Information recommendation method and device, electronic equipment and storage medium

Abstract

The application provides an information recommendation method and device, electronic equipment and a storage medium. The method comprises the following steps: displaying a heat map, wherein the heat map comprises a plurality of positions, and the display parameter of each position is related to the recommendation index data of the recommendation information associated with the position, and the recommendation information has an incentive attribute; in response to a trigger operation on the recommendation information associated with a first position in the plurality of positions, displaying the recommendation information details of the recommendation information. Through the application, interactive selection of the user can be realized, thereby improving the user experience, and the click rate and conversion rate of the recommendation information.

Description

Technical Field

[0001] This application relates to the field of Internet technology, and in particular to an information recommendation method, apparatus, electronic device, and storage medium. Background Technology

[0002] In the era of big data on the Internet, how to accurately recommend information to target audiences, satisfying users' personalized needs while ensuring the effectiveness of information recommendations, has become a key focus for many online platforms.

[0003] Related technologies provide location-based advertising platforms that allow advertisers to select the geographic locations where they want to place their ads and provide statistics on ad click-through rates and conversion rates.

[0004] However, the solutions offered by these technologies are relatively limited, resulting in insufficient interaction between advertisers and users. Users find it difficult to interact with and make choices regarding ads, thus reducing click-through rates and conversion rates. Furthermore, users have low acceptance of these ads, leading to a poor user experience. Summary of the Invention

[0005] This application provides an information recommendation method, apparatus, electronic device, computer-readable storage medium, and computer program product, which can enable interactive selection by users, thereby improving user experience and the click-through rate and conversion rate of recommended information.

[0006] The technical solution of this application embodiment is implemented as follows:

[0007] This application provides an information recommendation method, including:

[0008] Display a heatmap, wherein the heatmap includes multiple locations, and the display parameters of each location are related to the recommendation index data of the recommendation information associated with the location, and the recommendation information has incentive attributes;

[0009] In response to a trigger operation that associates the recommendation information with the first location among the plurality of locations, the recommendation information details are displayed.

[0010] This application provides an information recommendation device, including:

[0011] A display module is used to display a heat map, wherein the heat map includes multiple locations, and the display parameters of each location are related to the recommendation index data of the recommendation information associated with the location, and the recommendation information has incentive attributes;

[0012] The display module is further configured to display the recommendation information details of the recommendation information in response to a trigger operation for the recommendation information associated with the first location among the plurality of locations.

[0013] This application provides an electronic device, including:

[0014] Memory, used to store executable instructions;

[0015] The processor, when executing executable instructions stored in the memory, implements the information recommendation method provided in the embodiments of this application.

[0016] This application provides a computer-readable storage medium storing computer-executable instructions for implementing the information recommendation method provided in this application when executed by a processor.

[0017] This application provides a computer program product, including a computer program or computer executable instructions, which, when executed by a processor, implements the information recommendation method provided in this application.

[0018] The embodiments of this application have the following beneficial effects:

[0019] By displaying recommendation metrics data for multiple locations linked together using heatmaps, users can view the heatmaps and select recommendations that interest them and have incentive attributes. This increases the interactivity between users and the recommendations. This interactive selection method not only improves the click-through rate and conversion rate of the recommendations but also enhances user acceptance of the recommendations and personal user satisfaction. Attached Figure Description

[0020] Figure 1 This is a schematic diagram of the architecture of the information recommendation system 100 provided in an embodiment of this application;

[0021] Figure 2 This is a schematic diagram of the structure of the electronic device 500 provided in the embodiments of this application;

[0022] Figure 3 This is a flowchart illustrating the information recommendation method provided in an embodiment of this application;

[0023] Figure 4A and Figure 4B This is a flowchart illustrating the information recommendation method provided in an embodiment of this application;

[0024] Figures 5A to 5C This is a schematic diagram illustrating an application scenario of the information recommendation method provided in the embodiments of this application;

[0025] Figure 6A and Figure 6BThis is a schematic diagram illustrating an application scenario of the information recommendation method provided in the embodiments of this application;

[0026] Figure 7 This is a flowchart illustrating the information recommendation method provided in the embodiments of this application. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0028] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0029] It is understood that in the embodiments of this application, data such as user information are involved. When the embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0030] In the following description, the terms “first, second, ...” are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that “first, second, ...” may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0031] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0032] Before providing a further detailed description of the embodiments of this application, the nouns and terms involved in the embodiments of this application will be explained, and the nouns and terms involved in the embodiments of this application shall be interpreted as follows.

[0033] 1) Heatmap: A visual representation of the spatial characteristics and distribution of a large number of data points within a certain area. For example, in an electronic map, multiple users' preferred locations can be highlighted.

[0034] 2) Heat value: It is used to indicate the relative density of clicks, exposures and other feature data of multiple recommended information (such as advertisements) in a certain position, thereby reflecting the audience popularity of multiple recommended information associated with that position. In other words, the larger the heat value, the more popular the multiple recommended information associated with that position is with users, that is, the more interested users are in the multiple recommended information associated with that position.

[0035] 3) Response: used to indicate the conditions or states on which the operation is performed. When the conditions or states on which the operation is performed are met, one or more operations may be performed in real time or with a set delay. Unless otherwise specified, there is no restriction on the order in which the multiple operations are performed.

[0036] 4) Electronic maps: also known as digital maps, are maps stored and viewed digitally using computer technology. Electronic maps typically store information using vector graphics, and the map scale can be enlarged, reduced, or rotated without affecting the display effect.

[0037] 5) Recommendation index data: This is used to characterize the popularity of recommended information or the degree of user interest in recommended information. The higher the recommendation index data, the more popular the recommended information is or the more interested users are in the recommended information. The recommendation index data can be determined based on the heat value of the location.

[0038] 6) Recommendation Information: This refers to information recommended to the target audience. Recommendation information can have incentive attributes; for example, it can be incentivized advertising (such as incentivized video ads). The display methods for recommendation information can be varied, such as bubbles, pop-ups, or overlays. Taking bubbles as an example, short information can be displayed within the bubble, such as the ad name, video name, or brand name. Of course, a thumbnail of the ad logo can also be displayed within the bubble.

[0039] 7) Recommendation Information Details: This refers to the detailed information of the recommendation information. For example, if the recommendation information is an advertisement, the recommendation information details can include the name of the advertisement, the copy of the advertisement, and the spokesperson of the advertisement.

[0040] 8) Incentive attributes: Some form of positive feedback to users who participate in the interaction of recommended information (such as liking, watching, collecting, forwarding, etc.). For example, users can be guided to perform certain behaviors to obtain corresponding rewards. Taking incentivized video ads as an example, after watching a video ad, users can be given rewards such as game items or free trial periods to increase user enthusiasm.

[0041] 9) Incentive-based advertising: This is a form of advertising that uses rewards to guide user actions and attract user participation, transforming passive audience attention into active engagement, and even participation in the advertising campaign. For example, users can log in to the advertiser's website to participate in a prize draw, or redeem goods of varying value using points. By clicking on ads and receiving a certain reward, users are encouraged to actively engage with the ads, thereby gaining a deeper understanding of the advertising content and the products and services offered by the advertiser.

[0042] 10) Rewarded Video Ads: This is an ad format primarily used in mobile applications. Users earn in-app rewards or in-game items by watching video ads. This ad format is called rewarded video because it typically offers users incentives such as virtual currency, in-game items, or free trials. Rewarded videos are usually 15 to 30 seconds long, and users receive their reward after watching the entire ad. Video ads are generally full-screen and cannot be skipped to ensure users watch the entire ad, thereby increasing the advertiser's conversion rate.

[0043] 11) Software Development Kit (SDK): This is a collection of development tools, documentation, sample code, etc., used by software developers. SDKs typically include libraries, application programming interface (API) documentation, sample code, debugging tools, etc., required for software development, so that developers can develop software applications more easily and efficiently.

[0044] 12) Click-Through Rate (CTR): This refers to the ratio of the number of clicks on a specific recommendation to the number of times the recommendation is displayed. CTR is commonly used to evaluate the effectiveness of online or email advertising and is one of the important metrics for measuring ad click performance.

[0045] 13) Conversion Rate (CVR): This refers to the percentage of users who ultimately complete a target action during an advertising campaign, such as purchasing, registering, or downloading. Specifically, CVR is the ratio of the number of users who complete the target action to the total amount of advertising spent throughout the entire conversion funnel from ad placement to user completion of the target action.

