WO2019242149A1

WO2019242149A1 - Apartment share roommate recommending method and apparatus, and computer readable storage medium and server

Info

Publication number: WO2019242149A1
Application number: PCT/CN2018/108076
Authority: WO
Inventors: 靳倩慧; 黄晓霞; 黄俊凯; 杜立; 盛亮
Original assignee: 平安科技（深圳）有限公司
Priority date: 2018-06-22
Filing date: 2018-09-27
Publication date: 2019-12-26
Also published as: CN108985881A

Abstract

The present application relates to the field of Internet-based apartment renting, and in particular, to an apartment share roommate recommending method and apparatus, and a computer readable storage medium and a server. The method comprises: obtaining feature information of the current user, the feature information comprising basic information, tag information, and evaluation information of the user; obtaining feature information of first standby users that have published apartment renting demands, and computing the degree of matching between the feature information of the current user and the feature information of the first standby users; when a screening instruction input by the current user is obtained, determining a screening condition according to the screening instruction, obtaining from the first standby users second standby users satisfying the screening condition, and determining the second standby user having a degree of matching satisfying a recommendation condition as a recommended user; and displaying on a user interface the recommended user as a potential apartment share roommate of the current user to recommend the apartment share roommate to the user.

Description

Shared roommate recommendation method, device, computer-readable storage medium, and server

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on June 22, 2018, with application number 201810652532.1, and the invention name is "shared roommate recommendation method, device, and computer-readable storage medium, server". Incorporated by reference in this application.

Technical field

The present application relates to the field of Internet renting, and in particular, to a method, device, computer-readable storage medium, and server for recommending roommates for sharing.

Background technique

Renting is the first job that most people need to consider before entering the workplace. As more and more people live in the city, the demand for renting becomes more and more. In addition, there are considerations about renting costs and interpersonal social issues. Many people choose to share. The inventor realizes that the current way for users to rent a house is: the landlord or the agent or the user who has checked in by publishing the listing information on the renting platform for others to browse. Users who want to rent a house can get matching matches by entering conditions on the renting platform. Houses; that is, the current renting method is a house-oriented renting model, which recommends to the user a house that matches the conditions. And because a large number of listings are in the hands of the intermediary, most of the listings found through this method still need to find an intermediary, and the intermediary or the landlord has not given too much consideration to the choice of the renter, resulting in the final roommate relationship Disharmony does not allow co-tenants to live well under the same roof. At present, rent-related products do not take into account that the essence of renting is people. They are mainly based on recommended listings, which cannot help users quickly find suitable roommates for renting.

Summary of the Invention

In order to overcome the above technical problems, especially the lack of related functions recommended by roommates in the prior art, which cannot help users quickly find suitable roommates for shared renting, the following technical solutions are proposed:

In the first aspect, this application provides a method for sharing roommate recommendation, including:

Acquire the characteristic information of the current user, which includes the user's basic information, tag information, and evaluation information; acquire the characteristic information of the first pending user who has issued a rental demand, and calculate the characteristic information of the current user and the characteristic of the first pending user The matching degree of the information; when the filtering instruction input by the current user is obtained, a filtering condition is determined according to the filtering instruction, and a second pending user that meets the filtering condition is obtained from the first pending user, and The second pending user whose matching degree satisfies the recommendation condition is determined as a recommended user; the recommended user is displayed on the user interface as a potential shared roommate of the current user to recommend the shared roommate to the user.

In a second aspect, the present application provides a shared roommate recommendation device, including: an acquisition module for acquiring characteristic information of the current user, where the characteristic information includes basic information, tag information, and evaluation information of the user; a calculation module: for acquiring The feature information of the first pending user who has released the demand for housing is used to calculate the matching degree between the feature information of the current user and the feature information of the first pending user; a determining module is configured to: when a filtering instruction input by the current user is obtained, The screening instruction determines a screening condition, and obtains from the first pending user a second pending user that meets the filtering condition, and determines a second pending user whose matching degree meets the recommendation condition as a recommended user; a recommendation module: using The recommended user is displayed on the user interface as a potential shared roommate of the current user to recommend the shared roommate to the user.

