CN111027999B - Method and device for recommending collage renter, electronic equipment and storage medium - Google Patents

Method and device for recommending collage renter, electronic equipment and storage medium Download PDF

Info

Publication number
CN111027999B
CN111027999B CN201911005727.8A CN201911005727A CN111027999B CN 111027999 B CN111027999 B CN 111027999B CN 201911005727 A CN201911005727 A CN 201911005727A CN 111027999 B CN111027999 B CN 111027999B
Authority
CN
China
Prior art keywords
lease
user
weight
weight vector
rental
Prior art date
Legal status (The legal status 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 status listed.)
Active
Application number
CN201911005727.8A
Other languages
Chinese (zh)
Other versions
CN111027999A (en
Inventor
卫海波
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beike Technology Co Ltd
Original Assignee
Beike Technology Co Ltd
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 Beike Technology Co Ltd filed Critical Beike Technology Co Ltd
Priority to CN201911005727.8A priority Critical patent/CN111027999B/en
Publication of CN111027999A publication Critical patent/CN111027999A/en
Application granted granted Critical
Publication of CN111027999B publication Critical patent/CN111027999B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0202—Market predictions or forecasting for commercial activities
    • 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
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/16—Real estate

Abstract

The application discloses a method and a device for recommending a splice renter, electronic equipment and a storage medium. The method comprises the following steps: acquiring a first weight vector of a lease bias characteristic of a first lease user; acquiring second weight vectors of all second renters in the system; and acquiring corresponding renting recommended users according to the first weight vector and the second weight vector, and sending the corresponding renting recommended users to the first renting users. The method can efficiently and quickly recommend the renters with similar renting bias to the renters, and can avoid the problem of renting conflict caused by different renting bias.

Description

Method and device for recommending collage renter, electronic equipment and storage medium
Technical Field
The application relates to the technical field of internet renting, in particular to a method and a device for recommending a spliced renter, electronic equipment and a storage medium.
Background
Because the price of the metropolitan area is high, many people adopt the way of renting to live in the metropolitan area, and most of renting users are not known each other before renting, even some conflicts caused by different renting bias occur after renting, the specific situation of the renting users can not be known by the existing renting intermediary company when introducing business.
Developed internet technology only provides the capability of finding houses on a home line, but does not solve the problem of rental conflict caused by different rental trends.
Disclosure of Invention
Aiming at the prior art, the embodiment of the application discloses a method, a device, electronic equipment and a storage medium for recommending a splice renter, which can efficiently and quickly recommend the splice renter with similar splice renter bias to the splice renter, and can avoid the problem of splice renting conflict caused by different splice renter bias.
In order to solve the technical problems, the technical scheme of the application is realized as follows:
in one embodiment, a splice renter recommendation method is provided, the method comprising:
acquiring a first weight vector of a lease bias characteristic of a first lease user;
acquiring second weight vectors of all second renters in the system;
and acquiring corresponding renting recommended users according to the first weight vector and the second weight vector, and sending the corresponding renting recommended users to the first renting users.
The step of obtaining the corresponding rental recommendation user according to the first weight vector and the second weight vector comprises the following steps:
judging whether a lease bias feature with a weight greater than a first preset threshold exists in the first weight vector;
If yes, judging whether the weight of the corresponding lease deflection feature in the second weight vector is larger than the first preset threshold value;
when judging that the weight of the corresponding lease deflection characteristic in the second weight vector is larger than the first preset threshold, determining the corresponding second lease user as the lease recommendation user;
when judging that the weight of the corresponding lease deflection feature in the second weight vector is not larger than the first preset threshold, judging whether the difference value between the weight of the corresponding lease deflection feature in the second weight vector and the weight of the lease deflection feature of the first weight vector is smaller than a second preset threshold, and if so, determining the corresponding second lease user as the lease recommendation user.
The step of obtaining the corresponding rental recommendation user according to the first weight vector and the second weight vector further includes:
calculating the similarity between the first lessor and each second lessor by using the first weight vector of the first lessor and the second weight vector of each second lessor;
sorting the second splice renters from high to low according to the corresponding similarity;
And taking the M second lease users before sequencing as lease recommending users.
And when the similarity between the first renter and each second renter is calculated by using the first weight vector of the first renter and the second weight vector of each second renter, calculating by using a cosine similarity algorithm, a Jaccard similarity coefficient algorithm or a Pelson correlation coefficient algorithm.
Wherein before the second splice lessees rank according to the corresponding similarity from high to low, the method further comprises:
and filtering out the second user with the similarity smaller than the fourth preset threshold value.
