WO2018166280A1 - 信息推荐方法、装置、系统及储存介质 - Google Patents

信息推荐方法、装置、系统及储存介质 Download PDF

Info

Publication number
WO2018166280A1
WO2018166280A1 PCT/CN2017/119953 CN2017119953W WO2018166280A1 WO 2018166280 A1 WO2018166280 A1 WO 2018166280A1 CN 2017119953 W CN2017119953 W CN 2017119953W WO 2018166280 A1 WO2018166280 A1 WO 2018166280A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
information
trajectory
matching
location
Prior art date
Application number
PCT/CN2017/119953
Other languages
English (en)
French (fr)
Inventor
田元
Original Assignee
广州市动景计算机科技有限公司
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 广州市动景计算机科技有限公司 filed Critical 广州市动景计算机科技有限公司
Publication of WO2018166280A1 publication Critical patent/WO2018166280A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/55—Push-based network services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/51—Discovery or management thereof, e.g. service location protocol [SLP] or web services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/52—Network services specially adapted for the location of the user terminal
    • 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

Definitions

  • the present invention relates to the field of mobile communication information technologies, and in particular, to an information recommendation method, apparatus, system, and storage medium.
  • LBS Location Based Service acquires location information (geographic coordinates, or geodetic) of a mobile terminal user through a telecommunication mobile operator's radio communication network (such as GSM network, CDMA network) or external positioning method (such as GPS). Coordinates, a value-added service that provides users with corresponding services, supported by the Geographic Information System (GIS) platform.
  • GIS Geographic Information System
  • the recommended information generally includes local information, such as news information, food information, and the like.
  • 1A and 1B show a schematic diagram of presently providing different services to mobile terminal users based on the location of the mobile terminal.
  • the existing location-based recommendation method mainly recommends local news information to the user according to the city where the user is located or selected (Fig. 1A), or according to the geographical location of the user or the geographical location set by the user.
  • Recommend information such as nearby businesses ( Figure 1B) to the user.
  • the recommended information is only pushed according to the user's local area or a single geographic location when recommending information to the user, the recommended information does not accurately meet the potential individual needs of the user.
  • the present application provides an information recommendation method, apparatus, system, and storage medium.
  • the embodiment of the present application provides an information recommendation method, where the method may include: a location acquisition step for acquiring location information of the terminal user; and a trajectory determination step, configured to determine an activity of the terminal user according to the at least two location information. a track; and an information recommendation step for recommending information determined by the activity track to the end user.
  • the acquired activity track contains the user's travel information, and the potential individual needs of the user can be predicted according to the activity track, so that the information determined according to the activity track recommended to the terminal user can accurately meet the user's individual needs.
  • the information recommendation step may include: searching for a trajectory matching user whose activity trajectory is similar to the terminal user; and matching the user to the terminal user according to the trajectory recommendation information.
  • the information recommended to the end user can be determined according to the trajectory matching user, and the range of the recommended information is narrowed to the range related to the trajectory matching user, thereby improving the accuracy of the information recommendation and the personalized service.
  • the matching the user to the end user according to the trajectory matching information may include: calculating a time interval between the trajectory matching user and the terminal user based on the activity trajectory; selecting a time between the appearance time of the at least one location in the active trajectory and the appearance time of the terminal user The trajectory with the interval smaller than the first threshold matches the user; and the user is recommended to the end user according to the selected trajectory.
  • the trajectory close to the appearance time of the at least one location in the active trajectory of the end user can be matched to the user as a reference user with higher similarity with the end user, so that the information recommended by the reference user to the end user can be more Accurately meet the potential individual needs of end users.
  • the matching the user to the end user according to the trajectory matching information may include: calculating the number of occurrences of the trajectory matching user and the end user in at least one location in the active trajectory within a predetermined time period; selecting the number of occurrences at the same place as the end user is higher than The trajectory of the second threshold matches the user; and the user is recommended to the end user according to the selected trajectory.
  • the recommendation information may include at least one of the following: the trajectory matches the user; the trajectory matches the location where the user appears or is recommended on the matched active trajectory; and the trajectory matches the content viewed by the user.
  • various types of recommendation information can be provided to the end user.
  • the location obtaining step includes: continuously obtaining the location location of the end user's trajectory; and/or obtaining the check-in location actively submitted by the terminal user. Thereby, the location information of the terminal user can be obtained in various ways.
  • the trajectory determining step may include: matching the location tag according to the trajectory location and/or the at least two check-in locations; and determining the activity trajectory according to the location tag.
  • the embodiment of the present application further provides an information recommendation apparatus, where the apparatus may include: a location acquisition unit, configured to acquire location information of the terminal user; and a trajectory determination unit, configured to determine the terminal according to the at least two location information. a user activity track; and an information recommendation unit for recommending information determined by the activity track to the terminal user.
  • the information recommendation apparatus provided by the embodiment of the present application can accurately and personally determine the information content recommended to the terminal user, thereby improving the user experience.
  • the embodiment of the present application further provides a terminal device, where the terminal device includes: one or more processors; a memory; one or more applications, where the one or more applications are stored in The memory is configured to be executed by the one or more processors, the one or more programs configured to perform the above method.
  • the embodiment of the present application further provides an information recommendation system, including at least one server and multiple terminal users, where multiple terminal users actively or passively upload location information, and the at least one server is configured to: acquire multiple terminals. Position information of the user; determining an activity track of the terminal user according to the at least two pieces of location information; and recommending information determined according to the activity track to the terminal user.
  • an information recommendation system including at least one server and multiple terminal users, where multiple terminal users actively or passively upload location information, and the at least one server is configured to: acquire multiple terminals. Position information of the user; determining an activity track of the terminal user according to the at least two pieces of location information; and recommending information determined according to the activity track to the terminal user.
  • an embodiment of the present application further provides a computer readable storage medium carrying one or more computer instruction programs, where the computer instruction program is executed by one or more processors, the one or more The processors perform the above methods.
  • the information recommendation method, device, system and storage medium provided by the embodiments of the present application determine the activity trajectory of the travel information including the user, so that the potential personalization requirement of the user can be predicted according to the activity trajectory, thereby recommending the basis to the end user.
  • the information determined by the activity track can accurately meet the potential individual needs of the end user.
  • Figures 1A and 1B show an existing information recommendation scheme.
  • FIG. 2 is a block diagram showing a system for implementing an embodiment of the present application.
  • FIG. 3 shows a schematic flowchart of an information recommendation method according to an embodiment of the present application.
  • FIG. 4 shows a flow chart of sub-steps of the information recommendation step according to an embodiment of the present application.
  • FIG. 5 shows a flow chart of sub-steps of the information recommendation step according to another embodiment of the present application.
  • FIG. 6 shows a schematic block diagram of an information recommendation apparatus according to an embodiment of the present application.
  • Fig. 7 shows an application example according to the present application.
  • Fig. 8 is a view showing the effect of the application example of Fig. 7.
  • FIG. 9 is a schematic structural diagram of a terminal device according to an embodiment of the present application.
  • the embodiment of the present application provides an information recommendation method and apparatus, which can be based on the acquired or determined user activity track. Accurately recommend appropriate information to end users.
  • Embodiments of the present application will be specifically described below with reference to FIGS. 2 through 6. Description will first be made in conjunction with the system block diagram 2 for implementing the embodiments of the present application.
  • the system includes at least one server 20 and a plurality of terminal devices 10.
  • the terminal device 10 can implement information transceiving with the server 20 via the network 40.
  • the server 20 can acquire the content required by the terminal device 10 by accessing the database 30.
  • Mobile terminals (e.g., between 10_1 and 10_2 or 10_N) may also communicate with each other via the network 40.
  • Network 40 may be a network for information transfer in a broad sense, and may include one or more communication networks, such as a wireless communication network, the Internet, a private area network, a local area network, a metropolitan area network, a wide area network, or a cellular data network.
  • network 40 may also include a satellite network, thereby transmitting GPS signals of terminal device 10 to server 20.
  • a two-way arrow from the database 30 to the server 20 is shown in the figure for convenience of explanation, those skilled in the art can understand that the above-mentioned data can also be transmitted and received through the network 40.
  • Terminal device 10 is any suitable portable electronic device that can be used for network access, including but not limited to a smart phone, tablet or other portable client.
  • Server 20 is any server that is accessible over the network to provide the information needed for the interactive service.
  • a plurality of terminal devices 10-1...N and a single server 20 and database 30 are shown in the figure, one or a part of the mobile terminals will be described in the following description (for example, the terminal device 10-1), However, it should be understood by those skilled in the art that the above 1...N mobile terminals are intended to represent a large number of mobile terminals existing in a real network, and the illustrated single server 20 and database 30 are intended to indicate that the technical solution of the application relates to a server and a database. Operation.
  • the specific numbered mobile end and the individual servers and databases are detailed for at least convenience of explanation, and do not imply restrictions on the type or location of the mobile end and the server.
  • the trajectory acquisition of the "terminal device” rather than the "end user” is actually involved, since the system is via the terminal device held by the user (such as The smart phone (such as a smart phone) actively or passively uploads the geographical location information to know the user information, so here the geographic location or activity track of the terminal device held by the user can be equated with the "end user” geography described herein. Location or activity track.
