WO2019000887A1 - 信息推荐方法和装置 - Google Patents

信息推荐方法和装置 Download PDF

Info

Publication number
WO2019000887A1
WO2019000887A1 PCT/CN2017/119939 CN2017119939W WO2019000887A1 WO 2019000887 A1 WO2019000887 A1 WO 2019000887A1 CN 2017119939 W CN2017119939 W CN 2017119939W WO 2019000887 A1 WO2019000887 A1 WO 2019000887A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
time
area
access log
points
Prior art date
Application number
PCT/CN2017/119939
Other languages
English (en)
French (fr)
Inventor
徐江溢
Original Assignee
北京三快在线科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京三快在线科技有限公司 filed Critical 北京三快在线科技有限公司
Priority to JP2019568687A priority Critical patent/JP6987891B2/ja
Priority to US16/622,295 priority patent/US10795957B2/en
Priority to KR1020197036779A priority patent/KR20200006584A/ko
Priority to CA3064137A priority patent/CA3064137A1/en
Priority to EP17915769.8A priority patent/EP3623985A4/en
Publication of WO2019000887A1 publication Critical patent/WO2019000887A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0261—Targeted advertisements based on user location
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0255—Targeted advertisements based on user history
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences

Definitions

  • the present application relates to the field of geographic information technology, and in particular, to an information recommendation method and apparatus.
  • POI Point of Interest
  • GIS Global System for Mobile Communications
  • the APP in the mobile terminal can acquire the current location of the user and recommend the POI near the current location to the user, such as Restaurants, gas stations, supermarkets, etc., bring great convenience to users' lives.
  • the present application has been made in order to provide an information recommendation method and apparatus that overcomes the above problems or at least partially solves the above problems.
  • a method for recommending information including:
  • the interest point information of the current geographic area is recommended to the user.
  • determining the active time range of the user by the following steps:
  • the first density condition includes: the time point set includes an access time that exceeds a first threshold a point and a time interval between each of the two access time points in the set of time points is less than a preset interval;
  • the unfamiliar area of the user is determined by the following steps:
  • the second density condition comprises: using any one of the track point sets A track point whose number of presets in the center of the track point exceeds a second threshold;
  • the method further includes:
  • Collecting a historical access log of the user where the historical access log includes at least a user identifier, an access time, and a location trajectory corresponding to the user access behavior;
  • the active time range and the unfamiliar area of the user are obtained from the server.
  • the method further includes:
  • the current time is within the active time range of the user, and the current geographic area is an unfamiliar area of the user, acquiring a dwell time of the user in the current geographic area; When the time exceeds the preset time threshold, the interest point information of the current geographic area is recommended to the user.
  • an information recommendation apparatus including:
  • a first acquiring module configured to acquire a current time and a current geographic area where the user is located
  • a first recommendation module if the current time is within an active time range of the user, and the current geographic area is an unfamiliar area of the user, recommending the interest of the current geographic area to the user Point information.
  • the device further includes:
  • An active time range determining module configured to determine an active time range of the user
  • the active time range determining module includes:
  • a first obtaining sub-module configured to acquire a historical access log of the user within a preset time period, and extract an access time point corresponding to the historical access log;
  • a first clustering sub-module configured to cluster the extracted access time points to obtain a time point set that satisfies a first density condition; wherein the first density condition includes: the time point set includes The number of access time points exceeding the first threshold and the time interval between each of the two access time points in the set of time points is less than a preset interval;
  • the first statistic sub-module is configured to perform statistics on each of the access time points in the set of time points to determine an active time range of the user.
  • the device further includes:
  • a non-familiar area determining module for determining an unfamiliar area of the user
  • the unfamiliar area determining module includes:
  • a second obtaining sub-module configured to acquire a historical access log of the user within a preset time period, and determine a location trajectory corresponding to the historical access log
  • a second clustering sub-module configured to cluster the determined track points in the position trajectory according to latitude and longitude to obtain a track point set satisfying the second density condition; wherein the second density condition includes: Any track point in the set of track points is a track point where the number of preset coverages exceeds a second threshold;
  • the second statistic sub-module is configured to determine the unfamiliar area of the user according to the latitude and longitude of each track point in the set of track points.
  • the device further includes:
  • a collection module configured to collect a historical access log of the user, where the historical access log includes at least a user identifier, an access time, and a location trajectory corresponding to the user access behavior;
  • An uploading module configured to upload a historical access log of the user to the server, so that the server determines the active time range and the unfamiliar area of the user according to the historical access log; and the second acquiring module uses Acquiring the active time range and the unfamiliar area of the user from the server.
  • the device further includes:
  • a second recommendation module configured to acquire a residence time of the user in the current geographic area if the current time is within an active time range of the user and the current geographic area is an unfamiliar area of the user And if the stay time exceeds a preset time threshold, recommend the interest point information of the current geographic area to the user.
  • a computing device comprising: a memory, a processor, and a program stored on the memory and executable on the processor, the processor implementing the program The steps of the aforementioned information recommendation method.
  • a computer readable storage medium having stored thereon a program, the program being executed by a processor to implement the steps of the aforementioned information recommendation method.
  • the method further determines the current time and the current geographic area of the user. Whether the user has the need for POI information. Specifically, if the current time is within an active time range of the user, and the current geographic area is an unfamiliar area of the user, the user may be considered to have a POI information requirement, in which case The user recommends the POI information of the current geographic area, which not only can accurately deliver the POI information, but also can reduce the waste of network resources and the user's interruption to the irrelevant POI information recommendation.
  • FIG. 1 is a flow chart showing the steps of an information recommendation method according to an embodiment of the present application
  • FIG. 2 is a flow chart showing the steps of determining an active time range of a user according to an embodiment of the present application
  • FIG. 3 is a flow chart showing the steps for determining a non-familiar area of a user according to an embodiment of the present application
  • FIG. 4 is a flow chart showing the steps of an information recommendation method according to another embodiment of the present application.
  • FIG. 5 is a flow chart showing the steps of an information recommendation method according to still another embodiment of the present application.
  • FIG. 6 is a structural block diagram of an information recommendation apparatus according to an embodiment of the present application.
  • FIG. 7 is a structural block diagram of another information recommendation apparatus according to another embodiment of the present application.
  • FIG. 8 is a structural block diagram of an information recommendation apparatus according to still another embodiment of the present application.
  • FIG. 9 is a structural block diagram of an information recommendation apparatus according to still another embodiment of the present application.
  • FIG. 10 shows a block diagram of a computing device 1500 of the present application.
  • the accessed APP when the user accesses the APP in the mobile terminal, the accessed APP can obtain the current location of the user, and recommend POI information near the current location to the user. For example, if the user accesses the catering APP, the catering APP can be sent to the user. Recommend a restaurant within 500 meters of the current location.
  • the existing solution does not consider whether the user currently needs POI information, resulting in waste of network resources caused by transmitting unnecessary POI information, and disturbing users.
  • the current embodiment of the present application determines the current time and the current geographical area where the user is located, if the current time is active in the user. Within the time range, and the current geographic area is the unfamiliar area of the user, the user may be considered to have the requirement of the POI information. In this case, the POI information of the current geographic area is recommended to the user, and the POI information can be realized not only. Accurate delivery, and can reduce the waste of network resources and the interruption of users to irrelevant POI information recommendations.
  • FIG. 1 a flow chart of steps of an information recommendation method according to an embodiment of the present application is shown, which may specifically include the following steps:
  • Step 101 Obtain a current time and a current geographic area where the user is located;
  • Step 102 If the current time is within the active time range of the user, and the current geographic area is an unfamiliar area of the user, recommend the interest point information of the current geographic area to the user.
  • the embodiment of the present application can be applied to a mobile terminal to intelligently recommend POI information to a user through a mobile terminal, thereby saving network resources of the mobile terminal and improving user experience of using the mobile terminal.
  • the mobile terminal may be any mobile terminal such as a smart phone, a tablet computer, or a notebook computer.
  • the embodiment of the present application does not limit the specific mobile terminal.
  • the embodiment of the present application uses a smart phone as an example to describe the information recommendation method, and the information recommendation methods corresponding to other mobile terminals may refer to each other.
  • the active time range may be used to reflect a high frequency time period of the user's access behavior. For example, if the current time acquired by the catering APP is within the active time range of the user, the user may be considered to have a tendency to find a nearby restaurant in the catering APP, that is, the user has the POI information requirement, and the catering APP may recommend the POI information to the user.
  • the recommended POI information may include: restaurant information near the current geographic area where the user is located.
  • the unfamiliar area can be used to reflect the low frequency geographical area of the user activity. If the user is in the unfamiliar area, the user is not familiar with the POI information in the area, and the POI information can be recommended to the user.
  • the embodiment of the present application can determine whether the user has the POI information in the current time and the current geographic area based on the active time range of the user and the unfamiliar area of the user, and can not only accurately recommend the POI information, but also reduce the waste of network resources. And bothering the user.
  • the accessed APP may record the corresponding access information to the access log, where the access information may specifically include: access time and location information ( For example, the latitude and longitude, the street address, and the like, the source APP, or the URL (Uniform Resource Locator) address of the page, etc.
  • the embodiment of the present application may collect the historical access log of the user in the preset time period in advance, and The collected historical access logs are analyzed to obtain the active time range of the user and the unfamiliar area of the user.
  • the historical access log may be from an APP (such as a catering APP) in the mobile terminal, and may also be from multiple APPs in the mobile terminal (such as a catering APP, a navigation APP, a shopping APP, etc.).
  • the application may be from one or more of the plurality of mobile terminals of the user, for example, the user logs in the APP of the plurality of mobile terminals by using the user account, and the embodiment of the present application may collect multiple movements of the user by using the user account.
  • the historical access log of the APP record in the terminal. It can be understood that the specific collection manner of the user's historical access log in the preset time period is not limited in the embodiment of the present application.
  • the preset time period may be a recent period of time, such as the last month, the last three months, or the last six months, etc., it can be understood that the embodiment of the present application does not limit the length of the preset time period.
  • the active time range of the user may be determined by the following steps:
  • Step S11 Obtain a historical access log of the user within a preset time period and extract an access time point corresponding to the historical access log;
  • the historical access log may include an access log generated by the user through any access behavior performed by the mobile terminal, for example, the user accesses the APP, or clicks on the merchant list or the merchant page, or invokes the location service to locate the mobile terminal, or An access log generated by any access behavior such as a reservation or a transaction is generated on the merchant page. It can be understood that the specific content of the historical access log is not limited in the embodiment of the present application.
