WO2018192506A1

WO2018192506A1 - Method and apparatus for recommending social information, and storage medium

Info

Publication number: WO2018192506A1
Application number: PCT/CN2018/083449
Authority: WO
Inventors: 沈奕杰
Original assignee: 腾讯科技（深圳）有限公司
Priority date: 2017-04-18
Filing date: 2018-04-18
Publication date: 2018-10-25
Also published as: CN108733692A

Abstract

Disclosed are a method and apparatus for recommending social information, and a storage medium. The method is capable of acquiring a moving track, to be matched, of a current user, wherein the moving track comprises at least two track positions (101); according to the moving track to be matched, screening, in a pre-set database, other users with similar moving tracks to that of the current user to obtain a candidate user set (102); according to a pre-set strategy, determining, from the candidate user set, a user to be recommended (103); and according to the user to be recommended, determining social information to be recommended, and recommending the social information to the current user (104).

Description

Social information recommendation method, device and storage medium

The present application claims the priority of the Chinese Patent Application, which is filed on Apr. 18, 2017, the number of in.

Technical field

The present invention relates to the field of communications technologies, and in particular, to a social information recommendation method, apparatus, and storage medium.

Background technique

With the rapid development of Internet technology and the popularity of mobile terminals, people's lifestyles are quietly changing, and social methods are one of them.

Social information recommendation is an important function of most existing social applications. It can find people who have potential social relationships with users according to certain rules. For example, according to the location of the user at a certain time, according to the distance, recommend nearby people. Among them, the range of "nearby" can be set according to actual needs or user preferences, for example, a range centered on the current location, a radius of 500 or 1000 meters, and the like can be set.

Summary of the invention

The embodiment of the invention provides a social information recommendation method, device and storage medium; the accuracy of the recommendation can be improved, and the recommendation effect is improved.

An embodiment of the present invention provides a social information recommendation method, including:

Obtaining a moving track to be matched by the current user, where the moving track includes at least two track locations;

Selecting other users that have a matching moving track with the current user in the preset database according to the moving track to be matched, and obtaining a candidate user set;

Determining a user to be recommended from the candidate users according to a preset policy;

Get social information of the user to be recommended and send it to the current user.

Correspondingly, an embodiment of the present invention further provides a social information recommendation apparatus, including: a processor and a memory, where the processor executes machine readable instructions in the memory, where

Determining a user to be recommended from the candidate user according to a preset policy;

In addition, an embodiment of the present invention further provides a non-volatile storage medium storing one or more programs, the one or more programs comprising: computer readable instructions, when the computer readable instructions are executed by a computing device The computing device is caused to perform the methods provided herein.

DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the present invention. Other drawings can also be obtained from those skilled in the art based on these drawings without paying any creative effort.

FIG. 1 is a schematic diagram of a scenario of a social information recommendation method according to an embodiment of the present invention;

FIG. 1b is a flowchart of a social information recommendation method according to an embodiment of the present invention;

2a is another flowchart of a social information recommendation method according to an embodiment of the present invention;

2b is another schematic diagram of a scenario of a social information recommendation method according to an embodiment of the present invention;

FIG. 3 is a schematic structural diagram of a social information recommendation apparatus according to an embodiment of the present invention; FIG.

FIG. 3b is another schematic structural diagram of a social information recommendation apparatus according to an embodiment of the present invention;

FIG. 4 is a schematic structural diagram of a server according to an embodiment of the present invention.

detailed description

The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, but not all embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

Embodiments of the present invention provide a social information recommendation method, apparatus, and system.

The social information recommendation system may include any one of the social information recommendation devices provided by the embodiment of the present invention. The social information recommendation device may be integrated into a device such as a server. In addition, the social information recommendation system may further include other The device, for example, can include a terminal, and the like.

For example, the social information recommendation device is specifically integrated in the server, and the current user is the user A, and the terminal used by the user A is the terminal A. For example, as shown in FIG. 1a, the server can obtain the mobile track to be matched by the user A, where The moving track may include at least two track locations, for example, the position change information of the user A sent by the terminal A may be received, and then the moving track of the user A is generated according to the position change information, and the generated moving track is used as the moving track to be matched. Or, it is also possible to obtain a plurality of historical movement trajectories of the current user in the past preset time range, and select a historical movement trajectory whose appearance frequency meets the preset frequency condition (such as the highest frequency of occurrence) as the current trajectory to be matched by the current user. ,and many more. Thereafter, the server may select other users having similar movement trajectories with the user A in the preset database according to the movement trajectory to be matched, such as user B, user C, and user D, etc., to obtain candidate user sets, and then determine respectively. The candidate user sets the time at which each candidate user is located at the track location, determines the candidate user whose time meets the preset time condition as the user to be recommended, and determines the social information to be recommended according to the user to be recommended, and sends the information to the terminal A. For example, if the time when the user B is located at the track location can meet the preset time condition, and neither the user C nor the user D is satisfied, then the information of the user B can be determined as the social information to be recommended, and recommended to the user. A, and the information for the user C and the user D is not recommended (although the movement trajectories of the user C and the user D are similar to the movement trajectory of the user A).

The details are described below separately. It should be noted that the serial numbers of the following embodiments are not intended to limit the preferred order of the embodiments.

This embodiment will be described from the perspective of a social information recommendation device, which may be integrated into a server, such as a service server or the like.

A social information recommendation method includes: acquiring a movement trajectory to be matched by a current user, the movement trajectory includes at least two trajectory locations; and screening other users having similar movement trajectories with the current user in a preset database according to the movement trajectory to be matched The candidate user set is obtained; the user to be recommended is determined from the candidate user according to the preset policy, the social information to be recommended is determined according to the user to be recommended, and the recommendation is made to the current user.

As shown in FIG. 1b, the specific process of the social information recommendation method may be as follows:

101. Acquire a moving track to be matched by the current user, where the moving track includes at least two track locations.

In an embodiment of the present application, the current trajectory to be matched by the current user may include: the acquired trajectory of the current user's terminal.

The trajectory to be matched may be generated in real time, and may be specified or may be selected from the historical data, that is, the mobile trajectory to be matched by the current user may be obtained by using any one of the following methods:

(1) real-time generation;

A. Obtain the location change information of the current user.

For example, the location change information of the current user sent by the terminal or other device may be specifically received.

The terminal or other device may acquire the current location change information of the current user by using a Global Positioning System (GPS), base station positioning, or other positioning motion detection technology. For example, the location information of the current user within a certain time period may be obtained by using a positioning technology such as GPS or base station positioning, and the geographical location information is recorded, and then the location change information of the current user is generated according to the recorded geographical location information.

The geographical location information may be recorded by means of latitude and longitude, and the specific format is (longitude, latitude), for example, (113.34638, 23.11741), (113.34758, 23.11971), and the like.

B. Generate a movement trajectory of the current user according to the position change information, and use the generated movement trajectory as a movement trajectory to be matched by the current user.

For example, according to the sampling point position of each geographical location information in the position change information, and the sampling time, the sampling point position is sequentially drawn according to the sampling time sequence to form the current user's moving track, and then The generated moving track is taken as the moving track to be matched by the current user, and the like.

In an embodiment of the present application, the current trajectory to be matched by the current user may be based on the position coordinate of the starting point of the user, with the position coordinate of the ending point of the user as the end point, and the position coordinate of the approach point as the starting point. circuit diagram. If the position coordinates of the route point are not obtained, the movement track is a circuit diagram drawn with the position coordinates of the user's starting point as the starting point and the position coordinates of the user's ending point as the end point. If the user's starting point and ending point coincide, and the waypoint is not acquired, the moving track is a point. The starting point, the ending point, and the waypoint are all track locations.

