JP7214778B2 - Information recommendation method and device - Google Patents

Description

TECHNICAL FIELD Embodiments of the present application relate to the field of vehicle internet technology, and more particularly to an information recommendation method and apparatus.

Currently, with the rapid development of automobile technology, in addition to serving as a means of transportation for humans, automobiles can also provide users with various functions such as entertainment functions and information pushed from the service side. can.

In the information recommendation process in the current in-vehicle scenario, various applications (APP) are installed in the center console of the vehicle, the information to be recommended is preset, and when the driver or the passenger in the passenger seat clicks on the APP, These pieces of recommended target information are displayed to the user in a carousel format. After displaying for a predetermined period of time, eg 10 seconds, the APP jumps to the home page. In this method, the information displayed in the carousel is also called resident operational information, and the recommended information display method is also called the recommended information display at the desktop resident location.

In the process of displaying the recommended information at the desktop permanent location, it is necessary to set the recommended information manually in advance. However, manual setting of recommended information is labor-intensive, and there is a possibility that the user's attention to manually set recommended information is not high, resulting in inaccurate information recommendation.

Embodiments of the present application dynamically create a geofence in conjunction with the past user's search history within the validity period, and provide information to the current user based on the geofence when the current user enters the geofence. Provided is an information recommendation method and apparatus for achieving the purpose of improving the accuracy of pushing information through recommendation.

In a first aspect, the information recommendation method provided in the embodiments of the present application includes:
receiving location information reported from a first electronic device and used to indicate the location where the first electronic device is located;
determining recommended target information based on a target geofence to which the location point corresponding to the location information belongs, wherein the target geofence is included in a geofence set, and the geofences in the geofence set are: generated based on search history records of a plurality of second electronic devices in a reference area, the search history records being used to search for location points within the reference area;
and transmitting the recommended target information to the first electronic device.

In a second aspect, the information recommendation device provided in the embodiment of the present application includes:
a receiving unit for receiving location information reported from a first electronic device and used to indicate the location where the first electronic device is located;
A processing unit for determining recommended target information based on a target geofence to which a location point corresponding to the location information belongs, wherein the target geofence is included in a geofence set, and a geofence in the geofence set. an offense is generated based on search history records of a plurality of second electronic devices in a reference area, the search history records being used to search for location points within the reference area;
a transmitting unit for transmitting the recommended target information to the first electronic device.

In a third aspect, an electronic device provided in an embodiment of the present application comprises:
at least one processor;
a memory communicatively coupled to the at least one processor, wherein
The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to cause the at least one processor to perform the first aspect or the first aspect. Try to do whatever is feasible.

In a fourth aspect, a computer program product including instructions provided in the examples of the present application, when executed on an electronic device, causes the electronic device to perform the above first aspect or various possibilities of the first aspect. to execute the method in any implementation.

In a fifth aspect, a non-transitory computer-readable storage medium storing computer instructions provided in the embodiments of the present application, wherein the computer instructions are transferred to the electronic device according to the first aspect or the first aspect above. is used to perform methods in various possible implementations of aspects of .

In a sixth aspect, an information recommendation method provided in an embodiment of the present application is a step of obtaining a plurality of search history records within a validity period at a current time, wherein each of the plurality of search history records is and determining at least one geofence based on said plurality of search history records, wherein location points included in said geofence are located in said locating within the reference region.

In a seventh aspect, a computer program provided in an embodiment of the present application, said computer program being stored in a computer readable storage medium, wherein at least one processor of an electronic device stores said A computer program is readable, and the at least one processor executes the computer program to cause the electronic device to perform the method in the above first aspect or the various possible implementations of the first aspect. Let

One embodiment in the above application dynamically creates a geofence in combination with the past user's search history within the validity period, and when the current user enters the geofence, based on the geofence, the current user recommending information to has the advantage or beneficial effect of achieving the purpose of improving the accuracy of pushing information.

Other advantages of the above optional methods are described below in conjunction with specific examples.

The drawings are used for better understanding of the present technical solution and do not constitute the limitation of the present application.
1 is a schematic diagram of network architecture of an information recommendation method provided in an embodiment of the present application; FIG. Fig. 4 is a schematic diagram of another network architecture of the information recommendation method provided in the embodiments of the present application; 4 is a flow chart of an information recommendation method provided in an embodiment of the present application; FIG. 4 is a schematic diagram of clusters in the information recommendation method provided in the embodiments of the present application; FIG. 4 is a schematic diagram of creating a geofence in the information recommendation method provided in the embodiments of the present application; FIG. 4 is a schematic diagram of geofence in the information recommendation method provided in the embodiments of the present application; 4 is a flow chart of dynamically creating a geofence in the information recommendation method provided in an embodiment of the present application; 4 is a flow chart of an information recommendation method provided in an embodiment of the present application; 1 is a schematic diagram of the configuration of an information recommendation device provided in an embodiment of the present disclosure; FIG. 1 is a block diagram of an electronic device for implementing an information recommendation method according to an embodiment of the present disclosure; FIG.

Illustrative embodiments of the present application are described below in conjunction with the drawings, in which various details of the embodiments of the present application are included for ease of understanding and are merely exemplary. should be regarded as Accordingly, those skilled in the art should appreciate that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Also, in the following description, descriptions of well-known functions and configurations are omitted for clarity and brevity of description.