In a third aspect, the present application also provides a non-volatile computer-readable storage medium. The non-volatile computer-readable storage medium stores a computer program, and the program is implemented by a processor to implement a shared roommate. A recommendation method. The shared roommate recommendation method includes: acquiring characteristic information of the current user, the characteristic information including basic information, label information, and evaluation information of the user; acquiring characteristic information of the first pending user who has issued a rental demand, and calculating the current The degree of matching between the characteristic information of the user and the characteristic information of the first pending user; when the filtering instruction input by the current user is obtained, the filtering condition is determined according to the filtering instruction, and the satisfying requirements are obtained from the first pending user The second pending user of the screening condition is described, and the second pending user whose matching degree meets the recommendation condition is determined as the recommended user; the recommended user is displayed on the user interface as a potential shared roommate of the current user to recommend the shared roommate to the user .

According to a fourth aspect, the present application further provides a server, where the server includes one or more processors, memory, and one or more application programs, wherein the one or more application programs are stored in the memory and Configured to be executed by the one or more processors, the one or more programs configured to execute a shared roommate recommendation method, the shared roommate recommendation method includes: acquiring characteristic information of the current user, the characteristic The information includes the basic information, label information and evaluation information of the user; obtains the characteristic information of the first pending user who has released the rental demand, calculates the degree of matching between the characteristic information of the current user and the characteristic information of the first pending user; when the said When a filtering instruction is input by a current user, a filtering condition is determined according to the filtering instruction, and a second pending user that meets the filtering condition is obtained from the first pending user, and a second pending user whose matching degree meets the recommended condition Determined as a recommended user; displaying the recommended user as a potential shared roommate of the current user on the user interface To recommend shared roommates to users.

This application provides a renting model based on people-oriented + social, by obtaining the characteristic information of the current user, and then calculating the matching degree of the characteristic information of the current user and the pending user, whether or not the regular user has a custom shared filtering condition, it can Identify the recommended users whose matching degree meets the recommendation conditions, and display the recommended users on the user interface as potential shared roommates of the current user, breaking the current rental form that is mainly based on recommended listings, avoiding users looking for suitable ones Shared roommates need to find a lot of user information to match the problem of low success rate, and push more suitable potential shared roommates for users.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a schematic flowchart of an embodiment of a roommate recommendation method for an application;

FIG. 2 is a schematic flowchart of another embodiment of a method for recommending a roommate to be shared;

FIG. 3 is a schematic diagram of an embodiment of a roommate recommendation device for sharing the application; FIG.

FIG. 4 is a schematic structural diagram of an embodiment of a server of the present application.

detailed description

The application scenario of this application is a renting platform. The renting platform provides one-stop service functions for renting information display, renting roommate recommendation, renting confirmation, and rent collection.

The embodiment of the present application provides a method for prompting information among roommates in a shared room. The functions implemented by the method are integrated in the rental platform. The system where the rental platform is located executes and implements the following functions as the execution subject of the embodiment of this application, as shown in Figure 1. The method includes the following steps:

S100: Acquire characteristic information of the current user, where the characteristic information includes basic information, label information, and evaluation information of the user.

This step is mainly to obtain the user's characteristic information on the rental platform to better depict the user portrait of each user. The characteristic information includes basic information, and the basic information includes the user's workplace information, hometown information, and graduation school. Information; the characteristic information includes tag information, and various types of tags are provided on the rental platform for users to choose, and the tags include lifestyle tags, such as pets not entering, rules of routine, non-smokers, gourmet chefs, housekeepers, and personal tags such as IT expert, travel expert, social tags such as basketball masters and game black holes. When users complete personal characteristics information in the rental platform, they can check the lifestyle tags, personality tags, social tags provided by the system, and rent a house. The platform also provides users with the ability to add individual tags on their own; the feature information includes evaluation information, and an event initiation / participation section is set up on the rental platform. Users can sign up for the hosted event on the rental platform and can register for the same event. Evaluation by other users of the event, including checking the system-provided reviews Evaluation strip or add custom evaluated after renting internet converted to the evaluation information corresponding to the characteristic information of the user.

S200: Acquire the characteristic information of the first pending user who has issued the rental demand, and calculate the degree of matching between the characteristic information of the current user and the characteristic information of the first pending user.

This step is different from the current model of renting a house based on the recommendation of a house, and it is transformed into a model based on the recommendation of a roommate. Each user comes to the renting platform with the main purpose of renting. Each user can publish on the renting platform. Rental demand, rental demand includes "house location area", "rent", "check-in time", "rental period" and other information; in this embodiment, when a user uses a rental platform, the rental platform can obtain characteristic information of each user , Including at least the user's basic information and tag information, each user can be the current user or the first pending user described in this embodiment, the rental platform calculates the matching degree of the feature information of every two users, that is, the rental platform Each two users have corresponding matching values. For example, there are users A, B, and C on the rental platform. When A is the current user, users B and C can be the first pending user. At this time, the match between the current user A and the first pending user B is calculated. Value q1 of the degree of matching with the first pending user C; and when user B is the current user, users A and C are the first pending user. At this time, the current user B and the first pending user C are calculated. A value q1 of the degree of matching of the pending user A and a value q3 of the degree of matching with the first pending user C. By calculating the matching degree between each two users, this is used as a basis for subsequently recommending more matching roommates to the users.