Wherein, the sampling point position can be used as the track location. For example, if a geographical position change information includes two sampling point positions, respectively (113.34638, 23.11741) and (113.34758, 23.11971), then the obtained moving track is obtained. It can also include two track locations, (113.34638, 23.11741) and (113.34758, 23.11971), and so on.

In order to facilitate subsequent viewing and use, a geographical location label may also be added to each track location on the moving track, and saved to a preset database, that is, after the step “generate the current user's moving track according to the position change information”, the social information Recommended methods can also include:

Add a location tag to the track location on the current user's movement track, and save the movement track after the location tag is added to the default database.

The geographical location label is mainly used to identify the trajectory location, and may be marked by the most iconic or most well-known place name, building, bus station name or subway station name, etc., such as (113.34638, 23.11741) Corresponding to XX City XX subway station, (133.34638, 24.11741) corresponding to XX City XX Building, and so on.

(2) the specified movement trajectory;

A selection instruction is received, and the corresponding movement trajectory is selected as the movement trajectory to be matched according to the selection instruction.

For example, a user-triggered selection instruction may be received, and then a corresponding movement trajectory is selected as the movement trajectory to be matched according to the selection instruction; for example, if the user can specify a movement trajectory generated at a certain time as the movement trajectory to be matched, Alternatively, one or more moving tracks may be specified as the moving track to be matched, and the like.

(3) Obtained from historical data;

Obtaining a plurality of historical movement trajectories of the current user in the past preset time range, and selecting a historical movement trajectory whose appearance frequency meets the preset frequency condition from the obtained plurality of historical movement trajectories, as the movement trajectory of the current user to be matched.

The preset frequency condition may be set according to the requirements of the actual application. For example, the specific one may be as follows:

The historical moving track with the highest frequency of occurrence is selected from the obtained plurality of historical moving tracks as the moving track to be matched by the current user.

Or, the historical moving track whose appearance frequency exceeds the preset frequency threshold is selected from the obtained plurality of historical moving tracks as the moving track to be matched by the current user.

Or, the first K historical moving trajectories with the highest frequency of occurrence are selected from the obtained plurality of historical moving trajectories as the moving trajectory to be matched by the current user, where K is a positive integer, and the specific value may be determined according to the actual application requirement. For example, set K to 2, 3, or 5, and so on.

The preset time range may also be set according to the requirements of the actual application. For example, the preset time range is specifically 1 month, and a historical moving track with the highest frequency of occurrence is selected as an example, if user A is in the past In the month, there are a total of five moving trajectories. Among them, the historical moving trajectory 1 appears twice, and the other historical moving trajectories appear once. At this time, the historical moving trajectory 1 can be used as the moving trajectory of the current user to be matched. ,and many more.

102. Filter, according to the moving track to be matched, another user that has a matching moving track with the current user in the preset database, to obtain a candidate user set. In an embodiment of the present application, other users having a matching movement trajectory with the current user may include other users having similar movement trajectories with the current user, such as a movement trajectory whose similarity is greater than a set threshold. For example, the details can be as follows:

(1) Obtain the movement trajectory of all users in the preset database.

Wherein each movement track includes at least one track location.

(2) clustering the movement trajectory according to the trajectory location on the moving trajectory to be matched and the trajectory location on the movement trajectory of the user acquired in the preset database.

For example, the geographic location label of the track location on the moving track to be matched may be acquired, and the geographical location label of the track location on the moving track of other users in the preset database is obtained, and the moving track is performed according to the obtained geographical location label. Clustering operations.

Through the clustering operation, the moving trajectory for including the geographical location label of the trajectory location on the moving trajectory to be matched may be filtered, for example, the geographical location label of the trajectory location on the moving trajectory to be matched is “ For example, "A Building" and "XX Subway Station", at this time, it is possible to screen out moving tracks including "A Building" and "XX Subway Station", and so on.

Among them, clustering refers to the process of dividing a collection of physical or abstract objects into multiple classes consisting of similar objects. A cluster generated by clustering is a collection of data objects that are similar to objects in the same cluster and different from objects in other clusters. The specific algorithm of the clustering operation used in the embodiment of the present invention may be set according to the requirements of the actual application, and details are not described herein again.

(3) Filtering out other users having similar moving trajectories with the current user according to the operation result, and obtaining a candidate user set; for example, the specifics may be as follows:

The similarity between the movement trajectory of each user in the preset database and the movement trajectory to be matched is determined according to the operation result, and the user whose similarity is higher than the preset threshold is added as a candidate user to the candidate user set.

The preset threshold may be set according to the requirements of the actual application, and details are not described herein again.

In order to improve the effectiveness of the screening result, before the clustering operation on the moving track according to the track location on the moving track to be matched and the track position on the moving track of the user acquired in the preset database, The rule is to perform preliminary processing on the movement trajectory of the user acquired in the preset database, and then the movement trajectory is clustered according to the trajectory location on the trajectory to be matched and the trajectory location on the trajectory after the preliminary processing. Operation.

The preset rule may be set according to the requirements of the actual application. For example, the moving track within a certain period may be selected according to actual needs, or the moving track with a higher frequency of the user may be selected (ie, the frequently-traveled route). , etc.; that is, the step "preliminarily processing the movement trajectory of the user acquired in the preset database according to the preset rule" may be as follows:

Selecting, from the movement trajectory of the user acquired in the preset database, a movement trajectory whose trajectory generation time is within a preset period, as a movement trajectory after preliminary processing; or

From the movement trajectory of the user acquired in the preset database, the top M movement trajectories with the highest frequency of occurrence of each user are selected as the movement trajectory after the initial processing, wherein M is a positive integer, and M can be actually applied according to the actual application. Requirements are set.

103. Determine, according to a preset policy, a user to be recommended from the candidate user.

The preset policy can be set according to the requirements of the actual application. For example, the following can be:

(1) Determine the time when each candidate user in the candidate user set is located at the track location (ie, the track location on the moving track to be matched).

For example, the track location on the moving track of the current user A includes the XX subway station and the certain building, and the candidate user set includes the candidate user B and the candidate user C. At this time, the following information can be determined:

Determining the time when the candidate user B is located at the XX subway station; determining the time when the candidate user B is located in a certain building; determining the time when the candidate user C is located at the XX subway station; determining the time when the candidate user C is located in a certain building, and so on, etc. .

It should be noted that the time may include a year field, a month field, a day field, a time field, a minute field, and a second field. For example, if the time is “10:40:21 on December 13, 2014, then the year” The field is "2014", the month field is "12", the day field is "13", the time field is "10", the subfield is "40", the second field is "21", and so on.

(2) The information of the candidate user whose time meets the preset time condition is determined as the user to be recommended.

The preset time condition may be specifically set according to the requirements of the actual application, and details are not described herein again.

For example, the time when the current user is located at the track location (ie, the track location on the moving track to be matched) may be acquired, according to the time when the current user is located at the track location, and the time when each candidate user is located at the track location. The time difference between each candidate user and the current user is calculated as a time difference, and the candidate user whose time difference is less than the preset time threshold is determined as the user to be recommended.