After the second weight vectors of all the second rental users in the system are obtained, before the corresponding rental recommendation users are obtained according to the first weight vectors and the second weight vectors, the method further comprises:
calculating the difference value of the weight values of the corresponding lease bias characteristics of the first lease user and each second lease user;
and if the calculated absolute value of the difference value is larger than a third preset threshold value, deleting the lease bias weight vector of the corresponding second lease user.
Wherein, before the obtaining the first weight vector of the rental bias characteristic of the first rental user, the method further comprises:
determining whether the first spell renter is a blacklist user, and if so, providing whole renting information for the first spell renter; otherwise, a first weight vector of the lease bias characteristics of the first lease user is obtained.
Wherein the method further comprises:
and storing the rented user into a blacklist according to the received evaluation information of the rented user.
In another embodiment, there is provided a splice renter recommending apparatus, the apparatus comprising: the device comprises an acquisition unit, a determination unit and a sending unit;
the acquisition unit is used for acquiring a first weight vector of the lease bias characteristic of the first lease user; acquiring second weight vectors of all second renters in the system;
the processing unit is used for acquiring the corresponding renting recommended user according to the first weight vector and the second weight vector acquired by the acquisition unit and sending the corresponding renting recommended user to the first renting user.
Wherein, the liquid crystal display device comprises a liquid crystal display device,
the processing unit is specifically configured to determine whether a rental deviation feature with a weight greater than a first preset threshold exists in the first weight vector when the corresponding rental recommendation user is obtained according to the first weight vector and the second weight vector; if yes, judging whether the weight of the corresponding lease deflection feature in the second weight vector is larger than the first preset threshold value; when judging that the weight of the corresponding lease deflection characteristic in the second weight vector is larger than the first preset threshold, determining the corresponding second lease user as the lease recommendation user; when judging that the weight of the corresponding lease deflection feature in the second weight vector is not larger than the first preset threshold, judging whether the difference value between the weight of the corresponding lease deflection feature in the second weight vector and the weight of the lease deflection feature of the first weight vector is smaller than a second preset threshold, and if so, determining the corresponding second lease user as the lease recommendation user.
Wherein, the liquid crystal display device comprises a liquid crystal display device,
the processing unit is further configured to calculate a similarity between a first rental user and each second rental user by using the first weight vector of the first rental user and the second weight vector of each second rental user when the corresponding rental recommendation user is obtained according to the first weight vector and the second weight vector; sorting the second splice renters from high to low according to the corresponding similarity; and taking the M second lease users before sequencing as lease recommending users.
Wherein, the liquid crystal display device comprises a liquid crystal display device,
the processing unit is specifically configured to calculate, when calculating the similarity between the first rental user and each second rental user by using a first weight vector of the first rental user and a second weight vector of each second rental user, a cosine similarity algorithm, a Jaccard similarity coefficient algorithm, or a pearson correlation coefficient algorithm.
Wherein, the liquid crystal display device comprises a liquid crystal display device,
and the processing unit is further used for filtering out the second user with the similarity smaller than a fourth preset threshold before the second spell renter sorts the second spell renters according to the corresponding similarity from high to low.
Wherein, the liquid crystal display device comprises a liquid crystal display device,
the processing unit is further configured to perform difference calculation on weight values of corresponding rental deviation features of the first rental user and each second rental user before the corresponding rental recommendation user is obtained according to the first weight vector and the second weight vector; and if the calculated absolute value of the difference value is larger than a third preset threshold value, deleting the lease bias weight vector of the corresponding second lease user.
Wherein, the liquid crystal display device comprises a liquid crystal display device,
the obtaining unit is further configured to determine whether the first rental user is a blacklist user before obtaining a first weight vector of a rental bias characteristic of the first rental user;
the processing unit is further configured to provide whole lease information for the first renter when the obtaining unit determines that the first renter is a blacklist user;
the obtaining unit is further configured to obtain a first weight vector of a rental bias characteristic of the first rental user when the first rental user is determined not to be the blacklist user.
Wherein, the liquid crystal display device comprises a liquid crystal display device,
the obtaining unit is further configured to store the rented user in the blacklist according to the received evaluation information of the rented user.
In another embodiment, there is also provided an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the spell tenant recommendation method when the program is executed.
In another embodiment, a computer readable storage medium having stored thereon computer instructions which when executed by a processor may implement steps in the collage renter recommendation method is also provided.
In summary, by acquiring the lease bias weights of the lease subscribers, lease subscribers with similar lease bias are screened for one lease subscriber and recommended to the lease subscribers. The scheme can efficiently and quickly recommend the lease to the lease users with similar lease bias, and can avoid the lease conflict problem caused by different lease bias.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort to a person skilled in the art.
