may be performed: in response to a touch command for any thumbnail themes, the recommended content corresponding to the recommended themes corresponding to the thumbnail themes is displayed at the top of the recommended page; and / or, in response to a touch command for any recommended themes, the style of the thumbnail themes corresponding to the recommended themes is displayed as a preset selected style.

[0081] The target user can trigger a touch command on any of the displayed thumbnails. The touch command for any thumbnail can be implemented by clicking or pressing any of the thumbnails.

[0082] In response to a touch command for any thumbnail topic, the recommended content corresponding to that thumbnail topic is displayed at the top of the recommended page. That is, regardless of whether the recommended page is shrunk or not, the recommended content corresponding to the currently selected thumbnail topic is always displayed at the top.

[0083] The target user can also trigger touch commands for any recommended topic. Touch commands for any recommended topic can be implemented by clicking or pressing any recommended topic or hovering the mouse over any recommended topic.

[0084] In response to a touch command for any recommended theme, the thumbnail of that recommended theme will be displayed in the default selected style. In other words, for the currently selected recommended theme, the thumbnail of that recommended theme will be displayed in the default selected style.

[0085] In this embodiment, the displayed thumbnail theme may include at least two styles: a preset selected style and a non-selected style. The preset selected style and the non-selected style may differ in color, size, or animation, etc. For example, the preset selected style may be green, and the non-selected style may be red; the preset selected style may have a thickened outer frame, and the non-selected style may have a non-thickened outer frame; the preset selected style may feature a color-changing flashing effect, and the non-selected style may be a single color; the preset selected style may have a first size, and the non-selected style may have a second size, where the first size is larger than the second size, and so on. This application does not specifically limit the preset selected style and the non-selected style; they only need to be visually distinguishable.

[0086] Combining interfaces (3-b) and (3-a), after selecting the abbreviated theme 213 "Taking Baby to Hot Springs," the recommended content corresponding to the recommended theme 201 "Weekend Hot Spring Deals for Taking Baby to Hot Springs" in the reduced-size recommendation page 21 displayed in interface (3-b) is pinned to the top, and the abbreviated theme 213 "Taking Baby to Hot Springs" displays a preset selected style. After selecting the abbreviated theme 213 "Taking Baby to Hot Springs," the recommended content corresponding to the recommended theme 201 "Weekend Hot Spring Deals for Taking Baby to Hot Springs" in the recommended page 21 displayed in interface (3-a) is pinned to the top.

[0087] like Figure 5 The diagram shown is an example of a touch command for a thumbnail theme in the interaction method provided in this application embodiment. Figure 5The system includes interfaces (5-a) and (5-b). Interface (5-a) displays a scaled-down recommendation page 21. At the top of the scaled-down recommendation page 21, the corresponding thumbnails for the recommended themes are displayed: thumbnail theme 213 "Hot Springs with Baby", thumbnail theme 214 "Delicious Coffee", thumbnail theme 215 "Weekend Family Activities", and thumbnail theme 216 "Children's Play". In the scaled-down recommendation page 21 displayed in interface (5-a), the recommended content corresponding to recommendation theme 201 "Weekend Hot Springs with Baby Group Purchase Discount" is pinned to the top, and thumbnail theme 213 "Hot Springs with Baby" is displayed in a preset selected style. At this time, when the user triggers a touch command on thumbnail theme 214 "Delicious Coffee", as shown in interface (5-b), the recommended content corresponding to recommendation theme 206 "Delicious Coffee in xx Region" is pinned to the top in the scaled-down recommendation page 21, and the thumbnail theme 214 "Delicious Coffee" corresponding to recommendation theme 206 "Delicious Coffee in xx Region" is displayed in a preset selected style.

[0088] like Figure 6 The diagram shows an example of restoring a scaled-down recommendation page in the interaction method provided in this application. It includes interface (6-a) and interface (6-b). In interface (6-a), the recommended content corresponding to the recommended topic 206 "Delicious Coffee, Drink This Cup in xx Region" is pinned to the top of the scaled-down recommendation page 21. The abbreviated topic 214 "Delicious Coffee" corresponding to the recommended topic 206 "Delicious Coffee, Drink This Cup in xx Region" is presented in a preset selected style. When the user triggers the restore command on the scaled-down recommendation page, as shown in interface (6-b), the scaled-down recommendation page 21 is restored to recommendation page 20, and the recommended content corresponding to the recommended topic 206 "Delicious Coffee, Drink This Cup in xx Region" is pinned to the top of recommendation page 20.

[0089] Thus, by automatically linking the recommended content of the corresponding recommended topic to the top of the recommended page for each touched thumbnail topic, the user's actions and the display of the recommended page remain consistent. Furthermore, for each touched recommended topic, its corresponding thumbnail is displayed in a preset selection style, allowing the user to intuitively identify the currently selected recommended topic and improving information retrieval efficiency.

[0090] In one optional implementation, the recommendation page is displayed above the electronic map page; that is, the layer of the recommendation page is higher than the electronic map page, and the recommendation page will cover the electronic map page in the overlapping area. In this case, after displaying the recommendation page including the recommended topic and its recommended content, the following steps may be included: obtaining information on points of interest to be displayed on the electronic map page; wherein the points of interest are determined based on target recommended content in the recommendation page, and the target recommended content includes: recommended content displayed at the top of the recommendation page, or recommended content selected by the target user in the recommendation page; and displaying the information on the points of interest on the electronic map page.