The time when the current user is located at the track location (ie, the track location on the moving track to be matched) may also include the year field, the month field, the day field, the time field, the minute field, and the second field, and the embodiment of the present invention Saying "time difference" refers to the difference between the fields specified in the time. The specified field includes at least one of the year field, the month field, the day field, the time field, the minute field, and the second field. The specified field can be set according to the needs of the actual application. For example, if the specified field is “time field, sub-field, and second field”, if the current user is located at the track location, the time is “10:40:21 on December 13, 2014”, and a candidate user is located. The time of the track location is “10:45:21 on November 14, 2014”, the year field, month field and day field can be ignored when calculating the time difference, that is, only “10:40:21” and “ 10:45:21" difference.

104. Determine the social information to be recommended according to the user to be recommended, and make a recommendation to the current user.

In an embodiment of the present application, the recommending to the current user may include: sending the social information to the terminal device of the current user.

For example, the information of the user to be recommended may be directly used as the social information to be recommended; or the information of the user to be recommended may be used as the social information to be recommended.

The screening policy may be determined according to the requirements of the actual application. For example, the information of the user to be recommended that has the most “number of occurrences at the track location” may be selected as the social information to be recommended, etc., that is, in the step “according to Before recommending the user to determine the social information to be recommended, the recommended method of the social information may further include:

The number of times each candidate user in the candidate user set appears in the track location within a preset time period is determined separately.

The preset deadline may be set according to the requirements of the actual application, for example, may be set to one month, or one week, and the like.

For example, the trajectory location on the trajectory of the current user A includes the XX subway station and the XX building, and the candidate user set includes the candidate user B and the candidate user C, and the preset period is one month as an example. Determine the following information:

Determining the number of times that candidate user B appears in the XX subway station within one month (ie, starting from the current time and in the past month); determining the number of times that candidate user B appears in a certain building within one month; determining candidate user C The number of times that the XX subway station appeared in a month; the number of times a candidate user C appeared in a certain building within one month, and so on, and so on.

Then, the step of determining the social information to be recommended according to the user to be recommended may include: selecting, from the users to be recommended, the information of the user whose number of times meets the preset number of times as the social information to be recommended. For example, the details can be as follows:

Selecting, from the users to be recommended, the information of the user to be recommended that is greater than the preset number of times as the social information to be recommended; or

The candidate users are sorted based on the number of times, and the information of the N recommended users is determined as the social information to be recommended according to the ranking result, where N is a positive integer.

The preset condition, the preset time threshold, the preset number of thresholds, and the value of the N may be set according to actual application requirements, and details are not described herein again.

In order to make more accurate recommendations, "direction" can also be taken as one of the consideration factors, that is, after obtaining the social information to be recommended, the direction of the moving track (ie, the moving direction of the user on the moving track) can be preferentially recommended with the current user. The social information to be recommended corresponding to the user to be recommended is consistent.

As can be seen from the above, in this embodiment, the mobile trajectory to be matched by the current user may be acquired, where the trajectory includes multiple trajectory locations, and then candidate users having similar trajectories with the current user are selected in the preset database, and the candidate is selected from The candidate users who meet the preset time conditions at the time of the track are regarded as the users to be recommended, and the social information to be recommended is determined according to the user to be recommended, and is recommended to the current user. Since the scheme is recommended, compared with the prior art that the social information to be recommended is determined only according to the current location of the user, the application will include the entire moving track of multiple track locations as a consideration factor, thereby ensuring matching to the user. The movement trajectory has greater similarity with the movement trajectory of the user, thereby ensuring more accurate matching of the social information of the target user, avoiding repeated matching due to inaccuracy of the social information of the matched user, and reducing duplicate matching. The resulting system resources and time is wasted.

According to the method described in the above embodiments, the following will be exemplified in further detail.

In this embodiment, the social information recommendation device is specifically integrated in the server, the current user is the user A, the terminal where the user A is the terminal A, and the moving track to be matched is a real-time generated mobile track as an example. .

As shown in FIG. 2a, a social information recommendation method may be as follows:

201. The terminal A acquires location change information of the user A.

For example, the terminal A may acquire the geographical location information of the user A within a certain time period by using GPS, base station positioning, or other positioning motion detection technology, and record the geographical location information, and then generate the location of the user A according to the recorded geographical location information. Change information, and more.

202. The terminal A sends the location change information of the user A to the server.

For example, the terminal A can transmit the location change information of the user A to the server via the Internet or a wireless network.

The location change information may be sent to the server as an independent information, or may be carried in other information and sent to the server, and details are not described herein.

203. After receiving the location change information, the server generates a movement trajectory of the user A according to the position change information, and uses the generated movement trajectory as a movement trajectory to be matched.

For example, according to the sampling point position of each geographical location information in the position change information, and the sampling time and the like, the sampling point positions are sequentially drawn according to the order of the sampling time to constitute the movement track of the user A, etc. Wait.

Wherein, the moving track includes at least two track locations, for example, the sampling point position can be used as a track location, and the like. For example, if a geographical location change information includes two sampling point positions, namely (113.34638, 23.11741) and (113.34758, 23.11971), then the obtained moving track may also include two track locations, respectively ( 113.34638, 23.11741) and (113.34758, 23.11971), and so on, and so on.

In order to facilitate subsequent viewing and use, it is also possible to add a geographical location label to each track location on the moving track, and save the moving track after adding the geographical location label to the preset database.

204. The server acquires a movement track of other users in the preset database.

Wherein each moving track includes at least two track locations.

It should be noted that the method for generating the trajectory of the user is the same as the method for generating the trajectory of the user A. For details, refer to step 203, and details are not described herein again.

205. The server performs a clustering operation on the moving track according to the track location on the moving track to be matched, and the track location on the moving track of other users in the preset database.

For example, the server may obtain a geographical location label of the track location on the moving track to be matched, and obtain a geographical location label of the track location on the movement track of other users in the preset database, and then move the track according to the obtained geographical location label. Perform clustering operations.

Wherein, the specific algorithm of the clustering operation can be set according to the requirements of the actual application, for example, a division method, a hierarchy method, a density algorithm, a graph theory clustering method, a grid algorithm, or a model algorithm, etc., etc., Let me repeat.

In order to improve the effectiveness of the screening result, before the clustering operation, the movement trajectory of the user acquired in the preset database may be preliminarily processed according to a preset rule, and then according to the trajectory on the moving trajectory to be matched. The location and the trajectory location on the trajectory after the initial processing cluster the movement trajectory.

The preset rule may be set according to the requirements of the actual application. For example, the moving track within a certain period may be selected according to actual needs, or the moving track with a higher frequency of the user may be selected (ie, the frequently-traveled route). , etc.; for example, the specifics can be as follows:

The server selects a movement trajectory whose trajectory generation time is within a preset period from the movement trajectory of the user acquired in the preset database as the movement trajectory after the preliminary processing; for example, the generation time can be selected as “December 1, 2014 The movement trajectory between December 30, 2014, as the movement trajectory after the initial processing, or one day, such as the movement trajectory of "December 1, 2014", and the like.

Alternatively, the server may also select the first M moving trajectories with the highest frequency of occurrence of each user from the movement trajectory of the user acquired in the preset database, as the moving trajectory after preliminary processing, where M is a positive integer, M specific It can be set according to the requirements of the actual application; for example, taking M as 2 as an example, if A has 5 moving tracks, wherein the first two moving tracks with the highest frequency of occurrence are moving track 1 and moving track 2, then, The moving track 1 and the moving track 2 can be filtered out, as a preliminary processed moving track corresponding to A, and so on, and so on.