FIG. 1 is a schematic flow chart of recommending a rental user according to a first embodiment of the application;
fig. 2 is a schematic flow chart of a first method for obtaining a corresponding rental recommendation user according to a first weight vector and the second weight vector in the embodiment of the application;
FIG. 3 is a flow chart of a second method for obtaining corresponding rental recommendation users according to a first weight vector and the second weight vector in the embodiment of the application;
FIG. 4 is a flowchart illustrating a method for recommending a rental user according to a second embodiment of the present application;
FIG. 5 is a schematic diagram of a device applied to the above technology according to an embodiment of the present application;
fig. 6 is a schematic diagram of an entity structure of an electronic device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented, for example, in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those elements but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The technical scheme of the application is described in detail below by specific examples. The following embodiments may be combined with each other, and some embodiments may not be repeated for the same or similar concepts or processes.
The embodiment of the application provides a lease recommendation method for lease users, which is used for screening lease users with similar lease bias for a lease user and recommending the lease users to the lease users by acquiring lease bias weights of the lease users. The scheme can efficiently and quickly recommend the lease to the lease users with similar lease bias, and can avoid the lease conflict problem caused by different lease bias.
The device for implementing the method for recommending the split renters in the embodiment of the application can be equipment with computing processing capability, such as a PC.
The process of recommending the split renters in the embodiment of the application is described in detail below with reference to the accompanying drawings:
example 1
Referring to fig. 1, fig. 1 is a schematic flow chart of recommending a rental user according to a first embodiment of the application. The method comprises the following specific steps:
step 101, a first weight vector of a rental bias characteristic of a first rental user is obtained.
In the embodiment of the application, the first weight vector for acquiring the lease bias characteristics of the first lease subscriber can be the first weight vector which is locally stored, or the first weight vector can be acquired through the information input by the first lease subscriber;
The implementation of obtaining the first weight vector through the information input by the first spelling renter can be as follows:
providing an interface for inputting a weight value of a lease bias for a first lease subscriber;
the interface may be provided when a rental request issued by the first rental user is received, or may be provided when a set user logs in to an interface, or performs a specific operation.
The interface for inputting the lease bias weight provided herein may be a page, a document (word, excel, etc.), on which a plurality of lease bias options are provided, and when a lease user selects which lease bias, the lease bias weight needs to be filled in for the selected lease bias; the unselected rental metrics do not need to fill in the rental metrics weight, and the system defaults to a corresponding rental metrics weight of 0.
The lease bias items on the interface provided by the embodiment of the application can be set according to actual needs, so long as the lease bias provided for each lease user in the same period is ensured to be the same, the lease bias provided can be: clean, basketball, return home without strangers, gender, age group, whether pet care is allowed, etc.
Assume that the first splice renter has selected: clean, free from strangers, home, gender, age, and four lease deviations, and respectively give weight values as follows: 0.5, 0.2, 0.1, 0.2.
Then the generated lease bias weight vector x= [0.5,0,0.2,0.1,0.2,0] for the first lease. The weight value of the unselected rental bias is recorded as 0, and the sum of the weight values of the rental bias filled in by the rental user is 1.
If the first lease user input lease bias weight value is not received, the first lease user selects the lease user with lease requirement on the system platform, and does not recommend the lease user.
Step 102, obtaining second weight vectors of all second renters in the system.
The generated lease bias weight vector of each lease subscriber is stored, and when the lease bias weight vectors of all lease subscribers need to be obtained, the lease bias weight vectors of the lease subscribers can be directly obtained from the local or obtained from other equipment, and the lease bias weight vectors of the lease subscribers are not limited.
In the embodiment of the application, the first renter is a user for which the renter needs to be recommended; the second tenant stores weight vectors for all tenants in the system for the tenant.
If the weight vectors of the lease bias characteristics of the lease A, the lease B and the lease C are stored in the system, all second lease users in the system are the lease A, the lease B and the lease C.
In the embodiment of the application, after the second weight vectors of all the second lessees in the system are acquired, the method further comprises the following steps:
calculating the difference value of the weight values of the corresponding lease bias characteristics of the first lease user and each second lease user;
and if the calculated absolute value of the difference value is larger than a third preset threshold value, deleting the lease bias weight vector of the corresponding second lease user.
After filtering the lease bias weight vector of the second lease user, step 203 is performed.
If the weight value of the first lease bias (clean) of the first lease subscriber is 0.5, the weight value of the first lease bias (clean) of a certain second lease subscriber is 0.1, the absolute value of the difference value of the weight values of the corresponding lease bias is 0.4, whether the difference value is large or not is determined according to a set third preset threshold value, if the difference value is larger than the third preset threshold value, the difference value is determined to be larger, the lease bias of the two lease subscribers can generate conflict, the two lease subscribers are not suitable for the lease, the second lease subscriber is not recommended, and the corresponding second lease subscriber is filtered.