S300: When a filtering instruction input by the current user is obtained, a filtering condition is determined according to the filtering instruction, and a second pending user whose characteristic information satisfies the filtering condition is obtained from the first pending user, and the matching is performed. The second pending user who meets the recommendation condition is determined as the recommended user.

When the current user has a clear rental requirement, a corresponding filtering instruction is formed by entering a filtering condition on a page provided by the renting platform. When the renting platform obtains the filtering instruction entered by the current user, the filtering instruction is based on the filtering instruction. Determine the filter conditions for the current user's shared rent, for example, the current user filters the rental requirements issued by other users by customizing the filter conditions on a page such as the "Find a Shared Rent" page provided by the rental platform, and the filter conditions include "house location area", " Conditions such as “rent”, “check-in time”, and “rental period” also include conditions for shared roommates such as “gender”, “age”, “constellation”, etc., so as to form corresponding screening instructions. After the filtering instruction entered by the current user, the filtering condition of the current user is determined according to the filtering instruction, and then the published rental demand that meets the filtering condition for the listing is first filtered, and then the filtering condition for the shared roommate is selected from the filtering condition. Among the first pending users corresponding to these published rental needs, The pending user, that is, the second pending user that meets the screening condition is obtained from the first pending user according to this embodiment, and then further screening is performed based on the matching degree between the second pending user and the current user. A larger value indicates that the second pending user and the current user are more likely to become roommates and get along well. At this time, the rental platform determines the second pending user whose matching degree meets the recommendation conditions as a recommended user, and filters out A user who is closer to the current user-defined sharing conditions and has a higher degree of matching with the current user as a potential roommate of the current user.

S400: Display the recommended user as a potential shared roommate of the current user on the user interface to recommend the shared roommate to the user.

Considering that the main purpose of the user to the rental platform is to rent a house, when the rental platform selects from a large number of users on the platform, the second pending user who meets the filtering conditions of the current user and meets the recommendation conditions is determined as the recommended user, and then The recommended user is displayed on the user interface as a potential shared roommate of the current user to recommend the shared roommate to the current user. The current user can first know the recommended users pushed by the platform through the rental platform, browse the rental requirements posted by these recommended users, and then contact the recommended users to view the room or find a rental together, and convert the rental mode based on listings into The people-oriented renting model allows users to find the right roommates first, and then find the right house together, which can quickly enhance each other's feelings and lay a good foundation for subsequent renting. At the same time, if the user can find a suitable roommate from the rental platform, and then find a suitable rental, it can also bring a good reputation for the rental platform.

This embodiment provides a renting model based on people-oriented + social, by obtaining the characteristic information of the current user, and then calculating the matching degree of the characteristic information of the current user and the pending user, regardless of whether the regular user has a custom shared filtering condition, Can identify the recommended users whose matching degree meets the recommendation conditions, and display the recommended users on the user interface as potential shared roommates of the current user, breaking the current rental form that is mainly based on recommended listings, avoiding users looking for suitable Of shared roommates need to search for a lot of user information, match the problem of low success rate, and push more suitable potential roommates for users.

In an embodiment of the present application, as shown in FIG. 2, after calculating the matching degree between the feature information of the current user and the feature information of the first pending user, the method further includes:

S310: When the filtering instruction input by the current user is not obtained, a first pending user whose matching degree meets a recommendation condition is determined as a recommended user.

Considering that not all users have clear rental requirements, in this embodiment, if the current user does not have a custom-shared filter condition, that is, the current user does not have a custom-shared filter condition when entering the rental platform, and the rental platform does not obtain the current user. Entered filtering instructions. At this time, the rental platform pushes potential roommates for the current user according to the matching degree. When the current user's filtering conditions are not obtained, the rental platform will calculate the characteristic information of the current user and the first pending user. The matching degree of the feature information, determining the first pending user whose matching degree satisfies the recommendation condition as a recommended user, as a potential shared roommate of the current user, and subsequently displaying the recommended user on the user interface as a potential shared roommate, Automatically push potential roommates for the current user.