[0091] It should be noted that in this application, the information of the points of interest corresponding to the recommended content of the recommended topic can be obtained in advance. For example, the information of the points of interest corresponding to the recommended content of the recommended topic can be obtained at the same time as obtaining the recommended topic associated with the target user. In this way, while displaying the recommendation page including the recommended topic and its recommended content, the information of the points of interest corresponding to the target recommended content can be displayed on the electronic map page.

[0092] In this embodiment, after obtaining recommended topics associated with the target user, or in response to a command to shrink the display area of ​​the recommended page, information on points of interest to be displayed on the electronic map page can be obtained. These points of interest are determined based on target recommended content on the recommended page, which includes, but is not limited to, any of the following: recommended content displayed at the top of the recommended page, recommended content selected by the target user on the recommended page, or recommended content with the highest popularity value on the recommended page.

[0093] In one implementation of this application, before obtaining information about points of interest to be displayed on the electronic map page, the target user can manually select target recommended content. Specifically, the system can receive the target user's selection operation (which can be a click, long press, swipe, etc.) on one of a plurality of recommended topics, thereby using the recommended content corresponding to the selected topic as the target recommended content.

[0094] In this implementation, target users can independently select target recommended content from multiple recommended topics based on their own needs, giving users freedom and flexibility in their operations.

[0095] In another implementation of this application, the target recommended content can be automatically selected by the system. Specifically, the recommended content corresponding to the top-displayed recommended topic among multiple recommended topics can be used as the target recommended content.

[0096] In this implementation, the recommended content displayed at the top of the recommendation page is taken as the target recommended content. Generally, the earlier the recommended topic appears in the display order, the higher its relevance to the target user. Please refer to... Figure 2 Recommended topic 201 is placed before recommended topic 206, indicating that recommended topic 201 is more relevant to the target user than recommended topic 206. Thus, compared to recommended topics displayed later in the order, the recommended content corresponding to the top-displayed recommended topic better matches the needs, preferences, and interests of the target user, increasing the target user's trust and positive perception of the map navigation application.

[0097] In another implementation of this application, the target recommended content can be automatically selected by the system. Specifically, the recommended content of the topic with the highest popularity value among multiple recommended topics displayed on the recommendation page can be determined as the target recommended content. For example, if the recommendation page displays recommended topic 1, recommended topic 2, and recommended topic 3, and if recommended topic 2 has the most users currently interacting with it, indicating that recommended topic 2 has the highest popularity value, then the recommended content of recommended topic 2 can be used as the target recommended content.

[0098] In this implementation, popularity value is used as the determining factor for target recommended content. Since recommended topics with higher popularity values ​​have attracted more user attention, they are more likely to resonate with the target users.

[0099] The points of interest (POIs) to be displayed on the electronic map page can be POIs determined by the server based on the target recommended content. When the target recommended content includes multiple POIs, the POIs to be displayed on the electronic map page can be all of those POIs. Then, information about the POIs can be displayed on the electronic map page, which may include, but is not limited to, the geographical location information and the unique features of the POIs. Referring to interface (3-b), the multiple POIs displayed on the electronic map page for the target recommended content (the recommended content corresponding to recommended topic 201) are POIs "xx Hot Spring Hotel", "Geothermal Hot Spring", "Japanese Hot Spring", and "xxx Natural Hot Spring".

[0100] In this embodiment of the application, the points of interest displayed on the electronic map page can be dynamically updated through touch commands targeting the thumbnail topics.

[0101] It should be noted that due to limited interface space, the number of recommended topics displayed in the scaled-down recommendation page is less than the number displayed on the full recommendation page. For example, the scaled-down recommendation page may only display the top recommended topic, while the full recommendation page may display 3, 4, or 5 recommended topics. When a target user wants to display information about points of interest determined by the recommended content of any other recommended topic besides the top recommended topic on the electronic map page, the existing technology typically requires first restoring the scaled-down recommendation page, then selecting any other recommended topic on the restored page, and finally triggering a shrinkage command on the recommendation page before the information about points of interest determined by the recommended content of that other recommended topic can be displayed on the electronic map page. In this application, because abbreviated themes corresponding to recommended topics are displayed at the top or bottom of the minimized recommendation page, when a target user wants to see information about points of interest determined by the recommended content of any other recommended topic besides the top-ranked recommended topic displayed on the electronic map page, a touch command can be triggered on the abbreviated theme of any other recommended topic. In response to this touch command, the top-ranked recommended topic on the recommendation page is updated to the recommended content corresponding to that other recommended topic, and simultaneously, the information about points of interest displayed on the electronic map page is updated to the information about points of interest determined by the recommended content of that other recommended topic. Compared to the methods in the prior art, this application can effectively reduce the user's operational burden and improve the continuity and efficiency of information acquisition.

[0102] In an optional implementation, after displaying the information of the points of interest on the electronic map page, the interaction method provided in this application embodiment may further include the following steps: in response to the target user's selection of at least two points of interest, acquiring and displaying comparison information of the at least two points of interest.