Step 103, obtaining a corresponding rental recommendation user according to the first weight vector and the second weight vector, and sending the rental recommendation user to the first rental user.
In the embodiment of the application, the implementation modes for acquiring the corresponding renting recommended users according to the first weight vector and the second weight vector at least comprise the following three modes:
first kind:
referring to fig. 2, fig. 2 is a flowchart illustrating a first process of obtaining a corresponding rental recommendation user according to a first weight vector and the second weight vector in an embodiment of the present application. The method comprises the following specific steps:
step 201, judging whether a lease bias feature with a weight greater than a first preset threshold exists in the first weight vector, if so, executing step 202; otherwise, the process is ended.
Assuming that the first preset threshold is 0.45 and that there is a weight value (0.5) greater than 0.45 in the rental bias weight vector of the first rental user, step 202 is performed.
Step 202, judging whether the weight of the corresponding lease bias feature in the second weight vector is greater than the first preset threshold, if so, executing step 203; otherwise, step 204 is performed.
If the weight value in the lease bias weight vector of the first lease corresponds to the 1 st lease bias, if the weight value corresponding to the 1 st lease bias of the second lease is also greater than the first preset threshold, executing step 203; otherwise, step 204 is performed.
Step 203, determining the corresponding second spell renter as a spell recommended user; step 204 is performed.
After the execution of step 203, the present flow may be ended directly, or step 204 may be executed.
Step 204, determining whether a difference between the weight of the lease bias feature corresponding to the lease bias feature in the second weight vector and the weight of the lease bias feature of the first weight vector is smaller than a second preset threshold, and if so, executing step 205; otherwise, the process is ended.
Assuming that there is no corresponding rental bias weight vector of the second rental user that is not greater than the first preset threshold, looking at an absolute value of a difference between the corresponding rental bias weight vector and the corresponding rental bias weight vector of the first rental user, if the corresponding rental bias (1 st rental bias) of the first rental user has a weight value of 0.5, the corresponding rental bias (1 st rental bias) of the second rental user has a weight value of 0.4, and the absolute value of the difference is 0.1, if the second preset threshold is set to 0.15, executing step 205; the value set for the second preset threshold is given as an example, and is set according to actual needs in practical application, which is not limited herein.
Step 205, determining the second spell tenant user as a spell recommendation user.
That is, step 203 and step 205, the second rental recommended to the first rental user is: and a second rental user matched with the weight value with the largest rental deviation weight value of the first rental user, wherein the matching refers to that the weight value of the rental deviation corresponding to the largest weight value of the first rental user is larger than a first preset threshold value or the absolute value of the difference value of the weight value and the weight value is smaller than a second preset threshold value.
By the method, the first renter can recommend the renters with similar renting bias to the first renter so as to achieve the aim of renting faster and avoid conflict of the renting bias after renting.
Second kind:
referring to fig. 3, fig. 3 is a flow chart illustrating a second method for obtaining a corresponding rental recommendation user according to a first weight vector and the second weight vector in an embodiment of the present application. The method comprises the following specific steps:
step 301, calculating the similarity between the first tenant user and each second tenant user by using the first weight vector of the first tenant user and the second weight vector of each second tenant user.
The algorithm for calculating the similarity is as follows: cosine similarity algorithm, jaccard similarity coefficient algorithm, or Pelson correlation coefficient algorithm;
Assuming that three second renters exist, the corresponding renter deflection vectors of the three second renters are Y, Z, M, N, respectively, calculating the similarity of X and Y, the similarity of X and Z, the similarity of X and M, and the similarity of X and N as the similarity between the corresponding renters.
In the step, the similarity between the first renter and each second renter is calculated by adopting a preset similarity algorithm according to the renting bias weight vector of the first renter and the obtained renting bias weight vectors of all the second renters.
The preset similarity algorithm is not limited in the embodiment of the application, so long as the algorithm of the similarity of the two vectors can be calculated.
The preset similarity algorithm can be a cosine similarity algorithm, a Jaccard similarity coefficient algorithm, a Pelson correlation coefficient algorithm and other similarity algorithms; taking the pearson correlation coefficient algorithm as an example, the procedure of calculating the similarity between the first tenant and the second tenant is given as follows: .
Assuming that the rental bias weight vector of the first rental user is X and the rental bias weight vector of the second rental user is Y, the similarity of the first rental user and the second rental user can be calculated by the following formula:
Wherein, take the lease bias item as n as an example, X i The ith lease bias for the first lease user is corresponding weight value, Y i The ith lease bias of the second lease user is corresponding weight value; i is an integer of 1 or more and n or less;representing the average weight value of all rental biases of the first rental user, +.>Representing the average weight value of all the rental biases of the second rental user; the numerator is the covariance of vector X and vector Y, and the denominator identifies the product of the respective standard deviations of X and Y.