  • the server 20 can acquire geographic location information or trajectory information of a plurality of terminal devices (or terminal users) 10, and can recommend information to the terminal users more accurately based on the trajectory information of each terminal user. Specifically, the server 20 can execute the information recommendation method shown in FIG. FIG. 3 shows a schematic flowchart of an information recommendation method according to an embodiment of the present application.
  • step S310 location information of the terminal user is acquired.
  • the location information may be obtained by geographical location of the terminal device, for example, GPS latitude and longitude information uploaded by the user's smartphone, or may be actively uploaded by the terminal user, such as location check-in information, or determined by other means.
  • the location of the track location of the end user can be continuously obtained.
  • a GPS positioning method may be used to record a trajectory (motion trajectory) of a location where a user is located within a certain period of time (for example, from a current time to a previous time), forming a record of the user's activity track. Since the recording of such trajectories is actually uploaded and connected by location and time association (i.e., by points and lines), it can also be regarded as a (continuous) acquisition of the location of the end user.
  • the activity track can be recorded in the form of a table or the like.
  • the LBS check-in method can also be used to obtain the check-in location submitted by the terminal user.
  • a check-in is an operation in which a user informs another person or service provider of his or her specific location through a location service.
  • the terminal user inputs or selects a geographical location at the terminal, and the server determines the location information of the terminal user according to the input or selection of the terminal user.
  • the time point at which the terminal user appears at the corresponding location, and/or the length of time to stay at the location, or other related information may be acquired, so as to accurately obtain the terminal.
  • User's behavior or activity may also be maintained to store different geographical location information and related information of different end users.
  • an activity trajectory of the terminal user is determined based on the at least two pieces of location information.
  • the location information acquired in step S310 is the trajectory information (i.e., the continuously recorded location and associated time information)
  • the activity trajectory of the terminal user can be directly determined for this.
  • step S310 by associating the location of the terminal user acquired in step S310 within a certain period of time and related information, the trajectory of the location change of the terminal user is drawn according to the time trend, and the terminal user is further determined to be in a certain period of time. Activity track within.
  • trajectory information and the location information acquired in step S310 may be summarized to determine an activity trajectory of the end user in a larger range that combines the previously acquired trajectory information and location information.
  • the location information may be location coordinate information, and in real life, there may be multiple location coordinates corresponding to the same region (for example, Oriental Xintiandi Mall), and it is difficult to intuitively determine the location coordinate information determined only by latitude and longitude.
  • the similarity of the user activity track therefore, the acquired location information of the terminal user can be further processed.
  • the location tags e.g., different merchant tags in the Oriental Xintiandi mall
  • the activity track is determined based on the location tag.
  • the location tag may be a location corresponding to the location coordinate information, for example, a subway station, a shopping mall, an office building, or the like, or other location identifier.
  • the location and activity trajectory of the end user are determined by matching the location coordinates of the acquired location coordinate information with the corresponding location tag. For example, coordinates (113.34638, 23.11741), (113.34758, 23.11971), match a city subway station. Thereby, the place where the end user appears is obtained, and the activity track of the more intuitive end user is obtained.
  • step S330 information determined based on the activity trajectory is recommended to the end user.
  • the trajectory matching user whose activity track is similar to the terminal user can be found, and the user is recommended to the end user according to the trajectory matching information.
  • the end user's preferences can be guessed based on the similarity of the user's activity trajectory.
  • an existing clustering algorithm or the like may be used to find all other end users similar to the end user activity trajectory according to all the location tags based on the geographic location information on the activity track of the end user, as the trajectory matching user.
  • the similarity of the activity track may refer to a location tag having one or more coincidence (or the same) in the activity track of the user and the end user.
  • the trajectory matching users with higher trajectory location similarity are selected, and these users are included in the first set.
  • the level of similarity can be determined by the number of coincident (ie, identical) location tags in the active trajectories of the two. That is, the more coincidence locations, the higher the similarity.
  • the information is accurately and personalizedly recommended to the terminal user, thereby improving the user experience.
  • the recommendation information determined according to the above method is numerous and uneven. Therefore, in order to improve the accuracy of information recommendation, it may be further defined to select a preferred recommended user from the trajectory matching users with high similarity.
  • the following is a detailed description of the specific process of matching the user to the end user according to the trajectory in the information recommendation method of the present application.
  • the trajectory matching user may be further screened based on the trajectory matching user and the end user based on the time interval of the active trajectory.
  • FIG. 4 shows a flow chart of sub-steps of the information recommendation step 330 in accordance with an embodiment of the present application.
  • step S431 the time interval between the trajectory matching user and the end user based on the active trajectory is calculated.
  • the trajectory matching user may be derived from the first set of trajectories that match the trajectory sought in accordance with the method illustrated in FIG.
  • the trajectory matching user is selected in order from high to low, respectively, and the time when each trajectory matching user appears in each of the coincident place labels of the respective end users and the end user appearing at the place label are respectively calculated.
  • the time interval between the time, and the calculated time interval is associated with the corresponding end user related information (such as the end user ID, the track matching user ID, the number of similar tags, the coincident label, etc.) shown in Table 1 .
  • step S432 a trajectory matching user whose time interval between the occurrence time of at least one of the active trajectories and the appearance time of the end user is less than the first threshold is selected.
  • the time interval here may be an absolute time interval, that is, the end user and the matching user all come to a certain place at a certain time on a certain day of the month.
  • the time interval may also be a relative time interval, for example, taking a subway from station A to station B at a certain time of the working day. Or you will go to the National Art Museum on a rest day at a certain frequency. Since it is intended to filter the trajectory matching user whose behavior pattern is similar to the target end user, and the relative time interval is more able to judge the user's behavior pattern, the relative time interval is preferred here, and the mixture of absolute time interval and relative time interval may also be used to determine. mode.
  • the "first threshold” herein may be a fixed value, such as 10 minutes, 1 hour, one week, etc., or may be a fixed time, such as 8:00 am to 8:10 am on the working day, and may also match the user according to the trajectory. The degree of similarity of the end users is adjusted.
  • the time interval at which the trajectory matching user acquired in step S431 and the terminal user appear at the same place is compared with the first threshold according to the level of similarity, and the trajectory matching user smaller than the first threshold is selected as the preferred recommended user.
  • the track with the shortest time interval can be preferentially recommended to match the user.
  • step S433 the user is recommended to recommend information to the end user according to the selected trajectory.
  • the recommendation information may include a recommended trajectory matching user, a trajectory matching user appearing on a matching active trajectory or a recommended location, a trajectory matching content viewed by the user, and the like. For example, if the time interval in which users A and B appear at the same place is less than T 1 , then B is recommended to A. For another example, it is recommended to A to pass the route from the subway station to the e subway station between 8 am and 8:10 am on weekdays.
  • the preferred recommended user is selected from the trajectory matching users with high similarity of the activity trajectory of the terminal user, and the recommendation information is personalized to the end user, thereby improving the accuracy of the recommendation information.
  • FIG. 5 shows a flow chart of sub-steps of the information recommendation step 330 in accordance with another embodiment of the present application.
  • step S531 the number of occurrences of the trajectory matching user and the end user in at least one of the active trajectories in the predetermined time period is calculated.
  • the predetermined time period may be a preset fixed time period, such as a 24-hour, one-week, one-month, or other time period value, or may be adjusted according to the trajectory matching degree of the user and the end user's trajectory.
  • the trajectory matching user here can also be derived from the first set. According to the similarity between the trajectory matching user and the end user, the trajectory matching user is selected in order from high to low, and the number of occurrences of each trajectory matching user and the end user in each coincident place label is calculated, and the calculated occurrence times are respectively corresponding
  • the related information of the end user such as the information shown in Table 1) and the like are associated.
  • step S532 the trajectory matching the user whose number of occurrences at the same place as the terminal user is higher than the second threshold is selected to match the user.
  • the second threshold may be a fixed value, or may be adjusted according to the degree of similarity between the trajectory matching user and the end user.
  • the number of occurrences of the trajectory matching user acquired by the user and the terminal user at the same place is compared with a second threshold according to the level of similarity, and the number of occurrences higher than the second threshold is selected from the selection, and the number of occurrences is associated with the number of occurrences.
  • the trajectory matches the user as the preferred recommended user. Among them, it is also possible to sort the recommended users according to the number of occurrences, and provide more recommended choices for the end users. Among them, in the case that the similarity is high, the trajectory matching user with the most occurrences can be preferentially recommended.
  • step S533 the user is recommended to recommend information to the end user according to the selected trajectory.
  • the recommendation information may include a recommended trajectory matching user, a trajectory matching user appearing on a matching active trajectory or a recommended location, a trajectory matching content viewed by the user, and the like. For example, if users A and C appear more frequently in the same place, C is recommended to A. For another example, user A has visited a coffee shop corresponding to the location f tag five times in the past week, and recommends user C who has also visited the coffee shop three times.
  • the preferred recommended user may also be selected from the trajectory matching users with high similarity to the activity trajectory of the terminal user, and the recommendation information is personalized to the terminal user, and the accuracy of the information recommendation is improved.
  • the recommendation information may include a trajectory matching user, for example, recommending a trajectory matching user to the end user in the form of recommending “nearby people”, so that the end user can recognize new friends who are like-minded; or the trajectory matching user may appear on the matching activity trajectory.