[0103] This implementation is used to demonstrate the differences between different points of interest, so that the target user can quickly obtain key information.

[0104] Specifically, the target user can manually delineate a closed area on the electronic map page to simultaneously select at least two points of interest (POIs). The delineated closed area includes the at least two POIs. For example, if the at least two POIs are POI a, POI b, and POI c, the target user can delineate a closed area on the electronic map page including POI a, POI b, and POI c, thereby enabling simultaneous selection of POI a, POI b, and POI c. The target user can also perform a sliding operation connecting the at least two POIs to simultaneously select them. (The last sentence is a repetition of the previous one and can be omitted.) Taking point b and point of interest c as examples, the target user can perform the following swiping operations on the electronic map page: swiping from point of interest a to point of interest b and then to point of interest c; swiping from point of interest a to point of interest c and then to point of interest b; swiping from point of interest b to point of interest a and then to point of interest c; swiping from point of interest b to point of interest c and then to point of interest a; swiping from point of interest c to point of interest a and then to point of interest b; or swiping from point of interest c to point of interest b and then to point of interest a. This allows for the simultaneous selection of point of interest a, point of interest b, and point of interest c. This application does not limit the specific operation method for selecting at least two of the points of interest.

[0105] In response to the target user's selection of at least two of the points of interest, comparison information of the at least two points of interest can be obtained and displayed.

[0106] The map navigation application can pre-store corresponding detailed information for each point of interest (POI). This detailed information represents at least one scene attribute, such as location, opening hours, user reviews, consumption level, surrounding environment, and transportation. This allows the application to obtain detailed information for at least two POIs. Based on this detailed information, and for each scene attribute, the application compares the information of the at least two POIs on that scene attribute to obtain the differences between them, generating comparison information between the at least two POIs. In other words, the comparison information between the at least two POIs indicates the differences between them on various scene attributes.

[0107] like Figure 7The diagram shows an example of an interface for displaying comparison information in the interactive method provided in this application embodiment. It includes interface (7-a) and interface (7-b). Interface (7-a) displays an electronic map page 212, which shows information about points of interest determined based on the recommended content of the currently pinned recommended topic 206 on the recommended page. The target user can select between the points of interest "xx Hot Spring Hotel" and "Geothermal Hot Spring." At this time, interface (7-a) will switch to interface (7-b). Interface (7-b) displays comparison information 224 between the points of interest "xx Hot Spring Hotel" and "Geothermal Hot Spring." This comparison information 224 demonstrates the differences between the two from multiple scenario attributes: location—geothermal hot spring is closer; price—xx Hot Spring Hotel is cheaper; transportation—xx Hot Spring Hotel is more convenient; environment—geothermal hot spring is more beautiful; feedback—xx Hot Spring Hotel has better user reviews.

[0108] In this approach, target users can select at least two points of interest on the electronic map page, which will then display comparative information between the selected points of interest. This allows target users to quickly understand the differences by displaying the comparative information, avoiding the manpower and time consumption of manually comparing the information by clicking on one point of interest to view its details and then clicking on another point of interest to view its details.

[0109] In a further optional embodiment, a search control is also displayed on the electronic map page. After the information of the point of interest is displayed on the electronic map page, the interaction method provided in this application embodiment may further include the following steps: based on the search control, obtaining supplementary search information corresponding to the target recommended content for the target user; based on the supplementary search information and the recommended topics corresponding to the target recommended content, obtaining information of the target point of interest to be recommended; and based on the information of the target point of interest, displaying the target point of interest on the electronic map page.

[0110] In this embodiment, the target user can trigger an operation on the search control to input corresponding supplementary search information for the target recommended content. The supplementary search information corresponding to the target recommended content is used to characterize the target user's current temporary needs, and this supplementary search information may have a low degree of matching with the target user's historical behavior data.

[0111] For example, if the target user's historical behavior data indicates that the target user is keen on hand-shaken coffee, then the recommended points of interest for the user will all be hand-shaken coffee shops. If the target user's current temporary need is coffee that is served quickly, then the target user can trigger the search control and input supplementary search information representing the temporary need of "fast service".

[0112] After obtaining the supplementary search information, information about the target interest points to be recommended can be obtained based on the supplementary search information and the recommended topic corresponding to the target recommended content. For example, if the supplementary search information entered by the target user represents the temporary need for "fast food preparation," and the recommended topic corresponding to the target recommended content is "Delicious coffee in xx area, drink this one," then convenience stores that provide coffee, or interest points with coffee preparation times shorter than a preset time threshold, can be obtained as target interest points to be recommended. In other words, the target interest point among multiple interest points can be more accurately located based on the supplementary search information.

[0113] Then, based on the information of the target point of interest, the information of the target point of interest can be displayed on the electronic map page.

[0114] Thus, when the type of point of interest displayed on the current electronic map page is not the type required by the target user, the target user can efficiently display the required target point of interest on the electronic map through this embodiment, improving the user's freedom and flexibility of operation, and enabling the user to quickly obtain the required content.