  • the APP in the mobile terminal can obtain all historical access logs of the user in the most recent month, and filter out historical access logs with access time.
  • Step S12 clustering the extracted access time points to obtain a time point set that satisfies the first density condition; wherein the first density condition may include: the time point set includes the number exceeding the first a time point of access of the threshold and a time interval between each two access time points in the set of time points is less than a preset interval;
  • the embodiment of the present application uses DBScan (Density-Based Spatial Clustering of Applications with Noise) to cluster the access time points.
  • the algorithm utilizes the concept of density-based clustering, requiring that the number of objects (points or other spatial objects) contained in a certain region of the cluster space is not less than a given threshold.
  • the specific clustering algorithm is not limited in the embodiment of the present application.
  • an OPTICS (object sorting) clustering algorithm, a DENCLUE (density distribution function) clustering algorithm, and the like may also be used.
  • the preset interval is 30 seconds and the first threshold is 4, the time point set obtained after the clustering satisfies the first density condition, and the access time point exists within the time interval 30 seconds, and at this 30
  • the number of access time points in the second interval is greater than or equal to 4, and the obtained time point set includes the high frequency time point of the user access behavior, and the high frequency time point can reflect the active access behavior of the user. time.
  • Step S13 Perform statistics on the access time points in the set of time points to determine an active time range of the user.
  • the embodiment of the present application may perform statistics on the access time points in the time point set, and calculate an average value.
  • the average value calculated according to the access time point in the time point set is 12 o'clock on Sunday.
  • the access time of the user is usually not fixed at a specific time point. Therefore, the embodiment of the present application floats the appropriate time period up and down on the basis of the average value to obtain a more realistic active time. range.
  • the access time points in the set of time points are mostly distributed at 11:20 to 13:30 on Sunday, and in combination with the average, it can be determined that the active time range of the user is 11:00 on Sunday.
  • the active time range can reflect the high frequency time period of the user's access behavior. If the current time is within the active time range of the user, the user may be considered to have the need for POI information at the current time.
  • the time period of the above-mentioned floating time may be determined according to the distribution of the access time points, or may be determined according to the actual life experience, which is not limited by the embodiment of the present application.
  • the user typically has access requirements, etc. during the time range from lunch (11 to 13 o'clock) or dinner (17 to 19 o'clock).
  • the calculation when calculating the average value of the access time points in the time point set, the calculation may be performed according to all the access time points in the time point set, or the maximum value and the minimum value may be removed. After the value is calculated, the average value is taken to avoid the influence of individual extreme points on the average value, and the accuracy of the active time range is improved.
  • the specific manner in which the embodiment of the present application calculates the average value of the access time points in the set of time points is not limited.
  • the above-mentioned statistics are used to calculate the access time points in the set of time points, and the active time range of the user is determined as an application example of the present application.
  • the specific manner of performing statistics is not limited. For example, the access time point in the set of time points may be counted by using a standard deviation.
  • the APP may collect the historical access log of the user, and analyze the historical access log of the user to obtain an unfamiliar area of the user, for example, the unfamiliar area may be In addition to areas familiar to the area, the familiar area may include: a work area, a living area, and the like. If the current geographic area in which the user is located is the unfamiliar area of the user, the user is not familiar with the POI in the area, and therefore, the user may be considered to have the POI information requirement at the current time.
  • the unfamiliar area of the user may be determined by the following steps:
  • Step S21 Obtain a historical access log of the user within a preset time period, and determine a location track corresponding to the historical access log.
  • the historical access log may include an access log generated by the user through any access behavior performed by the mobile terminal, for example, the user accesses the APP, or clicks on the merchant list or the merchant page, or invokes the location service to locate the mobile terminal, or An access log generated by any access behavior such as a reservation or a transaction is generated on the merchant page. It can be understood that the specific content of the historical access log is not limited in the embodiment of the present application.
  • the APP in the mobile terminal can obtain all historical access logs of the user in the most recent month, and filter out historical access logs with latitude and longitude information, for example, the access information recorded in a historical access log includes latitude and longitude information, and The latitude and longitude information is: (34.2294710000, 108.9538400000), and according to the latitude and longitude information, the corresponding position can be determined as “SEG Shopping Center”, that is, the user has appeared in the “SEG Shopping Center”.
  • the location trajectory of the user corresponding to the historical access log may be obtained according to all the historical access logs with the latitude and longitude information of the user in the most recent month.
  • Step S22 Perform clustering on the determined track points in the position trajectory according to latitude and longitude to obtain a track point set satisfying the second density condition; wherein the second density condition may include: collecting the track point Any track point in the center of the preset coverage area has a track point whose number exceeds the second threshold;
  • the embodiment of the present application clusters the track points by using a DBScan clustering algorithm. For example, if the preset coverage is centered on any of the track points, the radius is 500 meters, and the second threshold is 50, then the second density is obtained after clustering.
  • the set of trajectory points of the condition there is a trajectory point in the circular coverage with a radius of 500 meters as the center of any trajectory point, and the number of trajectory points is greater than or equal to 50, and the obtained trajectory point set Included is the high-frequency location point of the user activity in the user location track, reflecting the geographical location of the user's frequent activities.
  • the shape of the preset coverage is not limited in the present application, and may be, for example, a rectangular area or the like.
  • Step S23 Determine, according to the latitude and longitude of the track point in the track point set, the unfamiliar area of the user.
  • the embodiment of the present application may perform statistics on the latitude and longitude of the track points in the track point set, calculate an average value, and obtain a familiar area of the user according to the distribution of the track points in the track point set and the common sense of life.
  • the unfamiliar area of the user may be an area other than the familiar area of the user.
  • the specific statistical process and mode are similar to the statistical process of the access time point, and are not described here.
  • the embodiment of the present application acquires a historical access log of the user within a preset time period, and a position track corresponding to the historical access log.
  • the access time corresponding to the historical access log may also be obtained. It is assumed that the track points in the set of track points obtained by the cluster are mostly distributed between 9 and 19 points. According to common sense of life, the time is usually the user's.
  • the track point set may be determined as the working area of the user; if the track points in the track point set are mostly distributed between 19:00 and 8:00, the track point set may be determined as the user's living area.
  • the embodiment of the present application further determines whether the user has the POI information according to the current time and the current geographic area where the user is located. Specifically, If the current time is within the active time range of the user, and the current geographic area is an unfamiliar area of the user, the user may be considered to have a POI information requirement, and in this case, recommend the current to the user.
  • the POI information of the geographic area can not only accurately deliver the POI information, but also reduce the waste of the network resources and the user's interruption to the irrelevant POI information recommendation.
  • the historical access log of the user may be collected by the mobile terminal, and the historical access log is analyzed, and the active time range of the user and the unfamiliar area of the user are obtained.
  • the embodiment of the present application may upload the historical access log of the user collected by the mobile terminal to the server, and the server analyzes and processes the historical access log of the user. Referring to FIG. 4, a flow chart of steps of an information recommendation method according to another embodiment of the present application is shown, which may specifically include the following steps:
  • Step 201 Collect a historical access log of the user, where the historical access log may include at least: a user identifier corresponding to the user access behavior, an access time, and a location trajectory;
  • the APP in the mobile terminal may record the access log of the user, and save the recorded access log locally in the mobile terminal.
  • the user identifier may be a device identifier corresponding to the mobile terminal of the user, or an identifier of the user account of the user, and the specific content of the user identifier is not limited in the embodiment of the present application.
  • Step 202 Upload a historical access log of the user to the server, so that the server obtains an active time range of the user and an unfamiliar area of the user according to the historical access log of the user.
  • the mobile terminal may periodically upload the historical access log of the locally stored user to the server in batches, and the historical access log may include at least: a user identifier corresponding to the user access behavior, an access time, and a location trajectory.
  • the server sorts the historical access logs of the users uploaded by the mobile terminal, filters the error data, and stores them in the server to continuously accumulate the historical access logs of the users.
  • the server analyzes and processes the historical access log of the user in the preset time range, calculates the active time range of the user and the unfamiliar area of the user through the clustering algorithm, and establishes the user identifier of the user and the active time range of the user in the server. And the mapping between the user's unfamiliar areas.
  • Step 203 Obtain, from the server, an active time range of the user corresponding to the user identifier of the user, and an unfamiliar area of the user.
  • the APP in the mobile terminal may acquire the current time and the current geographic area where the user is located, and acquire the active time range of the user corresponding to the user identifier of the user, and the unfamiliar area of the user from the server. .
  • Step 204 determining whether the current time is within the active time range of the user, and if so, executing step 205, otherwise performing step 207;
  • Step 205 determining whether the current geographic area is the non-familiar area of the user, and if so, executing step 206, otherwise performing step 207;
  • Step 206 Recommend, to the user, interest point information of the current geographic area.
  • Step 207 The interest point information of the current geographic area is not recommended to the user.
  • step 204 and step 205 are not limited in the embodiment of the present application, and the two may be executed sequentially, later, or in parallel.
  • the catering app when the user accesses the catering APP in the smartphone, the catering app can acquire the current time and the current geographic area where the user is located, and in addition, the catering app can also send the catering app to the catering review server.
  • the device identifier of the user's smart phone to request the active time range and the familiar area of the user from the catering review server, and the catering review server returns the active time range corresponding to the device identifier of the smart phone of the user after receiving the request of the catering APP Familiar with the area, if the catering APP determines that the current time is within the active time range of the user, and the current geographic area is an unfamiliar area of the user, recommend the restaurant of the current geographic area to the user information.
  • the embodiment of the present application uploads the historical access log of the user collected by the mobile terminal to the server, so that the server analyzes and processes the historical access log of the user, and obtains the active time range of the user and the unfamiliar area of the user, and implements the POI.
  • the accurate delivery of the information can save the storage space of the mobile terminal and reduce the computing burden of the mobile terminal on the basis of reducing the waste of the network resources and the user's interruption.
  • the embodiment of the present application uses a clustering analysis algorithm based on big data to cluster historical access logs of users to ensure the accuracy of clustering results.