According to an embodiment of the present application, the basic information includes workplace information, hometown information, and school information, and calculating the matching degree between the characteristic information of the current user and the characteristic information of the pending user includes:

Determine whether the current user has workplace information; if so, determine the reference value of the matching degree according to the similarity of the workplace information of the current user and the pending user;

The added value of the matching degree is determined through hometown information, school information, tag information, and evaluation information; wherein the added value is calculated as follows:

Added value = Boolean (same township) * 0.5 + Boolean (same school) * 0.5 + Boolean (the ideal roommate label of the current user and the lifestyle label of the pending user are the same) + Boolean (the positive user has positive evaluation information) * 0.2;

And calculating a matching degree of the feature information of the current user and the pending user according to the reference value and the additional value.

In this embodiment, calculating the matching degree between the characteristic information of the current user and the characteristic information of the pending user is specifically:

First, determine whether the current user has workplace information. If the current user has workplace information, determine the reference value of the matching degree according to the similarity of the workplace information of the current user and the pending user. If the current user has a workplace with the pending user, The similarity of the information is greater than the first preset value and is the first reference value; if the similarity of the workplace information of the current user and the pending user is less than or equal to the first preset value and greater than the second preset value, it is the first Two reference values; if the similarity between the workplace information of the current user and the pending user is less than a second preset value; a third reference value; when the similarity is higher, the reference value of the matching degree is higher. The workplace information not only refers to the industry and position, but also includes the workplace. For example, when a user enters workplace information, he can click to add a workplace. The rental platform will call the API of the map system for the user to select the workplace, and then record the workplace. To determine the similarity of workplace information.

Then, the added value of the matching degree is determined through hometown information, school information, tag information, and evaluation information. Specifically, the added value is calculated as follows:

T = Boolean (A1 & A2) * 0.5 + Boolean (B1 & B2) * 0.5 + Boolean (C1 & C2) + Boolean (D1) * 0.2.

Among them, Boolean (A1 & A2) indicates that the home information of the current user is compared with the home information of the first pending user. If they are the same, then Boolean (A1 & A2) is a preset value such as 1; Boolean (B1 & B2) indicates the school information of the current user Compared with the school information of the first pending user, if the same, then Boolean (B1 & B2) is a preset value such as 1; Boolean (C1 & C2) indicates that the ideal roommate label of the current user is compared with the lifestyle label of the first pending user. If there are the same, if there are 5 same, then Boolean (C1 & C2) is 5; Boolean (D1) means to evaluate the evaluation information of the first pending user, if there is positive evaluation information, if there are 2 positive evaluations Information, Boolean (D1) is 2. In this way, the added value of the matching degree is calculated.

Then the reference value is added to the additional value to obtain the matching degree. If the current user has no workplace information, the reference value can be recorded as 0, so as to calculate the characteristic information of the current user and the first pending user. Matching degree of feature information. In this embodiment, the calculation of the matching degree first considers the matching of workplace information. When the workplace information is closer, the reference value of the matching degree is higher, and then the additional value of the matching degree is determined by considering other characteristic information between users. The final matching degree between the two users is obtained from the reference value and the added value. When determining the recommended users, it is also possible to recommend the same or similar workplace users as potential roommates of the current user. Roommates in the same workplace can quickly understand each other.

Specifically, in the embodiments of the present application, the published renting requirements include: renting requirements issued when wanting to find a rented house, and renting requirements issued by a renting house who want to find a roommate to be shared.

In the embodiment of the present application, the renting demand may be issued by the user without finding a renting house. For example, if user A publishes a renting demand, the information includes “The house is located in area A, the rent range is 1000-1500 yuan, and the roommate ’s gender. I ’m a female, starting date is 5.20 ", and I will post the rental demand on the rental platform. If other users customize the filter conditions for subsequent rents, they can find the rental demand more quickly, and then find the person who posted the rental demand. user. Another type of rental demand is the rental demand that has been determined when the renter wants to find a shared roommate. For example, user B has released a rental demand to find a roommate, including the message "House location is in area A, the rent range is 1200 yuan, and the roommate is looking for Gender is female. Currently, there are users B and C who have checked in. The starting date is 5.15 ". Further, when it is determined that the rented house includes 2 or more roommates, the renting platform calculates the current The matching degree of the feature information of the user and the pending user will be calculated at the same time by the matching degree of the feature information of multiple roommates (the pending user) and the current user. When the matching degree of the feature information of the multiple roommates (the pending user) and the current user is determined, When the average value is higher, the pending users who indicate the demand for the rental house are more in line with the potential roommates who are the current users.