Generally, in in-vehicle scenarios, the user's attention is often focused on complex traffic situations. Therefore, if the service side frequently pushes information such as programmatic advertisements to the center console of the car, it not only mechanizes the recommendation process, but also has a serious impact on the normal driving of the user, and in serious cases, it may affect safety. It can lead to accidents. Therefore, the information recommendation method in the conventional in-vehicle scenario often adopts the method of manual intervention. Then, a plurality of pieces of information, for example, five pieces of information are displayed in a carousel manner, and each piece of information is displayed for one second. Also, when displaying information pushed from the server in a format embedded in the H5 mobile page, the user clicks a button on the center console screen to jump to the H5 page. However, both the information displayed in the carousel and the content displayed in the H5 page are manually preset. To some extent, this manual intervention scheme achieves the goal of not interfering with the user's driving. However, the manually set information includes a lot of information without clear directionality, so the user's attention to this information without clear directionality is low, and information recommendation is inaccurate.

In view of this, the embodiments of the present application dynamically create geofences in combination with search history records, and use the dynamic geofences to recommend information to users, thereby improving the accuracy of information pushes. To provide an information recommendation method that achieves the purpose.

FIG. 1A is a schematic diagram of the network architecture of the information recommendation method provided in the embodiments of the present application. Referring to FIG. 1A, this network architecture includes a first electronic device 1, a second electronic device 2 and a server 3, wherein the first electronic device 1 and the server 3 establish a network connection, 2, the electronic device 2 and the server 3 establish a network connection. A first electronic device 1 is an electronic device located in a reference area at the current time, such as an in-vehicle terminal device, a mobile phone, a tablet computer, or a notebook computer. A region, one reference region contains multiple location points, such as hotels, scenic spots, gourmet restaurants, and so on. The second electronic device 2 is an electronic device that has been located within the reference area within the valid period, for example, an electronic device that has been located within the reference area during the valid period before the current time, for example, the reference area within the past 5 hours. It is an electronic device that is located in an area and has performed the action of searching for a location point. The server 3 uses the search records of the second electronic device 2 to create multiple geofences within this reference area to form a geofence set. When the first electronic device 1 enters a certain geofence (hereinafter referred to as a target geofence), the server 3 recommends information about popular location points within the target geofence to this first electronic device 1. .

FIG. 1B is a schematic diagram of another network architecture of the information recommendation method provided in the embodiments of the present application. Whereas the functions of determining geographic locations of targets and determining recommended information are integrated into the server 3 of FIG. 1A, the network architecture shown in FIG. That is, Server 4 and Server 5 are included, Server 4 and Server 5 establish network connections, Server 4 is used to process location information, generate geofence sets, etc., and Server 5: Used to provide recommendation target information corresponding to each geofence. Each second electronic device 2 establishes a network connection with the server 4, each first electronic device 1 also establishes a network connection with the server 4, and each first electronic device 1 also establishes a network connection with the server 5. Establish. The server 4 uses the search records of the second electronic device 2 to create multiple geofences within the reference area to form a geofence set. When the first electronic device 1 enters a certain geofence (hereinafter referred to as a target geofence), the server 3 sends the identifiers of popular location points within the target geofence to the server 5, and the server 5: The recommendation target information is determined and transmitted to the first electronic device 1 .

1A and 1B above, if the first electronic device 1 is a mobile terminal such as a mobile phone, the first electronic device 1 has an APP, and the APP is installed in the first electronic device 1. It may be a native APP installed in the car, and this APP can establish a network connection with the in-vehicle system in the center console of the car. The first electronic device 1 can report location information to the server via this APP, and receive recommended target information transmitted from the server.

In FIGS. 1A and 1B above, when the first electronic device 1 is an in-vehicle terminal, a plug-in or a software development kit (Software Development Kit, SDK) on the operating system (OS) of the in-vehicle terminal, etc. may report location information to the server, receive recommended target information transmitted from the server, and the like.

Hereinafter, the information recommendation method according to the embodiment of the present application will be described in detail, taking the architecture shown in FIG. 1A as an example. See FIG. 2 for an example.

FIG. 2 is a flow chart of an information recommendation method provided in an embodiment of the present application, which includes 101, 102 and 103;

At 101, location information reported from a first electronic device and used to indicate a location at which said first electronic device is located is received.

Exemplarily, the location information may be latitude and longitude coordinates reported by the first electronic device, or may be a location point where the first electronic device is located, such as a hotel, an intersection, etc. Examples are not limiting.

At 102, information to be recommended is determined based on a target geofence to which the location point corresponding to the location information belongs.

However, the target geofence is included in a geofence set, the geofences in the geofence set are generated based on search history records of a plurality of second electronic devices in a reference region, and the search history records are , are used to search for location points within the reference region.

Exemplarily, an APP on the first electronic device relates to some Location Based Services (LBS), which is also called a location server and so on. Geo-fencing is a new application of LBS that turns virtual fences into virtual geographic boundaries. The server pushes information to the first electronic device when the first electronic device enters, exits, or otherwise operates within a geofence. A geofence set corresponding to the reference area is pre-stored on the server. However, the reference area may be a city, a prefectural castle, a district within a city, or the like. The server pre-creates multiple geofences within this reference area based on the relevant historical data of the reference area, and any two geofences are independent or intersecting. Each geofence includes multiple location points, which may be hotels, schools, scenic spots, gourmet restaurants, and so on.

The server, upon receiving the location information reported from the first electronic device, matches the location indicated by the location information with the region corresponding to each geofence in the geofence set, and matches the geofence with the location information to the geofence with the location information. If so, let this geofence be the target geofence. After that, the recommended target information is determined based on the target geofence. This recommendation information may be, for example, information about popular location points within the target geofence, such as hotel features.

