WO2019237571A1 - Procédé de recommandation directionnelle à un utilisateur, dispositif et support de stockage, et serveur - Google Patents

Procédé de recommandation directionnelle à un utilisateur, dispositif et support de stockage, et serveur Download PDF

Info

Publication number
WO2019237571A1
WO2019237571A1 PCT/CN2018/108072 CN2018108072W WO2019237571A1 WO 2019237571 A1 WO2019237571 A1 WO 2019237571A1 CN 2018108072 W CN2018108072 W CN 2018108072W WO 2019237571 A1 WO2019237571 A1 WO 2019237571A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
information
candidate
portrait
feature information
Prior art date
Application number
PCT/CN2018/108072
Other languages
English (en)
Chinese (zh)
Inventor
黄俊凯
黄晓霞
靳倩慧
杜立
盛亮
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 WO2019237571A1 publication Critical patent/WO2019237571A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0645—Rental transactions; Leasing transactions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/16—Real estate

Definitions

  • the present application relates to the technical field of house leasing, and in particular, the present application relates to a method, a device, a storage medium, and a server for recommending users in a targeted manner.
  • Landlords can post listing information in the relevant rental app. Landlords and tenants can contact this rental app to determine whether the current listing is suitable for tenants or landlords. Determine if the current tenant meets their requirements.
  • apps in the market generally lack basic information about landlords and tenants, which is not conducive to information screening when matching each other; lack of authentication information such as real name and credit information can not guarantee trust; there is no rich label information and evaluation information to help match More suitable roommate or landlord.
  • the purpose of this application is to solve at least one of the above-mentioned technical shortcomings, in particular, the inability to match more suitable roommates or landlords through rich content.
  • This application provides a method for recommending users in a targeted manner, which includes the following steps: acquiring characteristic information of a current user, constructing a user portrait based on the characteristic information, acquiring characteristic information to be matched set by the current user, and judging a candidate user set. Whether there is a target user whose user portrait matches the user portrait of the current user and whose feature information matches the feature information to be matched, and any candidate user in the candidate user set corresponds to a user portrait and feature information;
  • An apparatus for recommending users in a targeted manner includes a construction module for acquiring user characteristic information and constructing a user portrait based on the characteristic information; a first acquisition module for acquiring the current user settings Feature information to be matched; a judging module for judging whether there is a target user matching the user portrait and matching the matching feature information; a pushing module for when there is a match with the user portrait and with When the target user matched by the matching feature information is pushed to the user, a message including the feature information of the target user is pushed.
  • a non-volatile computer-readable storage medium provided in the embodiments of the present application.
  • a computer program is stored on the non-volatile computer-readable storage medium, and when the program is executed by a processor, a directed recommendation user is implemented.
  • Method, the method for directional recommending users includes the following steps: acquiring characteristic information of the current user, constructing a user portrait based on the characteristic information; acquiring characteristic information to be matched set by the current user; judging whether a user exists in a set of candidate users For a target user whose portrait matches the user portrait of the current user and whose feature information matches the feature information to be matched, any candidate user in the candidate user set corresponds to a user portrait and feature information; when When there is a target user whose user portrait matches the user portrait of the current user and whose feature information matches the feature information to be matched, a message including feature information of the target user is pushed to the current user.
  • a server provided in the embodiment of the present application includes: one or more processors; a memory; and one or more application programs, wherein the one or more application programs are stored in the memory and configured to be provided by The one or more processors execute, and the one or more application programs are configured to execute a method for recommending users in a targeted manner.
  • the method for recommending users in directed includes the following steps: acquiring characteristic information of a current user, Constructing a user portrait using the feature information; obtaining the feature information to be matched set by the current user; determining whether a user profile in the set of candidate users matches the user profile of the current user and the feature information matches the feature information to be matched For a matched target user, any candidate user in the candidate user set corresponds to a user portrait and feature information; when there is a user portrait that matches the user portrait of the current user and the feature information matches the candidate feature When the target user whose information matches, push to the current user a message including the characteristic information of the target user. Information.
  • the method for directionally recommending users not only can it recommend a preferred matching user to it based on the characteristic information of the current user, thereby improving the user's satisfaction during the residence, but also realizing the user's
  • the full range description also allows users to further understand their own characteristics, so that users can better plan their time.
  • FIG. 1 is a schematic flowchart of an implementation manner in a typical embodiment of a method for directional recommending users of this application;
  • FIG. 2 is a schematic flowchart of still another implementation manner in a typical embodiment of a method for directional recommending users
  • FIG. 3 is a schematic structural diagram of a typical embodiment of a device for directional recommending users in this application;
  • FIG. 4 is a schematic structural diagram of an embodiment of a server of the present application.
  • the method for directionally recommending users provided in the embodiments of the present application is mainly applied to the field of house leasing.
  • the landlord or tenant can be used to recommend the landlord or tenant with their personality, habits, and hobbies.
  • the doubts of the tenant in the process of renting a house match the house leasing transaction between the landlord and the tenant.
  • the user in the embodiment of the present application may be a landlord or a tenant.
  • a method for recommending users in a targeted manner provided in the embodiments of the present application.
  • the method includes the following steps:
  • S100 Acquire characteristic information of the current user, and construct a user portrait according to the characteristic information.