[0046] 14) Wireless Fidelity (WiFi) fingerprinting: This is an indoor positioning technology based on WiFi signals. It builds a fingerprint database by collecting information such as WiFi signal strength and signal source, and then calculates the user's location by comparing the user's current WiFi signal information with the data in the fingerprint database. This positioning method is usually performed inside buildings because indoor WiFi signals are less susceptible to interference, providing higher accuracy.

[0047] Taking recommendation information as an example, related technologies provide some location-based advertising platforms. These platforms allow advertisers to select the geographical locations where they want to place their ads and provide some statistics on ad click-through rates and conversion rates.

[0048] However, in implementing the embodiments of this application, the applicant discovered that these platforms do not provide the functionality for users to interactively select advertisements based on geographic location. This deficiency leads to insufficient interaction between advertisers and users, making it difficult for users to interact with and select advertisements, thereby reducing click-through rates and conversion rates. Furthermore, user acceptance of advertisements is low, resulting in a poor user experience and negatively impacting the revenue of both advertisers and the advertising platform.

[0049] In view of this, embodiments of this application provide an information recommendation method, apparatus, electronic device, computer-readable storage medium, and computer program product, which can realize interactive selection by users, thereby improving user experience and the click-through rate and conversion rate of recommended information. The electronic device provided in the embodiments of this application will be described below. The electronic device provided in the embodiments of this application can be implemented as a terminal device, or implemented collaboratively by a server and a terminal device. The following description uses the information recommendation method provided in the embodiments of this application implemented collaboratively by a server and a terminal device as an example.

[0050] For example, see Figure 1 , Figure 1 This is a schematic diagram of the architecture of the information recommendation system 100 provided in this application embodiment. To support applications that increase interaction between users and recommended information, thereby improving the click-through rate and conversion rate of recommended information, such as... Figure 1 As shown, the information recommendation system 100 includes: a server 200, a network 300, and a terminal device 400. The network 300 can be a local area network (LAN), a wide area network (WAN), or a combination of both. The terminal device 400 is the terminal device associated with the user. A client 410 runs on the terminal device 400. The client 410 can be various types of clients, such as instant messaging clients, video playback clients, e-commerce shopping clients, browsers, etc.

[0051] In some embodiments, a heatmap can be displayed on the client 410. The heatmap may include multiple locations, and the display parameters for each location are related to the recommendation metrics data of the recommendation information associated with that location. Furthermore, the recommendation information may have incentive attributes; for example, if the recommendation information is an incentivized video advertisement, the user can receive corresponding rewards (such as game items, free trials, etc.) after watching the video advertisement to increase user engagement. Subsequently, in response to a trigger operation for the recommendation information associated with a first location among the multiple locations, such as receiving a user's click operation on advertisement 1 associated with the first location (e.g., point of interest A), the client 410 sends a request to the server 200 via network 300 to obtain detailed information about advertisement 1. In response to the request sent by the client 410, the server 200 returns detailed information about advertisement 1 to the client 410 for presentation in the human-computer interaction interface of the client 410.

[0052] In other embodiments, the embodiments of this application can also be implemented with the aid of cloud technology, which refers to a hosting technology that unifies a series of resources such as hardware, software, and networks within a wide area network or local area network to realize the computation, storage, processing, and sharing of data.

[0053] Cloud technology is a general term encompassing network technology, information technology, integration technology, management platform technology, and application technology based on the cloud computing business model. It can form resource pools, allowing for on-demand use with flexibility and convenience. Cloud computing technology will become a crucial support. The backend services of cloud computing systems require substantial computing and storage resources.

[0054] Example, Figure 1 The server 200 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. The terminal device 400 can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, in-vehicle terminal, etc., but is not limited to these. The terminal device 400 and the server 200 can be directly or indirectly connected via wired or wireless communication, which is not limited in this embodiment.

[0055] In some embodiments, the terminal device or server may also implement the information recommendation method provided in this application embodiment by running various computer-executable instructions or computer programs. For example, computer-executable instructions may be microprogram-level commands, machine instructions, or software instructions. Computer programs may be native programs or software modules in an operating system; they may be native applications (APPs), i.e., programs that need to be installed in the operating system to run, such as video playback APPs or instant messaging APPs; or they may be applets, i.e., programs that only need to be downloaded to a browser environment to run. In summary, the aforementioned computer-executable instructions may be any form of instruction, and the aforementioned computer programs may be any form of application, module, or plugin.

[0056] The structure of the electronic device provided in the embodiments of this application will be further described below. Taking the electronic device as a terminal device as an example, see... Figure 2 , Figure 2 This is a schematic diagram of the structure of the electronic device 500 provided in the embodiments of this application. Figure 2 The illustrated electronic device 500 includes at least one processor 510, a memory 550, at least one network interface 520, and a user interface 530. The various components in the electronic device 500 are coupled together via a bus system 540. It is understood that the bus system 540 is used to implement communication between these components. In addition to a data bus, the bus system 540 also includes a power bus, a control bus, and a status signal bus. However, for clarity, ... Figure 2 The general labeled all buses as Bus System 540.

[0057] The processor 510 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0058] User interface 530 includes one or more output devices 531 that enable the presentation of media content, including one or more speakers and / or one or more visual displays. User interface 530 also includes one or more input devices 532, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.

[0059] The memory 550 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state storage, hard disk drives, optical disk drives, etc. The memory 550 may optionally include one or more storage devices physically located away from the processor 510.

[0060] The memory 550 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), and the volatile memory may be random access memory (RAM). The memory 550 described in this application embodiment is intended to include any suitable type of memory.

[0061] In some embodiments, memory 550 is capable of storing data to support various operations, examples of which include programs, modules, and data structures or subsets or supersets thereof, as illustrated below.

[0062] Operating system 551 includes system programs for handling various basic system services and performing hardware-related tasks, such as the framework layer, core library layer, driver layer, etc., for implementing various basic business functions and handling hardware-based tasks;

[0063] The network communication module 552 is used to reach other computing devices via one or more (wired or wireless) network interfaces 520, exemplary network interfaces 520 including: Bluetooth, WiFi, and Universal Serial Bus (USB), etc.

[0064] Presentation module 553 is configured to enable the presentation of information (e.g., a user interface for operating peripheral devices and displaying content and information) via one or more output devices 531 (e.g., a display screen, a speaker, etc.) associated with user interface 530;

[0065] The input processing module 554 is used to detect and translate one or more user inputs or interactions from one or more input devices 532.

[0066] In some embodiments, the apparatus provided in this application can be implemented in software. Figure 2An information recommendation device 555 stored in memory 550 is shown. This device can be software in the form of programs and plug-ins, and includes the following software modules: a display module 5551, an acquisition module 5552, a determination module 5553, a query module 5554, a sending module 5555, a jump module 5556, and a rendering module 5557. These modules are logically connected and can therefore be arbitrarily combined or further separated according to the functions implemented. It should be noted that... Figure 2 For ease of explanation, all the above modules are shown at once, but this should not be interpreted as excluding the implementation of the information recommendation device 555 which may only include the display module 5551. The functions of each module will be explained below.

[0067] The information recommendation method provided in this application will be specifically described below with reference to exemplary applications and implementations of the terminal devices provided in the embodiments of this application.

[0068] For example, see Figure 3 , Figure 3 This is a flowchart illustrating the information recommendation method provided in the embodiments of this application, which will be combined with... Figure 3 The steps shown are explained.

[0069] It should be noted that, Figure 3 The method illustrated can be executed by various forms of computer programs running on the terminal device, and is not limited to a client. For example, it can also be the operating system, software module, script, and applet mentioned above. Therefore, the client-side examples used below should not be considered as limiting the embodiments of this application. Furthermore, for ease of description, no specific distinction will be made between the terminal device and the client running on the terminal device below.

[0070] In step 101, a heat map is displayed.

[0071] Here, the heatmap can include multiple locations, and the display parameters of each location are related to the recommendation metrics data of the recommendation information associated with that location. The recommendation information can have incentive attributes. For example, taking the recommendation information as an incentivized advertisement, after a user completes an interactive action related to the incentivized advertisement (such as watching a video or browsing a page), the user can be given corresponding rewards (such as game items, free trials, etc.) to improve the advertisement's conversion rate and click-through rate.