  • recommended locations for example, the trajectory matches restaurants, theaters, etc. that the user has appeared or recommended; and may include trajectories that match what the user has viewed, such as local information, news, and the like. It should be understood that the foregoing examples are illustrative and are not intended to limit the embodiments of the present application. The embodiments of the present application may also recommend other forms of information content to the end user.
  • the content tag may be added to the recommendation information according to the content or the title of the information.
  • the content label of “Guangzhou Provident Fund Policy” is “Guangzhou”
  • the content label of “Golden Horse Award Double Egg” is “Star” and so on.
  • the priority level can be set according to the specific recommendation information content or the content tag.
  • the local content may be set to have a higher priority than the non-local content.
  • the recommendation information whose content tag is “Guangzhou” has higher priority than the recommendation information whose content tag is “star”, so that the terminal user has priority to know the geographical location of the content. Location local information.
  • the information recommendation method of the embodiment of the present application has been described in detail with reference to FIGS. 3 to 5.
  • the trajectory matching user similar to the activity track of the terminal user is calculated, and the user is accurately and personalizedly recommended to the terminal user according to the selected trajectory, thereby improving the user experience.
  • An embodiment of the present application further provides an information recommendation method, the method includes: acquiring location information of an end user; determining an activity track of the terminal user according to at least two location information; and recommending, according to the activity track, the terminal user The information determined.
  • the recommending, by the end user, the information determined according to the activity trajectory includes: searching for a trajectory matching user whose activity trajectory is similar to the terminal user; and matching the user to recommend information to the terminal user according to the trajectory.
  • the recommending, to the end user, information determined according to the activity track includes:
  • the matching the user to recommend the information to the terminal user according to the trajectory comprises: recommending, to the terminal user, the trajectory to match information information browsed within a preset time range of the user.
  • the method further includes: displaying, according to a preset rule, the identification information of the plurality of trajectory matching users respectively;
  • the identifier information is triggered, the trajectory corresponding to the identifier information is recommended to the terminal user to match the information information that has been browsed in the preset time range of the user, and the information information includes: a content title, a content summary, and a content-related image.
  • the information information includes: a content title, a content summary, and a content-related image.
  • the displaying, by the preset rules, the identification information of the plurality of the trajectory matching users includes: displaying an electronic map according to the location information of the terminal user; and displaying the electronic map on the electronic map On the interface, the trajectory is displayed to match the identification information of the user, where the identifier information is located at a position where the trajectory matches the user's presence or recommendation on the matched active trajectory; wherein the identification information includes image information, image information, One or more of the text messages.
  • the method further includes: when the identifier information is triggered, displaying a trajectory corresponding to the identifier information to match matching information between the user and the terminal user, and the identifier The trajectory corresponding to the information matches the link information of the user history browsing information.
  • the method further includes: when the identification information is triggered, the display manner of the triggered identification information is changed, so that the triggered identification information is different from The identification information that is not triggered.
  • FIG. 6 is a block diagram showing the structure of an information recommendation apparatus according to an embodiment of the present application.
  • the functional modules of the information recommendation device 600 may be implemented by hardware, software, or a combination of hardware and software that implements the principles of the embodiments of the present application.
  • Those skilled in the art can understand that the functional modules described in FIG. 6 can be combined or divided into sub-modules to implement the principles of the above invention. Accordingly, the description herein may support any possible combination, or division, or further limitation of the functional modules described herein.
  • the information recommendation device 600 shown in FIG. 6 can be used to implement the information recommendation method shown in FIG. 3-5.
  • the function modules that the information recommendation device 600 can have and the operations that can be performed by the function modules are briefly described.
  • the information recommendation apparatus 600 of the embodiment of the present application may include a location acquisition unit 610, a trajectory determination unit 620, and an information recommendation unit 630.
  • the location obtaining unit 610 can be configured to acquire location information of the terminal user.
  • the trajectory determining unit 620 can be configured to determine an activity trajectory of the terminal user according to the at least two pieces of location information.
  • the information recommendation unit 630 can be used to recommend information determined according to the activity trajectory to the end user.
  • the information recommendation device 600 may further include a matching user finding unit 640.
  • the matching user searching unit 640 is configured to find a trajectory matching user whose active trajectory is similar to the terminal user, and the information recommending unit 630 matches the user to recommend information to the terminal user according to the trajectory.
  • the information recommendation device 600 may further include a time interval/occurrence count calculation unit 650 and a matching user screening unit 660.
  • the time interval calculation unit 650 can be used to calculate a time interval between the trajectory matching user and the end user based on the active trajectory.
  • the matching user screening unit 660 may be configured to select a trajectory matching user whose time interval between the occurrence time of the at least one location in the active trajectory and the appearance time of the terminal user is less than the first threshold, and the information recommendation unit matches the user according to the selected trajectory Recommend information to end users.
  • the number of occurrences calculation unit 650 may be configured to calculate the number of occurrences of the trajectory matching user and the end user in at least one of the active trajectories within the predetermined time period.
  • the matching user screening unit 660 can be configured to select a trajectory matching user whose number of occurrences at the same place as the terminal user is higher than a second threshold, and the information recommending unit matches the user to recommend information to the end user according to the selected trajectory.
  • FIG. 6 may combine the time interval calculation unit and the appearance number calculation unit into one calculation unit 650 and multiplex the matching user screening unit 660, it is understood that the above functions may also be performed in separate modules, and the present application
  • the information recommendation apparatus 600 of an embodiment may further filter any one or both of the matching user schemes by time interval and number of occurrences as needed.
  • the terminal device is a smart phone (for example, The mobile phone, the Huawei mobile phone, and the like are taken as an example, and the information recommendation scheme of the embodiment of the present application is described in detail with reference to FIG. 7-8.
  • the specific implementation process is shown in FIG. 7:
  • step S710 the track location of the terminal user within a certain period of time is continuously acquired. 2.
  • step S720 the similarity of the location tag is calculated according to the track location location matching location tag.
  • step S730 the time interval between the user with high similarity and the end user at the coincidence location label is calculated, and the user whose recommended time interval is smaller than the first threshold is respectively recommended.
  • step S740 the number of visits of the user at a certain location tag is calculated, and the number of users who have visited a large number of times is recommended.
  • step S750 the local content is preferentially recommended according to the content browsed by the recommended user, and the non-local content is recommended next.
  • the embodiment of the present application further provides a terminal device, where the terminal device includes: one or more processors; a memory; one or more applications, wherein the one or more applications are stored in the memory and It is configured to be executed by the one or more processors configured to perform the methods described in the above embodiments.
  • the terminal device includes a processor, a memory, an internal memory, a network interface, and a display screen connected through a system bus.
  • the processor is configured to implement a function of information recommendation, and the processor is configured to perform the information recommendation method provided by the above embodiment.
  • the processor is configured to acquire location information of the terminal user, determine an activity track of the terminal user according to the at least two location information, and recommend information determined by the activity track to the terminal user.
  • the memory is a non-volatile storage medium storing an operating system, a database, and a computer program for implementing the search word method based on the input search term provided by the above embodiments, and executing candidate intermediate data generated by the computer program, and Result data.
  • the network interface is used to communicate with the server, and the network interface includes a radio frequency transceiver.
  • the embodiment of the present application further provides a computer readable storage medium carrying one or more computer instruction programs, where the computer instruction program is executed by one or more processors, the one or more processors executing the above The methods described in the various embodiments.
  • the terminal user may select one of the avatars of the plurality of recommended users, and the avatar of the selected user is appropriately enlarged to distinguish from other recommended users, and correspondingly, relevant recommendation information corresponding to the selected user is displayed at the bottom of the display interface. , such as similarity information, browsed information, and the like.
  • the information recommendation method and apparatus have been described in detail above with reference to the accompanying drawings.
  • the information recommendation method and device can match the user with the trajectory similar to the active trajectory according to the time matching rule, the location access frequency, etc. based on the location information and the activity trajectory of the terminal user, and according to the selected trajectory. Match users accurately, individually and recommend information to end users.
  • the foregoing program may be stored in a computer readable storage medium, and the program is executed when executed.
  • the foregoing storage medium includes: a mobile storage device, a random access memory (RAM), a read-only memory (ROM), a magnetic disk, or an optical disk.
  • RAM random access memory
  • ROM read-only memory
  • magnetic disk or an optical disk.
  • optical disk A medium that can store program code.
  • the above-described integrated unit of the present application may be stored in a computer readable storage medium if it is implemented in the form of a software function module and sold or used as a stand-alone product.
  • the technical solution of the embodiments of the present application may be embodied in the form of a software product in essence or in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for making
  • a computer device which may be a personal computer, server, or network device, etc.
  • the foregoing storage medium includes various media that can store program codes, such as a mobile storage device, a RAM, a ROM, a magnetic disk, or an optical disk.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本申请公开了一种信息推荐方法、装置及系统。该方法包括：位置获取步骤，用于获取终端用户的位置信息；轨迹确定步骤，用于根据至少两个位置信息确定所述终端用户的活动轨迹；以及信息推荐步骤，用于向所述终端用户推荐根据所述活动轨迹所确定的信息。