Step 302, sorting the second splice renters from high to low according to the corresponding similarity.
Before the second splice lessee ranks from high to low according to the corresponding similarity, the method further comprises:
and filtering out the second user with the similarity smaller than the fourth preset threshold value.
Through step 104, after the similarity between the first tenant-renter and each second tenant-renter can be calculated, the corresponding second tenant-renters are ranked according to the mode that the similarity is high to low, if the second tenant-renters with the same similarity appear, the second tenant-renters with the same similarity are randomly arranged, and the corresponding second tenant-renters can be prioritized according to the corresponding tenant-renting bias weight value of each second tenant-renter, which is the largest in the tenant-renting bias weight value and closest to the first tenant-renter.
In the embodiment of the application, when the similarity between all the second renters and the first renters is obtained in the concrete implementation, the second users with the similarity smaller than a fourth preset threshold value are filtered out, that is, only the second renters with high similarity with the first renters are reserved for recommending to the first renters;
in specific implementation, the first K second split renters after sorting can be recommended to the first split renter, that is, the first K split renters with relatively high similarity to the first split renter are recommended to the first split renter, and other second split renters are not recommended.
The embodiment screens the lease subscribers with similar lease bias for the lease subscribers and recommends the lease subscribers by using the lease bias weights input by the lease subscribers. The scheme can efficiently and quickly recommend the lease users with similar lease bias to the lease users.
And 303, taking the M second spell renters before sorting as spell recommended users.
Third kind:
combination of the first and second modes:
First bonding mode:
and the union of the determined lease recommendation user in the first mode and the lease recommendation user determined in the second mode is used as the determined lease recommendation user and is sent to the first lease user.
The second combination mode is as follows:
and when the first mode does not determine the rental recommendation user, determining the rental recommendation user by using the second mode, and sending the rental recommendation user to the first rental user.
Third mode of combination:
determining a lease recommendation user in a first mode, determining lease recommendation users except the lease recommendation users determined in a second lease user in a second mode, and transmitting the lease recommendation users determined in the two modes to the first lease user.
Example two
Referring to fig. 4, fig. 4 is a schematic flow chart of recommending a rental user in the second embodiment of the application. The method comprises the following specific steps:
step 401, obtaining a blacklist.
The blacklist is set for the spell renter with bad habit, can be set systematically, can be updated, and stores the spell renter into the blacklist according to the received evaluation information of the spell renter.
Here, it may be set that only the poor evaluation is received, and the users of the received evaluation information are all saved in the blacklist.
User identification may be used in the blacklist to represent a rental user, such as a user name, a user's cell phone number, etc.
Step 402, it is determined whether the first splice lessor is a blacklisted user, if so, step 403 is performed, otherwise step 404 is performed.
Matching the user identification of the first renter in the obtained blacklist, and executing step 403; otherwise, step 404 is performed.
Step 403, providing the whole renting information for the first renting user, and ending the process.
In this case, the rental user is not recommended to the first rental user, and only the whole rental information is provided.
Step 404, obtaining a first weight vector of a rental bias characteristic of the first rental user and second weight vectors of all second rental users in the system.
Step 405, obtaining a corresponding rental recommendation user according to the first weight vector and the second weight vector, and sending the rental recommendation user to the first rental user.
Example III
Taking the way of providing an interface to obtain a first weight vector of a first lessor as an example, a determination process of lessor recommended users is given as follows:
and the first step, when receiving a lease request sent by a first lease subscriber, obtaining a blacklist.
The blacklist is set for the spell renter with bad habit, can be set systematically, can be updated according to user feedback,
user identification may be used in the blacklist to represent a rental user, such as a user name, a user's cell phone number, etc.
And step two, determining whether the first splice renter is a blacklist user, if so, executing the step three, otherwise, executing the step four.
Matching the user identification of the first renting user in the obtained blacklist, and executing a third step; otherwise, the fourth step is performed.
And thirdly, providing whole renting information for the first renting user, and ending the process.
In this case, the rental user is not recommended to the first rental user, and only the whole rental information is provided.
And step four, providing an interface for inputting the lease bias weight value for the first lease subscriber.
The interface for inputting the lease bias weight provided herein may be a page, a document (word, excel, etc.), on which a plurality of lease bias options are provided, and when a lease user selects which lease bias, the lease bias weight needs to be filled in for the selected lease bias; the unselected rental metrics do not need to fill in the rental metrics weight, and the system defaults to a corresponding rental metrics weight of 0.
And fifthly, generating and storing a lease bias weight vector of the first lease subscriber when the lease bias weight value input by the first lease subscriber is received.