  • the characteristic information includes one or more of basic user information, behavior data, and evaluated information.
  • the method for recommending users in a targeted manner provided in the embodiments of the present application is mainly used in the field of renting houses. Therefore, the basic user information includes the user's name, gender, age, phone number, personal living habits, hometown, and company work hours. One or more of them; behavioral data mainly includes one or more of the user's home replacement frequency, cycle, rent delivery cycle, long period of rent advance or delay, etc .; the evaluated information includes other users ’ Housing rental app's evaluation information for the current user. Constructing a user portrait based on the user's characteristic information is a brief multi-dimensional description of the user.
  • Its representation can be text, data tables, histograms, radar graphics, etc. Further, in one or more of the foregoing forms, When representing user portraits, they can also be combined with ratings. That is, a scoring rule is preset in the system, and key information in the foregoing feature information is collected to determine a corresponding score, which includes a single score and a total score. The total score is a score based on all the user's characteristic information, and the individual score is the user's score on a certain category or a certain characteristic information, such as the score of the degree of care of the furniture for the rent, so that the user can follow the given Charts and / or text quickly, clearly, and quickly identify one or more target users.
  • a basic portrait model is first constructed according to the basic information of the user, which is convenient for first performing a rough screening based on the portrait model when looking for a tenant or a landlord. Narrow down the selection of tenants or landlords. For example, when the landlord is a female in Guangzhou, or when the tenant is a female in Guangzhou, the female tenant or landlord in Guangzhou can be selected based on the gender and hometown of the landlord or tenant and the landlord or tenant. For another example, in a shared room, the roommate who stays first works from 9:00 to 18:00, and sleeps at 10:00, so he can recommend to the roommates who live at the same time and go to bed according to their living habits and work hours.
  • the evaluated information is mainly the tenant's evaluation of the landlord. After the lease period ends, the tenant fills in the app's evaluation of the landlord and the evaluation of the entire property, such as the authenticity of the property. The degree of match between the listing information published by the landlord and the real listing information, the behavior habits and personality of the landlord, the convenience of the listing, and the configuration of the facilities surrounding the listing.
  • the evaluation information is mainly the landlord's evaluation of the tenant, such as a description of the behavior of the tenant during the renting period, a degree of care for furniture, and a description of the tenant's personal image.
  • the housing lease transaction is matched.
  • Get the matching feature information set by the current user that is, the user presets the conditions that the target user should have on the app to prevent the landlord or tenant from finding a tenant or landlord that they don't like.
  • the landlord when the landlord is a female, it may set the matching feature information to be that the gender of the tenant is female, and when recommending the tenant to the landlord, only the female tenant is recommended.
  • the tenant when the tenant is a female, in order to facilitate communication, it can also set the matching feature information to be the gender of the landlord as female, and when recommending the landlord to the tenant, only the female landlord is recommended.
  • step S200 may be performed before step S100
  • step S100 may be performed before step S200
  • step S200 and step S100 may be performed simultaneously.
  • S300 Determine whether there is a target user in the candidate user set whose user portrait matches the user portrait of the current user and whose feature information matches the characteristic information to be matched, any candidate in the candidate user set. Each user corresponds to a user portrait and feature information.
  • the method in determining whether there is a user portrait in the candidate user set that matches the user portrait and the feature information matches the feature information to be matched, the method includes:
  • S310 Acquire characteristic information of the candidate user, and construct a user portrait of the candidate user according to the characteristic information of the candidate user;
  • S320 Determine, according to the feature information to be matched, user portraits of the current user and the candidate user, whether a user portrait in the candidate user set matches the user portrait of the current user and the feature information matches the user profile of the current user. Matching target users with matching feature information.
  • the to-be-matched user portrait of the to-be-matched user is also constructed by the method of constructing the current user portrait described above. In the judging process, the target user determined based on the matching feature information, the user portrait, and the user portrait to be matched is more accurate.
  • the basic information of the user is displayed on the app page in the form of a data table, and the user evaluation information and social behavior data are expressed in the form of radar graphics, where the radar chart
  • Each vertex of a represents a category or a piece of feature information, and the vertex represents the text of the feature information, and the user is given a score based on the feature information.
  • the rules for determining the score are set by the R & D staff, such as setting the highest score for a single item. It is 100 points, and the score of the corresponding fixed-point item is given according to the evaluated information and behavior data.
  • the weight of the feature information in the total score is set, and the feature information and the weight product are summed to obtain the user's total score.
  • Matching the user profile of the user to be matched with the user profile of the current user corresponds to comparing the data corresponding to each feature information of the vertex in the radar chart, first comparing whether all the feature information of the two user profiles are the same or Similar (Similar can be set to set one or two feature information items of all the feature information items different, which can be set according to actual needs, and there is no restriction here). By comparing all the feature information of the two user portraits, it is determined to be the same or When similar, compare the scores corresponding to the same feature information in the two radar images.
  • the threshold for the number of score gaps can be preset, for example, the same feature information score gap threshold for the current user and the user to be matched is set to 0 to 10 points, and when the same feature information score gap between the current user and the user to be matched is 5 points, the gap threshold is set Within 0 to 10 minutes, at this time, it can be preliminarily determined that the same feature information of the current user and the user to be matched is the same or similar. Based on the foregoing process, the score of each feature information and the weight of all its feature information are multiplied to obtain the score of the feature information of the current user portrait and the user portrait to be matched in the total score.