  • the method may include the following steps:
  • Step 301 Obtain a current time and a current geographic area where the user is located;
  • Step 302 If the current time is within the active time range of the user, and the current geographic area is an unfamiliar area of the user, and the user stays in the current geographic area exceeds a preset The time threshold is used to recommend the point of interest information of the current geographic area to the user.
  • the embodiment of the present application may also be determined according to the user's stay time in the current geographic area.
  • the dwell time can be used to reflect the user's access tendency. For example, if the user stays in a mall for more than 30 minutes, the user may be considered to have a tendency to consume at the mall, and the merchant information in the mall may be recommended to the user. If the user's stay time in the mall is only 5 minutes, the user may be considered not to have a tendency to consume the mall, and the merchant information in the mall may not be recommended to the user.
  • FIG. 6 a structural block diagram of an information recommendation apparatus according to an embodiment of the present application is shown, which may specifically include the following modules:
  • a first obtaining module 401 configured to acquire a current time and a current geographic area where the user is located;
  • the first recommendation module 402 is configured to: if the current time is within an active time range of the user, and the current geographic area is an unfamiliar area of the user, recommend the current geographic area to the user Interest point information.
  • the apparatus may further include:
  • An active time range determining module 501 configured to determine an active time range of the user
  • the active time range determining module 501 may specifically include:
  • the first obtaining sub-module 5011 is configured to acquire a historical access log of the user within a preset time period and extract an access time point corresponding to the historical access log;
  • a first clustering sub-module 5012 configured to cluster the extracted access time points to obtain a time point set that satisfies a first density condition, where the first density condition includes: the time point set Include an access time point in which the number exceeds a first threshold and a time interval between each two access time points in the set of time points is less than a preset interval;
  • the first statistic sub-module 5013 is configured to perform statistics on each of the access time points in the set of time points to determine an active time range of the user.
  • the device may further include:
  • a non-familiar area determining module 502 configured to determine an unfamiliar area of the user
  • the unfamiliar area determining module 502 may specifically include:
  • the second obtaining sub-module 5021 is configured to acquire a historical access log of the user within a preset time period and determine a location trajectory corresponding to the historical access log;
  • a second clustering sub-module 5022 configured to cluster the determined track points in the position trajectory according to latitude and longitude to obtain a track point set satisfying a second density condition, wherein the second density condition includes : a preset track coverage centered on any track point in the set of track points has a track point whose number exceeds a second threshold;
  • the second statistic sub-module 5023 is configured to determine the unfamiliar area of the user according to the latitude and longitude of each track point in the set of track points.
  • the apparatus may further include:
  • the collecting module 601 is configured to collect a historical access log of the user, where the historical access log includes at least a user identifier, an access time, and a location trajectory corresponding to the user access behavior.
  • the uploading module 602 is configured to upload a historical access log of the user to the server, so that the server determines the active time range and the unfamiliar area of the user according to the historical access log.
  • the second obtaining module 603 is configured to acquire the active time range and the unfamiliar area of the user from the server.
  • FIG. 9 a structural block diagram of an information recommendation apparatus according to an embodiment of the present application is shown, which may specifically include the following modules:
  • a first obtaining module 401 configured to acquire a current time and a current geographic area where the user is located;
  • a second recommendation module 403 configured to: if the current time is within an active time range of the user, and the current geographic area is an unfamiliar area of the user, acquiring the user in the current geographic area a stay time; if the stay time exceeds a preset time threshold, recommend the point of interest information of the current geographic area to the user.
  • An embodiment of the present application provides a computing device, including: a memory, a processor, and a program stored on the memory and executable on the processor, wherein the processor executes the program to implement the methods of FIG. 1 to FIG. 5 The steps of the information recommendation method shown.
  • FIG. 10 a schematic structural diagram of a computing device 1500 of the present application is shown. Specifically, the method may include: at least one processor 1501, a memory 1502, at least one network interface 1504, and a user interface 1503.
  • the various components in computing device 1500 are coupled together by bus system 1505.
  • bus system 1505 is used to implement connection communication between these components.
  • the bus system 1505 includes a power bus, a control bus, and a status signal bus in addition to the data bus.
  • various buses are labeled as bus system 1505 in FIG.
  • the user interface 1503 may include a display, a keyboard, or a pointing device (eg, a mouse, a trackball, a touchpad, or a touch screen).
  • a pointing device eg, a mouse, a trackball, a touchpad, or a touch screen.
  • the memory 1502 in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory.
  • the non-volatile memory may be a read-only memory (ROM), a programmable read only memory (PROM), an erasable programmable read only memory (Erasable PROM, EPROM), or an electric Erase programmable read only memory (EEPROM) or flash memory.
  • the volatile memory can be a Random Access Memory (RAM) that acts as an external cache.
  • RAM Random Access Memory
  • many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (Synchronous DRAM).
  • Memory 1502 of the systems and methods described in this application embodiment is intended to comprise, without being limited to, these and any other suitable types of memory.
  • the memory 1502 stores elements, executable modules or data structures, or a subset thereof, or an extended set thereof: an operating system 15021 and an application 15022.
  • the operating system 15021 includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, for implementing various basic services and processing hardware-based tasks.
  • the application 15022 includes various applications, such as a media player (Media Player), a browser (Bro wser), etc., for implementing various application services.
  • a program implementing the method of the embodiment of the present application may be included in the application 15022.
  • the processor 1501 by calling the program or instruction stored in the memory 1502, specifically, the program or instruction stored in the application 15022, the processor 1501 is configured to acquire the current time and the current geographical area where the user is located; The current time is within the active time range of the user, and the current geographic area is an unfamiliar area of the user, and the interest point information of the current geographic area is recommended to the user.
  • a computer readable storage medium having stored thereon a program, wherein the program is executed by a processor to implement the steps of the information recommendation method shown in FIGS. 1 to 5.
  • the method disclosed in the foregoing embodiment of the present application may be applied to the processor 1501 or implemented by the processor 1501.
  • the processor 1501 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the foregoing method may be completed by an integrated logic circuit of hardware in the processor 1501 or an instruction in a form of software.
  • the processor 1501 may be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or the like. Programmable logic devices, discrete gates or transistor logic devices, discrete hardware components to implement or perform the methods, steps, and logic blocks disclosed in the embodiments of the present application.
  • the general purpose processor may be a microprocessor or may be any conventional processor or the like.
  • the steps of the method disclosed in the embodiments of the present application may be directly implemented by the hardware decoding processor, or may be performed by a combination of hardware and software modules in the decoding processor.
  • the software module can be located in a conventional storage medium such as random access memory, flash memory, read only memory, programmable read only memory or electrically erasable programmable memory, registers, and the like.
  • the storage medium is located in the memory 1502, and the processor 1501 reads the information in the memory 1502 and performs the steps of the above method in combination with its hardware.
  • the embodiments described in the embodiments of the present application can be implemented by hardware, software, firmware, middleware, microcode, or a combination thereof.
  • the processing unit can be implemented in one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSP devices, DSPDs), programmable Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), general purpose processor, controller, microcontroller, microprocessor, other electronics for performing the functions described herein Unit or combination thereof.
  • ASICs application specific integrated circuits
  • DSPs digital signal processors
  • DSP devices digital signal processing devices
  • DSPDs digital signal processing devices
  • PLD programmable Programmable Logic Device
  • FPGA Field Programmable Gate Array
  • the technology described in the embodiments of the present application can be implemented by a module (for example, a procedure, a function, and the like) that performs the functions described in the embodiments of the present application.
  • the software code can be stored in memory and executed by the processor.
  • the memory can be implemented in the processor or external to the processor.
  • the processor 1501 is further configured to determine an active time range of the user by using the following steps:
  • the first density condition includes: the time interval between each access time point in the time point set is less than a preset Interval, and the number of access time points in the set of time points exceeds a first threshold;
  • Statistics are performed on the access time points in the set of time points to obtain an active time range of the user.
  • the processor 1501 is further configured to determine the unfamiliar area of the user by the following steps:
  • the second density condition comprises: using any track point in the track point set as There is a track point whose number exceeds the second threshold in the preset coverage of the center;
  • the unfamiliar area of the user is obtained according to the latitude and longitude of the track point in the set of track points.
  • the processor 1501 is further configured to collect a historical access log of the user, where the historical access log includes at least: a user identifier corresponding to the user access behavior, an access time, and a location trajectory; uploading the historical access log of the user to the server. So that the server obtains the active time range of the user and the unfamiliar area of the user according to the historical access log statistics of the user; and obtains the activity of the user corresponding to the user identifier of the user from the server. The time range and the unfamiliar area of the user.
  • the processor 1501 is further configured to: if the current time is within an active time range of the user, and the current geographic area is an unfamiliar area of the user, and the user is in the current geographic area If the stay time exceeds the preset time threshold, the interest point information of the current geographic area is recommended to the user.
  • the embodiment of the present application further provides a computer readable storage medium, where a program is stored, and when the program is executed by the processor, the following steps are performed: acquiring a current time and a current geographic area where the user is located; Within the active time range of the user, and the current geographic area is an unfamiliar area of the user, the point of interest information of the current geographic area is recommended to the user.
  • modules in the devices of the embodiments can be adaptively changed and placed in one or more devices different from the embodiment.
  • the modules or units or components of the embodiments may be combined into one module or unit or component, and further they may be divided into a plurality of sub-modules or sub-units or sub-components.
  • any combination of the features disclosed in the specification, including the accompanying claims, the abstract and the drawings, and any methods so disclosed, or All processes or units of the device are combined.
  • Each feature disclosed in this specification (including the accompanying claims, the abstract and the drawings) may be replaced by alternative features that provide the same, equivalent or similar purpose.
  • the various component embodiments of the present application can be implemented in hardware, or in a software module running on one or more processors, or in a combination thereof.
  • a microprocessor or digital signal processor may be used in practice to implement some or all of the functionality of some or all of the components of the information recommendation method and apparatus in accordance with embodiments of the present application.
  • the application can also be implemented as a device or device program (eg, a program and program product) for performing some or all of the methods described herein.
  • Such a program implementing the present application may be stored on a computer readable medium or may be in the form of one or more signals. Such signals may be downloaded from an internet platform, provided on a carrier signal, or provided in any other form.