206. The server selects other users that have similar movement trajectories with the user A according to the operation result, and obtains the candidate user set; for example, the specifics may be as follows:

The server determines, according to the operation result, the similarity between the movement trajectory of each user in the preset database and the movement trajectory to be matched, and adds the user whose similarity is higher than the preset threshold as a candidate user to the candidate user set.

The preset threshold may be set according to the requirements of the actual application. For example, the preset threshold is specifically 95%. If the user B moves the trajectory to the matching trajectory, the similarity is 96%, and the user C The similarity between the movement trajectory and the movement trajectory to be matched is 95%, the similarity between the movement path of the user D and the movement trajectory to be matched is 98%, and the similarity between the movement path of the user E and the movement trajectory to be matched is 85. %, the similarity between the user F movement trajectory and the movement trajectory to be matched is 60%. At this time, user B, user C, and user D can be added as candidate users to the candidate user set corresponding to user A.

207. The server determines, respectively, a time when each candidate user in the candidate user set is located at the track location (ie, the track location on the moving track to be matched).

The time of the present invention may include a year field, a month field, a day field, a time field, a subfield, and a second field. In this embodiment, for the convenience of calculation, the "second field" is omitted as an example. .

It is also possible to separately determine the number of times each candidate user in the candidate user set appears at the track location within a preset time period.

For example, the track location on the moving track of the current user A includes the XX subway station and the certain building, and the candidate user set includes the candidate user B, the candidate user C, and the candidate user D, and the preset period is one month (ie, current Time is the starting point, in the past month), for example, at this point, you can determine the following information:

Determine the time when candidate user B is located at XX subway station, for example, "8:03 on December 13, 2014", and determine the number of times that the XX subway station appears in the month, for example, 10 times;

Determine the time when the candidate user B is located in a certain building, for example, "8:20 on December 13, 2014", and determine the number of times that a certain building appears in a certain building, for example, 10 times;

Determining the time when the candidate user C is located at the XX subway station, for example, "23:00 on December 12, 2014", and determining the number of times the XX subway station appears in the month, for example, 1 time;

Determine the time when the candidate user C is located in a certain building, for example, "23:30 on December 12, 2014", and determine the number of times that a certain building appears in a certain building, for example, 1 time;

Determining the time when the candidate user D is located at the XX subway station, for example, "7:55 on December 13, 2014", and determining the number of times the XX subway station appears in the same month, for example, 2 times;

Determine the time when the candidate user D is located in a certain building, for example, "8:25 on December 13, 2014", and determine the number of times that a certain building appears in a certain building, for example, 2 times;

And so on, and so on.

208. The server determines, by the server, the candidate user that meets the preset time condition as the user to be recommended.

For example, the server may obtain the time when the user A is located at the trajectory location, and calculate, according to the time when the user A is located at the trajectory location, and the time when each candidate user is located at the trajectory location, respectively, each candidate user is located at the same trajectory location as the user A. The time difference is determined by the candidate user whose time difference is less than the preset time threshold as the user to be recommended.

The "time difference" refers to the difference between the specified fields in the time. The specified field can be set according to the requirements of the actual application. For the convenience of description, in this embodiment, the specified field will be the "time field and The sub-field is described as an example. When calculating the time difference, the year field, the month field, the day field, and the second field can be ignored. For example, if the user A is located at the XX subway station, the time is "December 14, 2014, 8:00. ", while User B's time at XX subway station is "8:03 on December 13, 2014", at this time, it can be determined that User A's time at XX subway station is "8:00", and User B is at XX. The time at the subway station is "8:03", and then the time difference between "8:00" and "8:03" is calculated. It should be noted that, for convenience of description, when describing the time when each user is located at the track location, the following is an example of ignoring the year field, the month field, the day field, and the second field (ie, only representing the time field and the minute field). .

It should be noted that, when it is determined that the user is to be recommended, the candidate user may be determined as the user to be recommended when the “time difference” corresponding to all the track locations on the track is less than the preset time threshold, or It can be set that as long as the “time difference” corresponding to a certain track location is less than the preset time threshold, the corresponding candidate user can be determined as the user to be recommended, and so on. For the convenience of description, in the embodiment, the latter is taken as an example. Description.

The absolute value of the difference between the time when the user A is located at the trajectory location and the time when the candidate user is located at the trajectory location may be the time difference between the user A and the candidate user at the trajectory location.

For example, as shown in FIG. 2b, the candidate user includes the candidate user B, the candidate user C, and the candidate user D, and the preset time difference threshold is 12 minutes. If the user A is located at the XX subway station, the time is 8:00. The time at the certain building is “8:30”; the time for candidate user B at XX subway station is “8:03”, the time for a certain building is “8:20”; candidate user C is located at XX subway station. The time is "23:00", the time in a certain building is "23:30"; the time of candidate user D is XX subway station is "7:55", and the time in a certain building is "8:25" At this time, the time difference between user A and each candidate user at XX subway station and certain building can be calculated separately, as shown in Table 1:

Table I:

It can be seen that the time difference between the user A and the candidate user B, and the user A and the candidate user C in the XX subway station, and the time difference in the certain building are both smaller than the preset time threshold. Therefore, the candidate user B and the candidate user C can be treated as Recommended users.

209. The server determines the social information to be recommended according to the user to be recommended.

For example, the server may directly use the information of the user to be recommended as the social information to be recommended. For example, if both user B and user C are used as the user to be recommended in step 208, the information of the user B to be recommended may be separately obtained. And the information of the user C to be recommended, and the obtained information is used as the social information to be recommended.

The information of the user to be recommended (such as the information of the user B to be recommended, and the information of the user C to be recommended, etc.) may include user information such as user identification, gender, age, and/or hobbies of the user to be recommended, and may also include The similarity of the movement trajectory of the recommended user to the current user (such as user A), the same trajectory location that has been visited, the number of times the same trajectory location is visited, and/or the time of visiting the same trajectory location, and the like. The user identifier may include a user name and/or an account number and the like.

The server may also use the information of the user to be recommended as the social information to be recommended, and the server may also filter the information of the user to be recommended as the social information to be recommended, for example, in step 207. The server performs the step of “determining the number of times each candidate user in the candidate user set appears in the track location within a preset period of time”, and then selecting the number of times the predetermined number of times can be selected from the users to be recommended. User information as social information to be recommended.

The preset number of times can be set according to the requirements of the actual application. For example, the specific information may be as follows:

The information of the candidate user whose number is greater than the preset number threshold is determined as the social information to be recommended to make a recommendation to the current user.

For example, the candidate user B includes the candidate user B and the user D to be recommended, and the preset number of times is 5 times. If the user B to be recommended appears in the XX subway station within 10 months, the number of occurrences is 10 The number of times a building is 10 times; the number of times the user D is expected to appear in the XX subway station within one month is 3 times, and the number of occurrences in a certain building is 3 times, because the number of times the user B to be recommended corresponds to a preset number of times The threshold is "5 times". Therefore, the information of the user B to be recommended can be determined as the social information to be recommended, and the user A is recommended, and the user D to be recommended is not recommended.

In addition, the recommended users may be sorted based on the number of times, and the information of the N most recommended users is determined as the social information to be recommended according to the ranking result, so as to recommend to the current user, where N is a positive integer. .

