WO2019061656A1 - 电子装置、基于lbs数据的服务场所推荐方法及存储介质 - Google Patents

电子装置、基于lbs数据的服务场所推荐方法及存储介质 Download PDF

Info

Publication number
WO2019061656A1
WO2019061656A1 PCT/CN2017/108738 CN2017108738W WO2019061656A1 WO 2019061656 A1 WO2019061656 A1 WO 2019061656A1 CN 2017108738 W CN2017108738 W CN 2017108738W WO 2019061656 A1 WO2019061656 A1 WO 2019061656A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
data
predetermined
service
lbs
Prior art date
Application number
PCT/CN2017/108738
Other languages
English (en)
French (fr)
Inventor
吴振宇
刘睿恺
王建明
肖京
Original Assignee
平安科技(深圳)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 平安科技(深圳)有限公司 filed Critical 平安科技(深圳)有限公司
Publication of WO2019061656A1 publication Critical patent/WO2019061656A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search customisation based on user profiles and personalisation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9537Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241Advertisements
    • G06Q30/0251Targeted advertisements
    • G06Q30/0261Targeted advertisements based on user location
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/50Network services
    • H04L67/52Network services specially adapted for the location of the user terminal

Definitions

  • the present application relates to the field of Internet data processing, and in particular, to an electronic device, a service site recommendation method based on LBS data, and a storage medium.
  • the application based on the LBS (Location Based Services) data is limited to analyzing and determining the geographic information around the location where the user is located according to the obtained current LBS data of the mobile terminal user, and recommending the geographical information around the user.
  • the corresponding goods around to the user For example, find the current location of the mobile phone user as a street in Shanghai, and then find the name of the hotel, theater, library, gas station and other service places within 1 km of the current location of the mobile phone user within the fixed square kilometer of the street. And address and recommend it to the user.
  • This kind of recommendation method is very convenient, but in terms of application, the user's needs cannot be fully satisfied, and the recommended service place is not necessarily urgently needed by the user. Therefore, it has certain limitations.
  • the present application provides an electronic device, a service site recommendation method based on LBS data, and a storage medium, which can utilize a large amount of LBS data analysis to derive a behavior track of a user's preference, and perform a service site recommendation based on a behavior track of the user's preference. Improves the accuracy of recommendations and increases the limitations of LBS data applications.
  • a first aspect of the present application provides an electronic device including a memory, a processor, and an LBS data-based service place stored on the memory and operable on the processor.
  • the recommendation system when the LBS data-based service place recommendation system is executed by the processor, implements the following steps:
  • each predetermined user is obtained from a predetermined database.
  • the LBS data corresponding to the time is set, and the acquired LBS data of each user is clustered and analyzed by using a predetermined first clustering algorithm to respectively analyze at least one behavior trajectory data corresponding to each user;
  • each user is clustered by using a predetermined second clustering algorithm to obtain different user groups, and the users whose similarities are greater than the preset threshold are assigned to the same user group.
  • the user whose similarity is less than or equal to the preset threshold is divided into different user groups;
  • D Analyze the LBS data of all the users in the user group to which each predetermined user belongs by using the predetermined service place recommendation model, analyze the behavior track of each predetermined user preference, and send each predetermined terminal to the predetermined terminal. a recommendation instruction of the service place on the behavior track of the user preference, or analyzing the LBS data of all users in the user group to which the user who issued the recommendation request belongs by using the predetermined service place recommendation model, and determining the behavior track of the user preference And transmitting, to the predetermined terminal, a recommendation instruction of the service place on the behavior track of the user preference.
  • the second aspect of the present application further provides a service site recommendation method based on LBS data, where the method includes the following steps:
  • each predetermined user is obtained from a predetermined database. Performing cluster analysis on the acquired LBS data of each user by using a predetermined first clustering algorithm to analyze at least one behavior trajectory data corresponding to each user;
  • a third aspect of the present application further provides a computer readable storage medium storing a service place recommendation system based on LBS data, the service place recommendation based on LBS data
  • the system can be executed by at least one processor to cause the at least one processor to perform the following steps:
  • each predetermined user is obtained from a predetermined database in a preset.
  • the corresponding LBS data in the time, using the predetermined number A clustering algorithm performs cluster analysis on the acquired LBS data of each user to separately analyze at least one behavior trajectory data corresponding to each user;
  • each user is clustered by using a predetermined second clustering algorithm to obtain different user groups, and the users whose similarities are greater than the preset threshold are assigned to the same user group.
  • the user whose similarity is less than or equal to the preset threshold is divided into different user groups;
  • D Analyze the LBS data of all the users in the user group to which each predetermined user belongs by using the predetermined service place recommendation model, analyze the behavior track of each predetermined user preference, and send each predetermined terminal to the predetermined terminal. a recommendation instruction of the service place on the behavior track of the user preference, or analyzing the LBS data of all users in the user group to which the user who issued the recommendation request belongs by using the predetermined service place recommendation model, and determining the behavior track of the user preference And transmitting, to the predetermined terminal, a recommendation instruction of the service place on the behavior track of the user preference.
  • the electronic device, the personal user recommendation method based on the LBS data, and the computer readable storage medium proposed by the present application firstly acquire LBS data corresponding to each user within a preset time from a predetermined database. Performing cluster analysis on the acquired LBS data to analyze at least one behavior trajectory data corresponding to each user respectively; secondly, analyzing the behavior trajectory data of each user to analyze the similarity between the users; Based on the similarity between the users, each user is clustered to obtain different user groups. Finally, the LBS data of all users in the same user group is analyzed to analyze the behavioral trajectories of all users in the user group.
  • the service location recommendation instruction on the behavior track of the user in the user group is sent to the predetermined terminal.
  • FIG. 1 is a schematic diagram of an optional application environment of each embodiment of the present application.
  • FIG. 2 is a schematic diagram of an optional hardware architecture of the electronic device of FIG. 1;
  • FIG. 3 is a schematic diagram of a program module of an embodiment of a service site recommendation system based on LBS data according to the present application;
  • FIG. 4 is a schematic diagram of a program module of another embodiment of a service site recommendation system based on LBS data according to the present application;
  • FIG. 5 is a schematic flowchart of an implementation manner of an embodiment of a service site recommendation method based on LBS data according to the present application
  • FIG. 6 is a schematic flowchart of an implementation of another embodiment of a service site recommendation method based on LBS data according to the present application.
  • first, second and the like in the present application are for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. .
  • features defining “first” and “second” may include at least one of the features, either explicitly or implicitly.
  • the technical solutions between the various embodiments may be combined with each other, but must be based on the realization of those skilled in the art, and when the combination of the technical solutions is contradictory or impossible to implement, it should be considered that the combination of the technical solutions does not exist. Nor is it within the scope of protection required by this application.
  • FIG. 1 it is a schematic diagram of an optional application environment of each embodiment of the present application.
  • the present application is applicable to an application environment including, but not limited to, a mobile terminal 1, an electronic device 2, and a network 3.
  • the mobile terminal 1 may be a mobile device, a smart phone, a notebook computer, a digital broadcast receiver, a PDA (Personal Digital Assistant), a PAD (Tablet), a PMP (Portable Multimedia Player), a navigation device, or the like. And fixed terminals such as digital TVs, desktop computers, notebooks, servers, and the like.
  • PDA Personal Digital Assistant
  • PAD Tablet
  • PMP Portable Multimedia Player
  • the electronic device 2 can be a computing device such as a rack server, a blade server, a tower server, or a rack server.
  • the electronic device 2 can be a stand-alone server or a server cluster composed of multiple servers.
  • Network 3 can be an intranet, an Internet, a Global System of Mobile communication (GSM), a Wideband Code Division Multiple Access (WCDMA), a 4G network, a 5G network. , wireless or wired networks such as Bluetooth and Wi-Fi.
  • GSM Global System of Mobile communication
  • WCDMA Wideband Code Division Multiple Access
  • 4G Fifth Generation
  • 5G Fifth Generation
  • wireless or wired networks such as Bluetooth and Wi-Fi.
  • FIG. 2 it is a schematic diagram of an optional hardware architecture of the electronic device 2 of FIG.
  • the electronic device 2 may include, but is not limited to, the memory 11, the processor 12, and the network interface 13 being communicably connected to each other through a system bus.
  • FIG. 2 only shows the electronic device 2 having the components 11-13, but it should be understood that not all illustrated components may be implemented, and more or fewer components may be implemented instead.
  • the memory 11 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (for example, SD or DX memory, etc.), a random access memory (RAM), and a static random access.
  • Memory SRAM
  • ROM read only memory
  • EEPROM electrically erasable programmable read only memory
  • PROM programmable read only memory
  • magnetic memory magnetic disk, optical disk, and the like.
  • the memory 11 can be an internal storage unit of the electronic device 2, such as a hard disk or memory of the electronic device 2.
  • the memory 11 may also be an external storage device of the electronic device 2, such as a plug-in hard disk equipped on the electronic device 2, a smart memory card (SMC), and a secure digital (Secure Digital, SD). ) card, flash Flash card, etc.
  • the memory 11 can also include both an internal storage unit of the electronic device 2 and an external storage device thereof.
  • the memory 11 is generally used to store an operating system installed in the electronic device 2 and various types of application software, such as program codes of the service place recommendation system 200 based on the LBS data. Further, the memory 11 can also be used to temporarily store various types of data that have been output or are to be output.
  • Processor 12 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments.
  • the processor 12 is typically used to control the overall operation of the electronic device 2, such as performing control and processing related to data interaction or communication with the mobile terminal 1.
  • the processor 12 is configured to run program code or processing data stored in the memory 11, such as a running LBS data-based service place recommendation system 200 or the like.
  • the network interface 13 may include a wireless network interface or a wired network interface, and the network interface 13 is typically used to establish a communication connection between the electronic device 2 and other electronic devices.