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Remote Sensing (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Marketing (AREA)
  • Game Theory and Decision Science (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Business, Economics & Management (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

本申请提供了一种信息推荐方法和装置，根据一个实施例，所述方法具体包括：获取当前时间及用户所处的当前地理区域；若所述当前时间在所述用户的活跃时间范围内、且所述当前地理区域为所述用户的非熟悉区域，则向所述用户推荐所述当前地理区域的兴趣点信息。本申请实施例不仅可以实现POI信息的准确投放，而且可以减少无关POI信息推荐对网络资源的浪费和对用户的打扰。

Description

信息推荐方法和装置
相关申请的交叉引用
本专利申请要求于2017年6月26日提交的、申请号为201710496441.9、发明名称为“信息推荐方法和装置”的中国专利申请的优先权，该申请的全文以引用的方式并入本文中。
技术领域
本申请涉及地理信息技术领域，特别是涉及一种信息推荐方法和装置。
背景技术
POI(Point of Interest，兴趣点)是地理信息系统中的一个术语，泛指可以抽象为点的地理对象，尤其是一些与人们生活密切相关的地理实体，如学校、银行、餐馆、加油站、医院、超市等。
随着移动终端和通讯技术的迅速发展，用户在使用移动终端中的APP(Application，应用程序)时，移动终端中的APP可以获取用户的当前位置，并向用户推荐当前位置附近的POI，如餐馆、加油站、超市等，为用户的生活带来极大的便利。
现有的POI推荐方法，通常是基于用户的地理位置进行推荐。但是，如果用户在其较为熟悉的区域，如工作单位或者家附近，用户已经对附近的POI很熟悉，或者用户并无消费意愿时，若再向用户进行POI推荐，不仅造成POI信息传输过程中网络资源的浪费，而且给用户带来不必要的打扰。
发明内容
鉴于上述问题，提出了本申请以便提供一种克服上述问题或者至少部分地解决上述问题的一种信息推荐方法和装置。
依据本申请的一个方面，提供了一种信息推荐方法，包括：
获取当前时间及用户所处的当前地理区域；
若所述当前时间在所述用户的活跃时间范围内、且所述当前地理区域为所述用户的非熟悉区域，则向所述用户推荐所述当前地理区域的兴趣点信息。
可选地，通过如下步骤确定所述用户的活跃时间范围：
获取所述用户在预设时间段内的历史访问日志并提取所述历史访问日志对应的访问时间点；
对所提取的所述访问时间点进行聚类，以得到满足第一密度条件的时间点集合，其中，所述第一密度条件包括：所述时间点集合包括个数超过第一阈值的访问时间点且所述时间点集合中每两个访问时间点之间的时间间隔小于预设间隔；
对所述时间点集合中的各所述访问时间点进行统计，以确定所述用户的活跃时间范围。
可选地，通过如下步骤确定所述用户的非熟悉区域：
获取所述用户在预设时间段内的历史访问日志并确定所述历史访问日志对应的位置轨迹；
按照经纬度对所确定的所述位置轨迹中的轨迹点进行聚类，以得到满足第二密度条件的轨迹点集合，其中，所述第二密度条件包括：以所述轨迹点集合中的任一轨迹点为中心的预设覆盖范围内存在个数超过第二阈值的轨迹点；
依据所述轨迹点集合中各所述轨迹点的经纬度，确定所述用户的非熟悉区域。
可选地，所述方法还包括：
收集所述用户的历史访问日志，所述历史访问日志至少包括用户访问行为对应的用户标识、访问时间、以及位置轨迹；
向服务器上传所述用户的历史访问日志，以使所述服务器根据所述历史访问日志确定所述用户的所述活跃时间范围和所述非熟悉区域；
从所述服务器获取所述用户的所述活跃时间范围和所述非熟悉区域。
可选地，所述方法还包括：
若所述当前时间在所述用户的活跃时间范围内、且所述当前地理区域为所述用户的非熟悉区域，则获取所述用户在所述当前地理区域内的停留时间；若所述停留时间超过预设时间阈值，则向所述用户推荐所述当前地理区域的兴趣点信息。
根据本申请的另一方面，提供了一种信息推荐装置，包括：
第一获取模块，用于获取当前时间及用户所处的当前地理区域；
第一推荐模块，用于若所述当前时间在所述用户的活跃时间范围内、且所述当前地理区域为所述用户的非熟悉区域，则向所述用户推荐所述当前地理区域的兴趣点信息。
可选地，所述装置还包括：
活跃时间范围确定模块，用于确定所述用户的活跃时间范围；
所述活跃时间范围确定模块，包括：
第一获取子模块，用于获取所述用户在预设时间段内的历史访问日志并提取所述历史访问日志对应的访问时间点；
第一聚类子模块，用于对所提取的所述访问时间点进行聚类，以得到满足第一密度条件的时间点集合；其中，所述第一密度条件包括：所述时间点集合包括个数超过第一阈值的访问时间点且所述时间点集合中每两个访问时间点之间的时间间隔小于预设间隔；
第一统计子模块，用于对所述时间点集合中的各所述访问时间点进行统计，以确定所述用户的活跃时间范围。
可选地，所述装置还包括：
非熟悉区域确定模块，用于确定所述用户的非熟悉区域；
所述非熟悉区域确定模块，包括：
第二获取子模块，用于获取所述用户在预设时间段内的历史访问日志并确定所述历史访问日志对应的位置轨迹；
第二聚类子模块，用于按照经纬度对所确定的所述位置轨迹中的轨迹点进行聚类，以得到满足第二密度条件的轨迹点集合；其中，所述第二密度条件包括：以所述轨迹点集合中的任一轨迹点为中心的预设覆盖范围内存在个数超过第二阈值的轨迹点；
第二统计子模块，用于依据所述轨迹点集合中各所述轨迹点的经纬度，确定所述用户的非熟悉区域。
可选地，所述装置还包括：
收集模块，用于收集所述用户的历史访问日志，所述历史访问日志至少包括用户访问行为对应的用户标识、访问时间以及位置轨迹；
上传模块，用于向服务器上传所述用户的历史访问日志，以使所述服务器根据所述历史访问日志确定所述用户的所述活跃时间范围和所述非熟悉区域；第二获取模块，用于从所述服务器获取所述用户的所述活跃时间范围和所述非熟悉区域。
可选地，所述装置还包括：
第二推荐模块，用于若所述当前时间在所述用户的活跃时间范围内且所述当前地理区域为所述用户的非熟悉区域则获取所述用户在所述当前地理区域内的停留时间；若所述停留时间超过预设时间阈值，则向所述用户推荐所述当前地理区域的兴趣点信息。
根据本申请的再一方面，提供了一种计算设备，包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的程序，所述处理器执行所述程序时实现前述的信息推荐方法的步骤。
根据本申请的又一方面，提供了一种计算机可读存储介质，其上存储有程序，所述程序被处理器执行时实现前述的信息推荐方法的步骤。
根据本申请实施例提供的一种信息推荐方法和装置，在现有的基于用户的地理位置进行POI信息推荐的基础上，进一步根据获取到的当前时间、以及用户所处的当前地理区域，判断用户是否具有POI信息的需求。具体地，若所述当前时间在所述用户的活跃时间范围内、且所述当前地理区域为所述用户的非熟悉区域，则可以认为所述用户具有POI信息的需求，此种情况下向所述用户推荐当前地理区域的POI信息，不仅可以实现POI信息的准确投放，而且可以减少无关POI信息推荐对网络资源的浪费和对用户的打扰。
上述说明仅是本申请技术方案的概述，为了能够更清楚了解本申请的技术手段，而可依照说明书的内容予以实施，并且为了让本申请的上述和其它目的、特征和优点能够更明显易懂，以下特举本申请的具体实施方式。
附图说明
下文中将结合附图对可选实施方式进行详细描述，本发明的各种其他的优点和益处对于本领域普通技术人员将变得清楚明了。附图仅用于示出可选实施方式的目的，而并不认为是对本申请的限制。而且在整个附图中，用相同的参考符号表示相同的部件。在附图中：
图1示出了本申请一个实施例的一种信息推荐方法的步骤流程图；
图2示出了本申请一个实施例的用于确定用户的活跃时间范围的步骤流程图；
图3示出了本申请一个实施例的用于确定用户的非熟悉区域的步骤流程图；
图4示出了本申请另一个实施例的一种信息推荐方法的步骤流程图；
图5示出了本申请再一个实施例的一种信息推荐方法的步骤流程图；
图6示出了本申请一个实施例的一种信息推荐装置的结构框图；
图7示出了本申请另一个实施例的另一种信息推荐装置的结构框图；
图8示出了本申请又一个实施例的一种信息推荐装置的结构框图；
图9示出了本申请再一个实施例的一种信息推荐装置的结构框图；以及
图10示出了本申请的一种计算设备1500的结构示意图。
具体实施方式
下面将参照附图更详细地描述本公开的示例性实施例。虽然附图中显示了本公开的示例性实施例，然而应当理解，可以以各种形式实现本公开而不应被这里阐述的实施例所限制。相反，提供这些实施例是为了能够更透彻地理解本公开，并且能够将本公开的范围完整的传达给本领域的技术人员。
现有方案中，在用户访问移动终端中的APP时，被访问的APP可以获取用户的当前位置，并且向用户推荐当前位置附近的POI信息，例如，用户访问餐饮APP，则餐饮APP可以向用户推荐距离当前位置500米以内的餐厅。但是现有方案并未考虑用户当前是否需要POI信息，导致传输不必要的POI信息造成网络资源的浪费，以及对用户的打扰。
为了减少传输不必要的POI信息造成的网络资源的浪费，以及对用户的打扰，本申请实施例对当前时间及用户所处的当前地理区域进行判断，若所述当前时间在所述用户的活跃时间范围内、且所述当前地理区域为所述用户的非熟悉区域，则可以认为用户具有POI信息的需求，此种情况下向所述用户推荐当前地理区域的POI信息，不仅可以实现POI信息的准确投放，而且可以减少无关POI信息推荐对网络资源的浪费和对用户的打扰。
参照图1，示出了本申请一个实施例的一种信息推荐方法的步骤流程图，具体可以包括如下步骤：
步骤101、获取当前时间及用户所处的当前地理区域；
步骤102、若所述当前时间在所述用户的活跃时间范围内、且所述当前地理区域为所述用户的非熟悉区域，则向所述用户推荐所述当前地理区域的兴趣点信息。
本申请实施例可适用于移动终端，以通过移动终端向用户智能地推荐POI信息，因此能够节省移动终端的网络资源，且能够提升用户对于移动终端的使用体验。所述移动终端具体可以为智能手机、平板电脑、笔记本电脑等任意移动终端，本申请实施例对于具体的移动终端不加以限制。为便于描述，本申请实施例以智能手机为例对信息推荐方法进行说明，其它移动终端对应的信息推荐方法相互参照即可。
本申请实施例中，活跃时间范围可用于反映用户访问行为的高频时间段。例如，如果餐饮APP获取的当前时间在用户的活跃时间范围内，则可以认为用户具有在餐饮APP中查找附近餐厅的倾向，也即用户具有POI信息的需求，则餐饮APP可以向用户推荐POI信息，如推荐的POI信息可以包括：用户所处当前地理区域附近的餐厅信息。
本申请实施例中，非熟悉区域可用于反映用户活动的低频地理区域，如果用户处于非熟悉区域，则说明用户对该区域中的POI信息不够熟悉，可以向用户推荐POI信息。
本申请实施例可以基于用户的活跃时间范围和用户的非熟悉区域，判断用户在当前时间和当前地理区域是否具有POI信息的需求，不仅可以实现POI信息的准确推荐，并且能够减少网络资源的浪费和对用户的打扰。
在实际应用中，在用户访问移动终端中的APP，如餐饮APP时，被访问的APP可以将对应的访问信息记录至访问日志，其中，所述访问信息具体可以包括：访问时间、位置信息(如经纬度、街道地址等信息)、来源APP、或者页面的URL(Uniform Resource Locator，统一资源定位符)地址等，因此，本申请实施例可以预先收集预设时间段内用户的历史访问日志，并且对收集的历史访问日志进行分析，以得到用户的活跃时间范围和用户的非熟悉区域。
在本申请实施例中，上述历史访问日志不仅可以来自移动终端中的某一个APP(如餐饮APP)，还可以来自移动终端中的多个APP(如餐饮APP、导航APP、购物APP等)。或者，也可以来自用户的多个移动终端中的一个或多个APP，例如，用户通过用户账号登录多个移动终端中的APP，则本申请实施例可以通过用户账号收集该用户的多个移动终端中的APP记录的历史访问日志。可以理解，本申请实施例对于预设时间段内用户的历史访问日志的具体收集方式不加以限制。所述预设时间段可以为近期的一段时间，例如最近一个月、最近三个月、或者最近六个月内等，可以理解，本申请实施例对于预设时间段的长短不加以限制。