At 103, the recommended target information is transmitted to the first electronic device.

Exemplarily, the server transmits the recommended target information determined based on the target geofence to the first electronic device for the first electronic device to display to the user. In the display process, if the first electronic device displays the recommended target information on the full screen and displays it for a predetermined time period, for example, 10 seconds, and the user does not respond, that is, the first electronic device displays the recommended target information on the user's touch screen. If no touch operation, interval operation, or the like is received, the screen is switched to the original screen without displaying the recommended information on the full screen. For example, the first electronic device is an in-vehicle terminal, and the in-vehicle terminal is on the music playback screen before receiving the recommendation target information. When the in-vehicle terminal receives the recommendation target information assumed to be the characteristics of the hotel, it displays the recommendation target information on a full screen. After 10 seconds, if the user, such as the driver or the passenger in the front passenger seat, does not input an operation command by clicking the screen of the in-vehicle terminal, the in-vehicle terminal returns to the music playback screen.

According to the information recommendation method provided in the embodiments of the present application, the server pre-establishes a set of geofences corresponding to the reference area using historical data of a large number of users examining location points within the reference area. . In the information recommendation process, after receiving the location information reported from the first electronic device, the server determines the recommended target information based on the target geofence to which the location point corresponding to the location information belongs, and provides the first information. Send to electronic devices. In this process, the server creates a geofence by combining the search histories of many users within the validity period, uses the geofence to recommend information to the user, and the position points in the geofence are social Since it reflects the position points that are popular with the general public, the quality and timeliness of the recommendation information can be greatly improved, and the purpose of improving the accuracy of information push can be achieved.

Below is a detailed description of how the server dynamically establishes the geofence set of reference regions in the above example.

First, collect valid search history records.

In one possible implementation, based on a plurality of search history records within a validity period when each second electronic device of the plurality of second electronic devices is located in the reference area at a first time. obtaining a set of location points, wherein the validity period is a period between the first time and a second time before the first time, and the length of time of the validity period is preset less than the specified threshold.

Exemplarily, after the server recognizes a reference area such as a city or city where the first electronic device is currently located at the current time, the server acquires the position of the reference area. Based on this reference area, the server obtains a plurality of search records of other second electronic devices using the map APP to search for position points within the reference area. Any first time that a geofence needs to be created, for a certain reference area, the server pre-filters search records not related to this reference area from the search history records, i.e. search history records , filter the search records used to search for other location points outside the reference region, leaving only the search records used to search for location points within this reference region. Then, for each of the remaining plurality of search records, the server checks that the search record is within a set validity period, e.g., a first time and, e.g., before and from the first time It is determined whether it is within the period between the second time five hours ago, that is, the search history record is the search record five hours before the first time. If the first search record is a record corresponding to search behavior five hours before the current time, then this search record is treated as a valid search record, and this search record is related to search behavior five hours before the current time. If it is not a corresponding search record, then this search record cannot be deleted, ie this search record cannot be made a valid search record.

If this technical proposal is adopted, the purpose of ensuring the timeliness of the recommendation target information can be achieved by setting the valid time.

Next, determine popular search location points within the reference region.

In one possible implementation, the server clusters each location point in the above location point set to obtain at least one cluster, and the distance between any two location points in the same cluster is a predetermined Below threshold.

Illustratively, for one reference region, after collecting a set of valid search records, the server clusters location points that are close to each other based on a density-based clustering algorithm. That is, from the point of view of the clustering algorithm, if multiple users start searching with the second electronic device within the validity period, and the distances of the location points searched by these users are relatively close, these users will , are considered to be the same kind of users with the same interests, and furthermore, the popular location points in this one cluster are taken as the popular location points of this cluster, and these popular location points are used in subsequent information recommendations. information is recommended to the first electronic device. If this technical proposal is adopted, a highly accurate recommendation can be realized by determining a popular location point.

Then create a geofence.

Illustratively, upon obtaining a plurality of clusters within a reference region, the geographic coordinates of the location points in each of the at least one cluster can be determined, and the geofence of the corresponding cluster can be determined. , to obtain the geofence set. For an example, please refer to FIG. 3, which is a schematic diagram of clusters in the information recommendation method provided in the embodiments of the present application.

Referring to FIG. 3, the rectangular frame indicates the reference area, and the server clusters the search records within the effective period to obtain two clusters, cluster A and cluster B, respectively. contains the location points of Hotel 1, Hotel 2, Hotel 3, Scenic Spot 4, Scenic Spot 5 and Hotel 6; Contains location points. For cluster A, the server sets the average value of the abscissa of each position point in cluster A as the abscissa of the central point, and the average value of the ordinates of each position point in cluster A as the ordinate of the central point, Further, a circle is created around this center point that can cover at least each position point in the cluster. The server then makes this circle the geofence for cluster A. Similarly, the geofence for cluster B is obtained, as indicated by the dashed line in the figure. Also, the geofence radius may be a preset radius, such as 500 meters.

In the search history records stored or obtained by the server, the location point indicated by each search record further has a type tag, which was included in the search request when the second electronic device initiated the search. or determined by the server based on the location points retrieved by the second electronic device. A user may pay more attention to location points of a particular tag type within one validity period. a server determining a geofence of a corresponding cluster based on geographic coordinates of a location point in each of said at least one clusters to accurately obtain what a user is interested in; Before obtaining the set, for each of said at least one cluster, the server further determines the number of times location points with the same type tag in said cluster were searched, and for each of a plurality of type tags: A search frequency corresponding to the type tag is obtained, a type tag with the highest search frequency is set as a popular type tag of the cluster, and a popular type tag of each of the at least one cluster is obtained.