[0072] For example, the location mentioned above can be coordinates (such as a point on an electronic map), point of interest (POI), or area (i.e., a range of coordinates, such as a shopping mall, shopping center, park, etc.). Among these, a point of interest can be a building, a shop, a mailbox, a bus stop, etc.

[0073] For example, the display parameters mentioned above can be the lightness or darkness of a color (i.e., color brightness, also known as color luminance) or transparency. For instance, taking color lightness or darkness as the display parameter, a higher recommendation index for location-related recommendations indicates greater user interest in that location, resulting in a darker color for that location; conversely, a lower recommendation index indicates less user interest in that location, resulting in a lighter color for that location. In other words, darker colors associated with locations are more popular with users, while lighter colors are less popular. This allows users to intuitively select recommendations that interest them.

[0074] In some embodiments, before displaying the heatmap, the following processing may also be performed: obtaining multiple heat values ​​corresponding one-to-one with multiple locations; for each of the multiple locations, determining recommendation index data of the recommendation information associated with the location and display parameters of the location based on the location's heat value.

[0075] In other embodiments, following the above examples, the acquisition of multiple heat values ​​corresponding to multiple locations can be achieved in the following way: for each of the multiple locations, the following processing is performed: acquiring feature data of the recommendation information associated with the location, wherein the feature data includes at least one of click-through rate, exposure rate, and conversion rate; determining the heat value of the location based on the feature data of the recommendation information associated with the location.

[0076] For example, the feature data of the location-related recommendation information described above can be implemented in the following way to determine the heat value of the location: normalize the feature data of the location-related recommendation information to obtain normalized feature data; interpolate the normalized feature data to obtain a two-dimensional surface, where the surface is used to characterize the density distribution of the feature data; and determine the value corresponding to the density distribution as the heat value of the location, where the value is used to characterize the density of the feature data distribution.

[0077] The following example, using a location as an area, illustrates the specific process for determining the thermal value of that area.

[0078] For example, taking Region 1 (a region with multiple areas) and recommended information as advertisements as an example, after obtaining the click-through rate (CTR) and impression rate (IRR) data of multiple advertisements in Region 1, the data in Region 1 can be normalized to avoid errors caused by excessively large or small data volumes. Specifically, a Gaussian kernel density estimation algorithm can be used to process the data to obtain the density distribution of the CTR and IRR data of advertisements in Region 1. Subsequently, for the normalized data (which is not smooth), an interpolation algorithm can be used to transform it into a two-dimensional smooth surface. The interpolation algorithm can be bilinear interpolation, bicubic interpolation, etc. This two-dimensional smooth surface can be used to represent the spatial distribution of the CTR and IRR data of advertisements. Finally, for the density distribution of the CTR and IRR data of advertisements in Region 1 obtained after interpolation, the value representing the density distribution can be used as the heatmap value of Region 1. In other words, this value can be used to represent the relative density of data such as click-through rate and exposure rate of advertisements in region 1, thereby reflecting the audience popularity of advertisements in region 1. That is, it can be used to characterize the degree of user interest in these advertisements, or to characterize the popularity of these advertisements.

[0079] The following section continues to explain the process of obtaining feature data for location-related recommendation information.

[0080] For example, event tracking code can be inserted into the application to identify specific behavioral events. When a user triggers a specific behavioral event, the client packages the corresponding data into an event object and sends it to the backend server. The event object can include metadata (such as event name, timestamp, user identifier, etc.) and custom data (such as recommendation information identifiers, playback duration, etc.). The event object can be serialized using a lightweight data exchange format, such as JavaScript Object Notation (JSON), and then sent to the backend server via Hypertext Transfer Protocol (HTTP). After collecting the raw data sent by the client, the backend server can clean, filter, and process the raw data to obtain feature data of the recommendation information associated with each location (such as click-through rate, impression rate, conversion rate, etc. of advertisements).

[0081] In some embodiments, following the above examples, the above-described location-based heat values ​​can be used to determine the recommendation index data of location-associated recommendation information and the display parameters of the location in the following ways: obtaining the pre-built mapping relationship between heat values, recommendation index data, and display parameters; querying the recommendation index data corresponding to the heat values ​​of the location from the mapping relationship, and determining the queried recommendation index data as the recommendation index data of the location-associated recommendation information; querying the display parameters corresponding to the heat values ​​of the location from the mapping relationship, and determining the queried display parameters as the display parameters of the location.

[0082] For example, taking location 1 out of multiple locations as an example, after obtaining the heat value of location 1, a pre-built mapping table can be further obtained. This mapping table includes the mapping relationships between different heat values ​​and different recommendation index data, as well as different display parameters. For instance, the larger the heat value, the larger the corresponding recommendation index data (i.e., the more popular the recommended information is with users), and the more obvious the display parameters (e.g., the darker the color). Thus, the mapping table can be queried based on the heat value of location 1 to obtain the recommendation index data corresponding to that heat value, which can then be used as the recommendation index data for the recommended information associated with location 1. Similarly, the mapping table can also be queried based on the heat value of location 1 to obtain the display parameters corresponding to that heat value, which can then be used as the display parameters for location 1.

[0083] In other embodiments, a heatmap is used as an example of an electronic map heatmap; see [link to relevant documentation]. Figure 4A , Figure 4A This is a flowchart illustrating the information recommendation method provided in the embodiments of this application, such as... Figure 4A As shown, Figure 3 Step 101 shown can be achieved through Figure 4A Steps 1011A to 1014A shown are implemented by combining Figure 4A The steps shown are explained.

[0084] In step 1011A, an electronic map is obtained.

[0085] Here, the electronic map can include multiple locations.

[0086] In some embodiments, the electronic map can be a two-dimensional map or a three-dimensional map. For example, taking a two-dimensional map as an example, the electronic map can be a two-dimensional map of a city or a two-dimensional map of a neighborhood. The electronic map can include multiple locations, such as multiple points of interest.

[0087] For example, in a search scenario, after receiving a user's input of a point of interest (e.g., point of interest A) in the search box, an electronic map centered on point of interest A can be displayed.

[0088] For example, in a location-based scenario, after obtaining the user's current location (e.g., location B), an electronic map centered on location B (e.g., a store) can be displayed.

[0089] In step 1012A, multiple thermal values ​​corresponding to multiple locations are obtained.

[0090] In some embodiments, step 1012A can be implemented by performing the following process for each of a plurality of locations: obtaining feature data of location-associated recommendation information, wherein the feature data includes at least one of click-through rate, exposure rate, and conversion rate; and determining the heat value of the location based on the feature data of location-associated recommendation information.

[0091] For example, taking location as a point of interest, the heat value of each point of interest can be determined as follows: Normalize the feature data (e.g., click-through rate, conversion rate, exposure rate, etc.) of the recommendation information (e.g., advertisements) associated with the point of interest to obtain normalized feature data; perform interpolation (e.g., bilinear interpolation) on the normalized feature data to obtain a two-dimensional surface, where the surface is used to characterize the density distribution of the feature data; and determine the value corresponding to the density distribution as the heat value of the point of interest, where the value characterizes the density of the feature data distribution.

[0092] In step 1013A, multiple display parameters corresponding to multiple locations are determined based on multiple thermal values.

[0093] In some embodiments, after obtaining multiple thermal values ​​corresponding to multiple locations, a pre-built mapping table can be queried based on the multiple thermal values ​​to obtain multiple display parameters corresponding to the multiple locations. The mapping table includes the mapping relationship between different thermal values ​​and different display parameters.

[0094] For example, taking the heat value of position 1 as an example, after obtaining the heat value of position 1, the mapping table can be queried based on the heat value of position 1 to obtain the display parameters corresponding to the heat value of position 1, which can then be used as the display parameters for position 1.

[0095] It should be noted that the process for determining the display parameters for other positions is similar to the process for determining the display parameters for position 1. The process for determining the display parameters for position 1 can be referred to, and will not be repeated in this embodiment.

[0096] In step 1014A, the electronic map is rendered based on multiple display parameters corresponding to multiple locations to obtain a heat map of the electronic map.