The lease bias items on the interface provided by the embodiment of the application can be set according to actual needs, so long as the lease bias provided for each lease user in the same period is ensured to be the same, the lease bias provided can be: clean, basketball, return home without strangers, gender, age group, whether pet care is allowed, etc.
Assume that the first splice renter has selected: clean, free from strangers, home, gender, age, and four lease deviations, and respectively give weight values as follows: 0.5, 0.2,0.1, 0.2.
Then the generated lease bias weight vector x= [0.5,0,0.2,0.1,0.2,0] for the first lease. The weight value of the unselected rental bias is recorded as 0, and the sum of the weight values of the rental bias filled in by the rental user is 1.
If the first lease user input lease bias weight value is not received, the first lease user selects the lease user with lease requirement on the system platform, and does not recommend the lease user.
And sixthly, obtaining the lease bias weight vector of all second lease subscribers with lease requirements.
The generated lease bias weight vector of each lease subscriber is stored, and when the lease bias weight vectors of all lease subscribers need to be obtained, the lease bias weight vectors of the lease subscribers can be directly obtained from the local or obtained from other equipment, and the lease bias weight vectors of the lease subscribers are not limited.
Seventh, determining whether a weight value larger than a first preset threshold exists in the lease bias weight vector of the first lease user, if so, executing the eighth step, otherwise, executing the eleventh step.
Assuming that the first preset weight value is 0.45 and that a weight value (0.5) greater than 0.45 exists in the rental bias weight vector of the first rental user, the eighth step is performed.
Eighth, determining whether a weight value corresponding to the rental deviation exists in the acquired rental deviation weight vector of the second rental user, and if so, executing a tenth step; otherwise, the ninth step is performed.
If the weight value in the lease bias weight vector of the first lease corresponds to the 1 st lease bias, executing a tenth step if the weight value corresponding to the 1 st lease bias of the second lease is also greater than a first preset threshold; otherwise, the ninth step is performed.
A ninth step of determining whether a weight value corresponding to the rental deviation is not greater than a first preset threshold value in the obtained rental deviation weight vector of the second rental user, and if so, executing a tenth step, wherein the absolute value of the difference value between the weight value corresponding to the rental deviation and the weight value corresponding to the first rental user is smaller than the weight value of the second preset threshold value; otherwise, the eleventh step is performed.
If the rental deviation weight vector of the second rental user does not have a weight value of the corresponding rental deviation not greater than the first preset threshold, looking at an absolute value of a difference value between the weight value of the corresponding rental deviation and the weight value of the corresponding rental deviation of the first rental user, if the weight value of the corresponding rental deviation (1 st rental deviation) of the first rental user is 0.5, the weight value of the corresponding rental deviation (1 st rental deviation) of the second rental user is 0.4, and the absolute value of the difference value is 0.1, and if the second preset threshold is set to 0.15, executing a tenth step; if the second preset threshold is set to 0.5, the eleventh step is performed, where the value set for the second preset threshold is an example, and the value is set according to the actual needs in practical application, which is not limited herein.
And tenth, recommending the corresponding second renter to the first renter, and ending the process.
That is, in the tenth step, the second rental user recommended to the first rental user is: and a second rental user matched with the weight value with the largest rental deviation weight value of the first rental user, wherein the matching refers to that the weight value of the rental deviation corresponding to the largest weight value of the first rental user is larger than a first preset threshold value or the absolute value of the difference value of the weight value and the weight value is smaller than a second preset threshold value.
By the method, the first renter can recommend the renters with similar renting bias to the first renter so as to achieve the aim of renting faster and avoid conflict of the renting bias after renting.
And eleventh step, obtaining weight values of corresponding rental biases of the first rental user and the second rental user.
And twelfth, calculating the difference value of the obtained weight values of the corresponding lease bias of the first lease user and each second lease user.
And thirteenth, deleting the obtained lease bias weight vector corresponding to the second lease if the calculated difference absolute value is larger than a third preset threshold value.
If the weight value of the first lease bias (clean) of the first lease subscriber is 0.5, the weight value of the first lease bias (clean) of a certain second lease subscriber is 0.1, the absolute value of the difference value of the weight values of the corresponding lease bias is 0.4, whether the difference value is large or not is determined according to a set third preset threshold value, if the difference value is larger than the third preset threshold value, the difference value is determined to be larger, the lease bias of the two lease subscribers can generate conflict, the two lease subscribers are not suitable for the lease, the second lease subscriber is not recommended, and the corresponding second lease subscriber is filtered.
And fourteenth step, calculating the similarity between the first lessor and each second lessor according to the lessor deviation weight vector of the first lessor and the lessor deviation weight vectors of all the acquired second lessor.
Assuming that three second renters exist, the corresponding renter deflection vectors of the three second renters are Y, Z, M, N, respectively, calculating the similarity of X and Y, the similarity of X and Z, the similarity of X and M, and the similarity of X and N as the similarity between the corresponding renters.