  • the same feature information of the user portrait is added to the total score to obtain the total score of the same feature information of the current user portrait and the user portrait to be matched, so that the landlord / tenant will quickly determine the target user to be pushed based on the total score. Ideal tenant / landlord for yourself.
  • the user can also set the conditions that the target user has on the app, that is, the matching feature information, which can be set to a single feature information score greater than a fixed value, for example, the landlord sets the rent delivery term item to a value of 80 points
  • the matching feature information can be set to a single feature information score greater than a fixed value, for example, the landlord sets the rent delivery term item to a value of 80 points
  • some tenants (target users) similar to or similar to the landlord's portrait are preliminarily determined, and then the conditions set by the landlord can be adopted to further set the initial value of the rent delivery term to 80 points or less.
  • the identified target users are filtered out, and only those tenants who have similar or identical landlord portraits and whose rent delivery term is 80 or more are pushed to customers in the following manner.
  • the current user portrait is the portrait of the roommate who first moved into the shared room.
  • the roommate who stayed first worked from 9:00 to 18:00 and was sleeping at 10:00.
  • the user's behavioral data includes: rents are delivered in advance and the frequency of changing rooms is low; user portraits based on the basic information of the roommate who first checked in, the evaluated information, and the behavior data are constructed, as described above, the first move in
  • the basic information of the roommate is expressed in the form of a data table, which indicates the basic information of the user.
  • the evaluated information and behavioral data are used to construct a radar chart.
  • the straight lines at each vertex of the radar graph indicate the degree of care for furniture, living habits, personality, rental delivery, and frequency of house changes. Combined with the previous situation, the extraction can be very good.
  • each of the radar graphics is obtained The straight line of the vertex corresponds to the score of the feature information (specifically as described above).
  • the score can also be set according to the meaning of the words in the text, for example: preferably 80-90 points, good 90 points, very good 95 points or more, regular 80- 90 points, that is, the degree of caring for furniture 85 points, 90 points of habits, 90 points of personality, 95 points of rent delivery, 90 points of frequency of changing rooms, the total score is 90, the total score is various The score of the feature information is multiplied by its corresponding weight and then summed.
  • the matching feature information set by the first roommate is female, in the database, according to the score of the feature information of the first roommate, find the degree of loving furniture 75-95 points, living habits 80-100 points, personality 80 -100 points, 85-100 points for rent delivery, 80-100 points for changing rooms, and 80-100 points for female shared roommates.
  • the first roommate is recommended to find the user .
  • the process of matching the landlord and tenant is the same, so I won't go into details here.
  • the foregoing process is only an exemplary description, and the feature information may include only one or more of them, and may also include other feature information described above.
  • basic user information may also be included. Perform matching to recommend more suitable and ideal target users to current users.
  • the candidate user and the current user in the embodiment of the present application are users having a corresponding relationship, such as a landlord and a tenant or vice versa.
  • a message including the feature information of the target user is pushed to the user.
  • the characteristic information including the target user may be sent to the user through a short message or an email; the characteristic information including the target user may be automatically popped up when the user logs in to the app; and the user may also be associated on the rental app platform through the user.
  • the other contact end sends to the user characteristic information including the target user.
  • the message includes feature information of the target user that is the same as or similar to the current user characteristic information, and each feature information of the user.
  • the score and the total score of all characteristic information may also include the basic information of the user.
  • acquiring feature information of the current user and constructing a user portrait based on the feature information includes:
  • obtaining characteristic information of the candidate user and constructing a user portrait of the candidate user according to the characteristic information of the candidate user includes:
  • the key information needs to be extracted from the text.
  • the extracted key information constructs a user portrait and / or the user portrait to be matched.
  • the user current user or user to be matched
  • the evaluated information is: the listing information published on this listing network matches the real listing information with a high degree of convenience, travel is convenient, configuration within 500 meters
  • the method further includes: associating and storing the basic user information, the behavior data, and the evaluated information. As mentioned above, when extracting key information, only one-to-one information is extracted from a user.
  • the basic information of the user, behavior data, The evaluation information is stored in association, so that when extracting the user's characteristic information, it is convenient to be able to extract the key information of a user at one time, avoid the scattered data extraction, avoid increasing the difficulty of extracting key information in the later period, and the difficulty of associating key information with the user. .
  • each key information is in a dispersed state. In the process of constructing a user portrait, the foregoing processes need to be combined to give a corresponding score. Based on this, this application will extract Associated with every key piece of information
  • the method before acquiring feature information of the current user and constructing a user portrait based on the feature information, the method further includes:
  • the user's authentication information and user's personality description information are mainly used to enrich the content of the user information, increase the amount or content of the user's characteristic information, and facilitate the construction of an accurate user portrait.
  • the user authentication information includes real-name authentication and company authentication completed by the user of the house rental platform, thereby ensuring the qualifications of the user of the house rental platform, and preventing illegal users from obtaining other users' information through false information, so that both landlords and tenants on the house rental platform Is reliable.