Exemplarily, referring to FIG. 3 above, location points of various tag types are included in one cluster, for example, the type tags of location points in cluster B are gourmet, shopping mall and hotel. When the first electronic device enters the geofence corresponding to cluster B, the server recommends restaurant, shopping mall or hotel information to the first electronic device based on the location point within cluster B, and these information are Since it is complicated, there is a possibility that popular information cannot be displayed. For this reason, the server selects the type tag corresponding to the location point with the highest number of occurrences according to the voting rule, i.e., the server statistically counts the number of times the location point of each tag type is searched, for example, according to the statistics: For example, in cluster B, hotel 7 is searched 240 times, gourmet 8 45 times, gourmet 9 78 times, gourmet 10 120 times, shopping mall 11 15 times, and hotel 12 147 times in cluster B, Then, the number of searches for the hotel type tag = 240 + 147 = 387 times, the number of searches for the restaurant type tag = 45 + 78 + 120 = 243 times, the number of searches for the shopping mall type tag is 15, and the number of searches for the hotel type tag. is found to be the most common. These data show that during the lifetime, users pay more attention to information about hotels in cluster B, i.e., hotels are a popular social search during the lifetime. .

After obtaining the popular tag types, the server, in the process of determining a geofence set, for each cluster of said at least one cluster, calculates the abscissa of each location point having a popular type tag in each said cluster. obtaining the center of each cluster by determining the mean and the mean of the ordinate, and determining the at least one cluster based on the center of each of the at least one cluster and a preset fence shape; obtain the geofence set by determining the geofence corresponding to each cluster of . However, the preset fence shape is, for example, circular, rectangular, etc., and is not limited in the embodiments of the present application. In this process, the average value of the coordinates of the location points is used to achieve the purpose of creating a geofence.

Please refer to FIG. 4 for the geofence creation process of cluster B in FIG. 3 above. FIG. 4 is a schematic diagram of geofence creation in the information recommendation method provided in the embodiments of the present application. Referring to FIG. 4, the server first excludes from Cluster B location points with other type tags, such as location points whose type tags are gourmet and shopping mall, and one location point, such as a hotel type location point. Leave only the position points of one type tag. Then, the server sets the average value of the abscissas of the hotels 7 and 12 in the cluster B as the abscissa of the central point, and the average value of the ordinates of the hotels 7 and 12 in the cluster B as the ordinate of the central point. Furthermore, a circle is created with this central point as the center of the circle and a preset radius as the radius. The server then makes this circle the geofence for cluster B.

By adopting this technical proposal, it is possible to determine, from among a plurality of pieces of information, recommended information that is highly popular with the general public, based on popular tags.

In addition, maintain geofences.

In an embodiment of the present application, after the geofences in the geofence set are created, the server periodically determines whether the length of time the geofence set exists exceeds the preset length of time, and determines whether the geofence If the length of time that the set exists exceeds a preset period, update the geofence set, and if the existence period of the geofence set does not exceed the preset period, continue to use this geofence. . That is, after creating a geofence, combine it with the analysis results of the user's search history record most recently in the next validity period to dynamically create a geofence that matches the social hotspots of the current period. It is necessary to retrieve the created geofence in a timely manner according to the preset valid time so as to ensure

Illustratively, each geofence in the geofence set is valid within a period of time, eg, valid within 5 hours. After 5 hours, the server recreates the geofence based on search history records within the last 5 hours. Geofences created by the server at different times may be different. For example, please refer to FIG. 5, which is a schematic diagram of geofence in the information recommendation method provided in the embodiment of the present application. Referring to FIG. 5, within the valid time period of 4 hours from 1:00 to 5:00, the server clusters the search history records related to the reference area before 1:00, and divides into two clusters. and cluster A and cluster B, respectively, cluster A includes the location points of hotel 1, hotel 2, hotel 3, scenic spot 4, scenic spot 5 and hotel 6, cluster B includes hotel 7, gourmet 8 , Gourmet 9, Gourmet 10, Shopping Mall 11 and Hotel 12 location points. The server obtains a geofence set containing two geofences based on cluster A and cluster B. If the first electronic device enters the geofence corresponding to cluster A within the validity period of 1:00-5:00, push information about popular location points in cluster A to the first electronic device; Similarly, if the first electronic device enters the geofence corresponding to cluster B, it will push information about popular location points within cluster B to the first electronic device.

Starting at 5:00, the server uses the second electronic device's search records for location points within the reference area prior to 5:00 to create a Geofence within the next validity period. In the process of creation, the server clusters the search history records for the reference area before 5:00 and obtains three clusters, cluster C, cluster D and cluster E, respectively, cluster A is scenic spot 4, scenic spot 5 and scenic spot 13, cluster B includes location points of hotel 7, gourmet 8, gourmet 9, gourmet 10, cluster E includes location points of gourmet 8, hotel 14 and scenic spot 15 . The server obtains a geofence set including three geofences based on cluster C, cluster D and cluster E. After that, the valid time length of the geofence in this geofence set is set to 5 hours, and information is recommended to the first electronic device based on the geofence in this geofence set for 5 hours from 5:00 to 10:00. do.

Adopting this technique, dynamically creating a geofence ensures that the information recommended by the server to the first electronic device follows the hotspots of public interest. Also, creating geofences dynamically reduces the cost of maintaining a large number of geofence records on the server to some extent.