[0097] In some embodiments, after obtaining multiple display parameters corresponding to multiple locations, a heatmap of the electronic map can be obtained by rendering based on these display parameters. For example, location 1 in the electronic map can be rendered as red based on display parameter 1 (assuming RGB values ​​are 255, 0, 0); location 2 in the electronic map can be rendered as orange based on display parameter 2 (assuming RGB values ​​are 255, 165, 0); and location 3 in the electronic map can be rendered as blue based on display parameter 3 (assuming RGB values ​​are 67, 142, 219). The darker the color, the more popular the associated recommendation information (e.g., rewarded video ads, or simply ads) is with users.

[0098] For example, taking the Android platform as an example, a heatmap of an electronic map can be displayed using a custom view. Specifically, first, the base map of the electronic map needs to be drawn in the view, and the obtained geographical location information is converted into screen coordinates. Then, based on the heat value of each location, different colors or transparency are used to draw the heatmap. Finally, the custom view is added to the layout to display the heatmap of the electronic map on the interface.

[0099] In other embodiments, a heatmap serving as a location list is used as an example; see [link to relevant documentation]. Figure 4B , Figure 4B This is a flowchart illustrating the information recommendation method provided in the embodiments of this application, such as... Figure 4B As shown, Figure 3 Step 101 shown can also be achieved through Figure 4B Steps 1011B to 1014B shown are implemented by combining Figure 4B The steps shown are explained.

[0100] In step 1011B, the location list is obtained.

[0101] Here, the list of locations can include multiple locations.

[0102] In some embodiments, taking the location list as an example of a list of points of interest, a list of points of interest consisting of multiple points of interest can be obtained.

[0103] In other embodiments, the location list can be a list of locations within a specific area of ​​an electronic map, such as multiple attractions within a city. Alternatively, the location list can be composed of multiple locations saved by the user in an electronic map app or social media app; for example, multiple locations saved by the user in an electronic map app or social media app can be retrieved to form the location list. Furthermore, the location list can also consist of multiple locations frequently visited by the user; for example, multiple locations visited by the user more than a threshold number (e.g., 5 times) within a past period (e.g., the past month) can be retrieved to form the location list. This application does not specifically limit this aspect.

[0104] In step 1012B, multiple thermal values ​​corresponding to multiple locations are obtained.

[0105] In some embodiments, following the above example, after obtaining a list of points of interest consisting of multiple points of interest, multiple heat values ​​corresponding to each of the multiple points of interest can be obtained.

[0106] It should be noted that the specific implementation process of step 1012B is similar to that of step 1012A above, and can be implemented by referring to step 1012A above. The embodiments of this application will not be described again here.

[0107] In step 1013B, multiple display parameters corresponding to multiple locations are determined based on multiple thermal values.

[0108] In some embodiments, after obtaining multiple heat values ​​corresponding to multiple points of interest, a mapping table can be queried based on the multiple heat values ​​to obtain multiple display parameters corresponding to the multiple points of interest. The mapping table includes the mapping relationship between different heat values ​​and different display parameters.

[0109] It should be noted that the implementation process of step 1013B is similar to that of step 1013A above. You can refer to the implementation of step 1013A above. The embodiments of this application will not be repeated here.

[0110] In step 1014B, a heatmap of the location list is obtained by rendering based on multiple display parameters corresponding to multiple locations.

[0111] In some embodiments, after obtaining multiple display parameters corresponding to multiple locations, a heatmap of the location list can be generated based on these parameters. For example, taking a list of points of interest (POIs) as an example, assuming the POI list includes three POIs: POI 1, POI 2, and POI 3, and assuming the display parameters for POI 1 are RGB values ​​of 67, 142, and 219, then POI 1 can be rendered as blue; assuming the display parameters for POI 2 are RGB values ​​of 255, 0, and 0, then POI 2 can be rendered as red; and assuming the display parameters for POI 3 are RGB values ​​of 255, 165, and 0, then POI 3 can be rendered as orange. Thus, users can intuitively understand the recommendation metrics associated with each location, such as the popularity of the ads associated with each location, based on the heatmap of the location list, making it easier for users to select ads they are interested in.

[0112] In other embodiments, the following processing may also be performed: For at least one target location among multiple locations, the following processing may be performed: For each target location, display recommendation information associated with that target location. Taking advertisements as an example, the recommendation information may be displayed as a bubble containing the advertisement name or an advertisement thumbnail.

[0113] It should be noted that, in addition to displaying recommendation information through bubbles, other methods can also be used, such as displaying it through pop-ups or patches. This application embodiment does not specifically limit this method.

[0114] For example, taking location 1 out of multiple locations as the target location, the recommended information associated with location 1 can be displayed in the vicinity of location 1. For example, thumbnails of multiple recommended information associated with location 1 can be displayed, or some brief information, such as the names of multiple recommended information (e.g., the name of the advertisement), or the brand names involved in multiple recommended information.

[0115] In some embodiments, following the above example, the target location can be determined from multiple locations by: obtaining multiple thermal values ​​corresponding to multiple locations one-to-one; and determining the location corresponding to the thermal value that is greater than the thermal value threshold among the multiple thermal values ​​as the target location.

[0116] For example, taking location as a point of interest, assuming the heatmap includes 5 points of interest, namely point of interest 1 to point of interest 5, we can first obtain the 5 heat values ​​corresponding to these 5 points of interest. For example, assuming the heat value of point of interest 1 is 90, the heat value of point of interest 2 is 89, the heat value of point of interest 3 is 93, the heat value of point of interest 4 is 87, and the heat value of point of interest 5 is 94. Then, we can select the points of interest (i.e., points of interest 3 and points of interest 5) whose heat values ​​are greater than the heat value threshold (assuming it is 91) as target points of interest. Subsequently, we can display corresponding prompts on points of interest 3 and 5 respectively to prompt the multiple recommendation information associated with points of interest 3 and 5.

[0117] For example, taking a heatmap as a list of locations (e.g., a list of points of interest), the list of points of interest includes multiple points of interest, for example, points of interest 1 to 10. At the same time, assuming that points of interest 2 and 5 are points of interest with heat values ​​greater than the heat value threshold (i.e., target locations), then advertisements associated with point of interest 2 (e.g., advertisements 1, 2, and 3) can be displayed on point of interest 2, and advertisements associated with point of interest 5 (e.g., advertisements 4, 5, and 6) can be displayed on point of interest 5 to make recommendations to users.

[0118] It should be noted that the process of obtaining the heat value of the point of interest can be referred to the description above, and will not be repeated here in the embodiments of this application.

[0119] In other embodiments, the target location can also be determined from multiple locations by: for each of the multiple locations, determining the similarity between the location-associated recommendation information and the object data of the target object (e.g., user feature data, including browsing history, interests, etc.); and determining the location corresponding to the similarity greater than the similarity threshold among the multiple similarities as the target location.

[0120] For example, taking location as a point of interest, assuming the heatmap includes three points of interest, namely point of interest 1 to point of interest 3, we can calculate the similarity between the recommendation information associated with point of interest 1 to point of interest 3 and the object data of the target object (e.g., user A). For example, assuming the similarity between the feature vector of the recommendation information associated with point of interest 1 and the feature vector of user A is 90%, the similarity between the feature vector of the recommendation information associated with point of interest 2 and the feature vector of user A is 95%, and the similarity between the feature vector of the recommendation information associated with point of interest 3 and the feature vector of user A is 89%, then the point of interest (i.e., point of interest 2) with a similarity greater than the similarity threshold (e.g., 91%) among these three similarities can be identified as the target point of interest.

[0121] It should be noted that the aforementioned similarity can be the Euclidean distance, cosine distance, or L2 norm between two feature vectors. Furthermore, taking interest point 1 as an example, assuming interest point 1 is associated with three recommendation messages: Recommendation Message 1, Recommendation Message 2, and Recommendation Message 3, we can first extract features from these three recommendation messages to obtain the feature vector corresponding to each recommendation message. Then, we calculate the similarity between the feature vectors of these three recommendation messages and the feature vector of the target object. For example, assuming the similarity between the feature vector of Recommendation Message 1 and the feature vector of the target object is 90%, the similarity between the feature vector of Recommendation Message 2 and the feature vector of the target object is 94%, and the similarity between the feature vector of Recommendation Message 3 and the feature vector of the target object is 89%, we can take the average of these three similarities (i.e., 91%) as the similarity between the feature vectors of the three recommendation messages associated with interest point 1 and the feature vector of the target object.