Description

信息推荐方法、装置、系统及储存介质
交互参考
本申请要求以下优先权：2017年03月14日提出的申请号：201710155037.5，名称:“信息推荐方法、装置及系统”的中国专利，本申请参考引用了如上所述申请的全部内容。
技术领域
本发明涉及移动通讯信息技术领域，特别涉及一种信息推荐方法、装置、系统及储存介质。
背景技术
基于位置的服务(Location Based Service，LBS)是通过电信移动运营商的无线电通讯网络(如GSM网络、CDMA网络)或外部定位方式(如GPS)获取移动终端用户的位置信息(地理坐标，或大地坐标)，在地理信息系统(Geographic Information System，GIS)平台的支持下，为用户提供相应服务的一种增值业务。
目前仅根据用户移动终端定位的地理位置或者用户设置的地理位置信息向用户推荐信息，该推荐信息一般包括本地资讯，如新闻资讯、美食资讯等。图1A和图1B示出了目前基于移动终端的位置向移动终端用户提供不同服务的示意图。如图所示，现有的基于位置的推荐方式主要是根据用户所处或所选的城市向用户推荐本地新闻资讯(图1A)，或是根据用户所处的地理位置或用户设置的地理位置向用户推荐附近商家(图1B)等信息。
但是，由于在向用户推荐信息时，仅根据用户所在地域或是单个地理位置推送比较大范围的城市信息，因此所推荐的信息并不能精确地满足用户潜在的个性化需求。
发明内容
为解决现有技术存在的上述技术问题，本申请提供一种信息推荐方法、 装置、系统及储存介质已。
一个方面，本申请实施例提供了一种信息推荐方法，该方法可以包括：位置获取步骤，用于获取终端用户的位置信息；轨迹确定步骤，用于根据至少两个位置信息确定终端用户的活动轨迹；以及信息推荐步骤，用于向终端用户推荐根据活动轨迹所确定的信息。
所获取的活动轨迹包含了用户的出行信息，根据活动轨迹可以预测用户潜在的个性化需求，由此向终端用户推荐的根据活动轨迹所确定的信息可以精准地满足用户的个性化需求。
其中，信息推荐步骤可以包括：寻找活动轨迹与终端用户相似的轨迹匹配用户；以及根据轨迹匹配用户向终端用户推荐信息。
类似轨迹的用户在很大程度上会与目标终端用户有着相类似的活动模式或是喜好内容。因此可以根据轨迹匹配用户来确定向终端用户推荐的信息，将推荐信息的范围缩小至轨迹匹配用户相关的范围内，提高信息推荐的精准度以及个性化服务。
其中，根据轨迹匹配用户向终端用户推荐信息可以包括：计算轨迹匹配用户与终端用户基于活动轨迹的时间间隔；选择在活动轨迹中的至少一个地点的出现时间与终端用户的出现时间之间的时间间隔小于第一阈值的轨迹匹配用户；以及根据选择的轨迹匹配用户向终端用户推荐信息。
由此，可以将与终端用户在其活动轨迹中至少一个地点的出现时间接近的轨迹匹配用户作为与终端用户的相似度较高的参照用户，从而使得根据参照用户向终端用户推荐的信息可以更精准地满足终端用户的潜在的个性化需求。
优选地，根据轨迹匹配用户向终端用户推荐信息可以包括：计算预定时间段内轨迹匹配用户与终端用户在活动轨迹中至少一个地点的出现次数；选择与终端用户在同一地点的出现次数都高于第二阈值的轨迹匹配用户；以及根据选择的轨迹匹配用户向终端用户推荐信息。
由此，也可以将与终端用户在其活动轨迹中至少一个地点的出现次数较多的轨迹匹配用户作为与终端用户的相似度较高的参照用户。
其中，推荐信息可以包括如下至少一项：轨迹匹配用户；轨迹匹配用户在匹配的活动轨迹上出现或是推荐过的位置；轨迹匹配用户浏览过的内容。由此，基于选择的轨迹匹配用户，可以向终端用户提供多种类型的推 荐信息。
其中，位置获取步骤包括：持续获取终端用户的轨迹定位位置；和/或获取终端用户主动提交的签到位置。由此，可以根据多种方式获取终端用户的位置信息。
其中，轨迹确定步骤可以包括：根据轨迹定位位置和/或至少两个签到位置匹配地点标签；以及根据地点标签确定活动轨迹。由此，通过匹配地点标签，使得基于地点标签确定的活动轨迹可以更加直观清楚地反映出用户的出行信息。
另一方面，本申请实施例还提供了一种信息推荐装置，该装置可以包括：位置获取单元，用于获取终端用户的位置信息；以及轨迹确定单元，用于根据至少两个位置信息确定终端用户的活动轨迹；以及信息推荐单元，用于向终端用户推荐根据活动轨迹所确定的信息。
本申请实施例提供的信息推荐装置能够精准、个性地确定向终端用户推荐的信息内容，提升用户使用体验。
再一方面，本申请实施例还提供了一种终端设备，所述终端设备包括：一个或多个处理器；存储器；一个或多个应用程序，其中所述一个或多个应用程序被存储在所述存储器中并被配置为由所述一个或多个处理器执行，所述一个或多个程序配置用于执行上述方法。
再一方面，本申请实施例还提供了一种信息推荐系统，包括至少一个服务器和多个终端用户，多个终端用户主动或被动上传位置信息，所述至少一个服务器用于：获取多个终端用户的位置信息；根据至少两个位置信息确定该终端用户的活动轨迹；以及向该终端用户推荐根据所述活动轨迹所确定的信息。
再一方面，本申请实施例还提供了一种计算机可读存储介质，其上承载一个或多个计算机指令程序，所述计算机指令程序被一个或多个处理器执行时，所述一个或多个处理器执行上述方法。
本申请实施例提供的信息推荐方法、装置、系统及储存介质，通过确定包含了用户的出行信息的活动轨迹，使得可以根据活动轨迹预测用户潜在的个性化需求，由此向终端用户推荐的根据活动轨迹所确定的信息可以精准地满足终端用户的潜在的个性化需求。
附图说明
通过结合附图对本公开示例性实施方式进行更详细的描述，本公开的上述以及其它目的、特征和优势将变得更加明显，其中，在本公开示例性实施方式中，相同的参考标号通常代表相同部件。
图1A和1B示出了现有信息推荐方案。
图2是示出了用于实现本申请实施例的系统框图。
图3示出了根据本申请一实施例的信息推荐方法的示意性流程图。
图4示出了根据本申请一实施例的信息推荐步骤的子步骤流程图。
图5示出了根据本申请另一实施例的信息推荐步骤的子步骤流程图。
图6示出了根据本申请一实施例的信息推荐装置的示意性框图。
图7示出了根据本申请的应用例。
图8示出了图7应用例的效果图。
图9示出了本申请实施例提供的一种终端设备的结构示意图。
具体实施方式
下面将参照附图更详细地描述本公开的优选实施方式。虽然附图中显示了本公开的优选实施方式，然而应该理解，可以以各种形式实现本公开而不应被这里阐述的实施方式所限制。相反，提供这些实施方式是为了使本公开更加透彻和完整，并且能够将本公开的范围完整地传达给本领域的技术人员。
如前所述，为了向终端用户提供精准的个性化信息推荐服务，提升用户使用体验，本申请实施例提出了一种信息推荐方法及装置，其能够根据获取或确定的用户活动轨迹，更为精准地向终端用户推荐合适的信息。
下面将参照图2至图6来具体地描述本申请的实施例。首先将结合用于实现本申请实施例的系统框图2来进行描述。
如图2所示，系统包括至少一个服务器20和多个终端设备10。终端设备10可以经由网络40实现与服务器20的信息收发。服务器20可以通过访问数据库30来获取终端设备10所需的内容。移动终端之间(例如，10_1与10_2或10_N之间)也可以经由网络40彼此通信。网络40可以是广义上的用于信息传递的网络，可以包括一个或多个通信网络，诸如无线通信网络、因特网、私域网、局域网、城域网、广域网或是蜂窝数据网络 等。在一个实施例中，网络40也可以包括卫星网络，由此将终端设备10的GPS信号传送给服务器20。应当注意，虽然为了方便说明而在图中示出了从数据库30到服务器20的双向箭头，但本领域技术人员可以理解的是，上述数据的收发也是可以通过网络40实现的。
终端设备10是可用来进行网络访问的任何合适的便携式电子设备，包括但不限于智能电话、平板电脑或是其他便携式客户端。服务器20则是能够通过网络访问的提供交互服务所需信息的任何服务器。图中虽然示出了多个终端设备10-1…N以及单个服务器20和数据库30，并且在随后的描述中会选择其中的一个或部分移动终端加以描述(例如，终端设备10-1)，但是本领域技术人员应该理解的是，上述1…N个移动终端旨在表示真实网络中存在的大量移动终端，示出的单个服务器20和数据库30旨在表示申请明的技术方案涉及服务器及数据库的操作。对特定编号的移动端以及单个服务器和数据库加以详述至少为了说明方便，而非暗示对移动端和服务器的类型或是位置等具有限制。
在本文中技术方案中，虽然涉及的其实是对“终端设备”而非“终端用户”的轨迹获取，但由于系统是经由用户所持有的终端设备(如
Figure PCTCN2017119953-appb-000001
之类的智能电话)主动或被动上传的地理位置信息来获知用户信息的，于是在此可以将用户所持有的终端设备的地理位置或活动轨迹等同于本文述及的“终端用户”的地理位置或活动轨迹。
服务器20可以获取多个终端设备(或终端用户)10的地理位置信息或是轨迹信息，并可以基于各个终端用户的轨迹信息向其更为精准地推荐信息。具体地，服务器20可以执行图3所示的信息推荐方法。图3示出了根据本申请一实施例的信息推荐方法的示意性流程图。
在步骤S310，获取终端用户的位置信息。该位置信息既可以是通过对终端设备的地理位置定位获得的，例如，用户的智能手机上传的GPS经纬度信息，也可以是终端用户主动上传的，例如地点签到信息，或者通过其它方式确定的。