For example, the user to be recommended includes the user B to be recommended, the user C to be recommended, and the candidate user D, and N is 2, and if the user B to be recommended appears in the XX subway station within 10 months, the number of occurrences is 10 The number of times a certain building is 10 times; the number of users to be recommended C appears in the XX subway station within one month, and the number of occurrences in a certain building is 1; the recommended user D appears in the XX within one month. The number of subway stations is 3, and the number of occurrences in a certain building is 3; at this time, these times can be sorted based on the location of the track, such as from large to small: "XX subway station: user B to be recommended >Recommended user D>Recommended user C”, “A certain building: to be recommended user B>To be recommended user D>To be recommended user C”, therefore, the number of users to be recommended B and the user to be recommended D can be more frequently The information is determined to be recommended social information, recommended to user A, and so on.

210. The server sends the social information to be recommended to the terminal A to perform recommendation to the user A.

After receiving the social information to be recommended, the terminal A may display the social information to be recommended on the preset interface. For example, the information about the social information to be recommended is the user B. For example, the user B may be displayed. User identification, gender, age, hobbies, similarity of the movement trajectory of user B and user A, the same trajectory location that has been visited, the number of visits to the same trajectory location, and/or the time of visiting the same trajectory location, and many more.

Other information may also be displayed, such as displaying the moving track to be matched, and displaying the geographic location label of each track location on the moving track to be matched, and the like.

It can be seen that, after acquiring the location change information of the current user, the current trajectory of the current user may be generated according to the location change information, where the trajectory includes multiple trajectory locations, and then, the preset database is selected. a candidate user having a similar moving trajectory with the current user, selecting information of the candidate users that meet the preset conditions at the time and number of times of the trajectory locations as the social information to be recommended, and recommending to the current user; since the scheme is recommended, In addition to the current position as a consideration, it is also possible to compare the movement trajectory and other historical behavior data of these users, such as the time and number of occurrences at these locations, etc., therefore, relative to the present In the case of a single match, a more efficient match can be made, which greatly improves the accuracy of the recommendation and improves the recommendation.

The same as the previous embodiment, the embodiment is similar to the previous embodiment, in which the social information recommendation device is specifically integrated in the server, the current user is the user A, and the terminal where the user A is the terminal A is taken as an example, which is different from the previous embodiment. The trajectory to be matched used in this embodiment is selected from the historical data of the user A. That is, in the flow of the previous embodiment, the steps 201 to 203 may be replaced with the following steps:

The server obtains a plurality of historical movement trajectories of the user A in the past preset time range, and selects a historical movement trajectory whose appearance frequency meets the preset frequency condition from the obtained plurality of historical movement trajectories, as the movement trajectory of the user A to be matched.

The server selects the historical moving track with the highest frequency of occurrence from the obtained plurality of historical moving tracks as the moving track to be matched by the user A.

Alternatively, the server selects, from the obtained plurality of historical movement trajectories, a historical movement trajectory whose appearance frequency exceeds a preset frequency threshold, as a movement trajectory to which the user A is to be matched.

Alternatively, the server selects the top K historical moving trajectories with the highest frequency of occurrence from the obtained plurality of historical moving trajectories as the moving trajectory to be matched by the user A.

Where K is a positive integer, and the specific value may be determined by the actual application requirements, for example, setting K to 2, 3, or 5, and the like.

The preset time range may also be set according to the requirements of the actual application. For example, the preset time range is specifically 1 month, and a historical moving track with the highest frequency of occurrence is selected as an example, if user A is in the past In the month, there are a total of five moving trajectories. Among them, a certain moving trajectory such as "XX subway station -> XX building -> XX park" appears twice, while other historical movement trajectories have only appeared once, then At this time, it can be determined that the movement track "XX subway station -> XX building -> XX park" has the highest frequency of occurrence in the past month, so you can move the trajectory "XX subway station -> XX building -> XX park "As the movement track of user A to be matched.

Since the moving track to be matched is the moving track with the highest frequency of the user A in the past month, it is indicated that the user A is most likely to appear at each place on the moving track, so if a certain time difference is recommended at this time Within the scope of users who are also active near this moving track, especially those who are frequently active in the vicinity, the likelihood that the recommended user will establish a social relationship with User A is greatly increased.

For example, taking the preset time range as one week and selecting the first two historical moving trajectories with the highest frequency of occurrence as an example, if user A has a total of eight moving trajectories in the past week, one of the movements The trajectory such as "XX subway station -> XX Building -> XX Park" appeared three times, and a certain movement track such as "XX subway station -> XX Square -> L Building" appeared twice, while other historical movement trajectories Only once, then, at this time, you can determine the mobile track "XX subway station -> XX Building -> XX Park" and "XX subway station -> XX Square -> L Building" in the past week The first 2 (sorted according to the frequency of occurrence from high to low), so you can move the trajectory "XX subway station -> XX Building -> XX Park" and "XX subway station -> XX Square -> L Building" The movement track of user A to be matched, and subsequent matching and recommendation (ie execution) of the moving track "XX subway station -> XX building -> XX park" and "XX subway station -> XX square -> L building" Steps 204-210).

In order to improve flexibility, in addition to the historical movement trajectory of the user A's historical movement trajectory that meets the preset frequency condition, as the moving trajectory of the user A to be matched, a specific movement trajectory may be specified as User A's moving track to be matched; for example, the server may receive a user-triggered selection instruction, and then select a corresponding moving track as the moving track to be matched according to the selection instruction.

For example, if user A wishes to use the movement track "XX subway station -> XX building -> XX park" as the moving track to be matched, then at this time, user A triggers a selection instruction, and the terminal sends the selection instruction to the server through the terminal. Then, the server acquires the movement track of the "XX subway station -> XX building -> XX park" according to the selection instruction, as the moving track of the user A to be matched.

For another example, if user A wishes to use the movement trajectory during the period from December 12, 2014 to December 14, 2014 as the movement trajectory to be matched, then at this time, user A can trigger the selection instruction through the terminal. Sending the selection instruction to the server, and then obtaining, by the server, the corresponding movement trajectory according to the period indicated in the selection instruction (ie, the movement trajectory between December 12, 2014 and December 14, 2014) User A's movement track to be matched.

It can be seen that, in addition to the beneficial effects that can be achieved by the previous embodiment, the embodiment can further improve the accuracy, recommendation effect, and flexibility of the recommendation.

In order to better implement the above method, the embodiment of the present invention further provides a social information recommendation device, which may be integrated into a server, such as a service server or the like.

For example, as shown in FIG. 3a, the social information recommendation apparatus includes an acquisition unit 301, a screening unit 302, a determination unit 303, and a recommendation unit 304, as follows:

(1) acquisition unit 301;

The obtaining unit 301 is configured to use a moving track to be matched by the current user, where the moving track includes at least two track locations.

The moving track to be matched may be generated in real time, namely:

The acquiring unit 301 is specifically configured to acquire location change information of the current user, and generate a current trajectory of the current user according to the location change information.

For example, the acquiring unit 301 may be specifically configured to sequentially draw the sampling point position according to the sampling point position and the sampling time according to the information of each geographical location information in the position change information, to form the The current user's movement trajectory is then used as the movement trajectory to be matched by the current user, wherein the sampling point position can be used as the trajectory location.

Alternatively, the movement track to be matched can also be specified by the user, namely:

The obtaining unit 301 is specifically configured to receive a selection instruction, and select a corresponding movement trajectory as the movement trajectory to be matched according to the selection instruction.