如图2所示，在本申请的一种可选实施例中，可以通过如下步骤确定所述用户的活跃时间范围：
步骤S11、获取所述用户在预设时间段内的历史访问日志并提取所述历史访问日志对应的访问时间点；
其中，所述历史访问日志可以包括用户通过移动终端进行的任意访问行为所产生的访问日志，例如：用户访问APP、或者点击商户列表或商户页、或者调用定位服务定位移动终端的位置、或者在商户页上产生预定或交易等任意访问行为所产生的访问日志。可以理解，本申请实施例对于所述历史访问日志的具体内容不加以限制。
具体地，移动终端中的APP可以获取用户最近一个月的所有历史访问日志，并从中筛选出带有访问时间的历史访问日志。
步骤S12、对所提取的所述访问时间点进行聚类，以得到满足第一密度条件的时间点集合；其中，所述第一密度条件可以包括：所述时间点集合包含个数超过第一阈值的访问时间点且所述时间点集合中每两个访问时间点之间的时间间隔小于预设间隔；
可选地，本申请实施例采用DBScan(Density-Based Spatial Clustering of Applications with Noise，基于密度的聚类算法)对所述访问时间点进行聚类。该算法利用基于密度的聚类的概念，要求聚类空间中的一定区域内所包含对象(点或其他空间对象)的数目不小于某一给定阈值。可以理解，本申请实施例对于具体的聚类算法不加以限制，例如还可以采用OPTICS(对象排序识别)聚类算法、DENCLUE(密度分布函数)聚类算法等。
例如，假设所述预设间隔为30秒，第一阈值为4，则聚类后得到的满足第一密度条件的时间点集合中，在时间间隔30秒内存在访问时间点，并且在这30秒的时间间隔内存在的访问时间点的个数大于或等于4，由此得到的时间点集合中包括的是用户访问行为的高频时间点，该高频时间点可以反映用户访问行为的活跃时间。
步骤S13、对所述时间点集合中的访问时间点进行统计，以确定所述用户的活跃时间范围。
具体地，本申请实施例可以对所述时间点集合中的访问时间点进行统计，计算得到平均值，例如，根据所述时间点集合中的访问时间点计算得到平均值为周日12点，由于在实际应用中，用户的访问时间通常不会固定在某一具体时间点，因此，本申请实施例在所述平均值的基础上，上下浮动适当的时间段以得到更加符合实际的活跃时间范围。例如，所述时间点集合中的访问时间点大多分布在周日的11点20分至13点30分，则结合所述平均值，可以确定所述用户的活跃时间范围为周日11点至13点，该活跃时间范围可以反映用户访问行为的高频时间段。如果当前时间在用户的活跃时间范围内，可以认为用户在当前时间具有POI信息的需求。
可以理解，上述浮动的时间段可以根据访问时间点的分布来确定，或者还可以根据实际生活经验来确定，本申请实施例对此不加以限制。例如，对于餐饮APP，用户通常会在午餐(11点至13点)或者晚餐(17点至19点)的时间范围内具有访问需求等。
在本申请实施例中，在计算所述时间点集合中访问时间点的平均值时，可以根据所述时间点集合中所有的访问时间点进行计算，或者，还可以去掉其中的最大值和最小值后再计算平均值，以避免个别的极端点对平均值的影响，提高活跃时间范围的准确性。可以理解，本 申请实施例对于计算所述时间点集合中访问时间点的平均值的具体方式不加以限制。当然，上述通过计算平均值对所述时间点集合中访问时间点进行统计，并且确定用户的活跃时间范围仅作为本申请的一种应用示例，本申请实施例对所述时间点集合中访问时间点进行统计的具体方式不加以限制，例如还可以采用标准差的方式对所述时间点集合中访问时间点进行统计等。
在本申请实施例中，在用户访问移动终端中的APP时，APP可以收集用户的历史访问日志，并且对用户的历史访问日志进行分析，得到用户的非熟悉区域，如该非熟悉区域可以是除了熟悉区域之外的区域，该熟悉区域可以包括：工作区域、居住区域等。如果用户所处的当前地理区域为用户的非熟悉区域，则说明用户对该区域内的POI不够熟悉，因此，可以认为用户在当前时间具有POI信息的需求。
如图3所示，在本申请的一种可选实施例中，可以通过如下步骤确定所述用户的非熟悉区域：
步骤S21、获取所述用户在预设时间段内的历史访问日志并确定所述历史访问日志对应的位置轨迹；
其中，所述历史访问日志可以包括用户通过移动终端进行的任意访问行为所产生的访问日志，例如：用户访问APP、或者点击商户列表或商户页、或者调用定位服务定位移动终端的位置、或者在商户页上产生预定或交易等任意访问行为所产生的访问日志。可以理解，本申请实施例对于所述历史访问日志的具体内容不加以限制。
具体地，移动终端中的APP可以获取用户最近一个月的所有历史访问日志，并从中筛选出带有经纬度信息的历史访问日志，例如，某一历史访问日志中记录的访问信息包括经纬度信息，且该经纬度信息为：(34.2294710000，108.9538400000)，根据该经纬度信息可以确定对应的位置为“赛格购物中心”，也即用户曾经出现在“赛格购物中心”。根据用户最近一个月的所有带有经纬度信息的历史访问日志，可以获取所述历史访问日志对应的用户的位置轨迹。
步骤S22、按照经纬度对所确定的所述位置轨迹中的轨迹点进行聚类，以得到满足第二密度条件的轨迹点集合；其中，所述第二密度条件可以包括：以所述轨迹点集合中的任一轨迹点为中心的预设覆盖范围内存在个数超过第二阈值的轨迹点；
与访问时间点聚类的方式相同，本申请实施例采用DBScan聚类算法对所述轨迹点进行聚类。例如，假设所述预设覆盖范围为所述轨迹点集合中的任一轨迹点为中心，半径为500米 的圆形覆盖范围，第二阈值为50，则聚类后得到的满足第二密度条件的轨迹点集合中，以任一轨迹点为中心，以500米为半径的圆形覆盖范围内均存在轨迹点，且轨迹点的个数大于或等于50个，由此得到的轨迹点集合包括的是用户位置轨迹中用户活动的高频位置点，反映用户经常活动的地理位置。可以理解，本申请对于所述预设覆盖范围的形状不加以限制，例如也可以是矩形区域等。
步骤S23、依据所述轨迹点集合中轨迹点的经纬度，确定所述用户的非熟悉区域。
具体地，本申请实施例可以对所述轨迹点集合中轨迹点的经纬度进行统计，计算得到平均值，并且根据轨迹点集合中轨迹点的分布，以及结合生活常识，可以得到用户的熟悉区域，而用户的非熟悉区域可以为除了用户的熟悉区域之外的区域，具体的统计过程及方式与访问时间点的统计过程类似，此处不再赘述。
可选地，为了使得确定的非熟悉区域更加符合用户的实际生活习惯，本申请实施例在获取所述用户在预设时间段内的历史访问日志、以及所述历史访问日志对应的位置轨迹之外，还可以获取所述历史访问日志对应的访问时间，假设聚类得到的轨迹点集合中的轨迹点大多分布在9点至19点之间，根据生活常识可知，这段时间通常是用户的上班时间，则可以确定该轨迹点集合为用户的工作区域；如果该轨迹点集合中的轨迹点大多分布在19点至8点之间，则可以确定该轨迹点集合为用户的居住区域。
综上，本申请实施例在现有的基于用户的地理位置进行POI信息推荐的基础上，进一步根据当前时间、以及用户所处的当前地理区域，判断用户是否具有POI信息的需求，具体地，若所述当前时间在所述用户的活跃时间范围内、且所述当前地理区域为所述用户的非熟悉区域，则可以认为用户具有POI信息的需求，此种情况下向所述用户推荐当前地理区域的POI信息，不仅可以实现POI信息的准确投放，而且可以减少无关POI信息推荐对网络资源的浪费和对用户的打扰。
在本申请实施例中，可以通过移动终端收集用户的历史访问日志，并且对历史访问日志进行分析，得到用户的活跃时间范围和用户的非熟悉区域。可选地，为了节省移动终端的存储空间以及减轻移动终端的计算负担，本申请实施例可以将移动终端收集的用户的历史访问日志上传至服务器，由服务器对用户的历史访问日志进行分析处理。参照图4，示出了本申请另一个实施例的一种信息推荐方法的步骤流程图，具体可以包括如下步骤：
步骤201、收集用户的历史访问日志，所述历史访问日志至少可以包括：用户访问行为对应的用户标识、访问时间、以及位置轨迹；
在具体应用中，在用户访问移动终端中的APP时，移动终端中的APP可以记录用户的访问日志，并且将记录的访问日志保存在移动终端本地。其中，所述用户标识可以为所述用户的移动终端对应的设备标识，或者所述用户的用户账号等标识信息，本申请实施例对于所述用户标识的具体内容不加以限制。
步骤202、向服务器上传所述用户的历史访问日志，以使所述服务器根据所述用户的历史访问日志得到所述用户的活跃时间范围和所述用户的非熟悉区域；
具体地，移动终端可以定时批量地向服务器上传本地存储的用户的历史访问日志，所述历史访问日志至少可以包括：用户访问行为对应的用户标识、访问时间、以及位置轨迹。
服务器对移动终端上传的用户的历史访问日志进行整理，过滤其中的错误数据后存储在服务器，以对用户的历史访问日志进行不断积累。服务器对预设时间范围内的用户的历史访问日志进行分析处理，通过聚类算法计算得到用户的活跃时间范围以及用户的非熟悉区域，并且在服务器中建立用户的用户标识与用户的活跃时间范围以及用户的非熟悉区域之间的映射关系。
步骤203、从所述服务器获取所述用户的用户标识对应的所述用户的活跃时间范围和所述用户的非熟悉区域；
具体地，移动终端中的APP可以获取当前时间、以及用户所处的当前地理区域，并且从服务器获取所述用户的用户标识对应的所述用户的活跃时间范围、以及所述用户的非熟悉区域。
步骤204、判断当前时间是否在所述用户的活跃时间范围内，若是，则执行步骤205，否则执行步骤207；
步骤205、判断当前地理区域是否为所述用户的非熟悉区域，若是，则执行步骤206，否则执行步骤207；
步骤206、向所述用户推荐所述当前地理区域的兴趣点信息；
步骤207、不向所述用户推荐所述当前地理区域的兴趣点信息。
需要说明的是，本申请实施例对于步骤204和步骤205的执行顺序不加以限制，二者可以先后、后先或者并列执行。
在本申请的一种应用示例中，在用户访问智能手机中的餐饮APP时，该餐饮APP可以获取当前时间和用户所处的当前地理区域，此外，该餐饮APP还可以向餐饮点评服务器发 送该用户的智能手机的设备标识，以向餐饮点评服务器请求该用户的活跃时间范围和熟悉区域，餐饮点评服务器接收到餐饮APP的请求后，返回该用户的智能手机的设备标识对应的活跃时间范围和熟悉区域，如果该餐饮APP判断得知当前时间在所述用户的活跃时间范围内，且所述当前地理区域是所述用户的非熟悉区域，则向所述用户推荐所述当前地理区域的餐厅信息。
综上，本申请实施例将移动终端收集的用户的历史访问日志上传至服务器，以使服务器对用户的历史访问日志进行分析处理，得到用户的活跃时间范围和用户的非熟悉区域，在实现POI信息的准确投放，并且可以在减少无关POI信息推荐对网络资源的浪费和对用户的打扰的基础上，节省移动终端的存储空间以及减轻移动终端的计算负担。此外，本申请实施例采用基于大数据的聚类分析算法对用户的历史访问日志进行聚类，保证聚类结果的精准性。
参照图5，示出了本申请一个实施例的一种信息推荐方法的步骤流程图，具体可以包括如下步骤：
步骤301、获取当前时间及用户所处的当前地理区域；
步骤302、若所述当前时间在所述用户的活跃时间范围内、且所述当前地理区域为所述用户的非熟悉区域、以及所述用户在所述当前地理区域内的停留时间超过预设时间阈值，则向所述用户推荐所述当前地理区域的兴趣点信息。
除了根据用户的活跃时间范围和用户的熟悉区域判断是否向用户推荐POI信息之外，本申请实施例还可以根据用户在当前地理区域内的停留时间来判断。其中，所述停留时间可用于反映用户的访问倾向。例如，如果用户在某商场内的停留时间超过30分钟，可以认为该用户具有在该商场消费的倾向，可以向该用户推荐该商场内的商家信息。如果该用户在该商场内的停留时间仅为5分钟，则可以认为该用户对该商场不具有消费倾向，则可以不向该用户推荐该商场内的商家信息。
需要说明的是，对于方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请实施例并不受所描述的动作顺序的限制，因为依据本申请实施例，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作并不一定是本申请实施例所必须的。
参照图6，示出了本申请一个实施例的一种信息推荐装置的结构框图，具体可以包括如下模块：
第一获取模块401，用于获取当前时间及用户所处的当前地理区域；
第一推荐模块402，用于若所述当前时间在所述用户的活跃时间范围内、且所述当前地理区域为所述用户的非熟悉区域，则向所述用户推荐所述当前地理区域的兴趣点信息。
可选地，如图7所示，所述装置还可以包括：
活跃时间范围确定模块501，用于确定所述用户的活跃时间范围；
所述活跃时间范围确定模块501，具体可以包括：
第一获取子模块5011，用于获取所述用户在预设时间段内的历史访问日志并提取所述历史访问日志对应的访问时间点；