[0115] In a further implementation, there are multiple points of interest to be displayed on the electronic map page. Displaying the information of the points of interest on the electronic map page may include the following steps: displaying the information of the points of interest and the sorting information of the points of interest on the electronic map page.

[0116] The ranking information can be determined based on the target user's historical behavior data and the scene feature data corresponding to the multiple points of interest displayed on the electronic map page. The ranking information is used to characterize the relevance of the target user to the multiple points of interest displayed on the electronic map page.

[0117] In one implementation, a sorting display area can be set on the electronic map page to display the sorting information of all points of interest shown on the electronic map page. While this implementation can intuitively display the sorting information of all points of interest on the electronic map page, it will occupy a large amount of interface space and excessively obscure key information on the interface.

[0118] In another implementation, sorting information can be labeled at the respective marker locations of the points of interest displayed on the electronic map page. For example... Figure 8 The diagram shown is an example of an interface diagram illustrating the sorting information of points of interest provided in this application embodiment. The electronic map page 212 displays information corresponding to multiple points of interest, namely, "xx Hot Spring Hotel", "Geothermal Hot Spring", "Japanese Hot Spring" and "xx Natural Hot Spring". The sorting information corresponding to the multiple points of interest is displayed, in the following order: "Geothermal Hot Spring" → "xx Hot Spring Hotel" → "Japanese Hot Spring" → "xx Natural Hot Spring".

[0119] This implementation displays the corresponding sorting information at the marked locations of each point of interest. On the one hand, it can help target users make choices among multiple points of interest. On the other hand, displaying the sorting information at the marked locations can reduce the occupation of limited interface space, conveying key information without causing excessive obstruction of the interface, thus improving the user-friendliness of the interface.

[0120] The second embodiment of this application provides a data processing method applied to a server, such as... Figure 9 The diagram shown is a flowchart of a data processing method provided in the second embodiment of this application, including the following steps S201 to S204: Step S201: Receive a notification message sent by a client indicating a recommendation instruction triggered by a target user; Step S202: Obtain the user behavior data and current geographical location of the target user; Step S203: Determine the recommendation topic associated with the target user and the recommendation content corresponding to the recommendation topic based on the user behavior data and the current geographical location; Step S204: Return the recommendation topic and its recommendation content to the client.

[0121] The above steps are used to determine recommended topics that match the target user's historical preferences and behavioral habits and are associated with their current geographical location, as well as the recommended content corresponding to the recommended topics.

[0122] The map navigation application can be pre-connected to a preset artificial intelligence model, which can intelligently recommend topics. Thus, after obtaining the target user's historical behavior data and current geographical location, these data can be input into the artificial intelligence model, allowing the model to output recommended topics that match the target user's historical preferences and behavioral habits and are relevant to their current geographical location.

[0123] After generating the recommended topics, the recommended content corresponding to the recommended topics can be determined, and the recommended topics and their corresponding recommended content can be returned to the client.

[0124] Specifically, the recommended content corresponding to the recommended topic can be recommended information corresponding to points of interest associated with the recommended topic that are within a preset range of distance from the target user's current geographical location. This preset range can be 1 kilometer, 5 kilometers, or 10 kilometers, etc., and can be set according to actual needs; this application does not impose any restrictions on this.

[0125] Points of interest associated with the recommended topic refer to those that possess the characteristics indicated by the recommended topic. For example, if the recommended topic is "Recommended group deals for taking babies to hot springs on weekends," then associated points of interest could include hot spring hotels with baby ball pits, Japanese-style family hot spring resorts, etc.

[0126] Subsequently, for each identified point of interest (POI), at least one of the map navigation application's database, product database, and user review database can be accessed to retrieve the corresponding identifier data. This identifier data may include, but is not limited to, the prices of the goods or services offered by the POI, and other users' reviews and feedback regarding the POI.

[0127] Based on the identifier data corresponding to the points of interest, recommendation information corresponding to the points of interest can be generated. If the identifier data is the price of the goods or services provided by the point of interest, the generated recommendation information is a purchase card for the goods or services provided by the point of interest; if the identifier data is other users' evaluations and feedback on the point of interest, the generated recommendation information is other users' evaluation cards for the point of interest.

[0128] It should be noted that the aforementioned purchase cards and review cards can link to corresponding detail pages. Specifically, if the recommendation information is a purchase card for goods or services offered by the point of interest, the detail page linked to by the purchase card is the goods or services purchase detail page; if the recommendation information is a review card from other users for the point of interest, the detail page linked to by the review card is the user review detail page. In this way, by returning recommendation information presented in card form to the client, visual guidance can be provided to the target user, encouraging them to interact with the displayed cards and thus redirecting the page to the corresponding detail page. This guides the target user to explore the map navigation application more deeply, further enhancing the stickiness between the target user and the map navigation application.

[0129] It should be noted that, while the artificial intelligence model determines the recommended topics associated with the target user, it can also generate recommendation reasons and at least one generative question corresponding to the recommended topics based on the target user's historical behavior data, and send the recommendation reasons and at least one generative question corresponding to the recommended topics to the client, so that the client can display the recommendation reasons and the generative question while displaying the recommended topics and their recommended content.