Further, on the basis of the above embodiment, the current user-defined shared renting filter condition is equivalent to the current user publishing a rental demand for renting, that is, after the user releases the rental demand for renting, the system The rental demand is converted into a screening condition for shared renting, and the user is automatically assisted in screening the rental demand that satisfies the conditions and the corresponding pending users, and the matching degree is calculated, and the pending users whose matching degree meets the recommended conditions are determined as recommended users. The next time the user logs in to the rental platform, the rental platform can quickly recommend a shared roommate to the user; or, at a predetermined interval, the recommended recommended user recommends the shared roommate to the user in a form such as email, text message, and notification.

Further, in an embodiment of the present application, as shown in FIG. 2, the displaying the recommended user as a potential shared roommate of the current user on the user interface includes:

S410: Display the corresponding recommended user as a potential shared roommate of the current user on the user interface according to the update time sequence of the published rental demand. The update time includes editing the rental demand or polishing the corresponding time of the rental demand. .

After the rental platform determines the recommended users, the recommended users need to be sorted according to a certain arrangement rule. In this embodiment, the recommended users have issued rental requirements, and the rental platform sorts according to the update time of the rental requirements. , The corresponding recommended user is displayed on the user interface as a potential shared roommate of the current user, and the update time may be the time when the user refreshes the rental demand, for example, the user "polishs", "edits", etc. his published rental demand All operations can refresh the update time of rental demand. When the matching degree is the same, the recommended users with the latest update time are ranked first, so as to avoid that the rental demand has expired and still be recommended to the current user who needs the rental, thus wasting the current User's time situation.

Further, in an embodiment of the present application, after displaying the recommended user as a potential shared roommate of the current user on the user interface, the method further includes:

Receiving feedback information from the current user on the recommended user to update the matching degree between the current user and the characteristic information of the recommended user.

In this embodiment, the rental platform pushes some recommended users to the current user, and the current user can contact and communicate with the recommended user through the communication tool provided by the rental platform. For example, text communication can be performed first. If the user is interested / disinterested in the recommended user and / or the rental demand posted by the recommended user, the user can provide feedback through the buttons provided by the rental platform. After the rental platform receives the current user's feedback information on the recommended user, the feedback information It includes positive feedback information and negative feedback information. If it is negative feedback information, the value with the matching degree can be reduced according to the negative feedback information; if it is positive feedback information, the value of the matching degree can be increased according to the negative feedback information. For example, both parties can rate each other on a scale of 0-10. When the score is higher, it means that they are more satisfied with the other party. It also indirectly verifies that the potential roommate recommended by the rental platform for the user is in line with the needs of the user. The rental platform can also use this Modify the calculation rules of matching degree to better recommend more suitable potential roommates for users.

Further, in an embodiment of the present application, the method further includes: adding the added value of the matching degree to the characteristic information corresponding to the user in the rented house according to the length of time of the shared rent.

In this embodiment, the rental platform provides a function of recording which users are roommates in a shared room, and adds the added value of the matching degree to the characteristic information corresponding to the users in the shared room by the length of the shared room. For example, the shared room time is greater than 2 Month, add a certain added value b1 to the matching degree of the characteristic information of the users, and when the shared time is longer than 6 months, add a certain added value b2 to the matching degree of the characteristic information of the users, The algorithm of matching degree can be optimized, and the matching degree of each feature information is updated according to the length of time of the shared users, so as to provide a reference for subsequent users who need to find roommates for sharing.

As shown in FIG. 3, in another embodiment, the present application provides a shared roommate recommendation device, including:

The obtaining module 100 is configured to obtain characteristic information of a current user, where the characteristic information includes basic information, label information, and evaluation information of the user;

Calculation module 200: used to obtain the characteristic information of the pending user who has issued the rental demand, and calculate the degree of matching between the characteristic information of the current user and the characteristic information of the pending user;

A determining module 300 is configured to: when the current user defines a screening condition for a shared rent, obtain a pending user corresponding to the published rental demand that meets the screening condition, and determine the pending user whose matching degree meets the recommended condition as Recommend a user; when the current user does not have a custom shared filtering condition, determine a pending user whose matching degree meets the recommendation condition as a recommended user;

The recommendation module 400 is configured to display the recommended user as a potential shared roommate of the current user on the user interface to recommend the shared roommate to the user.

The basic information includes workplace information, hometown information, and school information. The calculating the matching degree between the characteristic information of the current user and the characteristic information of the pending user includes:

Determine whether the current user has workplace information; if so, determine the reference value of the matching degree according to the similarity between the workplace information of the current user and the pending user;

The published renting requirements include: renting requirements issued when wanting to find a rented house, and renting requirements issued when a renting house wants to find a roommate to be shared.