  • the network interface 13 is mainly used to connect the electronic device 2 to one or more mobile terminals 1 through the network 3, and establish a data transmission channel and a communication connection between the electronic device 2 and one or more mobile terminals 1. .
  • the present application proposes a service place recommendation system 200 based on LBS data.
  • the service location recommendation system 200 based on the LBS data may be divided into one or more modules, and one or more modules are stored in the memory 11 and are composed of one or more processors (in this embodiment The processor 12) executes to complete the application.
  • the service location recommendation system 200 based on the LBS data may be divided into an acquisition module 201, a first analysis module 202, a clustering module 203, and a second analysis module 204.
  • the program module referred to in the present application refers to a series of computer program instruction segments capable of performing a specific function, and is more suitable than the program to describe the execution process of the service site recommendation system 200 based on the LBS data in the electronic device 2.
  • the functions of each of the program modules 201-204 will be described in detail below.
  • the obtaining module 201 is configured to obtain a service site recommendation for each predetermined mobile terminal user, or obtain a service site recommendation request sent by a predetermined mobile terminal, and obtain each pre-determined database from a predetermined database.
  • the determined LBS data of the user in the preset time is clustered and analyzed by using the predetermined first clustering algorithm to analyze the LBS data of each user to analyze at least one behavior trajectory data corresponding to each user.
  • the LBS data includes geographic location information data, and various service information data related to the geographic location information data, the behavior trajectory data includes the travel type trajectory data, and/or the entertainment type trajectory data; the travel type trajectory data includes the itinerary.
  • Time and itinerary identification for example, frequent lunch at a restaurant at some time during noon
  • the entertainment type trajectory data includes entertainment time and address identification (for example, a trip to a determined location on weekends).
  • the mobile location service system is used to find the current geographic location of the mobile terminal user, and search Retrieve the name and address of a serviceable location within a certain range of the current location (for example, the name and address of a hotel, theater, library, gas station, etc.), and then recommend the searched name and address to the mobile terminal user So that the mobile terminal user selects the corresponding service according to the recommended name and address.
  • the mobile location service system records the current geographic location of the user (ie, the geographic location information data) and the selected service (ie, the related service information data), and stores the data in the database.
  • the acquiring module 201 may acquire LBS data of the mobile terminal user from the database (that is, the geographical location information data and the provided service information data related to the geographical location information data) ).
  • the obtained LBS data of each user is clustered and analyzed by using a predetermined first clustering algorithm to analyze at least one behavior trajectory data corresponding to each user.
  • the predetermined first aggregation is performed.
  • the class algorithm is a density-based clustering algorithm (for example, DBSCAN clustering algorithm).
  • the first time that the user A frequently locates in the preset time interval is the core point.
  • the number of times (20 times) is based on the geographical location of the restaurant B.
  • the geographic location F is the point where the density of the core point B reaches the area, and the area formed by the points in the density of each core point is the area where the density of the core point is reachable, if the time is within a preset time.
  • the third time that the geographic location G is located by the user A is equal to the first number of times, and the geographic location G is the boundary point of the density reachable area, so that the location frequently accessed by the user A within the preset time can be obtained.
  • frequent positioning A place to get the user's behavior trajectory data, for example, a period of time noon often go to a restaurant for lunch, or on weekends to determine the location and tourism.
  • the first analysis module 202 is configured to analyze behavior trajectory data of each user according to a predetermined similarity analysis rule, so as to analyze and obtain similarity between the users.
  • the predetermined similarity analysis rule in different embodiments may be a cosine angle similarity method, a Euclidean distance metric method, or a Pearson correlation coefficient method.
  • the Euclidean distance metric is taken as an example, wherein the Euclidean distance metric uses the following formula to calculate the similarity:
  • x and y in the above formula are respectively normalized vectors, and the result of the above formula is the similarity between the vector x and the vector y.
  • the similarity between the user A's behavior track data is in accordance with the preset normalization method. After the normalization process, the first vector x in the above formula is obtained, and the behavior track data of the user B is normalized according to a preset normalization manner, and then the second vector y in the above formula is obtained, and then the first A vector x and a second vector y are respectively substituted into the calculation formula of the above similarity, and the similarity between the user A and the user B is calculated.
  • the clustering module 203 is configured to cluster each user by using a predetermined second clustering algorithm based on the similarity between the users, so as to obtain different user groups, and the users whose similarities are greater than the preset threshold are divided into the same User groups, users whose similarity is less than or equal to the preset threshold are assigned to different user groups.
  • the predetermined second clustering algorithm includes a prototype-based objective function clustering algorithm (for example, k-means), a density-based clustering algorithm (for example, DBSCAN), or a hierarchical-based clustering algorithm (for example, Hiearchical). ).
  • k-means for example, k-means
  • DBSCAN density-based clustering algorithm
  • Hiearchical for example, Hiearchical
  • the second analysis module 204 is configured to analyze LBS data of all users in the user group to which each predetermined user belongs by using a predetermined service place recommendation model, and analyze behavior traces of each predetermined user preference, and to determine a predetermined behavior.
  • the terminal sends the recommendation instruction of the service place on the behavior track of each predetermined user preference, or uses the predetermined service place recommendation model to analyze the LBS data of all users in the user group to which the user who issued the recommendation request belongs, and determines the user.
  • a preferred behavior trajectory, and a recommendation instruction of the service place on the behavior track of the user preference is sent to the predetermined terminal.
  • the predetermined service place recommendation model is a collaborative filtering recommendation model, and the establishment of the service place recommendation model includes a training process of the model and a test process of the model.
  • the training process of the model includes:
  • the service site recommendation model is trained by using LBS data of each similar user in the training set to obtain a trained service place recommendation model
  • the service site recommendation model is tested by using the LBS data of each similar user in the test set. If the test passes, the training ends, or if the test fails, the LBS data samples of similar users in the training set are added and the training service place is re-executed. The steps to recommend the model.
  • the testing process for the model includes:
  • the obtained behavioral trajectories of the similar user preferences are compared with the behavior trajectories of the frequent activities of the similar users, and the number of users corresponding to the behavior trajectory of the corresponding preference is consistent with the preset percentage threshold (for example, 70) %), determining whether the test of the service place recommendation model passes, or determining the test of the service place recommendation model if the number of users corresponding to the preferred behavior track corresponding to the frequently active behavior track is less than or equal to the preset percentage threshold Fail.
  • the preset percentage threshold for example, 70
  • the service site recommendation system based on the LBS data may be further divided into a tracking module 205, which is used in the embodiment, as compared with the embodiment shown in FIG. Tracking the LBS data of the user who received the recommendation instruction, and analyzing the matching degree between the tracked user's LBS data and the recommended service location on the behavior track of the user preference, if the tracked user's LBS data and the location If the matching degree between the service places on the recommended behavior track of the user preference is less than or equal to the preset matching threshold, the restart command is issued for the first analysis module 202 and the clustering module 203.
  • a tracking module 205 Tracking the LBS data of the user who received the recommendation instruction, and analyzing the matching degree between the tracked user's LBS data and the recommended service location on the behavior track of the user preference, if the tracked user's LBS data and the location If the matching degree between the service places on the recommended behavior track of the user preference is less than or equal to the preset matching threshold, the restart command is issued for the first analysis module 202 and
  • the startup tracking module 205 tracks the user's LBS data, and according to the predetermined user's LBS data and behavior trajectory.
  • the mapping relationship between the LBS data of the user and the recommended behavior track of the service site is analyzed to further determine the accuracy of the recommendation of the service site recommendation model.
  • the analysis finds that the matching degree between the tracked LBS data of the user and the recommended service place behavior track is greater than a preset matching threshold, determining that the service place recommendation model is recommended for the user's service place. Accurate, the service site recommendation related to other users belonging to the same customer group as the user can be further performed.
  • a third analysis module (shown in the figure) is further included for utilizing a predetermined frequent item set before analyzing the similarity between the users.
  • the algorithm analyzes the behavior trajectory data of each user to analyze the living habit characteristics of each user.
  • the predetermined frequent item set analysis rule includes an FP-tree matching analysis algorithm.
  • the FP-tree matching analysis algorithm includes a construction process of the FP-tree matching model and a process of mining frequent patterns.
  • the construction process of the FP-tree matching model includes, firstly, constructing a database DB (also called a conditional projection database) composed of behavior trace data of each user and presetting a minimum support degree, and secondly, outputting a projection according to the database DB and the minimum support degree.
  • FP-tree continually iterating on the output FP-tree until the new FP-tree is constructed as an empty set, or the new FP-tree contains only one path (for example, only one behavior track data)
  • the construction process of the FP-tree matching model ends.
  • the process of mining frequent patterns is that when the constructed FP-tree is empty, its prefix is the frequent mode; when only one path is included, all possible combinations are enumerated by this.
  • the first analysis module 202 analyzes the lifestyle habits of each user by using a predetermined similarity analysis rule (for example, the user A is used to going to a specific place to exercise at the weekend, the user. B used to go to a specific mall for shopping, etc., to analyze the similarities between the users.
  • a predetermined similarity analysis rule for example, the user A is used to going to a specific place to exercise at the weekend, the user. B used to go to a specific mall for shopping, etc.
  • the LBS data service place recommendation method includes steps S301 to S304.