[0130] Optionally, after determining the recommended topics, the data processing method provided in this application embodiment further includes the following steps: extracting semantic feature data and keywords for the recommended topics; generating a shortened topic corresponding to the recommended topics based on the semantic feature data and the keywords; and returning the shortened topic corresponding to the recommended topics to the client. After determining the recommended topics, the shortened topics corresponding to the recommended topics can be determined. Specifically, this can be achieved through the following steps: extracting semantic feature data and keywords for each recommended topic; generating a shortened topic corresponding to the recommended topics based on the semantic feature data and the keywords; and returning the shortened topic corresponding to the recommended topics to the client.

[0131] The above steps can be implemented using Natural Language Processing (NLP) technology. NLP technology can preserve the core semantics and key information of long sentences while removing redundant expressions, resulting in more concise and clear short sentences. In this embodiment, the specific steps for converting the recommended topic into abbreviated topics using NLP technology are as follows:

[0132] The first step is to break down the recommended topic into words and obtain the part-of-speech (e.g., noun, verb, or adjective) of each word. The second step is to analyze the grammatical dependencies between the words in the recommended topic based on the obtained part-of-speech, thereby extracting the semantic feature data of the recommended topic. The third step is to identify key entities in the recommended topic (e.g., names, locations, times, or organizations) and extract keywords from them. The fourth step is to combine the extracted keywords into an initial abbreviated topic. The fifth step is to check whether the similarity between the semantic feature data of the initial abbreviated topic and the semantic feature data of the recommended topic reaches a preset similarity. If so, the initial abbreviated topic is determined as the abbreviated topic corresponding to the recommended topic.

[0133] Through the above steps, the recommended topic can be compressed into a shortened topic that is semantically consistent and shorter than its original text length. This shortened topic is then returned to the client, allowing the client to display it in the graphical user interface as needed. In a further optional implementation, after determining the recommended topic and its corresponding recommended content, the relevance between the target user and the recommended topic can be determined based on the target user's historical behavior data. The determined recommended topics are then sorted based on this relevance, and the sorting information is returned to the client. The client can then display the top-ranked recommended topic as the pinned recommended topic.

[0134] When determining the recommended topics associated with the target user, the system also determines the points of interest (POIs) corresponding to the recommended content of those topics. Alternatively, after sorting the determined recommended topics, the system determines the POIs to be displayed on the electronic map page based on the recommended content of the top-ranked topic. This information may include, but is not limited to, the geographical location information and distinctive features of the POIs. If the top-ranked recommended topic includes multiple POIs, then the POIs to be displayed on the electronic map page may also include multiple POIs within the recommended content of the top-ranked topic.

[0135] In one optional implementation, after determining the information of the points of interest to be displayed on the electronic map page, the data processing method provided in this application embodiment may further include the following steps:

[0136] The system receives a recommendation request from the client for points of interest displayed on an electronic map page; obtains the travel mode of the target user; selects a target recommended point of interest for the target user from the points of interest displayed on the electronic map page based on the travel mode; and returns the target recommended point of interest to the client.

[0137] Specifically, the step of selecting target recommended points of interest for the target user from the points of interest displayed on the electronic map page based on the travel mode may include:

[0138] If the mode of travel is motor vehicle travel, the points of interest with a smoothness greater than the preset smoothness and a parking space availability greater than the preset availability will be selected as target recommended points of interest from the routes from the current geographical location to the points of interest displayed on the electronic map page.

[0139] If the mode of travel is non-motorized vehicle travel, the points of interest in the routes from the current geographical location to the points of interest displayed on the electronic map page where the proportion of non-motorized vehicle lanes is greater than a preset proportion will be selected as target recommended points of interest.

[0140] In this implementation, target interest points matching the travel patterns of the target user are determined based on the behavioral dimension of travel mode, thus aligning with the target user's travel needs.

[0141] In another optional implementation, after determining the information of the points of interest to be displayed on the electronic map page, the data processing method provided in this application embodiment may further include the following steps:

[0142] The system receives a recommendation request from the client for points of interest displayed on an electronic map page; obtains the target points of interest viewed by the target user within a target time period; and identifies points of interest displayed on the electronic map page whose similarity to the target points of interest is greater than a preset value as target recommended points of interest. The target time period is the period from a target time to the current time, and the target time is a time preceding the current time and the time interval between the current time and the current time is a preset duration (e.g., 3 days, 5 days, 7 days, etc.).

[0143] In this implementation, recommended points of interest (POIs) matching the target user's viewing history are determined based on the user's viewing behavior within a recent target time period. For example, if the target user viewed Cantonese tea restaurants in the morning, then similar POIs displayed on the electronic map page can be used as recommended POIs. Similarly, if the target user frequently viewed Japanese cuisine the previous day, then similar POIs displayed on the electronic map page can be used as recommended POIs.

[0144] After the target recommended points of interest are determined, the target recommended points of interest can be returned to the client so that the client can highlight the target recommended points of interest on the electronic map as needed.

[0145] Optionally, when there are multiple points of interest to be displayed on the electronic map page, after determining the information of the points of interest to be displayed on the electronic map page, the data processing method provided in this application embodiment may further include the following steps: obtaining scene feature data corresponding to each point of interest to be displayed on the electronic map page; determining the relevance between the target user and each point of interest to be displayed on the electronic map page based on the historical behavior data and the scene feature data; sorting the points of interest to be displayed on the electronic map page according to the relevance to obtain sorting information of the points of interest to be displayed on the electronic map page; and returning the sorting information of the points of interest to be displayed on the electronic map page to the client.