The current user-defined sharing conditions include:

Current users post rental needs looking for rent.

The displaying the recommended user as a potential shared roommate of the current user on the user interface includes:

The corresponding recommended users are displayed on the user interface as potential shared roommates of the current user according to the updated time order of the rental demand, and the update time includes editing the rental demand or polishing the time corresponding to the rental demand.

The device further includes:

Feedback module: used to receive feedback information from the current user on the recommended user to update the matching degree between the current user and the characteristic information of the recommended user, the feedback information includes positive feedback information and negative feedback information.

In another embodiment, the present application provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the program is executed by a processor, the shared roommate recommendation method described in the foregoing embodiment 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 embodiment of the present application can realize obtaining characteristic information of a current user, where the characteristic information includes basic information, label information, and evaluation information of a user; and obtaining information of a first pending user who has issued a rental demand. Feature information, calculating the degree of matching between the feature information of the current user and the feature information of the first pending user; when a filtering instruction input by the current user is obtained, a filtering condition is determined according to the filtering instruction, and the first pending A second pending user that meets the screening conditions is obtained from the users, and the second pending user whose matching degree meets the recommended conditions is determined as a recommended user; the recommended user is displayed on the user interface as a potential shared roommate of the current user, and Recommend shared roommates to users. By providing a renting model based on people-oriented + social, by obtaining the characteristic information of the current user, and then calculating the matching degree of the characteristic information of the current user and the pending user, whether or not the regular user has a custom-shared filtering condition can be determined Recommended users whose current users' matching degree meets the recommendation conditions. The recommended users will be displayed on the user interface as potential shared roommates of the current user. This will break the current form of rented rooms that are mainly based on recommended listings and prevent users from looking for suitable shared roommates. You need to find a lot of user information to match the problem of low success rate, and push more suitable potential roommates for users.

The computer-readable storage medium provided in the embodiment of the present application can implement the embodiment of the above-mentioned roommate recommendation method. For specific function implementation, refer to the description in the method embodiment, and details are not described herein again.

In addition, in another embodiment, the present application further provides a server. As shown in FIG. 4, the server processor 403, the memory 405, the input unit 407, and the display unit 409 are components. Those skilled in the art can understand that the structural device shown in FIG. 4 does not constitute a limitation on all servers, and may include more or fewer components than shown in the figure, or combine some components. The memory 405 may be used to store an application program 401 and various functional modules, and the processor 403 runs the application program 401 stored in the memory 405 so as to execute various functional applications and data processing of the device. The memory 405 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. 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 405 disclosed in the present application is only an example and not a limitation.

The input unit 407 is configured to receive an input of a signal and a keyword input by a user. The input unit 407 may include a touch panel and other input devices. The touch panel can collect the user's touch operations on or near it (such as the operation of the user 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 a 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 409 may be used to display information input by the user or information provided to the user and various menus of the computer device. The display unit 409 may take the form of a liquid crystal display, an organic light emitting diode, or the like. The processor 403 is the control center of the computer equipment. It uses various interfaces and lines to connect various parts of the entire computer. The processor 403 runs or executes software programs and / or modules stored in the memory 403, and calls data stored in the memory to execute. Various functions and processing data. One or more processors 403 shown in FIG. 4 can execute and implement the functions of the acquisition module 100, the calculation module 200, the determination module 300, and the recommendation module 400 shown in FIG.

In one embodiment, the server includes one or more processors 403, and one or more memories 405, and one or more applications 401, wherein the one or more applications 401 are stored in the memory 405 And is configured to be executed by the one or more processors 403, and the one or more application programs 401 are configured to execute the shared roommate recommendation method described in the above embodiment.

An embodiment of the present application provides a server that can obtain characteristic information of a current user, where the characteristic information includes basic information, label information, and evaluation information of the user; acquire characteristic information of a first pending user who has issued a rental demand, and calculate The degree of matching between the feature information of the current user and the feature information of the first pending user; when a filtering instruction input by the current user is obtained, a filtering condition is determined according to the filtering instruction, and a satisfying condition is obtained from the first pending user The second pending user of the screening condition, and determining the second pending user whose matching degree meets the recommendation condition as the recommended user; displaying the recommended user as a potential shared roommate of the current user on the user interface to recommend the shared rental to the user roommate. By providing a renting model based on people-oriented + social, by obtaining the characteristic information of the current user, and then calculating the matching degree of the characteristic information of the current user and the pending user, whether or not the regular user has a custom-shared filtering condition can be determined Recommended users whose current users' matching degree meets the recommendation conditions. The recommended users will be displayed on the user interface as potential shared roommates of the current user. This will break the current form of rented rooms that are mainly based on recommended listings and prevent users from looking for suitable shared roommates. You need to find a lot of user information to match the problem of low success rate, and push more suitable potential roommates for users.