可以持续获取终端用户的轨迹定位位置。例如，可以采用GPS定位方法，记录用户在一定时间段内(例如，从当前时间往前一段时间内)所处的地点的轨迹(活动轨迹)，形成用户的活动轨迹记录。由于这种轨迹的记录其实也是地点和时间关联上传并连接而成(即，由点及线)，因此也 可以看成是对终端用户位置的(持续)获取。活动轨迹能够以表格等的形式加以记录。
另外，也可以使用LBS签到的方法获取终端用户主动提交的签到位置。签到是用户通过定位服务向他人或服务提供者告知自己具体地点的操作。例如，终端用户在终端输入或选择的地理位置，服务器根据终端用户的输入或选择，确定终端用户的位置信息。
在一个实施例中，在获取终端用户的位置信息的同时，还可以获取终端用户出现在相应位置的时间点，和/或在此位置停留的时间长度，或其它相关信息，以便于精准获知终端用户的行为或活动。并且，也可以维护一个数据库，以存储不同终端用户不同的地理位置信息及其相关信息。
在步骤S320，根据至少两个位置信息确定终端用户的活动轨迹。
一方面，如果在步骤S310中获取的位置信息就是轨迹信息(即，连续记录的位置和关联时间信息)，那么可以为此直接确定终端用户的活动轨迹。
另一方面，也可以通过将在步骤S310中获取的终端用户在一定时间段内的位置及其相关信息进行关联，按照时间走向，绘制终端用户的位置变化轨迹，进一步确定终端用户在一定时间段内的活动轨迹。
再一方面，可以对步骤S310中获取的轨迹信息和位置信息进行汇总，以确定糅合了在前获取的轨迹信息和位置信息的、该终端用户在更大范围内的活动轨迹。
如前所述，位置信息可以是位置坐标信息，而在现实生活中，可能存在多个对应于同一地域(例如，东方新天地商场)的位置坐标，仅以经纬度确定的位置坐标信息难以直观地确定用户活动轨迹的相似性，因此，还可以进一步对获取的终端用户的位置信息进行处理。在一个优选实施例中，可以根据轨迹定位位置和/或两个签到位置匹配地点标签(例如，东方新天地商场里不同的商户标签)，并且根据地点标签确定活动轨迹。
地点标签可以是位置坐标信息对应的地点，例如，地铁站、商场、办公大厦等建筑物，或其它地点标志。通过为获取的位置坐标信息匹配与其相对应的地点标签，确定终端用户的位置及活动轨迹。例如，坐标(113.34638，23.11741)，(113.34758，23.11971)，匹配某市某地铁站。由此，获得终端用户出现的地点，并且获得较为直观的终端用户的活动轨 迹。
在步骤S330，向终端用户推荐根据活动轨迹所确定的信息。
在具体的信息推荐过程中，可以寻找活动轨迹与终端用户相似的轨迹匹配用户，根据轨迹匹配用户向终端用户推荐信息。这样，就可以根据用户活动轨迹的相似性，来猜测终端用户的喜好。
这里，可以采用现有的聚类算法等方式，根据终端用户活动轨迹上所有基于地理位置信息的地点标签，寻找与终端用户活动轨迹相似的其他终端用户，作为轨迹匹配用户。其中，活动轨迹相似可以是指轨迹匹配用户与终端用户的活动轨迹中具有一个或多个重合(或相同)的地点标签。
根据聚类相似程度的高低，选出轨迹地点相似度较高的轨迹匹配用户，并将这些用户列入第一集合中。其中，相似程度的高低可以通过两者的活动轨迹中重合(即相同)的地点标签的个数确定。即，重合地点个数越多，相似度越高。
由此，根据终端用户的位置信息或活动轨迹，精准、个性地向终端用户推荐信息，提升用户的体验。
考虑到城市人口以及终端用户的数量，可能存在多个与终端用户的活动轨迹相似的轨迹匹配用户，根据上述方法确定的推荐信息繁多，并且参差不齐。因此，为提高信息推荐的精准度，还可以进一步限定，以从相似度高的轨迹匹配用户中筛选出优选推荐用户。下面就本申请的信息推荐方法中根据轨迹匹配用户向终端用户推荐信息的具体过程做进一步详细说明。
在一个实施例中，可以基于轨迹匹配用户与终端用户基于活动轨迹的时间间隔来对轨迹匹配用户进行进一步的筛选。图4示出了根据本申请一实施例的信息推荐步骤330的子步骤流程图。
如图4所示，在步骤S431中，计算轨迹匹配用户与终端用户基于活动轨迹的时间间隔。
这里，轨迹匹配用户可以来源于按照图3所示的方法寻找的轨迹匹配用户的第一集合。根据轨迹匹配用户与终端用户的相似度由高到低依次选择轨迹匹配用户，分别计算每个轨迹匹配用户在其各自与终端用户的每个重合地点标签出现的时间与终端用户在该地点标签出现的时间之间的时间间隔，并将计算的时间间隔分别与其相应的终端用户的相关信息(如表1所示的终端用户ID、轨迹匹配用户ID、相似标签个数、重合标签)等相关 联。
在步骤S432中，选择在活动轨迹中的至少一地点的出现时间与终端用户的出现时间之间的时间间隔小于第一阈值的轨迹匹配用户。
这里的时间间隔可以是绝对时间间隔，即，终端用户和匹配用户都于某月某日某时的不同分来到某一地点。时间间隔也可以是相对时间间隔，例如，都在工作日的某一时间段乘坐地铁从A站到B站。或是都会以一定的频率在休息日去逛中国美术馆等等。由于旨在筛选出行为模式与目标终端用户相类似的轨迹匹配用户，而相对时间间隔更能评判用户的行为模式，因此这里优选相对时间间隔，也可以使用绝对时间间隔和相对时间间隔的混合确定模式。
相应地，这里的“第一阈值”可以是固定值，如10分钟、1小时、一周等，也可以是固定时间，如工作日早上8点至8点10分，还可以根据轨迹匹配用户与终端用户的相似程度进行调整。
根据相似程度的高低，将步骤S431中获取的轨迹匹配用户与终端用户在同一地点出现的时间间隔与第一阈值进行比较，从中选出小于第一阈值的轨迹匹配用户，作为优选推荐用户。其中，在满足相似度高的情况下，还可以优先推荐时间间隔最短的轨迹匹配用户。
在步骤S433中，根据选择的轨迹匹配用户向终端用户推荐信息。
推荐信息可以包括推荐的轨迹匹配用户、轨迹匹配用户在匹配的活动轨迹上出现或是推荐过的位置、轨迹匹配用户浏览过的内容等等。例如，若用户A和B在同一地点出现的时间间隔小于T 1，则向A推荐B。又例如，向A推荐工作日早上8点至8点10分之间都路过从a地铁站到e地铁站这条轨迹路线的人。
由此，根据时间匹配规则，从与终端用户的活动轨迹相似度高的轨迹匹配用户中选出优选推荐用户，并向终端用户个性化推荐信息，提高推荐信息的精准度。
终端用户ID 轨迹匹配用户ID 相似标签个数 重合标签
A B 5 a,b,c,d,e
A C 4 b,c,d,e
表1
图5示出了根据本申请另一实施例的信息推荐步骤330的子步骤流程图。
如图5所示，在步骤S531中，计算预定时间段内轨迹匹配用户与终端用户在活动轨迹中至少一个地点的出现次数。
预定时间段可以是预先设定的固定时间段，如24小时、一周、一个月或其它时间段数值，也可以根据轨迹匹配用户与终端用户的轨迹相似程度进行调整。
这里的轨迹匹配用户同样可以来源于第一集合。根据轨迹匹配用户与终端用户的相似度由高到低依次选择轨迹匹配用户，分别计算每个轨迹匹配用户与终端用户在其每个重合地点标签出现的次数，并将计算的出现次数分别与其相应的终端用户的相关信息(如表1所示的信息)等相关联。
在步骤S532中，选择与终端用户在同一地点的出现次数都高于第二阈值的轨迹匹配用户。该第二阈值可以是固定值，也可以根据轨迹匹配用户与终端用户的相似程度进行调整。
根据相似程度的高低，将步骤S531中获取的轨迹匹配用户与终端用户在同一地点出现的次数与第二阈值进行比较，从中选出高于第二阈值的出现次数，并选择该出现次数所关联的轨迹匹配用户，作为优选推荐用户。其中，还可以根据出现次数的大小，为推荐用户排序，为终端用户提供更多的推荐选择。其中，在满足相似度高的情况下，还可以优先推荐出现次数最多的轨迹匹配用户。
在步骤S533中，根据选择的轨迹匹配用户向终端用户推荐信息。
推荐信息可以包括推荐的轨迹匹配用户、轨迹匹配用户在匹配的活动轨迹上出现或是推荐过的位置、轨迹匹配用户浏览过的内容等等。例如，若用户A和C在同一地点出现的次数多，则向A推荐C。又例如，用户A最近一周去过5次地点f标签对应的某咖啡店，则推荐也去过该咖啡店3次的用户C。
由此，根据位置访问频次规则，也可以从与终端用户的活动轨迹相似度高的轨迹匹配用户中选出优选推荐用户，并向终端用户个性化推荐信息，同时提高信息推荐的精准度。
值得说明的是，结合图4和图5描述的优选方案可以结合，也可以针对不同的情况分别执行，例如，在重合地点标签个数较多时，优选时间匹 配规则，在重合地点标签个数较少时，优选位置访问频次规则。也可以逐级执行两方案，例如，首先计算不同轨迹匹配用户与终端用户的时间间隔，其次计算出现次数，或者首先计算出现次数，其次计算时间间隔，以提高推荐的精准度。应当理解，上述举例是示意性的，不应用以限制本申请。本申请实施例的信息推荐方案还可以通过其它方式或方法实现。
推荐信息可以包括轨迹匹配用户，例如，以推荐“附近的人”的形式向终端用户推荐轨迹匹配用户，便于终端用户认识志趣相投的新朋友；也可以包括轨迹匹配用户在匹配的活动轨迹上出现或是推荐过的位置，例如，轨迹匹配用户出现或推荐过的餐厅、影院等；还可以包括轨迹匹配用户浏览过的内容，例如，本地资讯、新闻等。应当理解，上述举例是示意性的，不应用以限制本申请实施例，本申请实施例还可以向终端用户推荐其他形式的信息内容。