[0146] In this embodiment, the server can determine the relevance between the target user and the multiple points of interest displayed on the electronic map page based on the target user's historical behavior data and the scene feature data corresponding to each of the multiple points of interest displayed on the electronic map page; and sort the points of interest displayed on the electronic map page according to the relevance.

[0147] In map navigation applications, corresponding scene feature data can be pre-recorded for each point of interest. The scene feature data is used to characterize the scene type and scene environment of the corresponding point of interest.

[0148] After obtaining the historical behavior data of the target user and the scene feature data corresponding to the points of interest displayed on the electronic map page, the historical behavior data and the scene feature data can be converted into the same vector space. Then, the distance between the historical behavior data and the scene feature data in the same vector space can be calculated. The smaller the distance, the greater the correlation between the target user and the corresponding points of interest. The points of interest displayed on the electronic map page are sorted based on this distance.

[0149] After sorting the points of interest displayed on the electronic map page, the sorting information of the points of interest displayed on the electronic map page is returned to the client, so that the client can obtain the sorting information of the points of interest displayed on the electronic map page, and display the sorting information of the points of interest while displaying the information of the points of interest on the electronic map page.

[0150] Optionally, the data processing method provided in this application embodiment may further include the following steps: receiving a notification message sent by the client that includes supplementary search information corresponding to the target recommended content by the target user; determining information of target interest points to be recommended that are associated with the recommendation topic corresponding to the target recommended content and whose scene attribute features match the supplementary search information; and returning the information of the target interest points to the client.

[0151] In this embodiment, when supplementary search information corresponding to the target recommended content is obtained, at least one of the database, product database, and user review database of the map navigation application can be called to search for target interest points that are related to the recommended topic corresponding to the target recommended content and whose scene attribute features match the supplementary search information. In this way, the information of the target interest points to be recommended is obtained, and the information of the target interest points is returned to the client so that the information of the target interest points is displayed on the client.

[0152] As can be seen, the data processing method provided in the second embodiment of this application, upon receiving a notification message from the client indicating a recommendation instruction triggered by a target user, acquires the target user's user behavior data and current geographical location; based on the user behavior data and the current geographical location, it determines a recommendation topic associated with the target user and the corresponding recommendation content; thus, the determined recommendation topic conforms to the target user's historical preferences and behavioral habits and is associated with the target user's current geographical location, and the determined recommendation content corresponding to the recommendation topic also conforms to the target user's historical preferences and behavioral habits and is associated with the target user's current geographical location; the recommendation topic and its recommendation content are then returned to the client. Therefore, the data processing method provided in this embodiment can combine the user's historical behavior data and current geographical location to determine the corresponding recommendation topic and recommendation content, thereby meeting the user's personalized needs.

[0153] Corresponding to the interaction method provided in the first embodiment of this application, the third embodiment of this application also provides an interaction device, such as... Figure 10 As shown, the interactive device 1000 includes: a first acquisition unit 1001, used to acquire a recommendation topic associated with the target user in response to a recommendation instruction triggered by the target user; wherein the recommendation topic is generated by a preset artificial intelligence model based on the target user's historical behavior data and current geographical location; a second acquisition unit 1002, used to acquire the recommendation content corresponding to the recommendation topic; and a display unit 1003, used to display a recommendation page including the recommendation topic and its recommendation content.

[0154] Optionally, the display unit 1003 is further configured to:

[0155] Obtain the abbreviated topic corresponding to the recommended topic; wherein the abbreviated topic of the recommended topic has the same semantics as the recommended topic and the text length is shorter than that of the recommended topic;

[0156] Display the abbreviated themes corresponding to the recommended themes.

[0157] Optionally, the display unit 1003 is further configured to:

[0158] In response to a command to shrink the display area of ​​the recommendation page, a thumbnail of the recommended topic is displayed at the top or bottom of the shrunken recommendation page.

[0159] Optionally, the display unit 1003 is further configured to:

[0160] In response to a touch command for any thumbnail topic, the recommended content corresponding to that thumbnail topic is displayed at the top of the recommended page; and / or,

[0161] In response to a touch command for any recommended theme, the style of the thumbnail theme corresponding to that recommended theme is displayed as the preset selected style.

[0162] Optionally, the display unit 1003 is further configured to:

[0163] Obtain information about points of interest to be displayed on the electronic map page; wherein the points of interest are determined based on target recommended content on the recommendation page, and the target recommended content includes: recommended content displayed at the top of the recommendation page, or recommended content selected by the target user on the recommendation page;

[0164] Information about the points of interest is displayed on the electronic map page.

[0165] Optionally, the display unit 1003 is further configured to:

[0166] Obtain the recommendation reason and at least one generative question corresponding to the recommended topic; wherein, the recommendation reason and the generative question are generated by the artificial intelligence model based on the historical behavior data of the target user;

[0167] The page displays a recommendation page that includes the recommended topic and its reasons for recommendation, the recommended content, and at least one generative question.