第一聚类子模块5012，用于对所提取的所述访问时间点进行聚类，以得到满足第一密度条件的时间点集合，其中，所述第一密度条件包括：所述时间点集合包括个数超过第一阈值的访问时间点且所述时间点集合中每两个访问时间点之间的时间间隔小于预设间隔；
第一统计子模块5013，用于对所述时间点集合中各所述访问时间点进行统计，以确定所述用户的活跃时间范围。
可选地，所述装置还可以包括：
非熟悉区域确定模块502，用于确定所述用户的非熟悉区域；
所述非熟悉区域确定模块502，具体可以包括：
第二获取子模块5021，用于获取所述用户在预设时间段内的历史访问日志并确定所述历史访问日志对应的位置轨迹；
第二聚类子模块5022，用于按照经纬度对所确定过的所述位置轨迹中的轨迹点进行聚类，以得到满足第二密度条件的轨迹点集合，其中，所述第二密度条件包括：以所述轨迹点集合中的任一轨迹点为中心的预设覆盖范围内存在个数超过第二阈值的轨迹点；
第二统计子模块5023，用于依据所述轨迹点集合中各所述轨迹点的经纬度，确定所述用户的非熟悉区域。
可选地，如图8所示，所述装置还可以包括：
收集模块601，用于收集所述用户的历史访问日志，所述历史访问日志至少包括用户访问行为对应的用户标识、访问时间以及位置轨迹；
上传模块602，用于向服务器上传所述用户的历史访问日志，以使所述服务器根据所 述历史访问日志确定所述用户的所述活跃时间范围和所述非熟悉区域；
第二获取模块603，用于从所述服务器获取所述用户的所述活跃时间范围和所述非熟悉区域。
参照图9，示出了本申请一个实施例的一种信息推荐装置的结构框图，具体可以包括如下模块：
第一获取模块401，用于获取当前时间及用户所处的当前地理区域；
第二推荐模块403，用于若所述当前时间在所述用户的活跃时间范围内、且所述当前地理区域为所述用户的非熟悉区域，则获取所述用户在所述当前地理区域内的停留时间；若所述停留时间超过预设时间阈值，则向所述用户推荐所述当前地理区域的兴趣点信息。
对于图6到图9所示装置实施例而言，由于其与图1至图5所示方法实施例基本相似，所以描述的比较简单，相关之处参见图1至图5所示方法实施例的部分说明即可。
本申请实施例提供了一种计算设备，包括：存储器、处理器及存储在存储器上并可在处理器上运行的程序，其中，所述处理器执行所述程序时实现图1至图5所示的信息推荐方法的步骤。
参照图10，示出了本申请的一种计算设备1500的结构示意图，具体可以包括：至少一个处理器1501、存储器1502、至少一个网络接口1504和用户接口1503。计算设备1500中的各个组件通过总线系统1505耦合在一起。可理解，总线系统1505用于实现这些组件之间的连接通信。总线系统1505除包括数据总线之外，还包括电源总线、控制总线和状态信号总线。但是为了清楚说明起见，在图10中将各种总线都标为总线系统1505。
其中，用户接口1503可以包括显示器、键盘或者点击设备(例如，鼠标、轨迹球(trackball)、触感板或者触摸屏)等。
可以理解，本申请实施例中的存储器1502可以是易失性存储器或非易失性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(Read-Only Memory，ROM)、可编程只读存储器(Programmable ROM，PROM)、可擦除可编程只读存储器(Erasable PROM，EPROM)、电可擦除可编程只读存储器(Electrically EPROM，EEPROM)或闪存。易失性存储器可以是随机存取存储器(Random Access Memory，RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的RAM可用，例如静态随机存取存储器(Static RAM，SRAM)、动态随机存取存储器(Dynamic RAM，DRAM)、同步动态随机存取存储器(Synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(Double Data  Rate SDRAM，DDRSDRAM)、增强型同步动态随机存取存储器(Enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(Synchlink DRAM，SLDRAM)和直接内存总线随机存取存储器(Direct Rambus RAM，DRRAM)。本申请实施例描述的系统和方法的存储器1502旨在包括但不限于这些和任意其它适合类型的存储器。
在一些实施方式中，存储器1502存储了如下的元素，可执行模块或者数据结构，或者它们的子集，或者它们的扩展集：操作系统15021和应用程序15022。
其中，操作系统15021，包含各种系统程序，例如框架层、核心库层、驱动层等，用于实现各种基础业务以及处理基于硬件的任务。应用程序15022，包含各种应用程序，例如媒体播放器(Media Player)、浏览器(Bro wser)等，用于实现各种应用业务。实现本申请实施例方法的程序可以包含在应用程序15022中。
在本申请实施例中，通过调用存储器1502存储的程序或指令，具体的，可以是应用程序15022中存储的程序或指令，处理器1501用于获取当前时间及用户所处的当前地理区域；若所述当前时间在所述用户的活跃时间范围内、且所述当前地理区域为所述用户的非熟悉区域，则向所述用户推荐所述当前地理区域的兴趣点信息。
一种计算机可读存储介质，其上存储有程序，其特征在于，所述程序被处理器执行时实现图1至图5所示的信息推荐方法的步骤。
上述本申请实施例揭示的方法可以应用于处理器1501中，或者由处理器1501实现。处理器1501可能是一种集成电路芯片，具有信号处理能力。在实现过程中，上述方法的各步骤可以通过处理器1501中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器1501可以是通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件，以实现或者执行本申请实施例中公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器1502中，处理器1501读取存储器1502中的信息，结合其硬件完成上述方法的步骤。
可以理解的是，本申请实施例描述的这些实施例可以用硬件、软件、固件、中间件、 微码或其组合来实现。对于硬件实现，处理单元可以实现在一个或多个专用集成电路(Application Specific Integrated Circuit，ASIC)、数字信号处理器(Digital Signal Processor，DSP)、数字信号处理设备(DSP Device，DSPD)、可编程逻辑设备(Programmable Logic Device，PLD)、现场可编程门阵列(Field Programmable Gate Array，FPGA)、通用处理器、控制器、微控制器、微处理器、用于执行本申请所述功能的其它电子单元或其组合中。
对于软件实现，可通过执行本申请实施例中所述功能的模块(例如过程、函数等)来实现本申请实施例中所述的技术。软件代码可存储在存储器中并通过处理器执行。存储器可以在处理器中或在处理器外部实现。
可选地，处理器1501还用于通过如下步骤确定所述用户的活跃时间范围：
获取所述用户在预设时间段内的历史访问日志，以及提取所述历史访问日志对应的访问时间点；
对所述访问时间点进行聚类，以得到满足第一密度条件的时间点集合；其中，所述第一密度条件包括：所述时间点集合中各访问时间点之间的时间间隔小于预设间隔、且所述时间点集合中访问时间点的个数超过第一阈值；
对所述时间点集合中访问时间点进行统计，以得到所述用户的活跃时间范围。
可选地，处理器1501还用于通过如下步骤确定所述用户的非熟悉区域：
获取所述用户在预设时间段内的历史访问日志、以及所述历史访问日志对应的位置轨迹；
按照经纬度对所述位置轨迹中的轨迹点进行聚类，以得到满足第二密度条件的轨迹点集合；其中，所述第二密度条件包括：以所述轨迹点集合中的任一轨迹点为中心的预设覆盖范围内存在个数超过第二阈值的轨迹点；
依据所述轨迹点集合中轨迹点的经纬度，得到所述用户的非熟悉区域。
可选地，处理器1501还用于收集用户的历史访问日志，所述历史访问日志至少包括：用户访问行为对应的用户标识、访问时间、以及位置轨迹；向服务器上传所述用户的历史访问日志，以使所述服务器根据所述用户的历史访问日志统计得到所述用户的活跃时间范围和所述用户的非熟悉区域；从所述服务器获取所述用户的用户标识对应的所述用户的活跃时间范围和所述用户的非熟悉区域。
可选地，处理器1501还用于若所述当前时间在所述用户的活跃时间范围内、且所述 当前地理区域为所述用户的非熟悉区域、以及所述用户在所述当前地理区域内的停留时间超过预设时间阈值，则向所述用户推荐所述当前地理区域的兴趣点信息。
本申请实施例还提供了一种计算机可读存储介质，其上存储有程序，所述程序被处理器执行时实现以下步骤：获取当前时间及用户所处的当前地理区域；若所述当前时间在所述用户的活跃时间范围内、且所述当前地理区域为所述用户的非熟悉区域，则向所述用户推荐所述当前地理区域的兴趣点信息。
在此提供的算法和显示不与任何特定计算机、虚拟系统或者其它设备固有相关。各种通用系统也可以与基于在此的示教一起使用。根据上面的描述，构造这类系统所要求的结构是显而易见的。此外，本申请也不针对任何特定编程语言。应当明白，可以利用各种编程语言实现在此描述的本申请的内容，并且上面对特定语言所做的描述是为了披露本申请的最佳实施方式。
在此处所提供的说明书中，说明了大量具体细节。然而，能够理解，本申请的实施例可以在没有这些具体细节的情况下实践。在一些实例中，并未详细示出公知的方法、结构和技术，以便不模糊对本说明书的理解。
类似地，应当理解，为了精简本公开并帮助理解各个发明方面中的一个或多个，在上面对本申请的示例性实施例的描述中，本申请的各个特征有时被一起分组到单个实施例、图、或者对其的描述中。然而，并不应将该公开的方法解释成反映如下意图：即所要求保护的本申请要求比在每个权利要求中所明确记载的特征更多的特征。更确切地说，如下面的权利要求书所反映的那样，发明方面在于少于前面公开的单个实施例的所有特征。因此，遵循具体实施方式的权利要求书由此明确地并入该具体实施方式，其中每个权利要求本身都作为本申请的单独实施例。
本领域那些技术人员可以理解，可以对实施例中的设备中的模块进行自适应性地改变并且把它们设置在与该实施例不同的一个或多个设备中。可以把实施例中的模块或单元或组件组合成一个模块或单元或组件，以及此外可以把它们分成多个子模块或子单元或子组件。除了这样的特征和/或过程或者单元中的至少一些是相互排斥之外，可以采用任何组合对本说明书(包括伴随的权利要求、摘要和附图)中公开的所有特征以及如此公开的任何方法或者设备的所有过程或单元进行组合。除非另外明确陈述，本说明书(包括伴随的权利要求、摘要和附图)中公开的每个特征可以由提供相同、等同或相似目的的替代特征来代替。
此外，本领域的技术人员能够理解，尽管在此所述的一些实施例包括其它实施例中所 包括的某些特征而不是其它特征，但是不同实施例的特征的组合意味着处于本申请的范围之内并且形成不同的实施例。例如，在下面的权利要求书中，所要求保护的实施例的任意之一都可以以任意的组合方式来使用。
本申请的各个部件实施例可以以硬件实现，或者以在一个或者多个处理器上运行的软件模块实现，或者以它们的组合实现。本领域的技术人员应当理解，可以在实践中使用微处理器或者数字信号处理器(DSP)来实现根据本申请实施例的信息推荐方法和装置中的一些或者全部部件的一些或者全部功能。本申请还可以实现为用于执行这里所描述的方法的一部分或者全部的设备或者装置程序(例如，程序和程序产品)。这样的实现本申请的程序可以存储在计算机可读介质上，或者可以具有一个或者多个信号的形式。这样的信号可以从因特网平台上下载得到，或者在载体信号上提供，或者以任何其他形式提供。
应该注意的是上述实施例对本申请进行说明而不是对本申请进行限制，并且本领域技术人员在不脱离所附权利要求的范围的情况下可设计出替换实施例。在权利要求中，不应将位于括号之间的任何参考符号构造成对权利要求的限制。单词“包括”不排除存在未列在权利要求中的元件或步骤。位于元件之前的单词“一”或“一个”不排除存在多个这样的元件。本申请可以借助于包括有若干不同元件的硬件以及借助于适当编程的计算机来实现。在列举了若干装置的单元权利要求中，这些装置中的若干个可以是通过同一个硬件项来具体体现。单词第一、第二、以及第三等的使用不表示任何顺序。可将这些单词解释为名称。