  • the determined database obtains the LBS data corresponding to each predetermined user within the preset time, and uses the predetermined first clustering algorithm to perform cluster analysis on the acquired LBS data of each user, so as to analyze respectively corresponding to each user. At least one behavioral trajectory data.
  • the LBS data includes geographic location information data, and various service information data related to the geographic location information data, the behavior trajectory data includes the travel type trajectory data, and/or the entertainment type trajectory data; the travel type trajectory data includes the itinerary.
  • Time and itinerary identification for example, frequent lunch at a restaurant at some time during noon
  • the entertainment type trajectory data includes entertainment time and address identification (for example, a trip to a determined location on weekends).
  • the mobile location service system is used to find the current geographic location of the mobile terminal user and to search for the name and address of the serviceable location within a certain range of the current geographic location (eg, hotels, theaters, libraries, gas stations, etc.) Name and address), and then recommend the searched related name and address to the mobile terminal user, so that the mobile terminal user selects the corresponding service according to the recommended name and address.
  • the mobile location service system records the current geographic location of the user (ie, the geographic location information data) and the selected service (ie, the related service information data), and stores the data in the database.
  • the acquiring module 201 may acquire LBS data of the mobile terminal user from the database (that is, the geographical location information data and the provided service information data related to the geographical location information data) ).
  • the obtained LBS data of each user is clustered and analyzed by using a predetermined first clustering algorithm to analyze at least one behavior trajectory data corresponding to each user.
  • the predetermined first aggregation is performed.
  • the class algorithm is a density-based clustering algorithm (for example, DBSCAN clustering algorithm).
  • the first time that the user A frequently locates in the preset time interval is the core point.
  • the number of times (20 times) is based on the geographical location of the restaurant B.
  • the geographical position F is positioned by the user A for a second time greater than or equal to the first time within a preset time (within one month) If the number is, the geographic location F is the point where the density of the core point B can reach the area, and the area formed by the points in the density of each core point is the core point density reachable area, if the geographical position is within a preset time
  • the third time that G is located by user A is equal to the first number of times, and the geographic location G is the boundary point of the density reachable area, so that the location that user A frequently locates in the preset time can be obtained, and then according to Frequently located field A track user behavior to get the data, for example, a period of time noon often go to a restaurant for lunch, or on weekends to determine the location and tourism.
  • the predetermined similarity analysis rule in different embodiments may be a cosine angle similarity method, a Euclidean distance metric method, or a Pearson correlation coefficient method.
  • the Euclidean distance metric is taken as an example, wherein The Reed distance metric uses the following formula to calculate the similarity:
  • x and y in the above formula are respectively normalized vectors, and the result of the above formula is the similarity between the vector x and the vector y.
  • analyzing user A and user B The similarity between the user A's behavior trajectory data is normalized according to the preset normalization method to obtain the first vector x in the above formula, and the user B's behavior trajectory data is preset according to After the normalization process is performed, the second vector y in the above formula is obtained, and then the first vector x and the second vector y are respectively substituted into the calculation formula of the similarity degree, and the calculation between the user A and the user B is calculated. Similarity.
  • each user is clustered by using a predetermined second clustering algorithm to obtain different user groups. Users whose similarity is greater than a preset threshold are assigned to the same user group, and the similarity is obtained. Users less than or equal to the preset threshold are assigned to different user groups.
  • the predetermined second clustering algorithm includes a prototype-based objective function clustering algorithm (for example, k-means), a density-based clustering algorithm (for example, DBSCAN), or a hierarchical-based clustering algorithm (for example, Hiearchical). ).
  • k-means for example, k-means
  • DBSCAN density-based clustering algorithm
  • Hiearchical for example, Hiearchical
  • the predetermined service place recommendation model is a collaborative filtering recommendation model, and the establishment of the service place recommendation model includes a training process of the model and a test process of the model.
  • the training process of the model includes:
  • the service site recommendation model is trained by using LBS data of each similar user in the training set to obtain a trained service place recommendation model
  • the service site recommendation model is tested by using the LBS data of each similar user in the test set. If the test passes, the training ends, or if the test fails, the LBS data samples of similar users in the training set are added and the training service place is re-executed. The steps to recommend the model.
  • the testing process for the model includes:
  • the obtained behavioral trajectories of the similar user preferences are compared with the behavior trajectories of the frequent activities of the similar users, and the number of users corresponding to the behavior trajectory of the corresponding preference is consistent with the preset percentage threshold (for example, 70) %), then determine the recommendation model for the service place.
  • the test passes, or if the number of users corresponding to the preferred behavior trajectory corresponding to the frequently active behavior trajectory is less than or equal to the preset percentage threshold, it is determined that the test of the service place recommendation model fails.
  • FIG. 6 it is a schematic flowchart of an implementation manner of another embodiment of a service site recommendation method based on LBS data according to the present application.
  • the LBS data-based service place recommendation method of the present embodiment includes steps S401 to S403, as compared with the embodiment shown in FIG.
  • Step S401 If a predetermined service location recommendation instruction sent by the terminal user is received, the LBS data corresponding to each predetermined user within the preset time is obtained from the predetermined database, and the predetermined first cluster is used.
  • the algorithm performs cluster analysis on the acquired LBS data of each user to analyze at least one behavior trajectory data corresponding to each user.
  • Step S402 analyzing the behavior trajectory data of each user according to the predetermined similarity analysis rule, so as to analyze and obtain the similarity between the users.
  • Step S403 based on the similarity between the users, clustering each user by using a predetermined second clustering algorithm to obtain different user groups, and the users whose similarities are greater than the preset threshold are divided into the same user group, similar Users whose degree is less than or equal to the preset threshold are assigned to different user groups.
  • Step S404 analyzing the LBS data of all users in the user group to which the user who issued the recommendation request belongs by using the predetermined service place recommendation model, analyzing the behavior track of the user preference, and transmitting the behavior track of the user preference to the predetermined terminal. Recommended instructions for the service location.
  • the method further includes the step S405 (not shown), tracking the LBS data of the user who receives the recommendation instruction, and analyzing the LBS data of the tracked user and the recommended The degree of matching between the service places on the behavior track of the user preference, if the matching degree between the tracked user's LBS data and the recommended service location on the user preference behavior track is less than or equal to the preset If the threshold is matched, step S402 and step S403 are repeated.
  • the recommendation instruction for the service place behavior trajectory for the user issuing an instruction to track the LBS data of the user, and analyzing the tracked LBS data of the user and the recommended service place The degree of matching between the behavioral trajectories further determines whether the recommendation of the service place recommendation model is accurate.
  • the analysis finds that the matching degree between the tracked LBS data of the user and the recommended service place behavior track is greater than a preset matching threshold, determining that the service place recommendation model is recommended for the user's service place. Accurate, the service site recommendation related to other users belonging to the same customer group as the user can be further performed.
  • the method before the step of analyzing the similarity between the users, the method further includes the step of analyzing the behavior track data of each user by using a predetermined frequent item set algorithm.
  • the habit characteristics of each user are obtained by analysis (all shown in the figure).
  • the predetermined frequent item set analysis rule includes an FP-tree matching analysis algorithm.
  • the FP-tree matching analysis algorithm includes a construction process of the FP-tree matching model and a process of mining frequent patterns.
  • the construction process of the FP-tree matching model includes, firstly, constructing a database DB (also called a conditional projection database) composed of behavior trace data of each user and presetting a minimum support degree, and secondly, outputting a projection according to the database DB and the minimum support degree.
  • FP-tree continually iterating on the output FP-tree until the new FP-tree is constructed as an empty set, or the new FP-tree contains only one path (for example, only one behavior track data)
  • the construction process of the FP-tree matching model ends.
  • the process of mining frequent patterns is that when the constructed FP-tree is empty, its prefix is the frequent mode; when only one path is included, all possible combinations are enumerated by this.
  • the prefix connection of the book gives you frequent patterns.
  • the user's lifestyle characteristics are analyzed by using a predetermined similarity analysis rule (for example, user A is accustomed to going to a specific place to exercise at the weekend, and user B is accustomed to going to the weekend.
  • a predetermined similarity analysis rule for example, user A is accustomed to going to a specific place to exercise at the weekend, and user B is accustomed to going to the weekend.
  • Shopping malls, etc. to analyze the similarities between individual users.
  • the electronic device of the present application, the service site recommendation method based on the user LBS data, and the storage medium are firstly obtained by acquiring the LBS data corresponding to each user within a preset time from a predetermined database.
  • the determined first clustering algorithm performs cluster analysis on the acquired LBS data to analyze at least one behavior trajectory data corresponding to each user respectively; and then analyzes behavior trajectory data of each user according to a predetermined similarity analysis rule. To obtain the similarity between each user by analysis; then, the similarity between the analyzed users is substituted into a predetermined second clustering algorithm for cluster analysis to define different users respectively composed of acquainted users.
  • the LBS data of each user in the user group to which the user with the identification information belongs is analyzed by using a predetermined service place recommendation model to analyze the behavior track of the user preference, and based on the behavior track of the user preference
  • the determined terminal sends a service location behavior track for the user Recommended instructions.
  • the foregoing embodiment method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be through hardware, but in many cases, the former is better.
  • Implementation Based on such understanding, the technical solution of the present application, which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk,
  • the optical disc includes a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the methods described in various embodiments of the present application.