FIG. 6 is a flow chart of dynamically creating a geofence in the information recommendation method provided in an embodiment of the present application, including steps 201-210 as follows.

At 201, a reference region is determined.

Exemplarily, after the server recognizes the reference area that needs to create a geofence, such as the reference area of county, city, etc. at the current time, the server obtains the location of the reference area.

At 202, the server collects search history records located within the reference area.

Exemplarily, the server collects a plurality of search records in which other second electronic devices searched for location points within the reference area using the map APP before the current time.

At 203, the server traverses each of the plurality of search records and determines valid search records from the plurality of search records.

At 204, the server aggregates the close distance location points based on a density-based clustering algorithm to obtain multiple clusters.

At 205, the server sorts popular type tags within each cluster based on voting rules.

At 206, the server determines whether the number of popular type tag location points in the cluster is greater than or equal to a preset number, and determines whether the number of popular type tag location points in the cluster is equal to or greater than the preset number. If so, execute step 207; if the number of location points of popular type tags in the cluster is less than the preset number, end;

Exemplarily, in order to avoid generating a large amount of recommendation information with low popular tendency due to too few location points in one cluster, the server may, for each cluster among at least one cluster: determining whether the number of location points with the popular type tag in this cluster exceeds a preset threshold, and if the number exceeds the preset number, the information about the location points of this popular type tag is clear; If the number of popular type tag location points in this cluster is less than the preset number, the information about this popular type tag location point is , has no obvious popular trend, so there is no need to create a geofence for this cluster.

At 207, the location points without popular type tags are removed from within the clusters, and the location points with popular type tags are clustered to obtain a new cluster.

At 208, the coordinates of each location point in the new cluster are used to determine the barycentric coordinates of the new cluster.

Illustratively, for each cluster of the at least one cluster, the server determines the average abscissa and ordinate of each location point having a popular type tag in the cluster to create a new cluster. Obtain the center of each cluster, also called the barycentric coordinate of .

At 209, a geofence is created around the barycentric coordinates.

Illustratively, for each cluster, the server obtains a geofence set by completing the process of creating a virtual geofence with a predetermined radius around the barycentric coordinates of this cluster.

At 210, it is determined whether the age of the current geofence set exceeds the specified time, and if the age of the geofence set does not exceed the specified time, end geofence creation; If the time of existence of the offense set exceeds the specified time, return to step 201 .

Exemplarily, assuming that the server creates a geofence set at 5:00 and activates this geofence before 10:00, in the course of the server using the geofence in the geofence set, the current time is 10:00. Detect whether it exceeds, if it does not exceed 10 o'clock, continue to use this geofence, and if it exceeds 10 o'clock, recreate the geofence.

We now describe in detail how the server pushes information in the above example. Exemplarily, with reference to FIG. 7, which is a flow chart of the information recommendation method provided in the embodiment of the present application, the embodiment will be described from the perspective of the interaction between the first electronic device and the server, and the embodiment will be described. Examples include 301-306.

At 301, a first electronic device acquires location information in real time.

Exemplarily, the first electronic device obtains position information by performing real-time positioning using a Global Positioning System (GPS).

At 302, the first electronic device reports location information to a server.

At 303, the server determines a target geofence based on the location information.

304, the server determines the information already recommended to the first electronic device from the recommendation information corresponding to the target geofence based on the identity of the first electronic device;

However, the recommendation history information is information that has been recommended to the first electronic device.

At 305, information already recommended to the first electronic device is filtered from recommended information corresponding to the target geofence to obtain the recommended information.

Illustratively, because the driving range is likely to be large, i.e. the vehicle is continuously driving, creating a geofence pushes information to the user the moment the in-vehicle infotainment system enters the geofence. not only triggering geofence-based information recommendations too often, thereby ensuring that the same information is not pushed to the first electronic device too often while driving. do.

To solve this problem, the first electronic device reports its identity (ID) to the server at the same time it reports its location information, so that the server can identify the information sent to this first electronic device. can be updated in real time. For example, after the server pushes information to the first electronic device at 8:00, it marks this information as recommendation history information, and attaches an expiration time stamp of 10:00 to this recommendation history information. Indicates that this information should not be pushed to the first electronic device.

Referring to FIG. 5, in cluster E and cluster D there is the same location point, gourmet 8 . Regardless of the popular tag type, when the first electronic device enters the geofence corresponding to cluster D, the server pushes information about Hotel 7, Gourmet 8, Gourmet 9, and Gourmet 10 to the first electronic device. and an expiration timestamp for each piece of information. When the first electronic device enters within the geofence corresponding to cluster D to cluster E, the server discovers that the information about Gourmet 8 has an expired timestamp, and the current time is indicated by the expired timestamp. If the time to be served has not yet arrived, the server does not push the information about the gourmet 8 to the first electronic device.

At 306, the server transmits the recommendation target information to the first electronic device.

The information recommendation method provided in the embodiment of the present application is a method of dynamically creating a virtual geofence by mining popular location points of the public in real time by combining search history records. , recommending information on the rich popular location points in the first electronic device, greatly improving the quality and timeliness of the recommended information, and pushing the most timely information to the user without the user's perception; effectively enhances the user experience of in-vehicle infotainment system interaction.

The specific implementation of the information recommendation method according to the embodiments of the present disclosure has been introduced above, and the following embodiments of the apparatus of the present disclosure can be used to implement the embodiments of the method of the present disclosure. For details not disclosed in the apparatus embodiments of the present disclosure, please refer to the method embodiments of the present disclosure.