Claims (12)

  1. 一种信息推荐方法，其特征在于，所述方法包括：
    获取当前时间及用户所处的当前地理区域；
    若所述当前时间在所述用户的活跃时间范围内、且所述当前地理区域为所述用户的非熟悉区域，则向所述用户推荐所述当前地理区域的兴趣点信息。
  2. 根据权利要求1所述的方法，其特征在于，还包括：
    获取所述用户在预设时间段内的历史访问日志；
    提取所述历史访问日志对应的访问时间点；
    对所提取的所述访问时间点进行聚类，以得到满足第一密度条件的时间点集合，其中，所述第一密度条件包括：
    所述时间点集合包括个数超过第一阈值的访问时间点，且
    所述时间点集合中的每两个访问时间点之间的时间间隔小于预设间隔；及
    对所述时间点集合中的各所述访问时间点进行统计，以确定所述用户的活跃时间范围。
  3. 根据权利要求1所述的方法，其特征在于，还包括：
    获取所述用户在预设时间段内的历史访问日志；
    确定所述历史访问日志对应的位置轨迹；
    按照经纬度对所确定的所述位置轨迹中的轨迹点进行聚类，以得到满足第二密度条件的轨迹点集合，其中，所述第二密度条件包括：以所述轨迹点集合中的任一轨迹点为中心的预设覆盖范围内存在个数超过第二阈值的轨迹点；
    依据所述轨迹点集合中各所述轨迹点的经纬度，确定所述用户的非熟悉区域。
  4. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    收集所述用户的历史访问日志，所述历史访问日志至少包括用户访问行为对应的用户标识、访问时间以及位置轨迹；
    向服务器上传所述用户的历史访问日志，以使所述服务器根据所述历史访问日志确定所述用户的所述活跃时间范围和所述非熟悉区域；
    从所述服务器获取所述用户的所述活跃时间范围和所述非熟悉区域。
  5. 根据权利要求1至4中任一所述的方法，其特征在于，若所述当前时间在所述用户的活跃时间范围内、且所述当前地理区域为所述用户的非熟悉区域，则向所述用户推荐所述当前地理区域的兴趣点信息，包括：
    若所述当前时间在所述用户的活跃时间范围内且所述当前地理区域为所述用户的非熟悉区域，则获取所述用户在所述当前地理区域内的停留时间；
    若所述停留时间超过预设时间阈值，则向所述用户推荐所述当前地理区域的兴趣点信息。
  6. 一种信息推荐装置，其特征在于，所述装置包括：
    第一获取模块，用于获取当前时间及用户所处的当前地理区域；
    第一推荐模块，用于若所述当前时间在所述用户的活跃时间范围内、且所述当前地理区域为所述用户的非熟悉区域，则向所述用户推荐所述当前地理区域的兴趣点信息。
  7. 根据权利要求6所述的装置，其特征在于，所述装置还包括：
    活跃时间范围确定模块，用于确定所述用户的活跃时间范围；
    所述活跃时间范围确定模块，包括：
    第一获取子模块，用于获取所述用户在预设时间段内的历史访问日志并提取所述历史访问日志对应的访问时间点；
    第一聚类子模块，用于对所提取的所述访问时间点进行聚类，以得到满足第一密度条件的时间点集合；其中，所述第一密度条件包括：
    所述时间点集合包括个数超过第一阈值的访问时间点，且
    所述时间点集合中的每两个访问时间点之间的时间间隔小于预设间隔；及
    第一统计子模块，用于对所述时间点集合中的各所述访问时间点进行统计，以确定所述用户的活跃时间范围。
  8. 根据权利要求6所述的装置，其特征在于，所述装置还包括：
    非熟悉区域确定模块，用于确定所述用户的非熟悉区域；
    所述非熟悉区域确定模块，包括：
    第二获取子模块，用于获取所述用户在预设时间段内的历史访问日志并确定所述历史访问日志对应的位置轨迹；
    第二聚类子模块，用于按照经纬度对所确定的所述位置轨迹中的轨迹点进行聚类，以得到满足第二密度条件的轨迹点集合，其中，所述第二密度条件包括：以所述轨迹点集合中的任一轨迹点为中心的预设覆盖范围内存在个数超过第二阈值的轨迹点；
    第二统计子模块，用于依据所述轨迹点集合中各所述轨迹点的经纬度，确定所述用户的非熟悉区域。
  9. 根据权利要求6所述的装置，其特征在于，所述装置还包括：
    收集模块，用于收集所述用户的历史访问日志，所述历史访问日志至少包括用户访问行为对应的用户标识、访问时间以及位置轨迹；
    上传模块，用于向服务器上传所述用户的历史访问日志，以使所述服务器根据所述历史访问日志确定所述用户的所述活跃时间范围和所述非熟悉区域；及第二获取模块，用于从所 述服务器获取所述用户的所述活跃时间范围和所述非熟悉区域。
  10. 根据权利要求6至9中任一所述的装置，其特征在于，所述装置还包括：
    第二推荐模块，用于若所述当前时间在所述用户的活跃时间范围内且所述当前地理区域为所述用户的非熟悉区域，则获取所述用户在所述当前地理区域内的停留时间；若所述停留时间超过预设时间阈值，则向所述用户推荐所述当前地理区域的兴趣点信息。
  11. 一种计算设备，包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的程序，其特征在于，所述处理器执行所述程序时实现权利要求1-5中任意一项所述的信息推荐方法的步骤。
  12. 一种计算机可读存储介质，其上存储有程序，其特征在于，所述程序被处理器执行时实现权利要求1-5中任意一项所述的信息推荐方法的步骤。
PCT/CN2017/119939 2017-06-26 2017-12-29 信息推荐方法和装置 WO2019000887A1 (zh)

Priority Applications (5)

Application Number Priority Date Filing Date Title
JP2019568687A JP6987891B2 (ja) 2017-06-26 2017-12-29 情報推薦方法及び装置
US16/622,295 US10795957B2 (en) 2017-06-26 2017-12-29 Information recommending method and device
KR1020197036779A KR20200006584A (ko) 2017-06-26 2017-12-29 정보 추천 방법 및 장치
CA3064137A CA3064137A1 (en) 2017-06-26 2017-12-29 Method and device for recommending information
EP17915769.8A EP3623985A4 (en) 2017-06-26 2017-12-29 INFORMATION RECOMMENDATION PROCESS AND DEVICE

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710496441.9A CN107491474A (zh) 2017-06-26 2017-06-26 信息推荐方法和装置
CN201710496441.9 2017-06-26

Publications (1)

Publication Number Publication Date
WO2019000887A1 true WO2019000887A1 (zh) 2019-01-03

Family

ID=60643675

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/119939 WO2019000887A1 (zh) 2017-06-26 2017-12-29 信息推荐方法和装置

Country Status (7)