Landscapes

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

Abstract

本申请公开了一种基于LBS数据的服务场所推荐方法、电子装置及存储介质。所述方法包括:从预先确定的数据库中获取各个用户在预设时间内对应的LBS数据,对获取的LBS数据进行聚类分析,以分别分析出各个用户对应的至少一种行为轨迹数据;分析各个用户的行为轨迹数据,以分析得到各个用户之间的相似度;基于各个用户之间的相似度,对各个用户进行聚类,以得到不同的用户群体;分析同一用户群体中所有用户的LBS数据,以分析出该用户群体中所有用户偏好的行为轨迹,并基于分析出的所有用户偏好的行为轨迹向预先确定的终端发送针对该用户群体中的用户的行为轨迹上的服务场所推荐指令。本申请可以为用户提供更准确的推荐,同时提高LBS数据应用的精准性。

Description

电子装置、基于LBS数据的服务场所推荐方法及存储介质
本申请要求于2017年9月30日提交中国专利局、申请号为201710916517.9,发明名称为“电子装置、基于LBS数据的服务场所推荐方法及存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及互联网数据处理领域,尤其涉及一种电子装置、基于LBS数据的服务场所推荐方法及存储介质。
背景技术
随着互联网的发展,用户的兴趣越来越广泛,且随着用户所处环境及生活水平的改变,用户的需求也在发生改变。因此,如何更好地理解和分析用户的行为,为用户提供针对其需求的服务变得至关重要。
目前,基于LBS(Location Based Services,基于位置的服务)数据的应用仅限于根据获取到的移动终端用户当前的LBS数据来分析判断用户所在的地点周围的地理信息,并结合用户周围的地理信息推荐周围相应的商品至用户。例如,找到手机用户的当前地理位置为上海市的某街道,然后在该街道固定平方公里范围内寻找手机用户当前位置处1公里范围内的宾馆、影院、图书馆、加油站等服务场所的名称和地址,并推荐给该用户。这种推荐方式非常方便,但是在应用上来说,不能完全满足用户的需求,且推荐的服务场所不一定是用户急需的。因此,具有一定的局限性。
发明内容
有鉴于此,本申请提出一种电子装置、基于LBS数据的服务场所推荐方法及存储介质,能够利用海量的LBS数据分析得出用户偏好的行为轨迹,并基于用户偏好的行为轨迹进行服务场所推荐,提高了推荐的精准性,并提高了对LBS数据应用的局限性。
首先,为实现上述目的,本申请第一方面提出一种电子装置,所述电子装置包括存储器、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基于LBS数据的服务场所推荐系统,所述基于LBS数据的服务场所推荐系统被所述处理器执行时实现如下步骤:
A、若需要对各个预先确定的的用户进行服务场所推荐,或者,若收到一个预先确定的用户的终端发出的服务场所推荐请求,则从预先确定的数据库中获取各个预先确定的用户在预设时间内对应的LBS数据,利用预先确定的第一聚类算法对获取的各个用户的LBS数据进行聚类分析,以分别分析出各个用户对应的至少一种行为轨迹数据;
B、根据预先确定的相似度分析规则分析各个用户的行为轨迹数据,以分析得到各个用户之间的相似度;
C、基于各个用户之间的相似度,利用预先确定的第二聚类算法对各个用户进行聚类,以得到不同的用户群体,所述相似度大于预设阈值的用户分至同一用户群体,所述相似度小于或者等于预设阈值的用户分至不同的用户群体;
D、利用预先确定的服务场所推荐模型分析各个预先确定的用户所属的用户群体中所有用户的LBS数据,分析出各个预先确定的用户偏好的行为轨迹,并向预先确定的终端发送各个预先确定的用户偏好的行为轨迹上的服务场所的推荐指令,或者,利用预先确定的服务场所推荐模型分析发出所述推荐请求的用户所属的用户群体中所有用户的LBS数据,确定出该用户偏好的行为轨迹,并向预先确定的终端发送该用户偏好的行为轨迹上的服务场所的推荐指令。
此外,为实现上述目的,本申请第二方面还提供一种基于LBS数据的服务场所推荐方法,该方法包括如下步骤:
S1、若需要对各个预先确定的用户进行服务场所推荐,或者,若收到一个预先确定的用户的终端发出的服务场所推荐请求,则从预先确定的数据库中获取各个预先确定的用户在预设时间内对应的LBS数据,利用预先确定的第一聚类算法对获取的各个用户的LBS数据进行聚类分析,以分别分析出各个用户对应的至少一种行为轨迹数据;
S2、根据预先确定的相似度分析规则分析各个用户的行为轨迹数据,以分析得到各个用户之间的相似度;
S3、基于各个用户之间的相似度,利用预先确定的第二聚类算法对各个用户进行聚类,以得到不同的用户群体,所述相似度大于预设阈值的用户分至同一用户群体,所述相似度小于或者等于预设阈值的用户分至不同的用户群体;
S4、利用预先确定的服务场所推荐模型分析各个预先确定的用户所属的用户群体中所有用户的LBS数据,分析出各个预先确定的用户偏好的行为轨迹,并向预先确定的终端发送各个预先确定的用户偏好的行为轨迹上的服务场所的推荐指令,或者,利用预先确定的服务场所推荐模型分析发出所述推荐请求的用户所属的用户群体中所有用户的LBS数据,确定出该用户偏好的行为轨迹,并向预先确定的终端发送该用户偏好的行为轨迹上的服务场所的推荐指令。
进一步地,为实现上述目的,本申请第三方面还提供一种计算机可读存储介质,所述计算机可读存储介质存储有基于LBS数据的服务场所推荐系统,所述基于LBS数据的服务场所推荐系统可被至少一个处理器执行,以使所述至少一个处理器执行如下步骤:
A、若需要对各个预先确定的用户进行服务场所推荐,或者,若收到一个预先确定的用户的终端发出的服务场所推荐请求,则从预先确定的数据库中获取各个预先确定的用户在预设时间内对应的LBS数据,利用预先确定的第 一聚类算法对获取的各个用户的LBS数据进行聚类分析,以分别分析出各个用户对应的至少一种行为轨迹数据;
B、根据预先确定的相似度分析规则分析各个用户的行为轨迹数据,以分析得到各个用户之间的相似度;
C、基于各个用户之间的相似度,利用预先确定的第二聚类算法对各个用户进行聚类,以得到不同的用户群体,所述相似度大于预设阈值的用户分至同一用户群体,所述相似度小于或者等于预设阈值的用户分至不同的用户群体;
D、利用预先确定的服务场所推荐模型分析各个预先确定的用户所属的用户群体中所有用户的LBS数据,分析出各个预先确定的用户偏好的行为轨迹,并向预先确定的终端发送各个预先确定的用户偏好的行为轨迹上的服务场所的推荐指令,或者,利用预先确定的服务场所推荐模型分析发出所述推荐请求的用户所属的用户群体中所有用户的LBS数据,确定出该用户偏好的行为轨迹,并向预先确定的终端发送该用户偏好的行为轨迹上的服务场所的推荐指令。
相较于现有技术,本申请所提出的电子装置、基于LBS数据的个性户推荐方法及计算机可读存储介质,首先,从预先确定的数据库中获取各个用户在预设时间内对应的LBS数据,对获取的LBS数据进行聚类分析,以分别分析出各个用户分别对应的至少一种行为轨迹数据;其次,分析各个用户的行为轨迹数据,以分析得到各个用户之间的相似度;再次,基于各个用户之间的相似度,对各个用户进行聚类,以得到不同的用户群体;最后,分析同一用户群体中所有用户的LBS数据,以分析出该用户群体中所有用户偏好的行为轨迹,并基于分析出的所有用户偏好的行为轨迹,向预先确定的终端发送针对该用户群体中的用户的行为轨迹上的服务场所推荐指令。这样,既可以避免现有技术中对LBS数据应用的局限性的弊端,也可以提高推荐的精准性。附图说明
图1是本申请各个实施例一可选的应用环境示意图;
图2是图1中电子装置一可选的硬件架构的示意图;
图3是本申请基于LBS数据的服务场所推荐系统一实施例的程序模块示意图;
图4是本申请基于LBS数据的服务场所推荐系统另一实施例的程序模块示意图;
图5是本申请基于LBS数据的服务场所推荐方法一实施例的实施流程示意图;
图6是本申请基于LBS数据的服务场所推荐方法另一实施例的实施流程示意图。
本申请目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。
具体实施方式
为了使本申请的目的、技术方案及优点更加清楚明白,以下结合附图及实施例,对本申请进行进一步详细说明。应当理解,此处所描述的具体实施例仅用以解释本申请,并不用于限定本申请。基于本申请中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本申请保护的范围。
需要说明的是,在本申请中涉及“第一”、“第二”等的描述仅用于描述目的,而不能理解为指示或暗示其相对重要性或者隐含指明所指示的技术特征的数量。由此,限定有“第一”、“第二”的特征可以明示或者隐含地包括至少一个该特征。另外,各个实施例之间的技术方案可以相互结合,但是必须是以本领域普通技术人员能够实现为基础,当技术方案的结合出现相互矛盾或无法实现时应当认为这种技术方案的结合不存在,也不在本申请要求的保护范围之内。
参阅图1所示,是本申请各个实施例一可选的应用环境示意图。
在本实施例中,本申请可应用于包括,但不仅限于,移动终端1、电子装置2、网络3的应用环境中。
其中,移动终端1可以是移动电话、智能电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、导航装置等等的可移动设备,以及诸如数字TV、台式计算机、笔记本、服务器等等的固定终端。
电子装置2可以是机架式服务器、刀片式服务器、塔式服务器或机柜式服务器等计算设备,且电子装置2可以是独立的服务器,也可以是多个服务器所组成的服务器集群。
网络3可以是企业内部网(Intranet)、互联网(Internet)、全球移动通讯系统(Global System of Mobile communication,GSM)、宽带码分多址(Wideband Code Division Multiple Access,WCDMA)、4G网络、5G网络、蓝牙(Bluetooth)、Wi-Fi等无线或有线网络。
参阅图2所示,是图1中电子装置2一可选的硬件架构的示意图。本实施例中,电子装置2可包括,但不仅限于,可通过系统总线相互通信连接存储器11、处理器12、网络接口13。需要指出的是,图2仅示出了具有组件11-13的电子装置2,但是应理解的是,并不要求实施所有示出的组件,可以替代的实施更多或者更少的组件。