FIG. 8 is a schematic diagram of the configuration of an information recommendation device provided in an embodiment of the present disclosure. This device may be integrated in the server or implemented by the server. As shown in FIG. 8, in this embodiment, the information recommendation device 100
a receiving unit 11 for receiving location information reported from a first electronic device and used to indicate the location where said first electronic device is located;
A processing unit 12 for determining recommended target information based on a target geofence to which a location point corresponding to the location information belongs, wherein the target geofence is included in a geofence set, and a geofence is generated based on search history records of a plurality of second electronic devices in a reference area, said search history records being used to search for location points within said reference area;
a transmitting unit 13 for transmitting the recommended target information to the first electronic device.

In one possible design, the processing unit 12 is further configured to control each of the plurality of second electronic devices at a first time before the receiving unit 11 receives the reported location information from the first electronic device. obtaining a position point set based on a plurality of search history records within a validity period when the second electronic device of is located in the reference area, wherein the validity period is the first time and the a period between a first time and a second time before the first time, wherein the time length of the valid period is smaller than a preset threshold; and clustering each position point in the position point set. obtaining at least one cluster, wherein a distance between any two location points in the same cluster is less than a preset threshold; and obtaining the geofence set by determining the geofence of the corresponding cluster based on the coordinates.

In one possible design, the location point set further includes a type tag for each location point used to indicate the type of the corresponding location point, and the processing unit 12 processes each of the at least one cluster before obtaining the geofence set by determining geofences of corresponding clusters based on geographic coordinates of location points; further determining the number of times the position point having the tag is searched for, obtaining the number of searches corresponding to each type tag among the plurality of type tags, and determining the type tag with the most number of searches as the popular type tag of the cluster; , obtaining a popular type tag for each of said at least one cluster.

In one possible design, the processing unit 12 obtains the geofence set by determining geofences for corresponding clusters based on geographic coordinates of location points of each of the at least one cluster. wherein, for each cluster of said at least one cluster, the center of each cluster is determined by determining the average abscissa and ordinate of each location point having a popular type tag in each said cluster; and determining a geofence corresponding to each of the at least one cluster based on the center of each cluster and a preset fence shape of the at least one cluster, Used to get the offense set.

In one possible design, the processing unit 12, for each cluster of the at least one cluster, averages the abscissa and the ordinate of each location point having a popular type tag in each of the clusters. and obtaining the center of each cluster, further for each cluster of said at least one cluster, a number of location points having a popular type tag in each said cluster is a preset number of Used to determine exceeding.

In one possible design, the processing unit 12 further determines whether the length of time that the set of geofences exists exceeds a preset length of time; It is used to update the GeoFence Set if it exceeds a preset amount of time.

In one possible design, the processing unit 12 determines information already recommended to the first electronic device from recommendation information corresponding to the target geofence set, and provides recommendations corresponding to the target geofence set. Information that has already been recommended to the first electronic device is filtered from the information and used to obtain the recommended information.

The information recommendation method provided in the embodiments of the present disclosure can be used in the methods performed by the server in the above embodiments, and its implementation principle and technical effects are similar, and the description is omitted here. do.

According to an embodiment of the present application, there is further provided a computer program, said computer program stored on a computer readable storage medium, at least one processor of an electronic device being readable from said computer readable storage medium, comprising at least one One processor causes the electronic device to perform the methods described in the above embodiments by executing a computer program.

According to embodiments disclosed herein, the present application further provides an electronic device and a readable storage medium.

FIG. 9 is a block diagram of electronic equipment for implementing the information recommendation method of the embodiment of the present disclosure. Electronic equipment is intended to represent various forms of digital computers such as, for example, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. . Electronic devices can also represent various forms of mobile devices such as, for example, personal digital assistants, mobile phones, smart phones, wearable devices, and other similar computing devices. The components, their connections and relationships, and their functionality illustrated herein are merely examples and are not intended to limit the implementation of the application described and/or required herein.

As shown in FIG. 9, this electronic device includes one or more processors 21, a memory 22, and an interface including a high-speed interface and a low-speed interface for connecting each component. Each component may be connected by a different bus and mounted on a common motherboard, or may be mounted in other manners as desired. The processor, in the electronic device, instructions, including instructions stored in or on memory, to cause an external input/output device (e.g., a display device coupled to the interface) to display graphical information of the GUI. Executed instructions can be processed. In other embodiments, multiple processors and/or multiple buses may be used along with multiple memories, if desired. Similarly, multiple electronic devices can be connected, each providing a portion of the required operations (eg, a server array, blade servers, or multi-processor system). In FIG. 9, one processor 21 is taken as an example.

Memory 22 is a non-transitory computer-readable storage medium provided herein. However, the memory stores instructions executable by at least one processor such that the at least one processor performs the information recommendation method provided herein. A non-transitory computer-readable storage medium of the present application stores computer instructions used to cause a computer to perform the information recommendation method provided herein.