[0168] Optionally, the display unit 1003 is further configured to:

[0169] In response to the target user's selection of at least two points of interest, the comparison information of the at least two points of interest is obtained and displayed.

[0170] Optionally, a search control is also displayed on the electronic map page, and the display unit 1103 is further used for:

[0171] Based on the search control, obtain the supplementary search information of the target user for the target recommended content;

[0172] Based on the supplementary search information and the recommended topics corresponding to the target recommended content, information on the target interest points to be recommended is obtained;

[0173] Based on the information of the target point of interest, the information of the target point of interest is displayed on the electronic map page.

[0174] Optionally, multiple points of interest may be displayed on the electronic map page, and the display unit 1103 is further configured to:

[0175] The electronic map page displays information about the points of interest and their sorting information.

[0176] Corresponding to the data processing method provided in the second embodiment of this application, the fourth embodiment of this application also provides a data processing apparatus, such as... Figure 11 As shown, the data processing device 1100 includes: a receiving unit 1101, configured to receive a notification message sent by the client indicating a recommendation instruction triggered by a target user; an acquisition unit 1102, configured to acquire user behavior data and current geographical location of the target user; a determining unit 1103, configured to determine a recommendation topic associated with the target user and the recommendation content corresponding to the recommendation topic based on the user behavior data and the current geographical location; and a sending unit 1104, configured to return the recommendation topic and its recommendation content to the client.

[0177] Optionally, the determining unit 1103 is further configured to extract semantic feature data and keywords of the recommended topic; and generate abbreviated topics corresponding to the recommended topic based on the semantic feature data and the keywords;

[0178] The sending unit 1104 is also used to return the abbreviated topic corresponding to the recommended topic to the client.

[0179] Optionally, the receiving unit 1101 is further configured to receive a recommendation request from the client for points of interest displayed on the electronic map page;

[0180] The acquisition unit 1102 is also used to acquire the travel mode of the target user;

[0181] The determining unit 1103 is further configured to select a target recommended point of interest for the target user from the points of interest displayed on the electronic map page according to the travel mode;

[0182] The sending unit 1104 is also used to return the target recommended points of interest to the client.

[0183] Optionally, the acquisition unit 1102 is further configured to acquire scene feature data corresponding to the points of interest to be displayed on the electronic map page;

[0184] The determining unit 1103 is further configured to determine the relevance between the target user and the points of interest to be displayed on the electronic map page based on the historical behavior data and the scene feature data; and to sort the points of interest to be displayed on the electronic map page according to the relevance to obtain sorting information of the points of interest to be displayed on the electronic map page.

[0185] The sending unit 1104 is also used to return to the client the sorting information of the points of interest to be displayed on the electronic map page.

[0186] Optionally, the receiving unit 1101 is further configured to receive a notification message sent by the client, which includes supplementary search information corresponding to the target user's target recommended content;

[0187] The determining unit 1103 is further configured to determine information on target interest points to be recommended that are associated with the recommendation topic corresponding to the target recommended content and whose scene attribute features match the supplementary search information;

[0188] The sending unit 1104 is also used to return the information of the target point of interest to the client.

[0189] Corresponding to the interaction method provided in the first embodiment of this application or the data processing method provided in the second embodiment of this application, the fifth embodiment of this application also provides an electronic device for interaction or for data processing. For example... Figure 12 The diagram shown is a structural block diagram of an example of an electronic device for interaction or data processing provided in an embodiment of this application.

[0190] In this embodiment, an optional hardware structure of the electronic device 1200 may be as follows: Figure 12As shown, the device includes: at least one processor 1201, at least one memory 1202, and at least one communication bus 1205; the memory 1202 contains a program 1203 and data 1204. The bus 1205 can be a communication device for transmitting data between components within the electronic device 1200, such as an internal bus (e.g., a CPU-memory bus, where the processor is the central processing unit, or CPU for short) or an external bus (e.g., a Universal Serial Bus port, a Peripheral Component Interconnect Fast Port). Additionally, the electronic device also includes: at least one network interface 1206 and at least one peripheral interface 1207. Network interface 1206 provides wired or wireless communication with an external network 1208 (e.g., the Internet, intranet, local area network, mobile communication network, etc.). In some embodiments, network interface 1206 may include any number of network interface controllers (NICs), radio frequency (RF) modules, repeaters, transceivers, modems, routers, gateways, any combination of wired network adapters, wireless network adapters, Bluetooth adapters, infrared adapters, near field communication (NFC) adapters, cellular network chips, etc. Peripheral interface 1207 is used to connect to peripherals, such as peripheral 1 in the figure. Figure 12 1209 in the middle), peripheral 2 ( Figure 12 1210 in the middle) and peripheral 3 ( Figure 12 (1211 in the original text). Peripherals are peripheral devices, which may include, but are not limited to, cursor control devices (e.g., mouse, touchpad, or touchscreen), keyboards, displays (e.g., cathode ray tube displays, liquid crystal displays), displays or light-emitting diode displays, video input devices (e.g., cameras or input interfaces coupled to video files), etc. Processor 1201 may be a CPU, or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application. Memory 1202 may include high-speed RAM (Random Access Memory) and may also include non-volatile memory, such as at least one disk storage device. Processor 1201 calls the programs and data stored in memory 1202 to execute the interactive method of the first embodiment of this application or the data processing method provided in the second embodiment of this application.