In the step, the similarity between the first renter and each second renter is calculated by adopting a preset similarity algorithm according to the renting bias weight vector of the first renter and the obtained renting bias weight vectors of all the second renters.
The preset similarity algorithm is not limited in the embodiment of the application, so long as the algorithm of the similarity of the two vectors can be calculated.
The preset similarity algorithm can be a cosine similarity algorithm, a Jaccard similarity coefficient algorithm, a Pelson correlation coefficient algorithm and other similarity algorithms; taking the pearson correlation coefficient algorithm as an example, the procedure of calculating the similarity between the first tenant and the second tenant is given as follows: .
Assuming that the rental bias weight vector of the first rental user is X and the rental bias weight vector of the second rental user is Y, the similarity of the first rental user and the second rental user can be calculated by the following formula:
wherein, take the lease bias item as n as an example, X i Ith rental for first rental userBias towards corresponding weight value, Y i The ith lease bias of the second lease user is corresponding weight value; i is an integer of 1 or more and n or less;representing the average weight value of all rental biases of the first rental user, +.>Representing the average weight value of all the rental biases of the second rental user; the numerator is the covariance of vector X and vector Y, and the denominator identifies the product of the respective standard deviations of X and Y.
And fifteenth, sorting all second renter sharing users according to the corresponding similarity from high to low, and recommending the second renter sharing users to the first renter sharing users.
Through the fourteenth step, after the similarity between the first renter and each second renter can be calculated, the corresponding second renters are ranked in a mode that the similarity is high to low, if the second renters with the same similarity appear, the second renters with the same similarity are randomly arranged, and the corresponding second renters can be prioritized according to the corresponding renting bias weight value of each second renter, which is the largest in renting bias weight value and closest to the first renter.
In the embodiment of the application, when the similarity between all the second renters and the first renters is obtained in the concrete implementation, the second users with the similarity smaller than a fourth preset threshold value are filtered out, that is, only the second renters with high similarity with the first renters are reserved for recommending to the first renters;
in specific implementation, the first K second split renters after sorting can be recommended to the first split renter, that is, the first K split renters with relatively high similarity to the first split renter are recommended to the first split renter, and other second split renters are not recommended.
The embodiment screens the lease subscribers with similar lease bias for the lease subscribers and recommends the lease subscribers by using the lease bias weights input by the lease subscribers. The scheme can efficiently and quickly recommend the lease users with similar lease bias to the lease users.
This embodiment takes the house as a bridge between communicating splice renters by being based on the on-line house capabilities. Each renter can issue its own renting demands on line and screen the renting bias of the existing house source households to find out the proper renters. The scheme can enable the renter to efficiently and quickly find out the proper renter on line, shorten the house finding time, reduce the conflict of the subsequent renter life and the like.
Based on the same inventive concept, the embodiment of the application also provides a device for recommending the rented user. Referring to fig. 5, fig. 5 is a schematic view of a device structure according to an embodiment of the present application, where the device structure is applied to the above technology. The device comprises: an acquisition unit 501 and a processing unit 502;
an obtaining unit 501, configured to obtain a first weight vector of a rental bias characteristic of a first rental user; acquiring second weight vectors of all second renters in the system;
the processing unit 502 is configured to obtain a corresponding rental recommendation user according to the first weight vector and the second weight vector obtained by the obtaining unit 501, and send the first rental recommendation user to the first rental user.
Preferably, the method comprises the steps of,
the processing unit 502 is specifically configured to determine whether a rental deviation feature with a weight greater than a first preset threshold exists in the first weight vector when the corresponding rental recommendation user is obtained according to the first weight vector and the second weight vector; if yes, judging whether the weight of the corresponding lease deflection feature in the second weight vector is larger than the first preset threshold value; when judging that the weight of the corresponding lease deflection characteristic in the second weight vector is larger than the first preset threshold, determining the corresponding second lease user as the lease recommendation user; when judging that the weight of the corresponding lease deflection feature in the second weight vector is not larger than the first preset threshold, judging whether the difference value between the weight of the corresponding lease deflection feature in the second weight vector and the weight of the lease deflection feature of the first weight vector is smaller than a second preset threshold, and if so, determining the corresponding second lease user as the lease recommendation user.
Preferably, the method comprises the steps of,
the processing unit 502 is further configured to calculate a similarity between a first rental user and each second rental user by using the first weight vector of the first rental user and the second weight vector of each second rental user when the corresponding rental recommendation user is obtained according to the first weight vector and the second weight vector; the algorithm for calculating the similarity is as follows: cosine similarity algorithm, jaccard similarity coefficient algorithm, or Pelson correlation coefficient algorithm; sorting the second splice renters from high to low according to the corresponding similarity; and taking the M second lease users before sequencing as lease recommending users.