The memory 22 is a non-transitory computer-readable storage medium, for example, program instructions/modules (for example, the receiving unit 11, the processing unit 12 and the transmitting unit shown in FIG. 8) corresponding to the information recommendation method in the embodiments of the present application. 13), used to store non-transitory software programs, non-transitory computer-executable programs and modules. The processor 21 executes the non-transitory software programs, instructions and modules stored in the memory 22 to perform the various functional applications and data processing of the server, namely the information recommendation method in the above method embodiments. Realize

Memory 22 may include a program storage area and a data storage area, where the program storage area may store an operating system, application programs required for at least one function, and the data storage area may store information. Data created by using the recommended electronic device can be stored. Memory 22 may also include high speed random access memory and may further include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. is. In some embodiments, memory 22 can optionally include memory remotely located relative to processor 21, and these remote memories can be connected to information recommendation electronics via a network. can. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The electronic device that executes the information recommendation method can further include an input device 23 and an output device 24 . The processor 21, memory 22, input device 23, and output device 24 may be connected by a bus or in other manners, and connection by a bus is taken as an example in FIG.

The input device 23 is capable of receiving input numeric or character information and generating key signal inputs associated with user settings and functional controls of information recommendation electronics, such as touch panels, keypads, mice, trackpads, etc. , touch pads, pointing sticks, one or more mouse buttons, trackballs, joysticks, and the like. Output devices 24 may include display devices, auxiliary lighting devices (eg, LEDs), tactile feedback devices (eg, vibration motors), and the like. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, and a plasma display. In some embodiments, the display device may be a touch panel.

Various embodiments of the systems and techniques described herein may be digital electronic circuit systems, integrated circuit systems, application specific integrated circuits (ASICs), computer hardware, firmware, software, and/or can be realized by a combination of These various embodiments are embodied in one or more computer programs, which can be executed and/or interpreted in a programmable system including at least one programmable processor. The programmable processor may be a dedicated or general purpose programmable processor that receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits data and instructions to the storage system, It can be transmitted to the at least one input device and the at least one output device.

These computer programs (also called programs, software, software applications, or code) contain machine instructions for programmable processors and can be written in high-level process and/or object-oriented programming language and/or assembly/machine language. can be implemented. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus for providing machine instructions and/or data to a programmable processor. , and/or apparatus (eg, magnetic disk, optical disk, memory, programmable logic device (PLD)), including a machine-readable medium for receiving machine instructions, which are machine-readable signals. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide interaction with a user, the systems and techniques described herein can be implemented on a computer that includes a display device (e.g., CRT (Cathode Ray Tube)) for displaying information to the user. ) or LCD (liquid crystal display) monitor), and a keyboard and pointing device (e.g., mouse or trackball) through which a user can provide input to the computer. Other types of devices can also provide interaction with a user, e.g., the feedback provided to the user can be any form of sensing feedback (e.g., visual, auditory, or tactile feedback). may receive input from the user in any form (including acoustic, speech, or tactile input).

The systems and techniques described herein may be computing systems that include back-end components (e.g., data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include front-end components. system (e.g., a user computer having a graphical user interface or web browser through which a user interacts with embodiments of the systems and techniques described herein), or such a background It can be implemented in a computing system including any combination of end components, middleware components, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (eg, a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server is created by computer programs running on corresponding computers and having a client-server relationship to each other.

An information recommendation method further provided in an embodiment of the present application is a step of obtaining a plurality of search history records within a validity period at a current time, wherein each of the plurality of search history records is within a reference area and determining at least one geofence based on said plurality of search history records, wherein location points included in said geofence are located within said reference region. and

For the specific implementation principle of this embodiment, please refer to what has been described in the above embodiments, and the description thereof will be omitted here.

According to the technical solution of the embodiments of the present application, the server pre-establishes a geofence set corresponding to the reference area using the historical data of a large number of users looking at the location points in the reference area. In the information recommendation process, after receiving the location information reported from the first electronic device, the server determines the recommended target information based on the target geofence to which the location point corresponding to the location information belongs, and provides the first information. Send to electronic devices. In this process, the server creates a geofence by combining the search histories of many users within the validity period, uses the geofence to recommend information to the user, and the position points in the geofence are social Since it reflects the position points that are popular with the general public, the quality and timeliness of the recommendation information can be greatly improved, and the purpose of improving the accuracy of information push can be achieved.

It will be appreciated that steps may be rearranged, added, or deleted from the various forms of flow shown above. For example, each step described in this application may be executed in parallel, sequentially, or in a different order, but the technical solution disclosed in this application is There is no limitation herein as long as the desired result can be achieved.

The above specific embodiments are not intended to limit the protection scope of the present application. Persons skilled in the art can make various modifications, combinations, subcombinations, and substitutions based on design requirements and other factors. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall all fall within the protection scope of the present application.

Claims (17)