[0122] In some embodiments, the target location can also be determined from multiple locations by: determining the locations that the target object has previously visited from the multiple locations as the target location; or, determining the locations from the multiple locations whose distance from the target object's current location is less than a distance threshold as the target location.

[0123] For example, taking location as a point of interest, suppose the heatmap includes 5 points of interest, namely point of interest 1 to point of interest 5. Also suppose the target object (e.g., user A) has visited point of interest 2 and point of interest 3. Then point of interest 2 and point of interest 3 can be used as target points of interest. Subsequently, the associated recommendation information can be displayed on point of interest 2 and point of interest 3 respectively. For example, if the recommendation information associated with point of interest 2 is ad 1 and ad 2, then the names of ad 1 and ad 2 can be displayed on point of interest 2 as bubbles; if the recommendation information associated with point of interest 3 is ad 3 and ad 4, then the names of ad 3 and ad 4 can be displayed on point of interest 3 as bubbles.

[0124] For example, taking location as a point of interest (POI), suppose the heatmap includes 5 POIs, namely POI 1 to POI 5. If the target object (e.g., user A) is currently located at point A, then the distances from point A to POIs 1 through POI 5 can be calculated. For instance, suppose the distance between point A and POI 1 is 200 meters, the distance between point A and POI 2 is 300 meters, the distance between point A and POI 3 is 250 meters, the distance between point A and POI 4 is 400 meters, and the distance between point A and POI 5 is 240 meters. Then, the POIs whose distance from point A is less than a distance threshold (e.g., 250 meters) (i.e., POIs 1 and POI 5) can be designated as target POIs. Subsequently, associated recommendation information can be displayed at POIs 1 and POI 5 respectively. For example, taking point of interest 1 as an example, assuming that the recommended information associated with point of interest 1 is ad 1 and ad 2, thumbnails of ad 1 and ad 2 can be displayed on point of interest 1 as bubbles to remind the user that point of interest 1 is associated with ad 1 and ad 2.

[0125] In step 102, in response to a triggering operation for the recommendation information associated with the first location among multiple locations, the recommendation information details are displayed.

[0126] In some embodiments, step 102 can be implemented as follows: in response to a trigger operation for a first location among a plurality of locations, display recommendation information associated with the first location; in response to a trigger operation for recommendation information associated with the first location, display recommendation information details of the recommendation information.

[0127] For example, see the example of a heat map on an electronic map. Figure 5A , Figure 5A This is a schematic diagram illustrating an application scenario of the information recommendation method provided in the embodiments of this application, such as... Figure 5A As shown, the heatmap 501 of the electronic map displays multiple locations (e.g., points of interest, also known as hot zones), such as points of interest 502, 503, and 504. When a user clicks on point of interest 502 (i.e., the first location), recommended information 505 associated with point of interest 502 can be displayed on point of interest 502. For example, multiple advertisements associated with point of interest 502 can be displayed in a bubble format, such as the names of advertisements 1, 2, and 3. When a user clicks on the recommended information 505 associated with point of interest 502, a pop-up window 506 can be displayed in the heatmap 501, and the recommended information details 507 of recommended information 505 can be displayed in the pop-up window 506, such as the detailed information of advertisements 1, 2, and 3.

[0128] In other embodiments, location-related recommendation information can also be displayed automatically. For example, for a target location among multiple locations, recommendation information associated with the target location can be displayed automatically.

[0129] For example, see the example of a heat map on an electronic map. Figure 5B , Figure 5B This is a schematic diagram illustrating an application scenario of the information recommendation method provided in the embodiments of this application, such as... Figure 5B As shown, the heatmap 501 of the electronic map displays multiple locations (e.g., points of interest), such as points of interest 502, 503, and 504. Point of interest 502 displays associated recommendation information 505, such as multiple advertisements associated with point of interest 502 displayed as bubbles, for example, the names of advertisements 1, 2, and 3 can be displayed in the bubbles. Point of interest 504 displays associated recommendation information 508, such as multiple advertisements associated with point of interest 504 displayed as bubbles, for example, the names of advertisements 4, 5, and 6 can be displayed in the bubbles. When a user clicks on the recommendation information 505 associated with point of interest 502, a pop-up window 506 is displayed in the heatmap 501, and the recommendation information details 507 of recommendation information 505 are displayed in the pop-up window 506, for example, the detailed information of advertisements 1, 2, and 3 can be displayed in the pop-up window 506.

[0130] In some embodiments, when there are multiple recommendations, the recommendations can be displayed in a specific sorting order, including: the order of click-through rate from high to low; the order of exposure rate from high to low; and the order of conversion rate from high to low.

[0131] For example, let's take five rewarded video ads as the recommended content, assuming they are rewarded video ad 1 to rewarded video ad 5. Rewarded video ad 1 has a click-through rate (CTR) of 98%, rewarded video ad 2 has a CTR of 94%, rewarded video ad 3 has a CTR of 90%, rewarded video ad 4 has a CTR of 93%, and rewarded video ad 5 has a CTR of 91%. Then, the order of these five rewarded video ads would be: Rewarded Video Ad 1, Rewarded Video Ad 2, Rewarded Video Ad 4, Rewarded Video Ad 5, Rewarded Video Ad 3. This allows users to easily select and watch the rewarded video ads with higher CTRs.

[0132] For example, let's take five rewarded video ads as the recommended content, assuming they are rewarded video ad 1 to rewarded video ad 5. Rewarded video ad 1 has an exposure rate of 98%, rewarded video ad 2 has an exposure rate of 94%, rewarded video ad 3 has an exposure rate of 90%, rewarded video ad 4 has an exposure rate of 93%, and rewarded video ad 5 has an exposure rate of 91%. Then, the order of these five rewarded video ads would be: Rewarded Video Ad 1, Rewarded Video Ad 2, Rewarded Video Ad 4, Rewarded Video Ad 5, Rewarded Video Ad 3. This allows users to easily prioritize watching the rewarded video ads with the highest exposure rates.

[0133] For example, let's take five rewarded video ads as the recommended content, assuming they are rewarded video ad 1 to rewarded video ad 5. Rewarded video ad 1 has a conversion rate of 98%, rewarded video ad 2 has a conversion rate of 94%, rewarded video ad 3 has a conversion rate of 90%, rewarded video ad 4 has a conversion rate of 93%, and rewarded video ad 5 has a conversion rate of 91%. Then, the order of these five rewarded video ads would be: Rewarded Video Ad 1, Rewarded Video Ad 2, Rewarded Video Ad 4, Rewarded Video Ad 5, Rewarded Video Ad 3. This allows users to easily prioritize watching the rewarded video ads with higher conversion rates.

[0134] In other embodiments, the recommendation information may be a video (e.g., a rewarded video ad), and the following processing may also be performed: in response to a video selection operation, displaying a details interface corresponding to the selected video, wherein the details interface may include a playback control; in response to a trigger operation on the playback control, playing the selected video; and sending a reward distribution request to the server, wherein the reward distribution request is used to request the server to distribute a reward (e.g., game items, free trial period, etc.) associated with the selected video to the target object.

[0135] For example, the above-mentioned reward distribution request to the server can be implemented in the following way: In response to the fulfillment of the reward distribution conditions, a reward distribution request is sent to the server, wherein the reward distribution conditions include one of the following: the playback progress of the selected video reaches the progress threshold (e.g., 100%), the playback duration of the selected video reaches the duration threshold (e.g., 5 minutes), or the number of interactions with the selected video (e.g., the number of likes, the number of bullet comments) reaches the number threshold.

[0136] In other embodiments, upon meeting the reward distribution conditions, the following processing may also be performed: displaying a prompt message asking whether to continue playing the next video, wherein the prompt message includes an agree control and a refuse control; continuing to play the next video in response to a triggering operation on the agree control; and jumping back to the heatmap in response to a triggering operation on the refuse control.

[0137] For example, see Figure 5C , Figure 5C This is a schematic diagram illustrating an application scenario of the information recommendation method provided in the embodiments of this application, such as... Figure 5C As shown, after the selected video finishes playing, a prompt message 509 can be displayed on the video playback interface asking whether to continue playing the next video. The prompt message 509 may include an agree control 510 (e.g., a "Yes" button) and a refuse control 511 (e.g., a "No" button). When a user clicks on the agree control 510, the next video continues playing. When a user clicks on the refuse control 511, the user can be redirected back to the heatmap 501 to continue browsing advertisements associated with other locations.