Country Link
US (1) US10795957B2 (zh)
EP (1) EP3623985A4 (zh)
JP (1) JP6987891B2 (zh)
KR (1) KR20200006584A (zh)
CN (1) CN107491474A (zh)
CA (1) CA3064137A1 (zh)
WO (1) WO2019000887A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110334167A (zh) * 2019-06-26 2019-10-15 浪潮软件集团有限公司 基于神经网络轨迹的位置偏移预警方法和装置
KR102052452B1 (ko) * 2019-03-26 2019-12-05 민지연 공연 정보 제공 시스템
CN111190940A (zh) * 2019-12-27 2020-05-22 中国平安人寿保险股份有限公司 用户访问的离散数据处理方法、装置、设备及介质
CN113900906A (zh) * 2021-10-28 2022-01-07 北京达佳互联信息技术有限公司 日志容量确定方法、装置、电子设备及存储介质

Families Citing this family (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110392335B (zh) * 2018-04-12 2022-02-11 阿里巴巴集团控股有限公司 计步数据处理方法和设备
CN108960785B (zh) * 2018-07-13 2020-10-27 维沃移动通信有限公司 一种信息提示方法及装置
CN109344339B (zh) * 2018-09-28 2022-03-18 中山乐心电子有限公司 动态活动信息的发布方法、系统和推荐方法
CN109614556B (zh) * 2018-10-31 2020-03-13 拉卡拉支付股份有限公司 访问路径预测、信息推送方法及装置
CN111737602B (zh) * 2020-06-19 2024-06-21 中国银行股份有限公司 银行网点信息推送方法及装置
US11429798B2 (en) * 2020-08-10 2022-08-30 Innolux Corporation Wireless tag location system and method thereof
CN112148808B (zh) * 2020-09-28 2024-02-27 杭州海康威视系统技术有限公司 关系构建方法、装置和电子设备
CN111932350B (zh) * 2020-09-29 2021-02-12 浙江口碑网络技术有限公司 共享数据圈的生成方法及共享数据圈的数据共享方法
CN112560910B (zh) * 2020-12-02 2024-03-01 中国联合网络通信集团有限公司 用户分类方法和装置
CN112464096A (zh) * 2020-12-03 2021-03-09 北京五八信息技术有限公司 一种信息处理方法及装置
CN112559859B (zh) * 2020-12-08 2023-06-30 杭州海康威视系统技术有限公司 资源推荐方法、装置、电子设备及机器可读存储介质
CN112581060A (zh) * 2020-12-22 2021-03-30 北京优挂信息科技有限公司 基于车辆装卸点的配货需求度检测方法、装置及设备
CN112712392B (zh) * 2020-12-31 2024-08-20 京东科技控股股份有限公司 消息推送方法、装置、电子设备及存储介质
CN112991008B (zh) * 2021-03-04 2024-07-16 北京嘀嘀无限科技发展有限公司 一种位置推荐方法、装置及电子设备
CN113312563B (zh) * 2021-06-24 2022-09-16 北京三快在线科技有限公司 信息推荐方法、装置、设备及存储介质
CN113742557A (zh) * 2021-08-10 2021-12-03 北京深演智能科技股份有限公司 推荐应用程序识别规则的方法和装置
CN113407858B (zh) * 2021-08-20 2021-12-21 明品云(北京)数据科技有限公司 信息推送方法、系统、介质和电子设备
CN114359876B (zh) * 2022-03-21 2022-05-31 成都奥伦达科技有限公司 一种车辆目标识别方法及存储介质
US20230311898A1 (en) * 2022-03-30 2023-10-05 Rivian Ip Holdings, Llc Recommending activities for occupants during vehicle servicing
CN115134407B (zh) * 2022-06-27 2024-04-26 平安银行股份有限公司 活跃区域确定方法、装置、计算机设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103905978A (zh) * 2012-12-27 2014-07-02 中国电信股份有限公司 基于位置的信息推送方法、推送装置和网络
CN104102638A (zh) * 2013-04-02 2014-10-15 北京百度网讯科技有限公司 基于位置信息的推送方法、系统和装置
US20150234873A1 (en) * 2009-12-15 2015-08-20 Mapquest, Inc. Computer implemented methods and systems for multi-level geographic query
CN106484848A (zh) * 2016-09-30 2017-03-08 网易传媒科技（北京）有限公司 一种应用推荐方法和设备

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004199667A (ja) * 2002-12-04 2004-07-15 Matsushita Electric Ind Co Ltd 情報提供装置及びその方法
US7856311B2 (en) * 2003-02-19 2010-12-21 Panasonic Corporation Information providing device
CN101263540B (zh) * 2005-09-12 2010-08-04 松下电器产业株式会社 地图显示装置
CN102685662A (zh) 2011-03-17 2012-09-19 高德软件有限公司 基于位置的优惠券管理平台、发布方法、系统及智能终端
US8335524B2 (en) * 2011-04-29 2012-12-18 Navteq B.V. Method and system for providing location targeted advertisements
US9317834B2 (en) 2011-06-30 2016-04-19 Microsoft Technology Licensing, Llc User computing device with personal agent program for recommending meeting a friend at a service location based on current location, travel direction, and calendar activity
EP2541484B1 (en) * 2011-06-30 2023-02-15 Orange Geo-spatial recommendation and discovery system
JP2014192587A (ja) * 2013-03-26 2014-10-06 Zenrin Datacom Co Ltd 情報配信装置、情報配信方法及びプログラム
US20150332325A1 (en) * 2013-04-19 2015-11-19 xAd, Inc. System and Method for Visualizing Real-Time Location-Based Events
CN104636354B (zh) * 2013-11-07 2018-02-06 华为技术有限公司 一种位置兴趣点聚类方法和相关装置
CN104008184A (zh) * 2014-06-10 2014-08-27 百度在线网络技术（北京）有限公司 信息的推送方法和装置
CN105450594A (zh) 2014-08-12 2016-03-30 北京拉手网络技术有限公司 团购券信息推送方法及用户设备
CN104484817B (zh) 2014-12-22 2019-06-21 北京大唐智能卡技术有限公司 一种广告信息处理方法、广告业务服务器及系统
US20160379293A1 (en) * 2015-06-29 2016-12-29 International Business Machines Corporation Application for automatic ordering of food items
CN106528559B (zh) * 2015-09-10 2020-04-24 阿里巴巴集团控股有限公司 一种位置信息的提供方法和设备
CN105490926A (zh) 2015-12-30 2016-04-13 哈尔滨工业大学 一种基于位置服务的用户行为分析和信息推送系统
CN105488233A (zh) * 2016-01-25 2016-04-13 广东顺德中山大学卡内基梅隆大学国际联合研究院 阅读信息推荐方法和系统
US10417691B2 (en) * 2016-10-31 2019-09-17 Walmart Apollo, Llc System, method, and non-transitory computer-readable storage media for automatically checking in a customer

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150234873A1 (en) * 2009-12-15 2015-08-20 Mapquest, Inc. Computer implemented methods and systems for multi-level geographic query
CN103905978A (zh) * 2012-12-27 2014-07-02 中国电信股份有限公司 基于位置的信息推送方法、推送装置和网络
CN104102638A (zh) * 2013-04-02 2014-10-15 北京百度网讯科技有限公司 基于位置信息的推送方法、系统和装置
CN106484848A (zh) * 2016-09-30 2017-03-08 网易传媒科技（北京）有限公司 一种应用推荐方法和设备

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3623985A4

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102052452B1 (ko) * 2019-03-26 2019-12-05 민지연 공연 정보 제공 시스템
CN110334167A (zh) * 2019-06-26 2019-10-15 浪潮软件集团有限公司 基于神经网络轨迹的位置偏移预警方法和装置
CN110334167B (zh) * 2019-06-26 2023-06-09 浪潮软件集团有限公司 基于神经网络轨迹的位置偏移预警方法和装置
CN111190940A (zh) * 2019-12-27 2020-05-22 中国平安人寿保险股份有限公司 用户访问的离散数据处理方法、装置、设备及介质
CN111190940B (zh) * 2019-12-27 2024-04-02 中国平安人寿保险股份有限公司 用户访问的离散数据处理方法、装置、设备及介质
CN113900906A (zh) * 2021-10-28 2022-01-07 北京达佳互联信息技术有限公司 日志容量确定方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
KR20200006584A (ko) 2020-01-20
CN107491474A (zh) 2017-12-19
JP2020523696A (ja) 2020-08-06
US10795957B2 (en) 2020-10-06
US20200104333A1 (en) 2020-04-02
CA3064137A1 (en) 2019-01-03
JP6987891B2 (ja) 2022-01-05
EP3623985A1 (en) 2020-03-18
EP3623985A4 (en) 2020-07-22

Similar Documents

Publication Publication Date Title
WO2019000887A1 (zh) 信息推荐方法和装置
US9483498B2 (en) Apparatus and method for profiling users
US20190028836A1 (en) Determining timing for determination of applicable geo-fences
US20190102798A1 (en) Systems and methods to create a geographic heatmap
JP6074433B2 (ja) 動的デバイス構成のための周期的周囲波形分析
CN107885873B (zh) 用于输出信息的方法和装置
CN105447129B (zh) 个性化内容获取方法、用户属性挖掘方法、系统和装置
WO2021203728A1 (zh) 一种展业区域的选址方法、装置、计算机设备和介质
CN105103185A (zh) 日程偏离通知
CN104166700A (zh) 搜索词推荐方法及装置
CN103631888B (zh) 基于位置的多数据源的数据搜索方法和装置
CN106210163B (zh) 基于ip地址的定位方法及装置
US9009241B2 (en) Determining crowd topics from communications in a focus area
CN108174350B (zh) 一种定位方法和装置
US20120117006A1 (en) Method and apparatus for building a user behavior model
CN105103573A (zh) 图案标记
WO2016094276A1 (en) Lead allocation based on lead attributes for real estate transactions
CN106469205B (zh) 一种确定用户的地理位置信息的方法与装置
CN106937308B (zh) 一种用于确定用户访问服务区域及活动信息的方法与设备
US9565164B2 (en) Techniques to rate-adjust data usage with a virtual private network
CN110784392B (zh) 一种用于获取阅读提醒信息的方法与设备
CN103473290A (zh) Poi的属性数据的处理方法及装置
CN110619087B (zh) 用于处理信息的方法和装置
KR102252084B1 (ko) 블랙보드 기반의 사용자 모델링을 위한 방법, 장치 및 컴퓨터 판독가능 저장 매체
CN110619086A (zh) 用于处理信息的方法和装置

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 3064137

Country of ref document: CA

ENP Entry into the national phase

Ref document number: 20197036779

Country of ref document: KR

Kind code of ref document: A

Ref document number: 2019568687

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2017915769

Country of ref document: EP

Effective date: 20191211

NENP Non-entry into the national phase

Ref country code: DE

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17915769

Country of ref document: EP

Kind code of ref document: A1