receiving location information reported from a first electronic device and used to indicate the location where the first electronic device is located;
determining recommended target information based on a target geofence to which the location point corresponding to the location information belongs, wherein the target geofence is included in a geofence set, and the geofences in the geofence set are: generated based on search history records of a plurality of second electronic devices in a reference area, said search history records being records of search histories for location points within said reference area;
and transmitting the recommended target information to the first electronic device.
An information recommendation method characterized by: Prior to the step of receiving reported location information from the first electronic device, further comprising:
A position point set is obtained at a first time based on a plurality of search history records within a validity period when each second electronic device among the plurality of second electronic devices is located in the reference area. wherein the valid period is a period between the first time and a second time before the first time, and the length of time of the valid period is set in advance a step smaller than the threshold
clustering each location point in the set of location points to obtain at least one cluster, wherein the distance between any two location points in the same cluster is less than a preset threshold;
obtaining the set of geofences by determining geofences for corresponding clusters based on the geographic coordinates of location points in each of the at least one cluster;
2. The information recommendation method according to claim 1, wherein: The location point set further includes a type tag for each location point used to indicate the type of the corresponding location point, and based on the geographic coordinates of each location point in the at least one cluster, the corresponding cluster Prior to said step of obtaining said geofence set by determining a geofence, further comprising:
determining, for each cluster of the at least one cluster, the number of times location points having the same type tag in the cluster were retrieved, and obtaining the number of times of retrieval corresponding to each type tag among the plurality of type tags; obtaining a popular type tag for each of said at least one cluster, with the most searched type tag as a popular type tag of said cluster;
3. The information recommendation method according to claim 2, wherein: The step of obtaining the geofence set by determining a geofence for a corresponding cluster based on the geographic coordinates of location points in each of the at least one cluster,
determining, for each cluster of said at least one cluster, the mean abscissa and ordinate of each location point having a popular type tag in each said cluster to obtain the center of each cluster; When,
determining a geofence corresponding to each of the at least one cluster based on a center of each of the at least one cluster and a preset fence shape to obtain the geofence set. including steps and
4. The information recommendation method according to claim 3, characterized by: For each cluster of the at least one cluster, determining the mean abscissa and ordinate of each location point having a popular type tag in the cluster to obtain the center of each cluster. before and additionally,
determining, for each cluster of the at least one cluster, that the number of location points with popular type tags in each cluster exceeds a preset number;
5. The information recommendation method according to claim 4, wherein: determining whether the length of time that the geofence set exists exceeds a preset length of time;
updating the geofence set if the length of time that the geofence set exists exceeds a preset length of time;
6. The information recommendation method according to any one of claims 1 to 5, characterized in that: The step of determining recommendation target information based on a target geofence to which a location point corresponding to the location information belongs,
determining information already recommended to the first electronic device from recommended information corresponding to the target geofence;
obtaining the recommendation target information by filtering information already recommended to the first electronic device from the recommendation information corresponding to the target geofence;
6. The information recommendation method according to any one of claims 1 to 5, characterized in that: a receiving unit for receiving location information reported from a first electronic device and used to indicate the location where the first electronic device is located;
A processing unit for determining recommended target information based on a target geofence to which a location point corresponding to the location information belongs, wherein the target geofence is included in a geofence set, and a geofence in the geofence set. an offense is generated based on search history records of a plurality of second electronic devices in a reference area, the search history records being records of search histories for location points within the reference area;
a transmission unit for transmitting the recommended target information to the first electronic device;
An information recommendation device characterized by: Before the receiving unit receives the location information reported from the first electronic device, the processing unit further controls each second electronic device among the plurality of second electronic devices to be in the reference area. obtaining a location point set at a first time based on a plurality of search history records within a valid period when located, wherein the valid period comprises the first time and the first time; a period between a second time and a second time before the time period, wherein the time length of the valid period is less than a preset threshold; obtaining two clusters, wherein the distance between any two location points in the same cluster is less than a preset threshold, and based on the geographic coordinates of each location point in the at least one cluster , obtaining the geofence set by determining the geofences of the corresponding clusters;
9. The information recommendation device according to claim 8, characterized by: The location point set further includes a type tag for each location point used to indicate the type of the corresponding location point, and the processing unit, based on the geographic coordinates of each location point in the at least one cluster, , before obtaining the geofence set by determining a geofence for a corresponding cluster, further for each cluster of the at least one cluster, location points having the same type tag in the cluster are searched; obtaining the number of searches corresponding to each type tag among a plurality of type tags, and determining the type tag with the highest number of searches as a popular type tag of the cluster, among the at least one cluster used to get each popular type tag,
10. The information recommendation device according to claim 9, characterized by: the processing unit, in obtaining the geofence set, by determining a geofence for a corresponding cluster based on geographic coordinates of location points of each of the at least one cluster; determining the mean abscissa and the mean ordinate of each location point having a popular type tag in each said cluster to obtain the center of each cluster; determining a geofence corresponding to each cluster of the at least one cluster based on the center of each cluster and a preset fence shape of
11. The information recommendation device according to claim 10, characterized by: The processing unit determines, for each cluster of the at least one cluster, a mean abscissa and a mean ordinate of each location point having a popular type tag in the cluster, and a center of each cluster. is further used to determine, for each cluster of the at least one cluster, that the number of location points with the popular type tag in each cluster exceeds a preset number ,
12. The information recommendation device according to claim 11, characterized by: The processing unit further determines whether the length of time that the set of geofences exists exceeds a preset length of time, and if the length of time that the set of geofences exists exceeds the preset length of time , used to update the geofence set;
13. The information recommendation device according to any one of claims 8 to 12, characterized in that: The processing unit determines information already recommended to the first electronic device from recommendation information corresponding to the target geofence, and determines information already recommended to the first electronic device from recommendation information corresponding to the target geofence. Used to obtain the recommended information by filtering the information recommended to
13. The information recommendation device according to any one of claims 8 to 12, characterized in that: at least one processor;
a memory communicatively coupled to the at least one processor, wherein
The memory stores instructions executable by at least one processor, and the instructions are executed by the at least one processor so that the at least one processor performs any one of claims 1 to 7. so as to carry out the information recommendation method described in the paragraph,
An electronic device characterized by: A non-transitory computer-readable storage medium storing computer instructions, the computer instructions being used to cause a computer to execute the information recommendation method according to any one of claims 1 to 7,
A non-transitory computer-readable storage medium storing computer instructions characterized by: A computer program, which, when executed by a processor, causes a computer to execute the information recommendation method according to any one of claims 1 to 7,
A computer program characterized by:

Images