[0138] In some embodiments, the following processing may also be performed: displaying recommendation information associated with a second location among multiple locations, wherein the similarity between the recommendation information associated with the second location and the recommendation information associated with the first location is greater than a similarity threshold.

[0139] For example, taking position 1 out of multiple positions as the first position, assuming that the target object (e.g., user A) browses the recommended information associated with position 1, the similarity between the recommended information associated with other positions and the recommended information associated with position 1 can be calculated. For example, assuming that the similarity between the recommended information associated with position 3 and the recommended information associated with position 1 is greater than the similarity threshold, the recommended information associated with position 3 can be displayed in the heatmap to recommend to user A. In this way, the time spent by the user in searching for recommended information is reduced, and the user experience is improved.

[0140] The information recommendation method provided in this application displays recommendation index data of recommendation information associated with multiple locations in the form of a heatmap. This allows users to view the heatmap and select recommendation information with incentive attributes that they are interested in. This increases the interactivity between users and recommendation information. This interactive selection method can not only improve the click-through rate and conversion rate of recommendation information, but also improve users' acceptance of recommendation information and personal user experience satisfaction.

[0141] The following example, using recommended information as an incentive for video advertising, illustrates an exemplary application of this application in a real-world application scenario.

[0142] This application provides an information recommendation method that uses a geolocation-based heatmap to display users' interest in rewarded video ads, allowing users to select and watch ads that interest them, thereby increasing user interaction with the ads. This interactive selection method not only improves ad click-through rates and conversion rates but also enhances user acceptance and personal user experience satisfaction, ultimately maximizing revenue for both advertisers and the platform.

[0143] The information recommendation method provided in the embodiments of this application will be described in detail below.

[0144] In some embodiments, the technical solutions provided in this application can provide users with the function of interactively selecting rewarded video ads based on geographic location, allowing users to view a geographic location-based heatmap and select rewarded video ads that interest them.

[0145] For example, see Figure 6A , Figure 6A This is a schematic diagram illustrating an application scenario of the information recommendation method provided in the embodiments of this application, such as... Figure 6A As shown, when a user watches a rewarded video ad, the ad SDK displays a heatmap on an electronic map. This heatmap is calculated based on data such as ad click-through rate, impression rate, and conversion rate at different geographical locations. Different colored areas on the heatmap represent the heat value (or popularity value) of that area; the darker the color, the higher the heat value, indicating that the ads in that area are more popular with users. Each rewarded video ad on the heatmap can also display a thumbnail and some brief information, such as the ad name and brand name. For example, area 601 on the heatmap displays recommendation information 603 associated with area 601, such as displaying the names of multiple rewarded video ads associated with area 601 (e.g., ads 1, 2, and 3) in a bubble format; area 602 displays recommendation information 604 associated with area 602, such as displaying the names of multiple rewarded video ads associated with area 602 (e.g., ads 4, 5, and 6) in a bubble format.

[0146] In other embodiments, when a user clicks on a specific area in a heatmap, multiple incentivized video ads can be displayed for the user to choose from.

[0147] For example, see Figure 6B , Figure 6B This is a schematic diagram illustrating an application scenario of the information recommendation method provided in the embodiments of this application, such as... Figure 6BAs shown, users can click on the heatmap of the electronic map to expand a selection interface 605 containing multiple rewarded video ads. Selection interface 605 displays detailed information for multiple rewarded video ads, such as details for rewarded video ads A through F. For example, when a user clicks on a specific area in the heatmap, the server automatically identifies the heat value of that area and returns multiple rewarded video ads associated with that area to the client for display. In this selection interface 605, users can view more information and decide whether to watch a rewarded video ad by swiping the interface or clicking on it. For example, when a user clicks on rewarded video ad B displayed in selection interface 605, the details interface for rewarded video ad B can be displayed, allowing the user to decide whether to watch it.

[0148] In some embodiments, when a user selects a rewarded video ad, the video can play in full-screen mode. After the video finishes playing, the user receives a reward and can choose whether to continue watching the next rewarded video ad. Alternatively, the user can choose to browse ads in other areas of the heatmap or exit the heatmap interface.

[0149] It should be noted that, in addition to incentivized video ads, ads can also be displayed in other ways, such as interstitial ads and native ads.

[0150] The following will continue to combine Figure 7 The information recommendation method provided in the embodiments of this application will be described.

[0151] For example, see Figure 7 , Figure 7 This is a flowchart illustrating the information recommendation method provided in the embodiments of this application, which will be combined with... Figure 7 The steps shown are explained.

[0152] In step 201, the client responds to the open command and enters the running state.

[0153] In some embodiments, the advertising SDK can obtain the user's location information through methods such as Global Positioning System (GPS) and WiFi fingerprinting. For example, it can obtain the user's location information through methods such as obtaining latitude and longitude via API, obtaining location interface via map SDK, and WiFi fingerprinting.

[0154] In step 202, the client requests advertising data from the server.

[0155] In step 203, the server returns advertising data to the client.

[0156] In step 204, the client displays a heat map to the user.

[0157] In some embodiments, the display of a heatmap requires calculating the heat value of each point using an algorithm, such as one based on data like click-through rate, exposure rate, or conversion rate. This data can be statistically analyzed and calculated by a backend server and then returned to the client for display.

[0158] It should be noted that, in addition to calculating the heat value based on data such as ad click-through rate, impression rate, and conversion rate, other data can also be used to calculate the heat value, such as user location information, search history, and social media data.

[0159] For example, taking the Android platform, a heatmap can be displayed using a custom View. First, the base map needs to be drawn in the View, and the obtained geographical location information needs to be converted into screen coordinates. Then, based on the heat value of each point, different colors or transparency are used to draw the heatmap. Finally, the custom View is added to the layout to display the heatmap on the interface.

[0160] In addition to displaying heatmaps, users can also be offered interactive ad selection features. For example, markers can be added to the heatmap, and ad data can be set for each marker. When a user clicks on a marker, an information window can be displayed showing detailed ad information and providing the user with the option to select that rewarded video ad.

[0161] For example, on the heatmap display interface, when a user clicks on a specific marker, an interactive feature to select rewarded video ads can be added. For instance, a list component (such as RecyclerView) can be used to display multiple rewarded video ads, and a click event can be added to each ad. When a user clicks on a specific rewarded video ad, the user can be redirected to the corresponding ad page based on the ad's information.

[0162] In step 205, the client receives a region selection command triggered by the user.

[0163] In step 206, the client requests the advertising data associated with the selected region from the server.

[0164] In step 207, the server returns the advertising data associated with the selected region to the client.

[0165] In step 208, the client displays a list of advertisements to the user.

[0166] In step 209, the client receives an ad selection instruction triggered by the user.

[0167] In some embodiments, when a user clicks on a rewarded video ad on the heatmap, the client displays detailed information about the ad, such as the ad name, advertiser, and reward amount. The user can choose to watch the ad and receive the reward, or cancel. If the user chooses to watch the ad, the client displays the corresponding video and awards the reward upon completion. If the user cancels the ad, the client returns to the heatmap interface, allowing the user to select other rewarded video ads.

[0168] It should be noted that users can also select advertisements in other ways, such as through text search, voice search, or image search. This application embodiment does not specifically limit this method.

[0169] In step 210, the client reports the ad selection and viewing status to the server.

[0170] In some embodiments, when a user selects a rewarded video ad, data such as the selected ad location, time, and number of selections can be collected. When a user watches a rewarded video ad, data such as viewing duration and whether the video was skipped can be collected. When a user clicks on a rewarded video ad, data such as ad location, ad type, and click time can be collected.

[0171] For example, tracking code can be inserted into the client-side to identify specific behavioral events. When a user triggers a specific behavioral event, the client packages the corresponding data into an event object and sends the event object to the backend server. The event object can contain metadata (such as event name, event stamp, user identifier, etc.) and custom data (such as ad identifier, playback duration, etc.). The event object can be serialized using a format such as JSON and then sent to the backend server via the HTTP protocol.

[0172] The following section continues to explain the steps involved in the backend server.