  • the user's personality description information includes the user's description of himself and the user's description of the target user (ideal roommate or landlord), and then accurately describes the user's own portrait, and can also determine the specific conditions in the target user's portrait based on it, and further Select the ideal landlord or tenant based on the user's own needs.
  • the method specifically includes:
  • the preset information of the target user is displayed in a preset display manner; or when the current user is a landlord, the personal description of the target user is displayed in a preset display manner. information.
  • the evaluation information of other users on the target user is displayed to form a more comprehensive and objective description of the target user, thereby facilitating the current user to determine whether the pending user is based on the evaluation information.
  • the ideal user and thus enhance the trust and understanding between users (landlord and tenant), and facilitate matching transactions between users.
  • the preset display mode includes any one of a display mode combining text and pictures, a display mode of text, and a display mode of pictures.
  • the tenant is more concerned about the integrity of the landlord, when the current user is a tenant, the rated information of the target user is displayed in a preset display mode, so that the tenant can fully understand the landlord's integrity issues;
  • the landlord pays more attention to the preferences of the tenants, so that the tenants can better protect the landlord's house. Therefore, the personalized description information of the target user is displayed in a preset display manner, which is more convenient for the landlord. Understand tenants' hobbies and more clearly determine if they are suitable.
  • the apparatus includes:
  • a building module 100 configured to obtain characteristic information of a current user, and construct a user portrait according to the characteristic information
  • a first acquisition module 200 configured to acquire the feature information to be matched set by the current user
  • a judging module 300 is configured to determine whether there is a target user whose user portrait matches the user portrait and whose feature information matches the feature information to be selected in the candidate user set, and any one of the candidate users in the candidate user set is selected.
  • the selected users correspond to user portraits and feature information;
  • a pushing module 400 is configured to push feature information including the target user to the user when there is a target user whose user portrait matches the user portrait of the current user and feature information matches the feature information to be matched. News.
  • the apparatus for recommending users in a targeted manner further includes:
  • a constructing unit 310 is configured to acquire characteristic information of the candidate user, and construct a portrait of the user to be matched according to the characteristic information of the candidate user; a judging unit 320 is configured to according to the characteristic information to be matched, the current The user portraits of the user and the candidate user determine whether there is a target user in the candidate user set whose user portrait matches the user portrait of the current user and feature information matches the feature information to be matched.
  • a first extraction unit 500 is configured to extract key information in the feature information and construct a user portrait of the current user according to the key information; a second extraction unit 600 is configured to extract feature information of the candidate user And constructing a user portrait of the candidate according to the key information.
  • the second obtaining module 110 is configured to obtain authentication information of the user and / or personality description information of the user.
  • the display module 420 is configured to display the rated information of the target user in a preset display mode when the current user is a tenant; or display the target user in a preset display mode when the current user is a landlord.
  • the characteristic information includes one or more of basic user information, behavior data, and evaluated information.
  • An apparatus for directionally recommending users provided in the embodiments of the present application can implement the foregoing embodiment of the method for directionally recommending users.
  • An embodiment of the present application provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the program is executed by a processor, the method for recommending users according to any one of the technical solutions is implemented.
  • the computer-readable storage medium includes, but is not limited to, any type of disk (including floppy disks, hard disks, optical disks, CD-ROMs, and magneto-optical disks), ROM (Read-Only Memory, read-only memory), and RAM (Random Access Memory), EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electrically Programmable Read-Only Memory), flash memory, magnetic card or Rays card. That is, the storage device includes any medium that stores or transmits information in a readable form by a device (for example, a computer, a mobile phone), and may be a read-only memory, a magnetic disk, or an optical disk.
  • a computer-readable storage medium provided in the embodiments of the present application can realize the description of users in a multi-dimensional and omnidirectional manner, and implements the above-mentioned embodiment of recommending users in a targeted manner, which improves the user (landlord and tenant or roommate and roommate).
  • the degree of matching between them can not only match the transactions between users, but also improve the comfort of the user's living; obtain the characteristic information of the current user, construct a user portrait based on the characteristic information, and obtain the waiting information set by the current user.
  • Matching feature information determining whether there is a target user in the candidate user set whose user profile matches the user profile of the current user and the feature information matches the target user feature information, any one of the candidate user sets
  • the candidate users all have user portraits and feature information; when there is a target user whose user portrait matches the user portrait of the current user and the feature information matches the feature information to be matched, pushing to the current user includes A message of characteristic information of the target user.
  • the current user not only can the current user be recommended to a preferred matching user based on the characteristic information of the current user, thereby improving the user's satisfaction during the residence, but also enabling a full range of description of the user and enabling the user to follow Learn more about your own characteristics so that users can better plan their time.
  • the current user in the process of user matching, not only can the current user be recommended to the current user with the same or similar target users based on their overall characteristics, but also can be selected according to the user's personal preferences corresponding to their preferences, in order to To meet the user's personal needs, when constructing multi-faceted user portraits for users, combined with the user's personal preferences, they can better match transactions between landlords and tenants in the process of housing lease, or roommates and roommates. transaction.