其中,存储器11至少包括一种类型的可读存储介质,可读存储介质包括闪存、硬盘、多媒体卡、卡型存储器(例如,SD或DX存储器等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘等。在一些实施例中,存储器11可以电子装置2的内部存储单元,例如电子装置2的硬盘或内存。在另一些实施例中,存储器11也可以是电子装置2的外部存储设备,例如电子装置2上配备的插接式硬盘,智能存储卡(Smart Media Card,SMC),安全数字(Secure Digital,SD)卡,闪 存卡(Flash Card)等。当然,存储器11还可以既包括电子装置2的内部存储单元也包括其外部存储设备。本实施例中,存储器11通常用于存储安装于电子装置2的操作系统和各类应用软件,例如基于LBS数据的服务场所推荐系统200的程序代码等。此外,存储器11还可以用于暂时地存储已经输出或者将要输出的各类数据。
处理器12在一些实施例中可以是中央处理器(Central Processing Unit,CPU)、控制器、微控制器、微处理器、或其他数据处理芯片。处理器12通常用于控制电子装置2的总体操作,例如执行与移动终端1进行数据交互或者通信相关的控制和处理等。本实施例中,处理器12用于运行存储器11中存储的程序代码或者处理数据,例如运行的基于LBS数据的服务场所推荐系统200等。
网络接口13可包括无线网络接口或有线网络接口,网络接口13通常用于在电子装置2与其他电子设备之间建立通信连接。本实施例中,网络接口13主要用于通过网络3将电子装置2与一个或多个移动终端1相连,在电子装置2与一个或多个移动终端1之间的建立数据传输通道和通信连接。
至此,己经详细介绍了本申请各个实施例的应用环境和相关设备的硬件结构和功能。下面,将基于上述应用环境和相关设备,提出本申请的各个实施例。
首先,本申请提出一种基于LBS数据的服务场所推荐系统200。
参阅图3所示,是本申请基于LBS数据的服务场所推荐系统200一实施例的程序模块图。本实施例中,基于LBS数据的服务场所推荐系统200可以被分割成一个或多个模块,一个或者多个模块被存储于存储器11中,并由一个或多个处理器(本实施例中为处理器12)所执行,以完成本申请。例如,在图3中,基于LBS数据的服务场所推荐系统200可以被分割成获取模块201、第一分析模块202、聚类模块203、以及第二分析模块204。本申请所称的程序模块是指能够完成特定功能的一系列计算机程序指令段,比程序更适合于描述基于LBS数据的服务场所推荐系统200在电子装置2中的执行过程。以下将就各程序模块201-204的功能进行详细描述。
获取模块201,用于在若需要对各个预先确定的移动终端用户进行服务场所推荐,或者,若收到一个预先确定的移动终端发出的服务场所推荐请求,则从预先确定的数据库中获取各个预先确定的用户在预设时间内对应的LBS数据,利用预先确定的第一聚类算法对获取的各个用户的LBS数据进行聚类分析,以分别分析出各个用户对应的至少一种行为轨迹数据。
其中,LBS数据包括地理位置信息数据、及提供的与地理位置信息数据相关的各类服务信息数据,行为轨迹数据包括行程类型轨迹数据、及/或,娱乐类型轨迹数据;行程类型轨迹数据包括行程时间和行程标识(例如,中午某个时间段经常去某家餐馆吃午饭),娱乐类型轨迹数据包括娱乐时间和地址标识(例如,周末去确定的地点旅游)。
通常,移动定位服务系统用来找到移动终端用户的当前地理位置,并搜 索离当前地理位置一定范围内的可提供服务的场所的名称和地址(例如,宾馆、影院、图书馆、加油站等的名称和地址),然后推荐搜索到的相关名称和地址给移动终端用户,以使移动终端用户根据推荐的名称和地址选择对应的服务。其中,当移动终端用户选择服务后,移动定位服务系统会记录用户的当前地理位置(即所述地理位置信息数据)和所选择的服务(即所述相关的服务信息数据),并存储于数据库中。故,本实施例中,所述获取模块201可以从所述数据库中获取所述移动终端用户的LBS数据(即所述地理位置信息数据和提供的与所述地理位置信息数据相关的服务信息数据)。
然后,利用预先确定的第一聚类算法对获取的各个用户的LBS数据进行聚类分析,以分别分析出各个用户对应的至少一种行为轨迹数据,在本实施例,预先确定的第一聚类算法为基于密度的聚类算法(例如,DBSCAN聚类算法)。
进一步地,以获取的用户A的LBS数据为例说明具体的聚类分析过程,首先,需要预定义核心点,核心点密度可达的区域,以及密度可达区域的边界点,在本实施例中,以获取到的用户A在预设时间间隔内经常定位过的某一地理位置为核心点,例如,用户A在一个月内在中午12点钟定位餐厅E的第一次数超过了预设的次数(20次),则以该餐厅B的地理位置为核心点,若在预设的时间内(一个月内)若地理位置F被用户A定位过的第二次数大于或等于第一次数,则该地理位置F为核心点B密度可达区域中的点,由各个核心点密度可达区域中的点构成的区域为核心点密度可达的区域,若在预设的时间内若地理位置G被用户A定位过的第三次数等于第一次数,则该地理位置G为密度可达区域的边界点,这样,就可以获得用户A在预设时间内频繁定位过的场所,进而根据频繁定位过的场所得到用户A的行为轨迹数据,例如,中午某个时间段经常去某家餐馆吃午饭,或者,周末去确定的地点旅游等。
第一分析模块202,用于根据预先确定的相似度分析规则分析各个用户的行为轨迹数据,以分析得到各个用户之间的相似度。
其中,在不同的实施例中预先确定的相似度分析规则可以为余弦夹角相似法、欧几里德距离度量法、或皮尔逊相关系数法。
例如,在一实施例中,以欧几里德距离度量法为例来说明,其中,欧几里德距离度量法采用如下公式来计算相似度:
Figure PCTCN2017108738-appb-000001
需要说明的是,上述公式中的x和y分别为归一化之后的向量,上述公式的结果即为向量x和向量y的相似度,在本实施例中,例如,分析用户A与用户B之间的相似度,则将用户A的行为轨迹数据按照预设的归一化方式进行 归一化处理后得到上述公式中的第一向量x,将用户B的行为轨迹数据按照预设的归一化方式进行归一化处理后,得到上述公式中的第二向量y,然后将第一向量x与第二向量y分别代入上述相似度的计算公式,计算得到用户A与用户B之间的相似度。
聚类模块203,用于基于各个用户之间的相似度,利用预先确定的第二聚类算法对各个用户进行聚类,以得不同的用户群体,相似度大于预设阈值的用户分至同一用户群体,相似度小于或者等于预设阈值的用户分至不同的用户群体。
其中,预先确定的第二聚类算法包括基于原形的目标函数聚类算法(例如,k-means)、基于密度的聚类算法(例如,DBSCAN)、或基于层次的聚类算法(例如,Hiearchical)。
第二分析模块204,用于利用预先确定的服务场所推荐模型分析各个预先确定的用户所属的用户群体中所有用户的LBS数据,分析出各个预先确定的用户偏好的行为轨迹,并向预先确定的终端发送各个预先确定的用户偏好的行为轨迹上的服务场所的推荐指令,或者,利用预先确定的服务场所推荐模型分析发出推荐请求的用户所属的用户群体中所有用户的LBS数据,确定出该用户偏好的行为轨迹,并向预先确定的终端发送该用户偏好的行为轨迹上的服务场所的推荐指令。
其中,预先确定的服务场所推荐模型为协同过滤推荐模型,且服务场所推荐模型的建立包括模型的训练过程和模型的测试过程。
具体地,模型的训练过程包括:
获取预设数量(例如,100个)的相似用户的LBS数据样本,将各个相似用户的LBS数据样本分为对应的第一比例的训练集和第二比例的测试集;
利用训练集中的各个相似用户的LBS数据训练服务场所推荐模型,以得到训练好的服务场所推荐模型;
利用测试集中各个相似用户的LBS数据对服务场所推荐模型进行测试,若测试通过,则训练结束,或者,若测试不通过,则增加训练集中的相似用户的LBS数据样本并重新执行上述训练服务场所推荐模型的步骤。
模型的测试过程包括:
利用训练好的服务场所推荐模型对测试集中的各个相似用户的LBS数据进行分析,以得出各个相似用户偏好的行为轨迹;
将所得出的各个相似用户偏好的行为轨迹与各个相似用户经常活动的行为轨迹进行对比,若对应偏好的行为轨迹与经常活动的行为轨迹对应一致的用户数量超过预设的百分比阈值(例如,70%),则确定对服务场所推荐模型的测试通过,或者,若对应偏好的行为轨迹与经常活动的行为轨迹对应一致的用户数量小于或等于预设百分比阈值,则确定对服务场所推荐模型的测试不通过。
参阅图4所示,是本申请基于LBS数据的服务场所推荐系统另一实施例 的功能模块图。由图4可知,本实施例相较于图3所示的实施例,在本实施例中,基于LBS数据的服务场所推荐系统还可被分割为包括跟踪模块205,所述跟踪模块205用于跟踪接收到推荐指令的用户的LBS数据,并分析跟踪到的用户的LBS数据与所推荐的该用户偏好的行为轨迹上的服务场所之间的匹配度,若跟踪到的用户的LBS数据与所推荐的该用户偏好的行为轨迹上的服务场所之间的匹配度小于或等于预设的匹配阈值,则针对第一分析模块202及聚类模块203发出重新启动命令。
具体地,第二分析模块204向预先确定的终端发出针对该用户的服务场所行为轨迹推荐指令后,启动跟踪模块205跟踪该用户的LBS数据,并根据预先确定的用户的LBS数据与行为轨迹之间的映射关系,分析跟踪到的该用户的LBS数据与所推荐的服务场所行为轨迹之间的匹配度,进一步确定服务场所推荐模型推荐的准确性。
可以理解地,若分析得出跟踪到的该用户的LBS数据与所推荐的服务场所行为轨迹之间的匹配度大于预设的匹配阈值,则确定该服务场所推荐模型针对该用户的服务场所推荐准确,可以进一步地对与该用户属于同一客户群体的其他用户进行相关的服务场所推荐。
需要说明的是,在本申请的另一些实施例中,还包括第三分析模块(图中均为示出),用于在分析各个用户之间的相似度之前,利用预先确定的频繁项集算法对各个用户的行为轨迹数据进行分析,以分析得到各个用户的生活习惯特征。
其中,预先确定的频繁项集分析规则包括FP-tree匹配分析算法。具体地,FP-tree匹配分析算法包括FP-tree匹配模型的构造过程及挖掘频繁模式的过程。
FP-tree匹配模型的构造过程包括,首先,构建由各个用户的行为轨迹数据组成的数据库DB(也叫条件投影数据库)及预设一个最小支持度,其次,根据数据库DB及最小支持度输出投影FP-tree,不断地对输出的FP-tree通过迭代上述构建步骤,直到构造的新FP-tree为空集,或者新FP-tree只包含一条路径(例如,只有一条行为轨迹数据),则说明对FP-tree匹配模型的构造过程结束,挖掘频繁模式的过程为,当构造的FP-tree为空时,其前缀即为频繁模式;当只包含一条路径时,通过枚举所有可能组合与此书的前缀连接即可得到频繁模式。可以理解地,在分析出各个用户的生活习惯特征之后,第一分析模块202利用预先确定的相似度分析规则分析各个用户的生活习惯特征(例如,用户A习惯周末去特定的地点做运动,用户B习惯周末去特定商场购物等),以分析得到各个用户之间的相似度。