[0173] In some embodiments, the steps that the backend server needs to perform mainly include: data processing, heatmap data generation, and advertisement recommendation. The following is a detailed explanation of the above three steps.

[0174] 1. Data Processing

[0175] In some embodiments, the backend server needs to collect raw data from the client, such as user location information, ad impressions, clicks, and views. This data is stored in a backend database. Based on this, the backend server can clean, filter, and process the data to generate heatmap data and improve the accuracy of ad recommendations.

[0176] 2. Heatmap data generation

[0177] In some embodiments, after receiving user location information, ad impressions, clicks, and views from the client, the backend server can first aggregate the data based on the user location information to form a set of ad clicks, impressions, and other data within a region centered on the coordinates. Next, the backend server can normalize the data within each region to avoid errors caused by excessively large or small data volumes. For example, a Gaussian kernel density estimation algorithm can be used to process the data to obtain the density distribution of ad clicks, impressions, and other data within each region.

[0178] For the normalized data, the backend server can further use an interpolation algorithm to transform it into a smooth two-dimensional surface, and generate corresponding heatmap data (e.g., heat values) based on the numerical values ​​of this surface. The generated heatmap data can be stored in the backend database for subsequent querying and use. Simultaneously, to improve data query efficiency, caching techniques can be used to cache some of the heatmap data in memory.

[0179] 3. Advertising Recommendations

[0180] The backend server can make recommendations based on user behavior data and advertising data to improve ad click-through rates and conversion rates. The recommendation algorithm can employ collaborative filtering, content filtering, or hybrid filtering, and the appropriate algorithm can be selected based on different application scenarios.

[0181] In summary, the information recommendation method provided in this application has the following beneficial effects:

[0182] 1. Improve ad click-through rate: By displaying heatmaps, users can more intuitively see the click-through rate of ads in different positions, thus selecting the most attractive ads and improving the ad click-through rate.

[0183] 2. Improve ad conversion rate: Users can select ads that interest them, which can improve ad conversion rate and thus increase advertisers' revenue.

[0184] 3. Improve user experience: The technical solution provided in this application embodiment allows users to more intuitively select advertisements that interest them, thereby improving the user experience.

[0185] The following description continues to illustrate the exemplary structure of the information recommendation device 555 provided in the embodiments of this application as a software module. In some embodiments, such as... Figure 2 As shown, the software module stored in the information recommendation device 555 in the memory 550 may include: a display module 5551.

[0186] Display module 5551 is used to display a heatmap, wherein the heatmap includes multiple locations, and the display parameters of each location are related to the recommendation index data of the recommendation information associated with the location, and the recommendation information has an incentive attribute; display module 5551 is also used to display the recommendation information details of the recommendation information in response to a trigger operation for the recommendation information associated with the first location among the multiple locations.

[0187] In some embodiments, the display module 5551 is further configured to, in response to a trigger operation for a first location among a plurality of locations, display recommendation information associated with the first location; and in response to a trigger operation for the recommendation information associated with the first location, display recommendation information details of the recommendation information.

[0188] In some embodiments, the display module 5551 is further configured to perform the following processing for at least one target location among a plurality of locations: for each target location, display recommendation information associated with the target location.

[0189] In some embodiments, the information recommendation device 555 further includes an acquisition module 5552 and a determination module 5553, wherein the acquisition module 5552 is used to acquire multiple thermal values ​​corresponding to multiple locations one-to-one; and the determination module 5553 is used to determine the location corresponding to the thermal value that is greater than the thermal value threshold among the multiple thermal values ​​as the target location.

[0190] In some embodiments, the acquisition module 5552 is further configured to perform the following processing for each of the multiple locations: acquire feature data of location-associated recommendation information, wherein the feature data includes at least one of click-through rate, exposure rate, and conversion rate; and determine the heat value of the location based on the feature data of location-associated recommendation information.

[0191] In some embodiments, the determining module 5553 is further configured to normalize the feature data of the location-associated recommendation information to obtain normalized feature data; interpolate the normalized feature data to obtain a two-dimensional surface, wherein the surface is used to characterize the density distribution of the feature data; and determine the value corresponding to the density distribution as the thermal value of the location, wherein the value is used to characterize the density of the feature data distribution.

[0192] In some embodiments, the determining module 5553 is further configured to determine, for each of the multiple locations, the similarity between the location-associated recommendation information and the object data of the target object; and to determine the location corresponding to the similarity greater than the similarity threshold among the multiple similarities as the target location.

[0193] In some embodiments, the determining module 5553 is further configured to determine the location that the target object has visited among the multiple locations as the target location; or, to determine the location among the multiple locations whose distance from the target object's current location is less than a distance threshold as the target location.

[0194] In some embodiments, the acquisition module 5552 is further configured to acquire multiple heat values ​​corresponding to multiple locations one-to-one; the determination module 5553 is further configured to, for each of the multiple locations, determine the recommendation index data of the recommendation information associated with the location and the display parameters of the location based on the heat value of the location.

[0195] In some embodiments, the acquisition module 5552 is further configured to acquire the mapping relationship between pre-constructed heat values, recommended index data, and display parameters; the information recommendation device 555 further includes a query module 5554 configured to query recommended index data corresponding to the heat values ​​of a location from the mapping relationship; the determination module 5553 is further configured to determine the queried recommended index data as recommended index data for location-associated recommendation information; the query module 5554 is further configured to query the display parameters corresponding to the heat values ​​of a location from the mapping relationship; the determination module 5553 is further configured to determine the queried display parameters as display parameters for the location.

[0196] In some embodiments, when there are multiple recommendations, the recommendations are displayed in a specific sorting order, which includes: the click-through rate of the recommendations in descending order; the exposure rate of the recommendations in descending order; and the conversion rate of the recommendations in descending order.

[0197] In some embodiments, the recommended information is a video; the display module 5551 is further configured to, in response to a video selection operation, display a details interface corresponding to the selected video, wherein the details interface includes a playback control; and to, in response to a trigger operation on the playback control, play the selected video; the information recommendation device 555 further includes a sending module 5555, configured to send a reward distribution request to the server, wherein the reward distribution request is used to request the server to distribute a reward associated with the selected video to the target object.

[0198] In some embodiments, the sending module 5555 is further configured to send a reward distribution request to the server in response to the fulfillment of reward distribution conditions, wherein the reward distribution conditions include one of the following: the playback progress of the selected video reaches a progress threshold, the playback duration of the selected video reaches a duration threshold, or the number of interactions with the selected video reaches a number threshold.

[0199] In some embodiments, the display module 5551 is further configured to display a prompt message indicating whether to continue playing the next video when the reward distribution conditions are met, wherein the prompt message includes an agreement control and a rejection control; and to continue playing the next video in response to a triggering operation on the agreement control; the information recommendation device 555 further includes a jump module 5556, configured to jump back to the heatmap in response to a triggering operation on the rejection control.

[0200] In some embodiments, the display module 5551 is further configured to display recommendation information associated with a second location among multiple locations, wherein the similarity between the recommendation information associated with the second location and the recommendation information associated with the first location is greater than a similarity threshold.

[0201] In some embodiments, the acquisition module 5552 is further configured to acquire an electronic map, wherein the electronic map includes multiple locations; and to acquire multiple heat values ​​corresponding to the multiple locations; the determination module 5553 is further configured to determine multiple display parameters corresponding to the multiple locations based on the multiple heat values; the information recommendation device 555 further includes a rendering module 5557, configured to render the electronic map based on the multiple display parameters corresponding to the multiple locations to obtain a heat map of the electronic map.

[0202] In some embodiments, the acquisition module 5552 is further configured to acquire a location list, wherein the location list includes multiple locations; and to acquire multiple heat values ​​corresponding to the multiple locations; the determination module 5553 is further configured to determine multiple display parameters corresponding to the multiple locations based on the multiple heat values; and the rendering module 5557 is further configured to render the location list based on the multiple display parameters corresponding to the multiple locations to obtain a heat map of the location list.

[0203] It should be noted that the description of the apparatus in this application embodiment is similar to the description of the method embodiment above, and has similar beneficial effects as the method embodiment; therefore, it will not be repeated. For technical details not covered in the information recommendation apparatus provided in this application embodiment, please refer to... Figure 3 , Figure 4A ,or Figure 4B The meaning is understood in accordance with the description of any of the accompanying drawings.