Alternatively, the moving track to be matched may also be filtered from historical data, namely:

The acquiring unit 301 may be configured to acquire a plurality of historical movement trajectories of the current user in a preset time range, and select a historical movement trajectory whose appearance frequency meets the preset frequency condition from the acquired plurality of historical movement trajectories. The current user's movement trajectory.

The acquiring unit 301 is specifically configured to select, from the acquired plurality of historical moving trajectories, a historical moving trajectory with the highest frequency of occurrence as the moving trajectory to be matched by the current user.

Alternatively, the obtaining unit 301 may be specifically configured to select, from the acquired plurality of historical movement trajectories, a historical movement trajectory whose appearance frequency exceeds a preset frequency threshold as a movement trajectory to be matched by the current user.

Alternatively, the obtaining unit 301 may be specifically configured to select, from the acquired plurality of historical moving trajectories, the top K historical moving trajectories with the highest frequency of occurrence as the moving trajectory to be matched by the current user, where K is a positive integer, specifically The value can be determined by the actual application requirements, for example, setting K to 2, 3 or 5, and so on.

The preset time range may also be set according to the requirements of the actual application, and details are not described herein again.

In order to facilitate subsequent viewing and use, a geographical location label may also be added to each track location on the moving track, and saved to a preset database, that is, as shown in FIG. 3b, the social information recommendation apparatus may further include an adding unit 305 and saving. Unit 306 is as follows:

The adding unit 305 is configured to add a geographical location label to the track location on the generated moving track;

The saving unit 306 is configured to save the moving track after the geographic location tag is added to the preset database.

The geographical location label is mainly used to identify the trajectory location, and may be marked by the most iconic or most well-known place name, building, bus station name or subway station name on the trajectory location, as shown in the previous implementation. For example, it will not be described here.

(2) screening unit 302;

The filtering unit 302 is configured to filter other users having similar movement trajectories with the current user in the preset database according to the movement trajectory to be matched, to obtain a candidate user set;

For example, the screening unit 302 can include an acquisition subunit, an operation subunit, and a screening subunit, as follows:

The acquisition sub-unit is used to obtain the movement track of all users in the preset database.

The operation subunit is configured to cluster the movement trajectory according to the trajectory location on the movement trajectory to be matched and the trajectory location on the movement trajectory of the user acquired in the preset database.

For example, the operation subunit may be specifically configured to obtain a geographical location label of the track location on the moving track to be matched, and obtain a geographical location label of the track location on the moving track of other users in the preset database; The geolocation tag performs a clustering operation on the moving trajectory.

The filtering sub-unit is configured to filter other users having similar moving trajectories with the current user according to the operation result, and obtain a candidate user set.

For example, the screening sub-unit may be specifically configured to determine, according to the operation result, a similarity between a movement trajectory of each user in the preset database and the movement trajectory to be matched, and a user with a similarity higher than a preset threshold as a candidate user. Add to the candidate user set.

In order to improve the effectiveness of the screening result, before the clustering operation, the movement trajectory of the user acquired in the preset database may be preliminarily processed according to a preset rule, and then the operation subunit is based on the movement to be matched. The trajectory location on the trajectory and the trajectory location on the trajectory after the preliminary processing cluster the moving trajectory. That is, the screening unit 302 may further include an initial processing subunit, as follows:

The initial processing sub-unit is configured to perform preliminary processing on the movement track of the user acquired in the preset database according to a preset rule.

At this time, the operation subunit may be specifically configured to perform clustering operation on the movement trajectory according to the trajectory location on the moving trajectory to be matched and the trajectory location on the trajectory after the preliminary processing.

The preset rule may be set according to the requirements of the actual application. For example, the moving track within a certain period may be selected according to actual needs, or the moving track with a higher frequency of the user may be selected (ie, the frequently-traveled route). , etc.; that is:

The initial processing sub-unit may be specifically configured to select, from the movement trajectory of the user acquired in the preset database, a movement trajectory whose trajectory generation time is within a preset period, as a movement trajectory after the preliminary processing.

Alternatively, the initial processing sub-unit may be specifically configured to select, from the movement trajectory of the user acquired in the preset database, the top M movement trajectories with the highest frequency of occurrence of each user as the movement trajectory after the preliminary processing.

Where M is a positive integer, and the specific value may be determined according to the needs of the actual application.

(3) determining unit 303;

The determining unit 303 is configured to determine, from the candidate user set, the user to be recommended according to a preset policy.

The determining unit 303 may be specifically configured to determine time when each candidate user in the candidate user set is located in the track location, and determine, as the user to be recommended, the candidate user that meets the preset time condition at the time (ie, the time determined by the determining unit 303) .

For example, the determining unit 303 may be specifically configured to acquire a time when the current user is located at the track location (ie, a track location on the moving track to be matched); according to the current user located at the track location (ie, the moving track to be matched) The time when the track location is located, and the time when each candidate user is located at the track location (ie, the track location on the moving track to be matched), respectively calculates the time difference between each candidate user and the current user at the same track location; the time difference is less than the pre- The candidate user who sets the time threshold is determined as the user to be recommended.

It should be noted that the time may include a year field, a month field, a day field, a time field, a subfield, and a second field, and the “time difference” in the embodiment of the present invention refers to the difference between the specified fields in the time. The specified field can be set according to the requirements of the actual application. For example, the "time field" and the "subfield" can be used as the specified field, and so on. For details, refer to the foregoing method embodiment, and details are not described herein again.

(4) recommendation unit 304;

The recommendation unit 304 is configured to determine social information to be recommended according to the user to be recommended, and make a recommendation to the current user.

For example, the recommendation unit 304 may be specifically configured to use the information of the user to be recommended as the social information to be recommended.

Alternatively, the recommendation unit 304 may be configured to: after filtering the user to be recommended, use the information of the to-be-recommended user to be recommended as the social information to be recommended.

The screening policy may be determined according to the needs of the actual application. For example, the information of the user to be recommended that has the most “number of occurrences at the track location” may be selected as the social information to be recommended, etc., namely:

The determining unit 303 is further configured to determine, respectively, the number of times each candidate user in the candidate user set appears in the track location within a preset time limit.

Then, the recommendation unit 304 is specifically configured to select information of the user whose number of times meets the preset number of times from the users to be recommended as the social information to be recommended.

For example, the recommendation unit 304 may be specifically configured to select information of the user whose number of times is greater than a preset number of times from the users to be recommended as the social information to be recommended; or

The recommendation unit 304 is specifically configured to perform the ranking of the recommended users based on the number of times, and determine the information of the N recommended users according to the ranking result as the social information to be recommended, where N is a positive integer.

The preset period, the preset number threshold, and the value of N may be set according to actual application requirements, for example, may be set to one month, or one week, and the like.

In the specific implementation, the foregoing units may be implemented as a separate entity, or may be implemented in any combination, and may be implemented as the same or a plurality of entities. For the specific implementation of the foregoing, refer to the foregoing method embodiments, and details are not described herein.

It can be seen that the acquiring unit 301 of the social information recommendation apparatus of the present embodiment can acquire the movement trajectory to be matched by the current user, wherein the movement trajectory includes a plurality of trajectory locations, and then the screening unit 302 filters and presets in the preset database. a candidate user whose current user has a similar movement trajectory, and a candidate user selected by the determining unit 303 from the time of the trajectory location to meet the preset time condition as the user to be recommended, and determining the social information to be recommended according to the user to be recommended, Recommended by the recommendation unit 304 to the current user; since the scheme is recommended, in addition to the current location as a consideration factor, the movement trajectory can be similar, as well as other historical behavior data of the users, such as the appearance time at these locations, etc. It is also considered as one of the factors to be considered. Therefore, it is possible to perform more effective matching than the existing one that only performs a single matching, greatly improving the accuracy of the recommendation, and improving the recommendation effect.