参阅图5所示,是本申请基于LBS数据服务场所推荐方法一实施例的实施流程示意图。由图5可知,在本实施例中,基于LBS数据服务场所推荐方法包括步骤S301至步骤S304。
S301,用于在若需要对各个预先确定的移动终端用户进行服务场所推荐,或者,若收到一个预先确定的移动终端发出的服务场所推荐请求,则从预先 确定的数据库中获取各个预先确定的用户在预设时间内对应的LBS数据,利用预先确定的第一聚类算法对获取的各个用户的LBS数据进行聚类分析,以分别分析出各个用户对应的至少一种行为轨迹数据。
其中,LBS数据包括地理位置信息数据、及提供的与地理位置信息数据相关的各类服务信息数据,行为轨迹数据包括行程类型轨迹数据、及/或,娱乐类型轨迹数据;行程类型轨迹数据包括行程时间和行程标识(例如,中午某个时间段经常去某家餐馆吃午饭),娱乐类型轨迹数据包括娱乐时间和地址标识(例如,周末去确定的地点旅游)。
通常,移动定位服务系统用来找到移动终端用户的当前地理位置,并搜索离当前地理位置一定范围内的可提供服务的场所的名称和地址(例如,宾馆、影院、图书馆、加油站等的名称和地址),然后推荐搜索到的相关名称和地址给移动终端用户,以使移动终端用户根据推荐的名称和地址选择对应的服务。其中,当移动终端用户选择服务后,移动定位服务系统会记录用户的当前地理位置(即所述地理位置信息数据)和所选择的服务(即所述相关的服务信息数据),并存储于数据库中。故,本实施例中,所述获取模块201可以从所述数据库中获取所述移动终端用户的LBS数据(即所述地理位置信息数据和提供的与所述地理位置信息数据相关的服务信息数据)。
然后,利用预先确定的第一聚类算法对获取的各个用户的LBS数据进行聚类分析,以分别分析出各个用户对应的至少一种行为轨迹数据,在本实施例,预先确定的第一聚类算法为基于密度的聚类算法(例如,DBSCAN聚类算法)。
进一步地,以获取的用户A的LBS数据为例说明具体的聚类分析过程,首先,需要预定义核心点,核心点密度可达的区域,以及密度可达区域的边界点,在本实施例中,以获取到的用户A在预设时间间隔内经常定位过的某一地理位置为核心点,例如,用户A在一个月内在中午12点钟定位餐厅E的第一次数超过了预设的次数(20次),则以该餐厅B的地理位置为核心点,若在预设的时间内(一个月内)若地理位置F被用户A定位过的第二次数大于或等于第一次数,则该地理位置F为核心点B密度可达区域中的点,由各个核心点密度可达区域中的点构成的区域为核心点密度可达区域,若在预设的时间内地理位置G被用户A定位过的第三次数等于第一次数,则该地理位置G为密度可达区域的边界点,这样,就可以获得用户A在预设时间内频繁定位过的场所,进而根据频繁定位过的场所得到用户A的行为轨迹数据,例如,中午某个时间段经常去某家餐馆吃午饭,或者,周末去确定的地点旅游等。
S302,根据预先确定的相似度分析规则分析各个用户的行为轨迹数据,以分析得到各个用户之间的相似度。
其中,在不同的实施例中预先确定的相似度分析规则可以为余弦夹角相似法、欧几里德距离度量法、或皮尔逊相关系数法。
例如,在一实施例中,以欧几里德距离度量法为例来说明,其中,欧几 里德距离度量法采用如下公式来计算相似度:
Figure PCTCN2017108738-appb-000002
需要说明的是,上述公式中的x和y分别为归一化之后的向量,上述公式的结果即为向量x和向量y的相似度,在本实施例中,例如,分析用户A与用户B之间的相似度,则将用户A的行为轨迹数据按照预设的归一化方式进行归一化处理后得到上述公式中的第一向量x,将用户B的行为轨迹数据按照预设的归一化方式进行归一化处理后,得到上述公式中的第二向量y,然后将第一向量x与第二向量y分别代入上述相似度的计算公式,计算得到用户A与用户B之间的相似度。
S303,基于各个用户之间的相似度,利用预先确定的第二聚类算法对各个用户进行聚类,以得到不同的用户群体,相似度大于预设阈值的用户分至同一用户群体,相似度小于或者等于预设阈值的用户分至不同的用户群体。
其中,预先确定的第二聚类算法包括基于原形的目标函数聚类算法(例如,k-means)、基于密度的聚类算法(例如,DBSCAN)、或基于层次的聚类算法(例如,Hiearchical)。
S304,利用预先确定的服务场所推荐模型分析各个预先确定的用户所属的用户群体中所有用户的LBS数据,分析出各个预先确定的用户偏好的行为轨迹,并向预先确定的终端发送各个预先确定的用户偏好的行为轨迹上的服务场所的推荐指令。
其中,预先确定的服务场所推荐模型为协同过滤推荐模型,且服务场所推荐模型的建立包括模型的训练过程和模型的测试过程。
具体地,模型的训练过程包括:
获取预设数量(例如,100个)的相似用户的LBS数据样本,将各个相似用户的LBS数据样本分为对应的第一比例的训练集和第二比例的测试集;
利用训练集中的各个相似用户的LBS数据训练服务场所推荐模型,以得到训练好的服务场所推荐模型;
利用测试集中各个相似用户的LBS数据对服务场所推荐模型进行测试,若测试通过,则训练结束,或者,若测试不通过,则增加训练集中的相似用户的LBS数据样本并重新执行上述训练服务场所推荐模型的步骤。
模型的测试过程包括:
利用训练好的服务场所推荐模型对测试集中的各个相似用户的LBS数据进行分析,以得出各个相似用户偏好的行为轨迹;
将所得出的各个相似用户偏好的行为轨迹与各个相似用户经常活动的行为轨迹进行对比,若对应偏好的行为轨迹与经常活动的行为轨迹对应一致的用户数量超过预设的百分比阈值(例如,70%),则确定对服务场所推荐模型 的测试通过,或者,若对应偏好的行为轨迹与经常活动的行为轨迹对应一致的用户数量小于或等于预设百分比阈值,则确定对服务场所推荐模型的测试不通过。
参阅图6所示,为本申请基于LBS数据的服务场所推荐方法另一实施例的实施流程示意图。由图6可知,相较于图5所示的实施例,本实施例的基于LBS数据的服务场所推荐方法包括步骤S401至步骤S403。
步骤S401,若收到一个预先确定的终端用户发出的服务场所推荐指令,则从预先确定的数据库中获取各个预先确定的用户在预设时间内对应的LBS数据,利用预先确定的第一聚类算法对获取的各个用户的LBS数据进行聚类分析,以分别分析出各个用户对应的至少一种行为轨迹数据。
步骤S402,根据预先确定的相似度分析规则分析各个用户的行为轨迹数据,以分析得到各个用户之间的相似度。
步骤S403,基于各个用户之间的相似度,利用预先确定的第二聚类算法对各个用户进行聚类,以得到不同的用户群体,相似度大于预设阈值的用户分至同一用户群体,相似度小于或者等于预设阈值的用户分至不同的用户群体。
步骤S404,利用预先确定的服务场所推荐模型分析发出推荐请求的用户所属的用户群体中所有用户的LBS数据,分析出该用户偏好的行为轨迹,并向预先确定的终端发送该用户偏好的行为轨迹上的服务场所的推荐指令。
需要说明的是,在本申请的其他一些实施例中,还包括步骤S405(图中未示出),跟踪接收到推荐指令的用户的LBS数据,并分析跟踪到的用户的LBS数据与所推荐的该用户偏好的行为轨迹上的服务场所之间的匹配度,若跟踪到的用户的LBS数据与所推荐的该用户偏好的行为轨迹上的服务场所之间的匹配度小于或等于预设的匹配阈值,则重复执行步骤S402及步骤S403。
具体地,在执行完向预先确定的终端发出针对该用户的服务场所行为轨迹推荐指令后,发出跟踪该用户的LBS数据的指令,并分析跟踪到的该用户的LBS数据与所推荐的服务场所行为轨迹之间的匹配度,进一步确定服务场所推荐模型的推荐是否准确。
可以理解地,若分析得出跟踪到的该用户的LBS数据与所推荐的服务场所行为轨迹之间的匹配度大于预设的匹配阈值,则确定该服务场所推荐模型针对该用户的服务场所推荐准确,可以进一步地对与该用户属于同一客户群体的其他用户进行相关的服务场所推荐。
进一步需要说明的是,在本申请的另一些实施例中,在分析各个用户之间的相似度的步骤之前,还包括步骤利用预先确定的频繁项集算法对各个用户的行为轨迹数据进行分析,以分析得到各个用户的生活习惯特征(图中均为示出)。
其中,预先确定的频繁项集分析规则包括FP-tree匹配分析算法。具体地,FP-tree匹配分析算法包括FP-tree匹配模型的构造过程及挖掘频繁模式的过程。
FP-tree匹配模型的构造过程包括,首先,构建由各个用户的行为轨迹数据组成的数据库DB(也叫条件投影数据库)及预设一个最小支持度,其次,根据数据库DB及最小支持度输出投影FP-tree,不断地对输出的FP-tree通过迭代上述构建步骤,直到构造的新FP-tree为空集,或者新FP-tree只包含一条路径(例如,只有一条行为轨迹数据),则说明对FP-tree匹配模型的构造过程结束,挖掘频繁模式的过程为,当构造的FP-tree为空时,其前缀即为频繁模式;当只包含一条路径时,通过枚举所有可能组合与此书的前缀连接即可得到频繁模式。
可以理解地,在分析出各个用户的生活习惯特征之后,利用预先确定的相似度分析规则分析各个用户的生活习惯特征(例如,用户A习惯周末去特定的地点做运动,用户B习惯周末去特定商场购物等),以分析得到各个用户之间的相似度。
通过上述各个实施例可知,本申请的电子装置、基于用户LBS数据的服务场所推荐方法及存储介质,首先,通过从预先确定的数据库中获取各个用户在预设时间内对应的LBS数据,利用预先确定的第一聚类算法对所获取的LBS数据进行聚类分析,以分析出各个用户分别对应的至少一种行为轨迹数据;然后,根据预先确定的相似度分析规则分析各个用户的行为轨迹数据,以分析得到各个用户之间的相似度;接着,将分析得到的各个用户之间的相似度代入预先确定的第二聚类算法进行聚类分析,以定义出分别由相识用户组成的不同用户群体;最后,利用预先确定的服务场所推荐模型分析带有标识信息的用户所属的用户群体中各个用户的LBS数据,以分析出该用户偏好的行为轨迹,并基于该用户偏好的行为轨迹向预先确定的终端发送针对该用户的服务场所行为轨迹推荐指令。这样,既可以避免现有技术中对LBS数据应用的局限性的弊端,也可以提高推荐的精准性。
上述本申请实施例序号仅仅为了描述,不代表实施例的优劣。
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件,但很多情况下前者是更佳的实施方式。基于这样的理解,本申请的技术方案本质上或者说对现有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(如ROM/RAM、磁碟、光盘)中,包括若干指令用以使得一台终端设备(可以是手机,计算机,服务器,空调器,或者网络设备等)执行本申请各个实施例所述的方法。
以上仅为本申请的优选实施例,并非因此限制本申请的专利范围,凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换,或直接或间接运用在其他相关的技术领域,均同理包括在本申请的专利保护范围内。