在推荐信息为轨迹匹配用户浏览过的信息时，为便于向终端用户推荐该信息，还可以根据信息的内容或标题，为推荐信息添加内容标签。例如，“广州公积金政策”的内容标签为“广州”，“金马奖双生蛋”的内容标签为“明星”等等。并且，可以根据具体的推荐信息内容或内容标签设定优先级别。例如，可以设定本地内容的优先级高于非本地内容，如内容标签为“广州”的推荐信息的优先级高于内容标签为“明星”的推荐信息，以便于终端用户优先了解其所在地理位置本地的信息。
至此，已经结合图3至图5详细描述了本申请实施例的信息推荐方法。通过记录终端用户的活动轨迹，计算与终端用户的活动轨迹相似的轨迹匹配用户，并根据选择的轨迹匹配用户精准、个性地向终端用户推荐信息，提升用户体验。
本申请实施例还提供一种信息推荐方法，所述方法包括：获取终端用户的位置信息；根据至少两个位置信息确定所述终端用户的活动轨迹；向所述终端用户推荐根据所述活动轨迹所确定的信息。其中，所述向所述终端用户推荐根据所述活动轨迹所确定的信息包括：寻找活动轨迹与所述终端用户相似的轨迹匹配用户；以及根据所述轨迹匹配用户向所述终端用户推荐信息。
在一实施例中，所述向所述终端用户推荐根据所述活动轨迹所确定的信息，包括：
计算预定时间段内所述轨迹匹配用户与所述终端用户在所述活动轨迹中至少一个地点的出现次数；根据出现次数从高到低的排序，选择排序靠前的预设数量的所述轨迹匹配用户；根据选择的所述轨迹匹配用户向所述终端用户推荐信息。
在一实施例中，所述根据所述轨迹匹配用户向所述终端用户推荐信息，包括：向所述终端用户推荐所述轨迹匹配用户预设时间范围内浏览过的资讯信息。
在一实施例中，参见图8所示，所述轨迹匹配用户的数量为多个；相应的，所述方法还包括：按预设规则分别显示多个所述轨迹匹配用户的标识信息；当所述标识信息被触发时，向所述终端用户推荐所述标识信息对应的轨迹匹配用户预设时间范围内浏览过的资讯信息，所述资讯信息包括：内容标题、内容摘要、内容相关图片中的一种或几种。
在一实施例中，参见图8所示，所述按预设规则分别显示多个所述轨迹匹配用户的标识信息包括：根据所述终端用户的位置信息显示电子地图；在所述电子地图的界面上，显示所述轨迹匹配用户的标识信息，所述标识信息位于所述轨迹匹配用户在匹配的活动轨迹上出现或是推荐过的位置；其中，所述标识信息包括图片信息、图像信息、文字信息中的一种或几种。
在一实施例中，参见图8所示，所述方法还包括：当所述标识信息被触发时，显示所述标识信息对应的轨迹匹配用户与所述终端用户的匹配信息，以及所述标识信息对应的轨迹匹配用户历史浏览资讯信息的链接信息。
在一实施例中，参见图8所示，所述方法还包括：当所述标识信息被触发时，被触发的所述标识信息的显示方式发生改变，使被触发的所述标识信息区别于未被触发的所述标识信息。
图6示出了根据本申请一实施例的信息推荐装置的结构框图。其中，信息推荐装置600的功能模块可以由实现本申请实施例原理的硬件、软件或硬件和软件的结合来实现。本领域技术人员可以理解的是，图6所描述的功能模块可以组合起来或者划分成子模块，从而实现上述发明的原理。因此，本文的描述可以支持对本文描述的功能模块的任何可能的组合、或者划分、或者更进一步的限定。
图6所示的信息推荐装置600可以用来实现图3-5所示的信息推荐方法，下面仅就信息推荐装置600可以具有的功能模块以及各功能模块可以 执行的操作做简要说明，对于其中涉及的细节部分可以参见上文结合图3的描述，这里不再赘述。
如图6所示，本申请实施例的信息推荐装置600可以包括位置获取单元610、轨迹确定单元620以及信息推荐单元630。其中，位置获取单元610可以用于获取终端用户的位置信息。轨迹确定单元620可以用于根据至少两个位置信息确定终端用户的活动轨迹。信息推荐单元630可以用于向终端用户推荐根据活动轨迹所确定的信息。
另外，信息推荐装置600还可以包括匹配用户寻找单元640。其中，匹配用户寻找单元640用于寻找活动轨迹与终端用户相似的轨迹匹配用户，并且信息推荐单元630根据轨迹匹配用户向终端用户推荐信息。
其中，信息推荐装置600还可以包括时间间隔/出现次数计算单元650和匹配用户筛选单元660。
在一个实施例中，时间间隔计算单元650可以用于计算轨迹匹配用户与终端用户基于活动轨迹的时间间隔。匹配用户筛选单元660可以用于选择在活动轨迹中的至少一个地点的出现时间与终端用户的出现时间之间的时间间隔小于第一阈值的轨迹匹配用户，并且信息推荐单元根据选择的轨迹匹配用户向终端用户推荐信息。
在另一个实施例中，出现次数计算单元650可以用于计算预定时间段内轨迹匹配用户与终端用户在活动轨迹中至少一个地点的出现次数。匹配用户筛选单元660可以用于选择与终端用户在同一地点的出现次数都高于第二阈值的轨迹匹配用户，并且信息推荐单元根据选择的轨迹匹配用户向终端用户推荐信息。
虽然图6将时间间隔计算单元和出现次数计算单元可以合并为一个计算单元650，并且复用了匹配用户筛选单元660，但可以理解的是，上述功能也可以在分开的模块执行，并且本申请实施例的信息推荐装置600可以根据需要包括通过时间间隔和出现次数进一步筛选匹配用户方案中的任一或两者。
以下是本申请的应用例说明。
如下以终端设备为智能电话(例如，
Figure PCTCN2017119953-appb-000002
手机、华为手机等)为例，并结合图7-8详细说明本申请实施例的信息推荐方案，具体实现流程如图7所示：
1.在步骤S710，持续获取终端用户在一定时间段内的轨迹定位位置。2.在步骤S720，根据轨迹定位位置匹配地点标签，计算地点标签的相似度。
3.在步骤S730，分别计算相似度高的用户与终端用户在重合地点标签的时间间隔，推荐时间间隔小于第一阈值的用户。
4.在步骤S740，分别计算用户在某地点标签的访问次数，推荐访问次数多的用户。
5.在步骤S750，根据推荐用户浏览过的内容，优先推荐本地内容，其次推荐非本地内容。
本申请实施例还提供一种终端设备，所述终端设备包括：一个或多个处理器；存储器；一个或多个应用程序，其中所述一个或多个应用程序被存储在所述存储器中并被配置为由所述一个或多个处理器执行，所述一个或多个程序配置用于执行上述实施例所描述的方法。
在一实施例中，参见图9所示，终端设备包括通过系统总线连接的处理器、存储器、内存储器、网络接口和显示屏。处理器用于实现信息推荐的功能，处理器被配置为执行上述实施例提供的信息推荐方法。处理器用于获取终端用户的位置信息；根据至少两个位置信息确定所述终端用户的活动轨迹；以及向所述终端用户推荐根据所述活动轨迹所确定的信息。存储器是一种非易失性存储介质，存储有操作系统、数据库和用于实现上述实施例提供的的基于输入搜索词来推荐搜索词方法的计算机程序，以及执行计算机程序产生的候选中间数据以及结果数据。网络接口用于与服务器通信，网络接口包括射频收发器。
本申请实施例还提供一种计算机可读存储介质，其上承载一个或多个计算机指令程序，所述计算机指令程序被一个或多个处理器执行时，所述一个或多个处理器执行上述各实施例所描述的方法。
由此，实现向终端用户推荐信息，并将推荐用户以图8所示的效果图显示给终端用户。终端用户可以从多个推荐用户的头像中选择一位，该选择用户的头像被适当放大，以区别与其他推荐用户，相应的，在显示界面的底部显示出对应于该选择用户的相关推荐信息，如相似度信息、已浏览的信息等。
上文中已经参考附图详细描述了根据本申请实施例的信息推荐方法及 装置。通过本申请实施例的信息推荐方法及装置，能够基于终端用户的位置信息和活动轨迹，根据时间匹配规则、位置访问频次等为终端用户匹配与其活动轨迹相似的轨迹匹配用户，并根据选择的轨迹匹配用户精准、个性地并向终端用户推荐信息。
本领域普通技术人员可以理解：实现上述方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成，前述的程序可以存储于一计算机可读取存储介质中，该程序在执行时，执行包括上述任意方法实施例的步骤；而前述的存储介质包括：移动存储设备、随机存取存储器(RAM，Random Access Memory)、只读存储器(ROM，Read-Only Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
或者，本申请上述集成的单元如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请实施例的技术方案本质上或者说对相关技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机、服务器、或者网络设备等)执行申请各个实施例所述方法的全部或部分。而前述的存储介质包括：移动存储设备、RAM、ROM、磁碟或者光盘等各种可以存储程序代码的介质。
以上已经描述了本申请的各实施例，上述说明是示例性的，并非穷尽性的，并且也不限于所披露的各实施例。在不偏离所说明的各实施例的范围和精神的情况下，对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。本文中所用术语的选择，旨在最好地解释各实施例的原理、实际应用或对市场中的技术的改进，或者使本技术领域的其它普通技术人员能理解本文披露的各实施例。