Correspondingly, the embodiment of the present invention further provides a social information recommendation system, which may include any social information recommendation device provided by the embodiment of the present invention, where the social information recommendation device may be specifically integrated in a server. For example, it can be as follows:

a server, configured to acquire a moving track to be matched by the current user, where the moving track includes at least two track locations; and other users having similar moving tracks with the current user are filtered in the preset database according to the moving track to be matched, and the candidate user set is obtained. Determining the user to be recommended from the candidate users according to the preset policy, determining the social information to be recommended according to the user to be recommended, and making recommendations to the current user.

The preset policy can be set according to the requirements of the actual application, for example, as follows:

The server may be specifically configured to determine time when each candidate user in the candidate user set is located at the track location, and determine the candidate user that meets the preset time condition as the user to be recommended.

Among them, there are many ways to filter other users who have similar movement trajectories with the current user, for example, as follows:

The server may specifically acquire a movement trajectory of all users in the preset database, and cluster the movement trajectory according to the trajectory location on the movement trajectory to be matched and the trajectory location on the movement trajectory of the user acquired in the preset database. The operation extracts other users having similar movement trajectories from the current user according to the operation result, and obtains a candidate user set.

In order to improve the effectiveness of the screening result, the trajectory of the user's trajectory acquired in the preset database may be pre-processed according to the preset rule before the clustering operation. For details, refer to the previous embodiment, and details are not described herein. .

The manner in which the server obtains the current trajectory to be matched by the current user may be various, for example, as follows:

The server may be configured to obtain the location change information of the current user, generate a current trajectory of the current user according to the location change information, and use the generated trajectory as the trajectory of the current user to be matched.

Alternatively, the server may be specifically configured to receive a selection instruction, and select a corresponding movement trajectory as the movement trajectory to be matched according to the selection instruction.

Alternatively, the server may be configured to obtain a plurality of historical movement trajectories of the current user within a preset time range, and select a historical movement trajectory whose appearance frequency meets the preset frequency condition from the acquired plurality of historical movement trajectories. The movement track of the current user to be matched.

When the social information to be recommended is determined according to the user to be recommended, the information of the user to be recommended may be directly used as the social information to be recommended, and the information of the user to be recommended may be selected as the information of the user to be recommended. Social information to be recommended, for example, can be as follows:

The server may be specifically configured to determine, respectively, the number of times that each candidate user in the candidate user set appears in the track location within a preset time period, and select, from the users to be recommended, the information of the user that meets the preset number of times as the to-be-recommended Social information.

The preset period can be set according to the requirements of the actual application, and details are not described herein again.

The social information recommendation system may also include other devices, such as a terminal, etc., as follows:

The terminal is configured to receive social information to be recommended sent by the server.

The terminal may be further configured to obtain location change information of the current user, and send the location change information to the server.

For the specific implementation of the foregoing devices, refer to the foregoing embodiments, and details are not described herein again.

The social information recommendation system may include any of the social information recommendation devices provided by the embodiments of the present invention. Therefore, the beneficial effects of any of the social information recommendation devices provided by the embodiments of the present invention may be implemented. The foregoing embodiments are not described herein again.

The embodiment of the present invention further provides a server, as shown in FIG. 4, which shows a schematic structural diagram of a server according to an embodiment of the present invention, specifically:

The server may include one or more processing core processor 401, one or more computer readable storage medium memories 402, power source 403, and input unit 404. It will be understood by those skilled in the art that the server structure illustrated in FIG. 4 does not constitute a limitation to the server, and may include more or less components than those illustrated, or some components may be combined, or different component arrangements. among them:

The processor 401 is the control center of the server, connecting various portions of the entire server using various interfaces and lines, by running or executing software programs and/or modules stored in the memory 402, such as computer readable instructions, and calls stored in The data in the memory 402 performs various functions of the server and processes the data, thereby integrally monitoring the server. The processor 401 may include one or more processing cores; preferably, the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, an application, etc., and performs modulation and demodulation. The processor primarily handles wireless communications. It can be understood that the above modem processor may not be integrated into the processor 401.

The memory 402 can be used to store software programs and modules, and the processor 401 executes various functional applications and data processing by running software programs and modules stored in the memory 402. The memory 402 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application required for at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may be stored according to Data created by the use of the server, etc. Moreover, memory 402 can include high speed random access memory, and can also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, memory 402 can also include a memory controller to provide processor 401 access to memory 402.

The server also includes a power source 403 that supplies power to the various components. Preferably, the power source 403 can be logically coupled to the processor 401 via a power management system to enable management of charging, discharging, and power management functions through the power management system. The power supply 403 may also include any one or more of a DC or AC power source, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like.

The server can also include an input unit 404 that can be used to receive input numeric or character information and to generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function controls.

Although not shown, the server may further include a display unit or the like, and details are not described herein again. Specifically, in this embodiment, the processor 401 in the server loads the executable file corresponding to the process of one or more applications into the memory 402 according to the following instruction, and is stored in the memory by the processor 401. The application in 402, thereby implementing the method illustrated in Figures 1b and 2a above, and the operation of the apparatus illustrated in Figures 3a and 3b, for example:

Obtaining a moving track to be matched by the current user, the moving track includes at least two track locations; and screening other users having similar moving tracks with the current user according to the moving track to be matched, obtaining a candidate user set, according to the preset The policy determines the user to be recommended from the candidate user set. For example, the time when each candidate user in the candidate user set is located at the track location may be determined separately; the candidate user whose time meets the preset time condition is determined as the user to be recommended, and then, according to The recommended user determines the social information to be recommended and makes a recommendation to the current user.

For example, the movement trajectory of all users in the preset database may be acquired, and the movement trajectory is clustered according to the trajectory location on the movement trajectory to be matched and the trajectory location on the movement trajectory of the user acquired in the preset database, According to the operation result, other users having similar movement trajectories with the current user are selected to obtain a candidate user set.

The manner in which the server obtains the current trajectory to be matched by the current user may be various, that is, the processor 401 may also run an application stored in the memory 402 to implement the following functions:

Obtaining the position change information of the current user, generating a movement trajectory of the current user according to the position change information, and using the generated movement trajectory as a movement trajectory to be matched by the current user.

Alternatively, a selection instruction is received, and the corresponding movement trajectory is selected as the movement trajectory to be matched according to the selection instruction.

Or, acquiring a plurality of historical movement trajectories of the current user in the past preset time range, and selecting a historical movement trajectory whose appearance frequency meets the preset frequency condition from the obtained plurality of historical movement trajectories, as the current trajectory to be matched by the current user. .

When the social information to be recommended is determined according to the user to be recommended, the information of the user to be recommended may be directly used as the social information to be recommended, and the information of the user to be recommended may be selected as the information of the user to be recommended. The social information to be recommended, that is, the processor 401 can also run an application stored in the memory 402 to implement the following functions:

The number of times that each candidate user in the candidate user set appears in the track location within a preset time period is determined, and the information of the user whose number of times meets the preset number of times is selected from the users to be recommended as the social information to be recommended.