  • user authentication information and personal description information are also obtained. The authentication information can ensure that the user's authentication information not only increases the quantity or content of the user's characteristic information, but also can ensure the qualifications of the user of the housing rental platform.
  • the user's personality description information includes the user's description of himself and the user's description of the target user (ideal roommate or landlord), and then accurately describes the user's own portrait, and can also determine the specific conditions in the target user's portrait based on it, and further Select the ideal landlord or tenant based on the user's own needs.
  • the computer-readable storage medium provided in this embodiment of the present application can implement the foregoing embodiment of the method for recommending users in a targeted manner.
  • the present application further provides a server.
  • the server processor 503, the memory 505, the input unit 507, and the display unit 509 are devices.
  • the memory 505 may be used to store an application program 501 and various functional modules, and the processor 503 runs the application program 501 stored in the memory 505 so as to execute various functional applications and data processing of the device.
  • the memory 505 may be an internal memory or an external memory, or include both an internal memory and an external memory.
  • the internal memory may include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a flash memory, or a random access memory.
  • ROM read-only memory
  • PROM programmable ROM
  • EPROM electrically programmable ROM
  • EEPROM electrically erasable programmable ROM
  • flash memory or a random access memory.
  • External storage can include hard disks, floppy disks, ZIP disks, U disks, magnetic tapes, and so on.
  • the memory disclosed in this application includes, but is not limited to, these types of memory.
  • the memory 505 disclosed in this application is only an example and not a limitation.
  • the input unit 507 is used for receiving an input of a signal, and receiving characteristic information input by a customer and an operation instruction input by a user.
  • the input unit 507 may include a touch panel and other input devices.
  • the touch panel can collect the touch operations of the customer on or near it (such as the operation of the customer on the touch panel or near the touch panel using any suitable object or accessory such as a finger or a stylus), and according to the preset
  • the program drives the corresponding connection device; other input devices may include, but are not limited to, one or more of a physical keyboard, function keys (such as playback control keys, switch keys, etc.), a trackball, a mouse, and an joystick.
  • the display unit 509 may be used to display information input by the customer or information provided to the customer and various menus of the computer device.
  • the display unit 509 may take the form of a liquid crystal display, an organic light emitting diode, or the like.
  • the processor 503 is the control center of the computer equipment. It uses various interfaces and lines to connect various parts of the entire computer. It runs or executes the software programs and / or modules stored in the memory 503, and calls the data stored in the memory to execute Various functions and processing data.
  • One or more processors 503 shown in FIG. 4 can execute and implement the functions of the building module 100, the function of the first acquisition module 200, the function of the determination module 300, the function of the push module 400, and construction shown in FIG. Functions of the unit 310, functions of the determination unit 320, functions of the first extraction unit 500, functions of the second extraction unit 600, functions of the storage module 410, functions of the second acquisition module 210, and functions of the display module 420.
  • the server includes one or more processors 503, and one or more memories 505, one or more applications 501, wherein the one or more applications 501 are stored in the memory 505 And is configured to be executed by the one or more processors 503, and the one or more application programs 301 are configured to execute the method for directional recommending users described in the above embodiments.
  • a server provided in the embodiments of the present application can describe users in a multi-dimensional and omni-directional manner, implement the above-mentioned embodiment of targeted recommendation users, and improve the matching between users (landlords and tenants or roommates and roommates).
  • Degree which can not only match transactions between users, but also improve the living comfort of users; obtain feature information of the current user, construct a user portrait based on the feature information, and obtain feature information to be matched set by the current user; Determine whether there is a target user in the candidate user set whose user portrait matches the user portrait of the current user and the characteristic information matches the characteristic information to be matched, and any candidate user in the candidate user set is Corresponding user portrait and feature information; when there is a target user whose user portrait matches the user portrait of the current user and whose feature information matches the feature information to be matched, pushing to the current user including the target user Characteristic information message.
  • the current user not only can the current user be recommended to a preferred matching user based on the characteristic information of the current user, thereby improving the user's satisfaction during the residence, but also enabling a full range of description of the user and enabling the user to follow Learn more about your own characteristics so that users can better plan their time.
  • the current user in the process of user matching, not only can the current user be recommended to the current user with the same or similar target users based on their overall characteristics, but also can be selected according to the user's personal preferences corresponding to their preferences, in order to To meet the user's personal needs, when constructing multi-faceted user portraits for users, combined with the user's personal preferences, they can better match transactions between landlords and tenants in the process of housing lease, or roommates and roommates. transaction.
  • user authentication information and personal description information are also obtained. The authentication information can ensure that the user's authentication information not only increases the quantity or content of the user's characteristic information, but also can ensure the qualifications of the user of the housing rental platform.
  • the user's personality description information includes the user's description of himself and the user's description of the target user (ideal roommate or landlord), and then accurately describes the user's own portrait, and can also determine the specific conditions in the target user's portrait based on it, and further Select the ideal landlord or tenant based on the user's own needs.
  • the server provided in this embodiment of the present application can implement the foregoing embodiment of the method for recommending users in a targeted manner.