Claims (20)

  1. 一种电子装置,其特征在于,所述电子装置包括存储器、处理器,所述存储器上存储有可在所述处理器上运行的基于LBS数据的服务场所推荐系统,所述基于LBS数据的服务场所推荐系统被所述处理器执行时实现如下步骤:
    A、若需要对各个预先确定的用户进行服务场所推荐,或者,若收到一个预先确定的用户的终端发出的服务场所推荐请求,则从预先确定的数据库中获取各个预先确定的用户在预设时间内对应的LBS数据,利用预先确定的第一聚类算法对获取的各个用户的LBS数据进行聚类分析,以分别分析出各个用户对应的至少一种行为轨迹数据;
    B、根据预先确定的相似度分析规则分析各个用户的行为轨迹数据,以分析得到各个用户之间的相似度;
    C、基于各个用户之间的相似度,利用预先确定的第二聚类算法对各个用户进行聚类,以得到不同的用户群体,所述相似度大于预设阈值的用户分至同一用户群体,所述相似度小于或者等于预设阈值的用户分至不同的用户群体;
    D、利用预先确定的服务场所推荐模型分析各个预先确定的用户所属的用户群体中所有用户的LBS数据,分析出各个预先确定的用户偏好的行为轨迹,并向预先确定的终端发送各个预先确定的用户偏好的行为轨迹上的服务场所的推荐指令,或者,利用预先确定的服务场所推荐模型分析发出所述推荐请求的用户所属的用户群体中所有用户的LBS数据,确定出该用户偏好的行为轨迹,并向预先确定的终端发送该用户偏好的行为轨迹上的服务场所的推荐指令。
  2. 如权利要求1所述的电子装置,其特征在于,所述预先确定的数据库包括从所有移动终端用户的定位服务系统中获取到的移动定位数据及提供的与位置相关的服务数据,所述LBS数据包括地理位置信息数据、及提供的与所述地理位置信息数据相关的各类服务数据,所述行为轨迹数据包括行程类型轨迹数据、及/或,娱乐类型轨迹数据;所述行程类型轨迹数据包括行程时间和行程标识,所述娱乐类型轨迹数据包括娱乐时间和地址标识。
  3. 如权利要求1所述的电子装置,其特征在于,所述预先确定的第一聚类算法包括基于密度的聚类算法;所述预先确定的相似度分析规则包括余弦夹角相似法、欧几里德距离度量法、或皮尔逊相关系数法;所述预先确定的第二聚类算法包括基于原型的目标函数聚类算法、基于密度的聚类算法、或基于层次的聚类算法。
  4. 如权利要求1所述的电子装置,其特征在于,所述预先确定的服务场所推荐模型为协同过滤推荐模型。
  5. 如权利要求1所述的电子装置,其特征在于,所述基于LBS数据的服务场所推荐系统被所述处理器执行时还实现如下步骤:
    跟踪接收到推荐指令的用户的LBS数据,并分析跟踪到的用户的LBS数据与所推荐的该用户偏好的行为轨迹上的服务场所之间的匹配度,若跟踪到的用户的LBS数据与所推荐的该用户偏好的行为轨迹上的服务场所之间的匹配度小于或等于预设的匹配阈值,则重复执行步骤B和步骤C。
  6. 如权利要求2所述的电子装置,其特征在于,所述基于LBS数据的服务场所推荐系统被所述处理器执行时还实现如下步骤:
    跟踪接收到推荐指令的用户的LBS数据,并分析跟踪到的用户的LBS数据与所推荐的该用户偏好的行为轨迹上的服务场所之间的匹配度,若跟踪到的用户的LBS数据与所推荐的该用户偏好的行为轨迹上的服务场所之间的匹配度小于或等于预设的匹配阈值,则重复执行步骤B和步骤C。
  7. 如权利要求3所述的电子装置,其特征在于,所述基于LBS数据的服务场所推荐系统被所述处理器执行时还实现如下步骤:
    跟踪接收到推荐指令的用户的LBS数据,并分析跟踪到的用户的LBS数据与所推荐的该用户偏好的行为轨迹上的服务场所之间的匹配度,若跟踪到的用户的LBS数据与所推荐的该用户偏好的行为轨迹上的服务场所之间的匹配度小于或等于预设的匹配阈值,则重复执行步骤B和步骤C。
  8. 如权利要求4所述的电子装置,其特征在于,所述基于LBS数据的服务场所推荐系统被所述处理器执行时还实现如下步骤:
    跟踪接收到推荐指令的用户的LBS数据,并分析跟踪到的用户的LBS数据与所推荐的该用户偏好的行为轨迹上的服务场所之间的匹配度,若跟踪到的用户的LBS数据与所推荐的该用户偏好的行为轨迹上的服务场所之间的匹配度小于或等于预设的匹配阈值,则重复执行步骤B和步骤C。
  9. 一种基于LBS数据的服务场所推荐方法,其特征在于,所述方法包括如下步骤:
    S1、若需要对各个预先确定的用户进行服务场所推荐,或者,若收到一个预先确定的用户的终端发出的服务场所推荐请求,则从预先确定的数据库中获取各个预先确定的用户在预设时间内对应的LBS数据,利用预先确定的第一聚类算法对获取的各个用户的LBS数据进行聚类分析,以分别分析出各个用户对应的至少一种行为轨迹数据;
    S2、根据预先确定的相似度分析规则分析各个用户的行为轨迹数据,以分析得到各个用户之间的相似度;
    S3、基于各个用户之间的相似度,利用预先确定的第二聚类算法对各个用户进行聚类,以得到不同的用户群体,所述相似度大于预设阈值的用户分至同一用户群体,所述相似度小于或者等于预设阈值的用户分至不同的用户群体;
    S4、利用预先确定的服务场所推荐模型分析各个预先确定的用户所属的用户群体中所有用户的LBS数据,分析出各个预先确定的用户偏好的行为轨迹,并向预先确定的终端发送各个预先确定的用户偏好的行为轨迹上的服务场所的推荐指令,或者,利用预先确定的服务场所推荐模型分析发出所述推 荐请求的用户所属的用户群体中所有用户的LBS数据,确定出该用户偏好的行为轨迹,并向预先确定的终端发送该用户偏好的行为轨迹上的服务场所的推荐指令。
  10. 如权利要求9所述的基于LBS数据的服务场所推荐方法,其特征在于,所述预先确定的数据库包括从所有移动终端用户的定位服务系统中获取到的移动定位数据及提供的与位置相关的服务数据,所述LBS数据包括地理位置信息数据、及提供的与所述地理位置信息数据相关的各类服务数据,所述行为轨迹数据包括行程类型轨迹数据、及/或,娱乐类型轨迹数据;所述行程类型轨迹数据包括行程时间和行程标识,所述娱乐类型轨迹数据包括娱乐时间和地址标识。
  11. 如权利要求9所述的基于LBS数据的服务场所推荐方法,其特征在于,所述预先确定的第一聚类算法包括基于密度的聚类算法;所述预先确定的相似度分析规则包括余弦夹角相似法、欧几里德距离度量法、或皮尔逊相关系数法;所述预先确定的第二聚类算法包括基于原形的目标函数聚类算法、基于密度的聚类算法、或基于层次的聚类算法。
  12. 如权利要求9所述的基于LBS数据的服务场所推荐方法,其特征在于,所述预先确定的服务场所推荐模型为协同过滤推荐模型。
  13. 如权利要求9所述的基于LBS数据的服务场所推荐方法,其特征在于,所述基于LBS数据的服务场所推荐系统被所述处理器执行时还实现如下步骤:
    跟踪接收到推荐指令的用户的LBS数据,并分析跟踪到的用户的LBS数据与所推荐的该用户偏好的行为轨迹上的服务场所之间的匹配度,若跟踪到的用户的LBS数据与所推荐的该用户偏好的行为轨迹上的服务场所之间的匹配度小于或等于预设的匹配阈值,则重复执行步骤B和步骤C。
  14. 如权利要求10所述的基于LBS数据的服务场所推荐方法,其特征在于,所述基于LBS数据的服务场所推荐系统被所述处理器执行时还实现如下步骤:
    跟踪接收到推荐指令的用户的LBS数据,并分析跟踪到的用户的LBS数据与所推荐的该用户偏好的行为轨迹上的服务场所之间的匹配度,若跟踪到的用户的LBS数据与所推荐的该用户偏好的行为轨迹上的服务场所之间的匹配度小于或等于预设的匹配阈值,则重复执行步骤B和步骤C。
  15. 如权利要求11所述的基于LBS数据的服务场所推荐方法,其特征在于,所述基于LBS数据的服务场所推荐系统被所述处理器执行时还实现如下步骤:
    跟踪接收到推荐指令的用户的LBS数据,并分析跟踪到的用户的LBS数据与所推荐的该用户偏好的行为轨迹上的服务场所之间的匹配度,若跟踪到的用户的LBS数据与所推荐的该用户偏好的行为轨迹上的服务场所之间的匹配度小于或等于预设的匹配阈值,则重复执行步骤B和步骤C。
  16. 如权利要求12所述的基于LBS数据的服务场所推荐方法,其特征在 于,所述基于LBS数据的服务场所推荐系统被所述处理器执行时还实现如下步骤:
    跟踪接收到推荐指令的用户的LBS数据,并分析跟踪到的用户的LBS数据与所推荐的该用户偏好的行为轨迹上的服务场所之间的匹配度,若跟踪到的用户的LBS数据与所推荐的该用户偏好的行为轨迹上的服务场所之间的匹配度小于或等于预设的匹配阈值,则重复执行步骤B和步骤C。
  17. 一种计算机可读存储介质,所述计算机可读存储介质存储有基于LBS数据的服务场所推荐系统,所述基于LBS数据的服务场所推荐系统可被至少一个处理器执行,以使所述至少一个处理器执行如下步骤:
  18. 如权利要求17所述的计算机可读存储介质,其特征在于,所述预先确定的数据库包括从所有移动终端用户的定位服务系统中获取到的移动定位数据及提供的与位置相关的服务数据,所述LBS数据包括地理位置信息数据、及提供的与所述地理位置信息数据相关的各类服务数据,所述行为轨迹数据包括行程类型轨迹数据、及/或,娱乐类型轨迹数据;所述行程类型轨迹数据包括行程时间和行程标识,所述娱乐类型轨迹数据包括娱乐时间和地址标识。
  19. 如权利要求17所述的计算机可读存储介质,其特征在于,所述预先确定的第一聚类算法包括基于密度的聚类算法;所述预先确定的相似度分析规则包括余弦夹角相似法、欧几里德距离度量法、或皮尔逊相关系数法;所述预先确定的第二聚类算法包括基于原型的目标函数聚类算法、基于密度的聚类算法、或基于层次的聚类算法。
  20. 如权利要求17所述的计算机可读存储介质,其特征在于,所述基于LBS数据的服务场所推荐系统被所述处理器执行时还实现如下步骤:
    跟踪接收到推荐指令的用户的LBS数据,并分析跟踪到的用户的LBS数据与所推荐的该用户偏好的行为轨迹上的服务场所之间的匹配度,若跟踪到的用户的LBS数据与所推荐的该用户偏好的行为轨迹上的服务场所之间的匹配度小于或等于预设的匹配阈值,则重复执行步骤B和步骤C。
PCT/CN2017/108738 2017-09-30 2017-10-31 电子装置、基于lbs数据的服务场所推荐方法及存储介质 WO2019061656A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710916517.9A CN107798557B (zh) 2017-09-30 2017-09-30 电子装置、基于lbs数据的服务场所推荐方法及存储介质
CN201710916517.9 2017-09-30

Publications (1)

Publication Number Publication Date
WO2019061656A1 true WO2019061656A1 (zh) 2019-04-04