For the specific implementation of the above operations, refer to the foregoing embodiments, and details are not described herein again.

It can be seen that the server in this embodiment can acquire the moving track to be matched by the current user, where the moving track includes multiple track locations, and then, in the preset database, select candidate users having similar moving tracks with the current user, from which Selecting a candidate user that meets the preset time condition at the time of the track location as the user to be recommended, and determining the social information to be recommended according to the user to be recommended, recommending to the current user; since the solution is recommended, in addition to the current In addition to the location considerations, the similar trajectories of movement, as well as other historical behavioral data of these users, such as the time of appearance at these locations, are also considered as one of the considerations. Therefore, compared with the existing scheme of only performing a single match. In other words, more effective matching can be performed, which greatly improves the accuracy of the recommendation and improves the recommendation effect.

A person skilled in the art may understand that all or part of the various steps of the foregoing embodiments may be performed by a program to instruct related hardware. The program may be stored in a computer readable storage medium, and the storage medium may include: Read Only Memory (ROM), Random Access Memory (RAM), disk or optical disk.

The method, device and system for recommending social information provided by the embodiments of the present invention are described in detail. The principles and implementations of the present invention are described in the specific examples. The description of the above embodiments is only for help. The method of the present invention and its core idea are understood; at the same time, those skilled in the art, according to the idea of the present invention, will have some changes in the specific embodiments and application scopes. It is understood to be a limitation of the invention.

Claims

A social information recommendation method, applied to a social information recommendation device, comprising:

Obtaining a moving track to be matched by the current user, where the moving track includes at least two track locations;

Selecting other users that have a matching moving track with the current user in the preset database according to the moving track to be matched, and obtaining a candidate user set;

Determining a user to be recommended from the candidate users according to a preset policy;

Obtaining social information of the user to be recommended and sending to the current user.
The method according to claim 1, wherein the determining the user to be recommended from the candidate users according to a preset policy comprises:

Determining, respectively, a time when each candidate user in the candidate user set is located at the track location;

The candidate user whose time meets the preset time condition is determined as the user to be recommended.
The method according to claim 2, wherein the determining the candidate user whose time meets the preset time condition as the user to be recommended comprises:

Obtaining a time when the current user is located at the track location, where the time includes a year field, a month field, a day field, a time field, a minute field, and a second field;

Calculating, according to the time when the current user is located at the trajectory location, and the time when each candidate user is located at the trajectory location, calculating a time difference between each candidate user and the current user at the same trajectory location, where the time difference is the difference between the specified fields in the time The specified field includes: at least one of the year field, the month field, the day field, the time field, the minute field, and the second field;

The candidate user whose time difference is less than the preset time threshold is determined as the user to be recommended.
The method according to claim 1, wherein the screening of other users having a matching trajectory with the current user in the preset database according to the movement trajectory to be matched, and obtaining the candidate user set, includes:

Get the movement trajectory of all users in the preset database;

Performing a clustering operation on the moving trajectory according to the trajectory location on the moving trajectory to be matched and the trajectory location on the moving trajectory of the user acquired in the preset database;

According to the operation result, other users having matching movement trajectories with the current user are filtered to obtain a candidate user set.
The method according to claim 4, wherein the trajectory is calculated according to the trajectory location on the trajectory to be matched and the trajectory location on the trajectory of the user acquired in the preset database, including:

Obtaining a geographical location label of the track location on the moving track to be matched, and acquiring a geographical location label of the track location on the moving track of other users in the preset database;

The moving trajectory is clustered according to the obtained geographical location label.
The method according to claim 4, wherein the filtering of other users having a matching trajectory with the current user according to the operation result, and obtaining the candidate user set, includes:

Determining, according to the operation result, a similarity between a movement trajectory of each user in the preset database and the movement trajectory to be matched;

A user whose similarity is higher than a preset threshold is added as a candidate user to the candidate user set.
The method of claim 4, further comprising:

Performing preliminary processing on the movement trajectory of the user acquired from the preset database according to a preset rule;

Performing a clustering operation on the moving trajectory according to the trajectory location on the moving trajectory to be matched and the trajectory location on the moving trajectory of the user acquired in the preset database, including: according to the moving trajectory to be matched The trajectory location and the trajectory location on the trajectory after the initial processing cluster the movement trajectory.
The method according to claim 7, wherein the preliminary processing of the movement trajectory of the user acquired in the preset database according to the preset rule comprises:

Selecting, from the movement trajectory of the user acquired in the preset database, a movement trajectory whose trajectory generation time is within a preset period, as a movement trajectory after preliminary processing; or

From the movement trajectory of the user acquired in the preset database, the top M movement trajectories with the highest frequency of occurrence of each user are selected as the movement trajectory after the preliminary processing, and the M is a positive integer.
The method according to any one of claims 1 to 8, wherein the obtaining a movement trajectory to be matched by the current user comprises:

Obtaining a position change information of the current user, generating a movement trajectory of the current user according to the position change information, and using the generated movement trajectory as a movement trajectory to be matched; or

Receiving a selection instruction, and selecting a corresponding movement trajectory as a movement trajectory to be matched according to the selection instruction; or

Obtaining a plurality of historical movement trajectories of the current user in the past preset time range, and selecting a historical movement trajectory whose appearance frequency meets the preset frequency condition from the obtained plurality of historical movement trajectories, as the movement trajectory of the current user to be matched.
The method according to claim 9, wherein after the generating the current user's movement trajectory according to the position change information, the method further includes:

Add a location tag to the track location on the resulting mobile track;

Save the movement track after adding the location label to the default database.
The method according to any one of claims 1 to 8, further comprising:

Determining, respectively, the number of times each candidate user in the candidate user set appears in the track location within a preset time period;

Acquiring the social information of the user to be recommended, including: selecting, from the users to be recommended, the information of the user whose number of times meets the preset number of times as the social information to be recommended.
The method of claim 11, wherein the information about the user whose number of times the predetermined number of times is satisfied is selected from the users to be recommended as the social information to be recommended, including:

Selecting, from the users to be recommended, the information of the user whose number of times is greater than the preset number of times as the social information to be recommended; or

The recommended users are sorted based on the number of times, and the information of the N recommended users with the highest number of times is determined as the social information to be recommended according to the sorting result.
A social information recommendation apparatus includes: a processor and a memory, the processor executing machine readable instructions in the memory, for

Obtaining a moving track to be matched by the current user, where the moving track includes at least two track locations;

Selecting other users that have a matching moving track with the current user in the preset database according to the moving track to be matched, and obtaining a candidate user set;

Determining a user to be recommended from the candidate users according to a preset policy;

Get social information of the user to be recommended and send it to the current user.
The apparatus of claim 13 wherein said processor further executes machine readable instructions in said memory for

The time when each candidate user in the candidate user set is located at the track location is determined separately, and the candidate user whose time meets the preset time condition is determined as the user to be recommended.
The apparatus of claim 13 wherein said processor further executes machine readable instructions in said memory for

Get the movement trajectory of all users in the preset database;

Performing a clustering operation on the moving trajectory according to the trajectory location on the moving trajectory to be matched and the trajectory location on the moving trajectory of the user acquired in the preset database;

According to the operation result, other users having matching movement trajectories with the current user are filtered to obtain a candidate user set.
A non-volatile storage medium storing one or more programs, the one or more programs comprising: computer readable instructions that, when executed by a computing device, cause the computing device to perform The method of any of claims 1-12.