The server provided in this embodiment of the present application can implement the above-mentioned embodiment of the shared roommate recommendation method. For specific function implementation, refer to the description in the method embodiment, and details are not described herein again.

Claims

A shared roommate recommendation method includes:

Obtaining characteristic information of the current user, where the characteristic information includes basic information, label information, and evaluation information of the user;

Acquiring the characteristic information of the first pending user who has issued the rental demand, and calculating the degree of matching between the characteristic information of the current user and the characteristic information of the first pending user;

When the filtering instruction input by the current user is obtained, a filtering condition is determined according to the filtering instruction, and a second pending user that meets the filtering condition is obtained from the first pending users, and the matching degree meets the recommended condition Of the second pending users are determined as recommended users;

The recommended user is displayed on the user interface as a potential shared roommate of the current user to recommend the shared roommate to the user.
The method according to claim 1, after calculating the matching degree between the feature information of the current user and the feature information of the first pending user, further comprising:

When the filtering instruction input by the current user is not obtained, the first pending user whose matching degree meets the recommendation condition is determined as the recommended user.
The method according to claim 1, wherein the basic information includes workplace information, hometown information, and school information, and the calculating the degree of matching between the characteristic information of the current user and the characteristic information of the first pending user includes:

Determine whether the current user has workplace information; if so, determine the reference value of the matching degree according to the similarity between the workplace information of the current user and the first pending user;

Determine the added value of the matching degree according to the hometown information, school information, tag information, and evaluation information; the calculation of the added value is as follows:

T = Boolean (A1 & A2) * 0.5 + Boolean (B1 & B2) * 0.5 + Boolean (C1 & C2) + Boolean (D1) * 0.2; Among them, A1, A2 represents hometown information, B1, B2 represents school information, C1, C2 represents label information D1 indicates evaluation information;

And calculating a matching degree of the feature information of the current user and the first pending user according to the reference value and the additional value.
The method according to claim 1, wherein displaying the recommended user as a potential shared roommate of the current user on the user interface comprises:

The corresponding recommended users are displayed on the user interface as potential shared roommates of the current user according to the updated time order of the rental demand, and the update time includes editing the rental demand or polishing the time corresponding to the rental demand.
The method according to claim 1, after displaying the recommended user as a potential shared roommate of the current user on the user interface, further comprising:

Receiving feedback information of the current user on the recommended user to update the matching degree between the current user and the characteristic information of the recommended user, the feedback information includes positive feedback information and negative feedback information.
A shared roommate recommendation device includes:

Obtaining module: used to obtain the characteristic information of the current user, the characteristic information includes the basic information, label information and evaluation information of the user;

A calculation module: used to obtain characteristic information of a first pending user who has issued a rental demand, and calculate a degree of matching between the characteristic information of the current user and the characteristic information of the first pending user;

A determining module, configured to: when a filtering instruction input by the current user is obtained, determine a filtering condition according to the filtering instruction, and obtain a second pending user that meets the filtering condition from the first pending user, and The second pending user whose matching degree meets the recommendation condition is determined as the recommended user;

Recommendation module: It is used to display the recommended user as a potential shared roommate of the current user on the user interface to recommend the shared roommate to the user.
The apparatus according to claim 6, the determining module further comprises:

When the filtering instruction input by the current user is not obtained, the first pending user whose matching degree meets the recommendation condition is determined as the recommended user.
The apparatus according to claim 6, further comprising:

Feedback module: used to receive feedback information from the current user on the recommended user to update the matching degree between the current user and the characteristic information of the recommended user, the feedback information includes positive feedback information and negative feedback information.
A non-volatile computer-readable storage medium stores a computer program on the non-volatile computer-readable storage medium. When the program is executed by a processor, a shared roommate recommendation method is implemented. The shared roommate recommendation method includes :

Obtaining characteristic information of the current user, where the characteristic information includes basic information, label information, and evaluation information of the user;

Acquiring the characteristic information of the first pending user who has issued the rental demand, and calculating the degree of matching between the characteristic information of the current user and the characteristic information of the first pending user;