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Engineering & Computer Science (AREA)
  • Finance (AREA)
  • Economics (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Human Resources & Organizations (AREA)
  • General Health & Medical Sciences (AREA)
  • Development Economics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

La présente invention concerne un procédé de recommandation directionnelle à un utilisateur, comportant les étapes consistant à: acquérir des informations caractéristiques d'un utilisateur actuel, et construire un portrait d'utilisateur d'après les informations caractéristiques; acquérir des informations caractéristiques à mettre en correspondance qui sont configurées par l'utilisateur actuel; déterminer si un utilisateur cible doté d'un portrait d'utilisateur qui correspond au portrait d'utilisateur de l'utilisateur actuel et présentant des informations caractéristiques qui correspondent aux informations caractéristiques à mettre en correspondance est présent dans un ensemble d'utilisateurs à sélectionner; lorsqu'un utilisateur cible doté d'un portrait d'utilisateur qui correspond au portrait d'utilisateur de l'utilisateur actuel et présentant des informations caractéristiques qui correspondent aux informations caractéristiques à mettre en correspondance est présent, distribuer sélectivement un message comportant les informations caractéristiques de l'utilisateur cible à l'utilisateur actuel. La présente invention peut recommander l'utilisateur correspondant optimal à un utilisateur actuel selon des informations caractéristiques de l'utilisateur actuel de façon à améliorer la satisfaction d'utilisateurs pendant un séjour, tandis qu'un propriétaire et un locataire peuvent mieux se connaître au moyen de leurs portraits respectifs, accroissant ainsi le degré de confiance entre le propriétaire et le locataire, et facilitant donc une transaction de location de maison entre le propriétaire et le locataire.
PCT/CN2018/108072 2018-06-15 2018-09-27 Procédé de recommandation directionnelle à un utilisateur, dispositif et support de stockage, et serveur WO2019237571A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810623443.4 2018-06-15
CN201810623443.4A CN109062938A (zh) 2018-06-15 2018-06-15 定向推荐用户的方法、装置及存储介质、服务器