[0204] This application provides a computer program product comprising a computer program or computer-executable instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer-executable instructions from the computer-readable storage medium and executes the computer-executable instructions, causing the computer device to perform the information recommendation method described in this application.

[0205] This application provides a computer-readable storage medium storing computer-executable instructions. When these computer-executable instructions are executed by a processor, they cause the processor to execute the information recommendation method provided in this application, for example... Figure 3 , Figure 4A ,or Figure 4B The information recommendation method is shown.

[0206] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or it may be a variety of devices including one or any combination of the above-mentioned memories.

[0207] In some embodiments, executable instructions may take the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a standalone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0208] As an example, executable instructions can be deployed to execute on a single electronic device, or on multiple electronic devices located in one location, or on multiple electronic devices distributed across multiple locations and interconnected via a communication network.

[0209] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, and improvements made within the spirit and scope of this application are included within the scope of protection of this application.

Claims

1. An information recommendation method, characterized in that, The method includes: For each of the multiple locations, perform the following processing: Obtain feature data of the location-related recommendation information, wherein the feature data includes at least one of click-through rate, exposure rate, and conversion rate; Based on the feature data of the location-related recommendation information, the heat value of the location is determined; Obtain the mapping relationship between pre-built thermal values ​​and recommended index data, as well as display parameters; Query the recommended index data corresponding to the heat value of the location from the mapping relationship, and determine the retrieved recommended index data as the recommended index data of the recommended information associated with the location; Query the display parameters corresponding to the thermal value of the location from the mapping relationship, and determine the obtained display parameters as the display parameters of the location; Display a heatmap, wherein the heatmap includes the plurality of locations, and the display parameters of each location are related to the recommendation index data of the recommendation information associated with the location, and the recommendation information has incentive attributes; In response to a trigger operation that associates the recommendation information with the first location among the plurality of locations, the recommendation information details are displayed.

2. The method according to claim 1, characterized in that, The trigger operation in response to the recommendation information associated with the first location among the plurality of locations, displays the recommendation information details, including: In response to a trigger operation targeting a first location among the plurality of locations, recommended information associated with the first location is displayed; In response to a trigger operation for the recommendation information associated with the first location, the recommendation information details are displayed.

3. The method according to claim 1, characterized in that, The method further includes: For at least one target location among the plurality of locations, perform the following processing: For each target location, recommended information associated with that target location is displayed.

4. The method according to claim 3, characterized in that, The method further includes: Obtain multiple thermal values ​​corresponding to the multiple locations; The location corresponding to the thermal value that is greater than the thermal value threshold among the plurality of thermal values ​​is determined as the target location.

5. The method according to claim 1, characterized in that, The feature data based on the location-associated recommendation information, used to determine the heat value of the location, includes: The feature data of the location-related recommendation information is normalized to obtain the normalized feature data. The normalized feature data is interpolated to obtain a two-dimensional surface, wherein the surface is used to characterize the density distribution of the feature data. The numerical value corresponding to the density distribution is determined as the thermal value of the location, wherein the numerical value is used to characterize the density of the feature data distribution.

6. The method according to claim 3, characterized in that, The method further includes: For each of the plurality of locations, determine the recommendation information associated with that location and the similarity between that location and the object data of the target object; The location corresponding to the similarity scores that are greater than a similarity threshold among the multiple similarity scores is determined as the target location.

7. The method according to claim 3, characterized in that, The method further includes: The location that the target object has visited among the multiple locations is determined as the target location; or... The location among the plurality of locations whose distance from the current location of the target object is less than a distance threshold is determined as the target location.

8. The method according to claim 1, characterized in that, When there are multiple pieces of recommended information, these pieces of recommended information are displayed according to a specific sorting method, wherein the sorting method includes: The order of click-through rates of the multiple recommended items from highest to lowest; The order of exposure rate of the multiple recommended items from highest to lowest; The conversion rates of the multiple recommended items are listed in descending order.

9. The method according to claim 1, characterized in that, The recommended information is in the form of videos; The method further includes: In response to a video selection operation, a details interface corresponding to the selected video is displayed, wherein the details interface includes playback controls; In response to a trigger operation on the playback control, the selected video is played; A reward distribution request is sent to the server, wherein the reward distribution request is used to request the server to distribute a reward associated with the selected video to the target object.

10. The method according to claim 9, characterized in that, Sending the reward distribution request to the server includes: In response to the fulfillment of reward distribution conditions, a reward distribution request is sent to the server, wherein the reward distribution conditions include one of the following: the playback progress of the selected video reaches a progress threshold, the playback duration of the selected video reaches a duration threshold, or the number of interactions with the selected video reaches a number threshold.

11. The method according to claim 10, characterized in that, In response to the fulfillment of reward disbursement conditions, the method further includes: A prompt message is displayed asking whether to continue playing the next video, including an agreement control and a rejection control. In response to the triggering action of the consent control, continue playing the next video; In response to a trigger operation on the rejection control, the system jumps back to the heatmap.

12. The method according to claim 1, characterized in that, The method further includes: The recommendation information associated with the second location among the plurality of locations is displayed, wherein the similarity between the recommendation information associated with the second location and the recommendation information associated with the first location is greater than a similarity threshold.

13. The method according to claim 1, characterized in that, The displayed heatmap includes: Obtain an electronic map, wherein the electronic map includes multiple locations; Obtain multiple thermal values ​​corresponding to the multiple locations; Based on the multiple thermal values, multiple display parameters corresponding to the multiple locations are determined; In the electronic map, a heat map of the electronic map is obtained by rendering based on multiple display parameters that correspond one-to-one with the multiple locations.

14. The method according to claim 1, characterized in that, The displayed heatmap includes: Obtain a list of locations, wherein the list of locations includes multiple locations; Obtain multiple thermal values ​​corresponding to the multiple locations; Based on the multiple thermal values, multiple display parameters corresponding to the multiple locations are determined; In the location list, a heatmap of the location list is obtained by rendering based on multiple display parameters that correspond one-to-one with the multiple locations.

15. An information recommendation device, characterized in that, The device includes: The acquisition module is configured to perform the following processing for each of multiple locations: acquire feature data of recommendation information associated with the location, the feature data including at least one of click-through rate, exposure rate, and conversion rate; and determine the heat value of the location based on the feature data of the recommendation information associated with the location. The acquisition module is also used to acquire the mapping relationship between pre-constructed thermal values ​​and recommended index data, as well as display parameters; The query module is used to query recommended index data corresponding to the heat value of the location from the mapping relationship; The determining module is used to determine the retrieved recommendation index data as the recommendation index data of the location-related recommendation information; The query module is also used to query the display parameters corresponding to the thermal value of the location from the mapping relationship; The determining module is further configured to determine the display parameters obtained from the query as the display parameters for the location; A display module is used to display a heat map, wherein the heat map includes the plurality of locations, and the display parameters of each location are related to the recommendation index data of the recommendation information associated with the location, and the recommendation information has incentive attributes; The display module is further configured to display the recommendation information details of the recommendation information in response to a trigger operation for the recommendation information associated with the first location among the plurality of locations.

16. The apparatus according to claim 15, characterized in that, The display module is further configured to, in response to a trigger operation for a first location among the plurality of locations, display recommendation information associated with the first location; and in response to a trigger operation for the recommendation information associated with the first location, display recommendation information details of the recommendation information.

17. The apparatus according to claim 15, characterized in that, The display module is further configured to perform the following processing for at least one target location among the plurality of locations: for each target location, display recommendation information associated with the target location.

18. The apparatus according to claim 17, characterized in that, The acquisition module is further configured to acquire multiple thermal values ​​corresponding to the multiple locations; the determination module is further configured to determine the location corresponding to the thermal value that is greater than the thermal value threshold among the multiple thermal values ​​as the target location.

19. An electronic device, characterized in that, include: Memory, used to store executable instructions; A processor, when executing executable instructions stored in the memory, implements the information recommendation method according to any one of claims 1 to 14.

20. A computer-readable storage medium storing computer-executable instructions, characterized in that, When the computer-executable instructions are executed by the processor, they implement the information recommendation method according to any one of claims 1 to 14.

21. A computer program product, comprising a computer program or computer-executable instructions, characterized in that, When the computer program or computer-executable instructions are executed by a processor, the information recommendation method according to any one of claims 1 to 14 is implemented.

Images