Claims (20)

  1. 一种信息推荐方法，包括：
    获取终端用户的位置信息；
    根据至少两个位置信息确定所述终端用户的活动轨迹；以及
    向所述终端用户推荐根据所述活动轨迹所确定的信息。
  2. 如权利要求1所述的方法，其中，所述向所述终端用户推荐根据所述活动轨迹所确定的信息包括：
    寻找活动轨迹与所述终端用户相似的轨迹匹配用户；以及
    根据所述轨迹匹配用户向所述终端用户推荐信息。
  3. 如权利要求2所述的方法，其中，根据所述轨迹匹配用户向所述终端用户推荐信息包括：
    计算所述轨迹匹配用户与所述终端用户基于所述活动轨迹的时间间隔；
    选择在所述活动轨迹中的至少一个地点的出现时间与所述终端用户的出现时间之间的时间间隔小于第一阈值的所述轨迹匹配用户；以及
    根据选择的所述轨迹匹配用户向所述终端用户推荐信息。
  4. 如权利要求2所述的方法，其中，根据所述轨迹匹配用户向所述终端用户推荐信息包括：
    计算预定时间段内所述轨迹匹配用户与所述终端用户在所述活动轨迹中至少一个地点的出现次数；
    选择与所述终端用户在同一地点的出现次数都高于第二阈值的所述轨迹匹配用户；以及
    根据选择的所述轨迹匹配用户向所述终端用户推荐信息。
  5. 如权利要求2所述的方法，其中，所述推荐信息包括如下至少一项：
    所述轨迹匹配用户；
    所述轨迹匹配用户在所述匹配的活动轨迹上出现或是推荐过的位置；
    所述轨迹匹配用户浏览过的内容。
  6. 如权利要求1所述的方法，其中，所述获取终端用户的位置信息包括：
    持续获取所述终端用户的轨迹定位位置；和/或
    获取所述终端用户主动提交的签到位置。
  7. 如权利要求2所述的方法，其中，所述根据至少两个位置信息确定所述终端用户的活动轨迹包括：
    根据轨迹定位位置和/或至少两个签到位置匹配地点标签；以及
    根据所述地点标签确定所述活动轨迹。
  8. 如权利要求2所述的方法，其中，所述向所述终端用户推荐根据所述活动轨迹所确定的信息，包括：
    计算预定时间段内所述轨迹匹配用户与所述终端用户在所述活动轨迹中至少一个地点的出现次数；
    根据出现次数从高到低的排序，选择排序靠前的预设数量的所述轨迹匹配用户；
    根据选择的所述轨迹匹配用户向所述终端用户推荐信息。
  9. 如权利要求2所述的方法，其中，所述根据所述轨迹匹配用户向所述终端用户推荐信息，包括：
    向所述终端用户推荐所述轨迹匹配用户预设时间范围内浏览过的资讯信息。
  10. 如权利要求9所述的方法，其中，所述轨迹匹配用户的数量为多个；
    相应的，所述方法还包括：按预设规则分别显示多个所述轨迹匹配用户的标识信息；
    当所述标识信息被触发时，向所述终端用户推荐所述标识信息对应的轨迹匹配用户预设时间范围内浏览过的资讯信息，所述资讯信息包括：内容标题、内容摘要、内容相关图片中的一种或几种。
  11. 如权利要求10所述的方法，其中，所述按预设规则分别显示多个所述轨迹匹配用户的标识信息包括：
    根据所述终端用户的位置信息显示电子地图；
    在所述电子地图的界面上，显示所述轨迹匹配用户的标识信息，所述标识信息位于所述轨迹匹配用户在匹配的活动轨迹上出现或是推荐过的位置；其中，所述标识信息包括图片信息、图像信息、文字信息中的一种或几种。
  12. 如权利要求10所述的方法，其中，所述方法还包括：
    当所述标识信息被触发时，显示所述标识信息对应的轨迹匹配用户与 所述终端用户的匹配信息，以及所述标识信息对应的轨迹匹配用户历史浏览资讯信息的链接信息。
  13. 如权利要求10所述的方法，其中，所述方法还包括：
    当所述标识信息被触发时，被触发的所述标识信息的显示方式发生改变，使被触发的所述标识信息区别于未被触发的所述标识信息。
  14. 一种信息推荐装置，包括：
    位置获取单元，用于获取终端用户的位置信息；以及
    轨迹确定单元，用于根据至少两个位置信息确定所述终端用户的活动轨迹；以及
    信息推荐单元，用于向所述终端用户推荐根据所述活动轨迹所确定的信息。
  15. 如权利要求14所述的装置，还包括：
    匹配用户寻找单元，用于寻找活动轨迹与所述终端用户相似的轨迹匹配用户，并且
    所述信息推荐单元根据所述轨迹匹配用户向所述终端用户推荐信息。
  16. 如权利要求15所述的装置，还包括：
    时间间隔计算单元，用于计算所述轨迹匹配用户与所述终端用户基于所述活动轨迹的时间间隔；
    匹配用户筛选单元，用于选择在所述活动轨迹中的至少一个地点的出现时间与所述终端用户的出现时间之间的时间间隔小于第一阈值的所述轨迹匹配用户，并且
    所述信息推荐单元根据选择的所述轨迹匹配用户向所述终端用户推荐信息。
  17. 如权利要求15所述的装置，还包括：
    出现次数计算单元，用于计算预定时间段内所述轨迹匹配用户与所述终端用户在所述活动轨迹中至少一个地点的出现次数；
    匹配用户筛选单元，用于选择与所述终端用户在同一地点的出现次数都高于第二阈值的所述轨迹匹配用户，并且
    所述信息推荐单元根据选择的所述轨迹匹配用户向所述终端用户推荐信息。
  18. 一种终端设备，所述终端设备包括：
    一个或多个处理器；
    存储器；
    一个或多个应用程序，其中所述一个或多个应用程序被存储在所述存储器中并被配置为由所述一个或多个处理器执行，所述一个或多个程序配置用于执行权利要求1至13任意一项所述的方法。
  19. 一种信息推荐系统，包括至少一个服务器和多个终端用户，多个终端用户主动或被动上传位置信息，所述至少一个服务器用于：
    获取多个终端用户的位置信息；
    根据至少两个位置信息确定该终端用户的活动轨迹；以及
    向该终端用户推荐根据所述活动轨迹所确定的信息。
  20. 一种计算机可读存储介质，其上承载一个或多个计算机指令程序，所述计算机指令程序被一个或多个处理器执行时，所述一个或多个处理器执行权利要求1至13任一项所述的方法。
PCT/CN2017/119953 2017-03-14 2017-12-29 信息推荐方法、装置、系统及储存介质 WO2018166280A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710155037.5 2017-03-14
CN201710155037.5A CN108574715A (zh) 2017-03-14 2017-03-14 信息推荐方法、装置及系统