Family

ID=61533085

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/108738 WO2019061656A1 (zh) 2017-09-30 2017-10-31 电子装置、基于lbs数据的服务场所推荐方法及存储介质

Country Status (2)

Country Link
CN (1) CN107798557B (zh)
WO (1) WO2019061656A1 (zh)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110309379A (zh) * 2019-05-22 2019-10-08 中国平安人寿保险股份有限公司 产品推荐方法、装置、设备及计算机可读存储介质
CN110941278A (zh) * 2019-12-20 2020-03-31 交控科技股份有限公司 一种站内动态安全分析方法
CN111177534A (zh) * 2019-12-06 2020-05-19 南京欣网互联信息技术有限公司 一种基于互联网大数据的用户行为轨迹分析方法
CN111814067A (zh) * 2020-06-30 2020-10-23 北京百度网讯科技有限公司 好友推荐方法、装置、设备及存储介质
CN111881243A (zh) * 2020-07-30 2020-11-03 河北工程大学 一种出租车轨迹热点区域分析方法及系统
CN111882399A (zh) * 2020-07-31 2020-11-03 平安国际融资租赁有限公司 服务信息推荐方法、装置、计算机系统及可读存储介质
CN112040024A (zh) * 2020-08-28 2020-12-04 北京明略昭辉科技有限公司 数据处理方法、装置、设备及存储介质
CN112069913A (zh) * 2020-08-13 2020-12-11 东软集团股份有限公司 用户的识别方法、装置、存储介质和电子设备
CN112348614A (zh) * 2019-11-27 2021-02-09 北京京东尚科信息技术有限公司 用于推送信息的方法和装置
CN114036516A (zh) * 2021-10-27 2022-02-11 西安电子科技大学 一种基于两阶段类比推理的未知敏感函数发现方法

Families Citing this family (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108985950B (zh) * 2018-07-13 2023-04-18 平安科技(深圳)有限公司 电子装置、用户骗保风险预警方法及存储介质
CN110874609B (zh) * 2018-09-04 2022-08-16 武汉斗鱼网络科技有限公司 基于用户行为的用户聚类方法、存储介质、设备及系统
CN110895588B (zh) * 2018-09-13 2022-07-22 中国移动通信有限公司研究院 一种数据处理方法及设备
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
CN109829020B (zh) * 2018-12-20 2023-04-07 平安科技(深圳)有限公司 地点资源数据推送方法、装置、计算机设备和存储介质
CN110348990A (zh) * 2019-06-19 2019-10-18 北京淇瑀信息科技有限公司 基于用户出行轨迹的信贷额度调整方法、装置及电子设备
CN110750603B (zh) * 2019-09-06 2022-08-12 日立楼宇技术(广州)有限公司 楼宇服务预测方法、装置、系统、计算机设备和存储介质
CN110753102B (zh) * 2019-10-15 2021-01-05 浙江口碑网络技术有限公司 基于地磁的服务信息推送方法及装置
CN110730432B (zh) * 2019-10-21 2021-01-08 深圳市名通科技股份有限公司 邻近用户识别方法、终端及可读存储介质
CN111222686A (zh) * 2019-11-21 2020-06-02 施甸县保施高速公路投资开发有限公司 优化高速公路服务区业态的方法
CN111209487B (zh) * 2020-01-02 2020-10-27 平安科技(深圳)有限公司 用户数据分析方法、服务器及计算机可读存储介质
CN111523058B (zh) * 2020-04-21 2023-11-03 北京嘀嘀无限科技发展有限公司 服务区域分析处理方法、装置、设备及存储介质
CN112085099B (zh) * 2020-09-09 2022-05-17 西南大学 一种分布式学生聚类集成方法及系统
CN111949891B (zh) * 2020-10-09 2021-06-15 广州斯沃德科技有限公司 一种基于车辆轨迹聚类的个性化信息推荐方法及系统
CN112231392A (zh) * 2020-10-29 2021-01-15 广东机场白云信息科技有限公司 民航客源数据分析方法、电子设备、计算机可读存储介质
CN112395500B (zh) * 2020-11-17 2023-09-05 平安科技(深圳)有限公司 内容数据推荐方法、装置、计算机设备及存储介质
CN113310495B (zh) * 2021-06-08 2022-07-12 湖南师范大学 一种室内定位方法、系统、电子设备及可读存储介质
CN113379454A (zh) * 2021-06-09 2021-09-10 北京房江湖科技有限公司 数据处理方法、装置、电子设备及存储介质
CN113254570B (zh) * 2021-07-15 2021-10-01 浙江网商银行股份有限公司 数据识别方法以及装置
CN114282126B (zh) * 2022-03-01 2022-05-27 阿里健康科技(中国)有限公司 信息推荐方法、装置、介质及设备
CN115795318A (zh) * 2022-11-17 2023-03-14 北京白龙马云行科技有限公司 用例对象的归类方法、模型训练方法、设备和存储介质
CN115659197A (zh) * 2022-12-28 2023-01-31 湖南财政经济学院 数据安全监测模型训练方法及应用方法、装置和存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102880719A (zh) * 2012-10-16 2013-01-16 四川大学 基于位置社交网络的用户轨迹相似性挖掘方法
CN103116614A (zh) * 2013-01-25 2013-05-22 北京奇艺世纪科技有限公司 一种基于用户轨迹的协同过滤推荐方法、装置及系统
CN103747523A (zh) * 2014-01-14 2014-04-23 上海河广信息科技有限公司 一种基于无线网络的用户位置预测系统和方法
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

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102880719A (zh) * 2012-10-16 2013-01-16 四川大学 基于位置社交网络的用户轨迹相似性挖掘方法
CN103116614A (zh) * 2013-01-25 2013-05-22 北京奇艺世纪科技有限公司 一种基于用户轨迹的协同过滤推荐方法、装置及系统
CN103747523A (zh) * 2014-01-14 2014-04-23 上海河广信息科技有限公司 一种基于无线网络的用户位置预测系统和方法
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

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110309379A (zh) * 2019-05-22 2019-10-08 中国平安人寿保险股份有限公司 产品推荐方法、装置、设备及计算机可读存储介质
CN110309379B (zh) * 2019-05-22 2023-07-25 中国平安人寿保险股份有限公司 产品推荐方法、装置、设备及计算机可读存储介质
CN112348614A (zh) * 2019-11-27 2021-02-09 北京京东尚科信息技术有限公司 用于推送信息的方法和装置
CN111177534A (zh) * 2019-12-06 2020-05-19 南京欣网互联信息技术有限公司 一种基于互联网大数据的用户行为轨迹分析方法
CN110941278A (zh) * 2019-12-20 2020-03-31 交控科技股份有限公司 一种站内动态安全分析方法
CN111814067B (zh) * 2020-06-30 2024-03-15 北京百度网讯科技有限公司 好友推荐方法、装置、设备及存储介质
CN111814067A (zh) * 2020-06-30 2020-10-23 北京百度网讯科技有限公司 好友推荐方法、装置、设备及存储介质
CN111881243A (zh) * 2020-07-30 2020-11-03 河北工程大学 一种出租车轨迹热点区域分析方法及系统
CN111881243B (zh) * 2020-07-30 2024-04-02 河北工程大学 一种出租车轨迹热点区域分析方法及系统
CN111882399A (zh) * 2020-07-31 2020-11-03 平安国际融资租赁有限公司 服务信息推荐方法、装置、计算机系统及可读存储介质
CN112069913A (zh) * 2020-08-13 2020-12-11 东软集团股份有限公司 用户的识别方法、装置、存储介质和电子设备
CN112069913B (zh) * 2020-08-13 2024-04-30 东软集团股份有限公司 用户的识别方法、装置、存储介质和电子设备
CN112040024A (zh) * 2020-08-28 2020-12-04 北京明略昭辉科技有限公司 数据处理方法、装置、设备及存储介质
CN112040024B (zh) * 2020-08-28 2023-05-09 北京明略昭辉科技有限公司 数据处理方法、装置、设备及存储介质
CN114036516A (zh) * 2021-10-27 2022-02-11 西安电子科技大学 一种基于两阶段类比推理的未知敏感函数发现方法

Also Published As

Publication number Publication date
CN107798557A (zh) 2018-03-13
CN107798557B (zh) 2020-09-25

Similar Documents

Publication Publication Date Title
WO2019061656A1 (zh) 电子装置、基于lbs数据的服务场所推荐方法及存储介质
US20220245118A1 (en) Refining Location Estimates and Reverse Geocoding Based on a User Profile
US10692151B1 (en) Homeowners insurance application process using geotagged photos
US8560608B2 (en) Crowd formation based on physical boundaries and other rules
Ojagh et al. A location-based orientation-aware recommender system using IoT smart devices and Social Networks
US9420426B2 (en) Inferring a current location based on a user location history
US20130205196A1 (en) Location-based mobile application marketplace system
WO2015120746A1 (zh) 一种用户目的地点的预测方法及装置
EP2710819A2 (en) Discovering nearby places based on automatic query
US10871378B2 (en) Detecting changes in map data based on device location data
US9747304B2 (en) Approximating a user location
WO2021259007A1 (zh) 基于行为轨迹的数据推送方法、系统和计算机设备
Cheng et al. Chinese Location Word Recognition Using Service Context Information for Location‐Based Service
CN107924415B (zh) 从位置不可感知设备向搜索查询提供位置信息以提高用户交互性能
WO2018227773A1 (zh) 地点推荐方法、装置、计算机设备和存储介质
JP2015158799A (ja) 時空間クラスタリング処理装置、方法及びプログラム
US20140180574A1 (en) Electronic device and method for updating rendezvous location of communication devices
WO2017088475A1 (zh) 一种定位方法和装置
US20140214791A1 (en) Geotiles for finding relevant results from a geographically distributed set
US11963128B2 (en) Evaluating IP location on a client device
US10006985B2 (en) Mobile device and method for determining a place according to geolocation information
CN110709836B (zh) 对网页上的位置变化的反应
KR101820043B1 (ko) 모바일 단말 식별 및 이를 이용한 비즈니스 모델
US20240224223A1 (en) Evaluating IP Location On A Client Device
KR20160087199A (ko) 멤버십 카드의 사용 정보를 이용한 가맹점 위치정보 수집 시스템, 가맹점 위치정보 수집 방법 및 이를 위한 장치

Legal Events

Date Code Title Description
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 13.10.2020)

122 Ep: pct application non-entry in european phase

Ref document number: 17927105

Country of ref document: EP

Kind code of ref document: A1