When the filtering instruction input by the current user is obtained, a filtering condition is determined according to the filtering instruction, and a second pending user that meets the filtering condition is obtained from the first pending users, and the matching degree meets the recommended condition Of the second pending users are determined as recommended users;

The recommended user is displayed on the user interface as a potential shared roommate of the current user to recommend the shared roommate to the user.
The non-transitory computer-readable storage medium according to claim 9, after calculating the matching degree between the characteristic information of the current user and the characteristic information of the first pending user, further comprising:

When the filtering instruction input by the current user is not obtained, the first pending user whose matching degree meets the recommendation condition is determined as the recommended user.
The non-transitory computer-readable storage medium according to claim 9, wherein the basic information includes workplace information, hometown information, and school information, and the matching degree of the characteristic information of the current user and the characteristic information of the first pending user is calculated. ,include:

Determine whether the current user has workplace information; if so, determine the reference value of the matching degree according to the similarity between the workplace information of the current user and the first pending user;

Determine the added value of the matching degree according to the hometown information, school information, tag information, and evaluation information; the calculation of the added value is as follows:

T = Boolean (A1 & A2) * 0.5 + Boolean (B1 & B2) * 0.5 + Boolean (C1 & C2) + Boolean (D1) * 0.2; Among them, A1, A2 represents hometown information, B1, B2 represents school information, C1, C2 represents label information D1 indicates evaluation information;

And calculating a matching degree of the feature information of the current user and the first pending user according to the reference value and the additional value.
The non-transitory computer-readable storage medium of claim 9, wherein displaying the recommended user as a potential shared roommate of the current user on a user interface comprises:

The corresponding recommended users are displayed on the user interface as potential shared roommates of the current user according to the updated time order of the rental demand. The update time includes editing the rental demand or polishing the time corresponding to the rental demand.
The non-transitory computer-readable storage medium according to claim 9, after displaying the recommended user as a potential shared roommate of the current user on the user interface, further comprising:

Receiving feedback information of the current user on the recommended user to update the matching degree between the current user and the characteristic information of the recommended user, the feedback information includes positive feedback information and negative feedback information.
A server including:

One or more processors;

Memory

One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications are configured to execute A shared roommate recommendation method, the shared roommate recommendation method includes:

Obtaining characteristic information of the current user, where the characteristic information includes basic information, label information, and evaluation information of the user;

Acquiring the characteristic information of the first pending user who has issued the rental demand, and calculating the degree of matching between the characteristic information of the current user and the characteristic information of the first pending user;

When the filtering instruction input by the current user is obtained, a filtering condition is determined according to the filtering instruction, and a second pending user that meets the filtering condition is obtained from the first pending users, and the matching degree meets the recommended condition Of the second pending users are determined as recommended users;

The recommended user is displayed on the user interface as a potential shared roommate of the current user to recommend the shared roommate to the user.
The server according to claim 14, after calculating the matching degree between the characteristic information of the current user and the characteristic information of the first pending user, further comprising:

When the filtering instruction input by the current user is not obtained, the first pending user whose matching degree meets the recommendation condition is determined as the recommended user.
The server according to claim 14, wherein the basic information includes workplace information, hometown information, and school information, and the calculating the degree of matching between the characteristic information of the current user and the characteristic information of the first pending user includes:

Determine whether the current user has workplace information; if so, determine the reference value of the matching degree according to the similarity between the workplace information of the current user and the first pending user;

Determine the added value of the matching degree according to the hometown information, school information, tag information, and evaluation information; the calculation of the added value is as follows:

T = Boolean (A1 & A2) * 0.5 + Boolean (B1 & B2) * 0.5 + Boolean (C1 & C2) + Boolean (D1) * 0.2; Among them, A1, A2 represents hometown information, B1, B2 represents school information, C1, C2 represents label information D1 indicates evaluation information;

And calculating a matching degree of the feature information of the current user and the first pending user according to the reference value and the additional value.
The server according to claim 14, wherein displaying the recommended user as a potential shared roommate of the current user on the user interface comprises:

The corresponding recommended users are displayed on the user interface as potential shared roommates of the current user according to the updated time order of the rental demand, and the update time includes editing the rental demand or polishing the time corresponding to the rental demand.
The server according to claim 14, after displaying the recommended user as a potential shared roommate of the current user on the user interface, further comprising:

Receiving feedback information of the current user on the recommended user to update the matching degree between the current user and the characteristic information of the recommended user, the feedback information includes positive feedback information and negative feedback information.