Publications (1)

Publication Number Publication Date
WO2019237571A1 true WO2019237571A1 (fr) 2019-12-19

Family

ID=64820387

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/108072 WO2019237571A1 (fr) 2018-06-15 2018-09-27 Procédé de recommandation directionnelle à un utilisateur, dispositif et support de stockage, et serveur

Country Status (2)

Country Link
CN (1) CN109062938A (fr)
WO (1) WO2019237571A1 (fr)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109684470B (zh) * 2019-01-09 2021-03-09 中国科学技术大学 法律信息推荐方法及装置、存储介质及电子设备
CN110163723A (zh) * 2019-05-20 2019-08-23 深圳市和讯华谷信息技术有限公司 基于产品特征的推荐方法、装置、计算机设备及存储介质
CN110505285B (zh) * 2019-07-31 2022-03-22 万翼科技有限公司 园区会话方法及相关装置
CN110889737A (zh) * 2019-10-17 2020-03-17 贝壳技术有限公司 合租室友的推荐方法、装置、服务器及存储介质
CN111311306A (zh) * 2020-01-17 2020-06-19 青梧桐有限责任公司 基于房主期望和租户期望的派单优化方法及系统
CN112785197B (zh) * 2021-02-04 2024-03-29 中国工商银行股份有限公司 信息推荐方法、装置、计算设备、介质和程序产品
CN112991110B (zh) * 2021-04-25 2024-02-02 湖南知名未来科技有限公司 多维度画像标准的客户类型识别方法及知识产权监控系统
CN113255801B (zh) * 2021-06-02 2024-07-02 抖音视界有限公司 一种数据处理的方法、装置、计算机设备及存储介质
CN117973789A (zh) * 2021-07-30 2024-05-03 北京壹心壹翼科技有限公司 基于全流程用户画像的智能匹配方法、装置、设备及介质
CN113781166B (zh) * 2021-09-03 2024-10-18 珠海格力电器股份有限公司 消息推送方法、装置、电子设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016099228A1 (fr) * 2014-12-19 2016-06-23 Samsung Electronics Co., Ltd. Procédé de fourniture d'un contenu et appareil électronique réalisant le procédé
CN105976195A (zh) * 2015-10-22 2016-09-28 乐视移动智能信息技术（北京）有限公司 一种推荐合租信息的方法和装置
CN106126582A (zh) * 2016-06-20 2016-11-16 乐视控股（北京）有限公司 推荐方法及装置
CN107291841A (zh) * 2017-06-01 2017-10-24 广州衡昊数据科技有限公司 一种基于位置和用户画像智能匹配社交目标的方法和系统
CN108073659A (zh) * 2016-11-18 2018-05-25 腾讯科技（深圳）有限公司 一种婚恋对象推荐方法及装置