[0191] Corresponding to the interaction method of the first embodiment of this application or the data processing method provided in the second embodiment of this application, the sixth embodiment of this application provides a computer-readable storage medium storing a program of the interaction method or the data processing method, which is executed by a processor to perform the interaction method of the first embodiment of this application or the data processing method provided in the second embodiment of this application.

[0192] It should be noted that for detailed descriptions of the methods, apparatus, electronic devices, and computer-readable storage media provided in the second, third, fourth, fifth, and sixth embodiments of this application, please refer to the relevant descriptions of the first embodiment of this application, which will not be repeated here.

[0193] Although this application discloses preferred embodiments as described above, it is not intended to limit this application. Any person skilled in the art can make possible changes and modifications without departing from the spirit and scope of this application. Therefore, the scope of protection of this application should be determined by the scope defined in the claims of this application.

[0194] In a typical configuration, a node device in a blockchain includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0195] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0196] 1. Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage media, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include non-transitory computer-readable media, such as modulated data signals and carrier waves.

[0197] 2. Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0198] Although this application discloses preferred embodiments as described above, it is not intended to limit this application. Any person skilled in the art can make possible changes and modifications without departing from the spirit and scope of this application. Therefore, the scope of protection of this application should be determined by the scope defined in the claims of this application.

Claims

1. An interaction method, characterized in that, include: In response to a recommendation instruction triggered by a target user, the system retrieves recommendation topics associated with the target user; wherein, the recommendation topics are generated by a preset artificial intelligence model based on the target user's historical behavior data and current geographical location. Obtain the recommended content corresponding to the recommended topic; A recommendation page will be displayed, including the recommended topics and their recommended content.

2. The method according to claim 1, characterized in that, Simultaneously or subsequently, the process includes: Obtain the abbreviated topic corresponding to the recommended topic; wherein the abbreviated topic of the recommended topic has the same semantics as the recommended topic and the text length is shorter than that of the recommended topic; Simultaneously or after displaying the recommendation page, which includes the recommended topics and their recommended content, the following are also included: Display the abbreviated themes corresponding to the recommended themes.

3. The method according to claim 2, characterized in that, The display of the thumbnail topics corresponding to the recommended topics includes: In response to a command to shrink the display area of ​​the recommendation page, a thumbnail of the recommended topic is displayed at the top or bottom of the shrunken recommendation page.

4. The method according to claim 2, characterized in that, After displaying the abbreviated themes corresponding to the recommended themes, the following is also included: In response to a touch command for any thumbnail topic, the recommended content of the corresponding recommended topic is displayed at the top of the recommended page; and / or, In response to a touch command for any recommended theme, the style of the thumbnail theme corresponding to that recommended theme is displayed as the preset selected style.

5. The method according to any one of claims 1-4, characterized in that, The recommendation page is displayed on top of the electronic map page. After displaying the recommendation page, which includes the recommended topics and their recommended content, it also includes: Obtain information about points of interest to be displayed on the electronic map page; wherein the points of interest are determined based on target recommended content on the recommendation page, and the target recommended content includes: recommended content displayed at the top of the recommendation page, or recommended content selected by the target user on the recommendation page; Information about the points of interest is displayed on the electronic map page.

6. The method according to any one of claims 1-4, characterized in that, Before displaying the recommendation page, which includes the recommended topics and their recommended content, the following is also included: Obtain the recommendation reason and at least one generative question corresponding to the recommended topic; wherein, the recommendation reason and the generative question are generated by the artificial intelligence model based on the historical behavior data of the target user; The display includes a recommendation page featuring the recommended topics and their recommended content, comprising: The page displays a recommendation page that includes the recommended topic and its reasons for recommendation, the recommended content, and at least one generative question.

7. The method according to claim 5, characterized in that, After displaying the information of the point of interest on the electronic map page, the method further includes: In response to the target user's selection of at least two points of interest, the comparison information of the at least two points of interest is obtained and displayed.

8. The method according to claim 5, characterized in that, A search control is also displayed on top of the electronic map page. After the information of the point of interest is displayed on the electronic map page, the method further includes: Based on the search control, obtain the supplementary search information of the target user for the target recommended content; Based on the supplementary search information and the recommended topics corresponding to the target recommended content, information on the target interest points to be recommended is obtained; Based on the information of the target point of interest, the information of the target point of interest is displayed on the electronic map page.

9. The method according to claim 5, characterized in that, Multiple points of interest (POIs) will be displayed on the electronic map page. Information about these POIs will be displayed on the electronic map page, including: The electronic map page displays information about the points of interest and their sorting information.

10. An interactive device, characterized in that, include: The first acquisition unit is used to acquire recommendation topics associated with the target user in response to a recommendation instruction triggered by the target user; wherein the recommendation topics are generated by a preset artificial intelligence model based on the target user's historical behavior data and current geographical location; The second acquisition unit is used to acquire the recommended content corresponding to the recommended topic; The display unit is used to display a recommendation page that includes the recommended topics and their recommended content.

Images