Publications (1)

Publication Number Publication Date
WO2018166280A1 true WO2018166280A1 (zh) 2018-09-20

Family

ID=63522780

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/119953 WO2018166280A1 (zh) 2017-03-14 2017-12-29 信息推荐方法、装置、系统及储存介质

Country Status (2)

Country Link
CN (1) CN108574715A (zh)
WO (1) WO2018166280A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111242535A (zh) * 2020-01-07 2020-06-05 贵阳货车帮科技有限公司 运输路线推送方法、装置、电子设备及可读存储介质
CN112131481A (zh) * 2020-10-03 2020-12-25 北京一点网聚科技有限公司 推荐方法及装置
CN115150462A (zh) * 2022-05-25 2022-10-04 东风柳州汽车有限公司 行车话题推送方法、装置、设备及存储介质

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113316944B (zh) * 2019-01-11 2022-10-18 张彬 一种通信录分级展示方法、装置及电子设备
CN110287419A (zh) * 2019-06-28 2019-09-27 重庆金窝窝网络科技有限公司 一种商品推荐方法、装置、服务器及存储介质
CN111680870B (zh) * 2020-04-29 2023-06-06 西南电子技术研究所（中国电子科技集团公司第十研究所） 目标运动轨迹质量综合评估方法
CN112712392A (zh) * 2020-12-31 2021-04-27 京东数字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
CN113301137B (zh) * 2021-05-18 2022-08-16 浙江微能科技有限公司 一种基于物联终端协同分析的信息智能推送方法及装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040156326A1 (en) * 2003-02-05 2004-08-12 Autodesk, Inc. Use of triggers and a location hypercube to enable push-based location applications
CN102509170A (zh) * 2011-10-10 2012-06-20 浙江鸿程计算机系统有限公司 一种基于历史轨迹数据挖掘的位置预测系统及方法
CN104765873A (zh) * 2015-04-24 2015-07-08 百度在线网络技术（北京）有限公司 用户相似度确定方法和装置
CN104796468A (zh) * 2015-04-14 2015-07-22 蔡宏铭 实现同行人即时通讯及同行信息共享的方法和系统
CN105279207A (zh) * 2014-07-25 2016-01-27 腾讯科技（深圳）有限公司 一种用户推荐方法、装置和系统

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104572937B (zh) * 2014-12-30 2017-12-22 杭州云象网络技术有限公司 一种基于室内生活圈的线下好友推荐方法
KR20160095412A (ko) * 2015-02-03 2016-08-11 주식회사 다올넷 위치 정보를 활용한 푸드 트럭 영업지역 추천 시스템
CN105005615B (zh) * 2015-07-17 2017-03-08 广东小天才科技有限公司 一种基于移动轨迹进行终端推荐的方法、装置和系统
CN105791085B (zh) * 2016-01-26 2018-11-20 西安电子科技大学 在位置社交网络中基于位置与时间的好友推荐方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040156326A1 (en) * 2003-02-05 2004-08-12 Autodesk, Inc. Use of triggers and a location hypercube to enable push-based location applications
CN102509170A (zh) * 2011-10-10 2012-06-20 浙江鸿程计算机系统有限公司 一种基于历史轨迹数据挖掘的位置预测系统及方法
CN105279207A (zh) * 2014-07-25 2016-01-27 腾讯科技（深圳）有限公司 一种用户推荐方法、装置和系统
CN104796468A (zh) * 2015-04-14 2015-07-22 蔡宏铭 实现同行人即时通讯及同行信息共享的方法和系统
CN104765873A (zh) * 2015-04-24 2015-07-08 百度在线网络技术（北京）有限公司 用户相似度确定方法和装置

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111242535A (zh) * 2020-01-07 2020-06-05 贵阳货车帮科技有限公司 运输路线推送方法、装置、电子设备及可读存储介质
CN111242535B (zh) * 2020-01-07 2023-04-07 贵阳货车帮科技有限公司 运输路线推送方法、装置、电子设备及可读存储介质
CN112131481A (zh) * 2020-10-03 2020-12-25 北京一点网聚科技有限公司 推荐方法及装置
CN115150462A (zh) * 2022-05-25 2022-10-04 东风柳州汽车有限公司 行车话题推送方法、装置、设备及存储介质
CN115150462B (zh) * 2022-05-25 2023-10-31 东风柳州汽车有限公司 行车话题推送方法、装置、设备及存储介质

Also Published As

Publication number Publication date
CN108574715A (zh) 2018-09-25

Similar Documents

Publication Publication Date Title
WO2018166280A1 (zh) 信息推荐方法、装置、系统及储存介质
US8457653B2 (en) Method and apparatus for pre-fetching location-based data while maintaining user privacy
US10506373B2 (en) Harvesting labels for significant locations based on candidate points of interest and contextual data
US20190332615A1 (en) Interpersonal Spacetime Interaction System
US8775570B2 (en) Geographic recommendation online search system
US8923888B2 (en) Local content recommendations
JP2018528505A (ja) モバイルデバイスのロケーション履歴記録を提供、編成、および管理すること
KR20150010734A (ko) 지리적 위치에 기초한 정보 검색 방법 및 시스템
RU2569572C2 (ru) Способ и система для отображения деятельности пользователей на основе информации о географическом местоположении и компьютерный носитель данных для его реализации
US10484817B1 (en) Methods and systems for surfacing a user-customized segment within a geospatial navigation application
US11573988B2 (en) Storage of point of interest data on a user device for offline use
US20130073358A1 (en) Recommending print locations
US20150186530A1 (en) Point of interest tagging from social feeds
JP2019185612A (ja) 情報提供装置及び情報提供方法
US9141657B2 (en) Content delivery system with profile generation mechanism and method of operation thereof
JP6028493B2 (ja) サーバ装置、プログラム及び通信システム
US9406079B1 (en) Content relevance weighting system
US20170076338A1 (en) Content relevance weighting sysetm
US9396487B1 (en) System and method for weighting content items
JP4828653B1 (ja) サーバ、辞書生成方法、辞書生成プログラム、及びそのプログラムを記録するコンピュータ読み取り可能な記録媒体
JP5867760B1 (ja) コミュニケーション支援システム
KR102655723B1 (ko) 장소 추천 방법 및 시스템
US20150193795A1 (en) System and method for generating information regarding demographic composition of locations
US20160162809A1 (en) Enhanced searching and selection of rental properties and associated activities based on historic travel-related data
KR20120126690A (ko) 명함정보를 이용한 검색 서비스 제공 시스템 및 방법

Legal Events

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

Ref document number: 17900357

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC , EPO FORM 1205A DATED 06.12.2019.