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108090162A (zh) * 2017-12-13 2018-05-29 北京百度网讯科技有限公司 基于人工智能的信息推送方法和装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016099228A1 (fr) * 2014-12-19 2016-06-23 Samsung Electronics Co., Ltd. Procédé de fourniture d'un contenu et appareil électronique réalisant le procédé
CN105976195A (zh) * 2015-10-22 2016-09-28 乐视移动智能信息技术（北京）有限公司 一种推荐合租信息的方法和装置
CN106126582A (zh) * 2016-06-20 2016-11-16 乐视控股（北京）有限公司 推荐方法及装置
CN108073659A (zh) * 2016-11-18 2018-05-25 腾讯科技（深圳）有限公司 一种婚恋对象推荐方法及装置
CN107291841A (zh) * 2017-06-01 2017-10-24 广州衡昊数据科技有限公司 一种基于位置和用户画像智能匹配社交目标的方法和系统

Also Published As

Publication number Publication date
CN109062938A (zh) 2018-12-21

Similar Documents

Publication Publication Date Title
WO2019237571A1 (fr) Procédé de recommandation directionnelle à un utilisateur, dispositif et support de stockage, et serveur
Gray et al. Syntax for calculation of discounting indices from the monetary choice questionnaire and probability discounting questionnaire
KR20180121858A (ko) 인터넷기반 사회 연결망 서비스에서 회원 프로필의 순위 및 등급 산출 시스템 및 방법과 이를 위한 기록매체
JP5548654B2 (ja) 情報処理装置、情報処理方法、情報処理プログラム、及び情報処理プログラムが記録された記録媒体
US20130218864A1 (en) Real Estate Search Engine
US9094396B2 (en) Integrated profile creation for a social network environment
US20150302515A1 (en) Method, apparatus, and system for simulating objects
WO2019218654A1 (fr) Procédé de rangement de produit
WO2017090678A1 (fr) Système et procédé de traitement d'informations
US8943044B1 (en) Analyzing event invitees
Hartono et al. Applying Kansei Engineering, the Kano model and QFD to services
US20200134748A1 (en) Residential real estate layout data collection, search, rating and ranking system and method
JP2017167893A (ja) 情報検索装置、情報検索方法及び情報検索プログラム
Song et al. Comparing the influence of substantive and communicative servicescape on healthcare traveler emotions: the moderating effect of accommodation type and interior design style
JP2022159518A (ja) 知的財産評価支援システム、知的財産評価支援プログラム、知的財産評価支援方法、サーバ及び知的財産評価支援装置
US20130219315A1 (en) Graphical User Interface for Real Estate Search
JP2016206783A (ja) 情報提供方法及び情報提供装置
US11620682B2 (en) Apparatus and method for online data collection and processing
US10943314B2 (en) Determining a closest estimated market value of a real estate property
US9972057B2 (en) Determining a user's rank in a social network
Liu et al. Can Trust Bring Satisfaction to the Festival Under Pandemic?
US20160350429A1 (en) System and method for matching, qualifying and disseminating real estate information
Sun et al. Eye‐Tracking Technology in Online Real Estate Rental
KR101373825B1 (ko) 현재 상황정보 기반의 집단선호정보 서비스 시스템 및 서비스 방법
López-Arellano et al. Bibliometric and systemic analysis of the relationship between quality of work life and productivity during the COVID-19 pandemic

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: 18922792

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 05.02.2021)

122 Ep: pct application non-entry in european phase

Ref document number: 18922792

Country of ref document: EP

Kind code of ref document: A1