Preferably, the method comprises the steps of,
the processing unit 502 is specifically configured to calculate, when calculating the similarity between the first tenant user and each second tenant user by using the first weight vector of the first tenant user and the second weight vector of each second tenant user, a cosine similarity algorithm, a Jaccard similarity coefficient algorithm, or a pearson correlation coefficient algorithm.
Preferably, the method comprises the steps of,
the processing unit 502 is further configured to filter out the second user whose similarity is smaller than the fourth preset threshold before the second spell renter ranks from high to low according to the corresponding similarity.
Preferably, the method comprises the steps of,
the processing unit 502 is further configured to perform difference calculation on weight values of corresponding rental bias characteristics of the first rental user and each second rental user before obtaining the corresponding rental recommendation user according to the first weight vector and the second weight vector; and if the calculated absolute value of the difference value is larger than a third preset threshold value, deleting the lease bias weight vector of the corresponding second lease user.
Preferably, the method comprises the steps of,
an obtaining unit 501, configured to determine whether the first rental user is a blacklisted user before obtaining a first weight vector of a rental bias characteristic of the first rental user;
the processing unit 502 is further configured to provide the first rental user with whole rental information when the obtaining unit 501 determines that the first rental user is a blacklisted user;
the obtaining unit 501 is further configured to obtain a first weight vector of a rental bias characteristic of the first rental user when it is determined that the first rental user is not a blacklisted user.
Preferably, the method comprises the steps of,
the obtaining unit 501 is further configured to save the rented user to the blacklist according to the received evaluation information of the rented user.
The units of the above embodiments may be integrated or may be separately deployed; can be combined into one unit or further split into a plurality of sub-units.
In another embodiment, there is also provided an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the spell tenant recommendation method when the program is executed.
In another embodiment, a computer readable storage medium having stored thereon computer instructions which when executed by a processor may implement steps in the collage renter recommendation method is also provided.
Fig. 6 is a schematic diagram of an entity structure of an electronic device according to an embodiment of the present invention. As shown in fig. 6, the electronic device may include: processor 610, communication interface (Communications Interface) 620, memory 630, and communication bus 640, wherein processor 610, communication interface 620, and memory 630 communicate with each other via communication bus 640. The processor 610 may call logic instructions in the memory 630 to perform the following methods:
acquiring a first weight vector of a lease bias characteristic of a first lease user;
acquiring second weight vectors of all second renters in the system;
and acquiring corresponding renting recommended users according to the first weight vector and the second weight vector, and sending the corresponding renting recommended users to the first renting users.
Further, the logic instructions in the memory 630 may be implemented in the form of software functional units and stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.

Claims (9)

1. A method for a splice renter recommendation, the method comprising:
acquiring a first weight vector of a lease bias characteristic of a first lease user;
acquiring second weight vectors of all second renters in the system;
acquiring corresponding renting recommended users according to the first weight vector and the second weight vector, and sending the corresponding renting recommended users to the first renting users;
the step of obtaining the corresponding rental recommendation user according to the first weight vector and the second weight vector comprises the following steps:
Judging whether a lease bias feature with a weight greater than a first preset threshold exists in the first weight vector;
if yes, judging whether the weight of the corresponding lease deflection feature in the second weight vector is larger than the first preset threshold value;
when judging that the weight of the corresponding lease deflection characteristic in the second weight vector is larger than the first preset threshold, determining the corresponding second lease user as the lease recommendation user;
when judging that the weight of the corresponding lease deflection feature in the second weight vector is not larger than the first preset threshold, judging whether the difference value between the weight of the corresponding lease deflection feature in the second weight vector and the weight of the lease deflection feature of the first weight vector is smaller than a second preset threshold, and if so, determining the corresponding second lease user as the lease recommendation user.
2. The method of claim 1, wherein the step of obtaining the corresponding rental recommendation user from the first weight vector and the second weight vector further comprises:
calculating the similarity between the first lessor and each second lessor by using the first weight vector of the first lessor and the second weight vector of each second lessor;
Sorting the second splice renters from high to low according to the corresponding similarity;
and taking the M second lease users before sequencing as lease recommending users.
3. The method of claim 2, wherein before ranking the second splice lessees from high to low in their respective similarities, the method further comprises:
and filtering out the second user with the similarity smaller than the fourth preset threshold value.
4. The method of claim 1, wherein after the obtaining the second weight vectors of all the second rental users in the system, before the obtaining the corresponding rental recommendation users according to the first weight vectors and the second weight vectors, the method further comprises:
calculating the difference value of the weight values of the corresponding lease bias characteristics of the first lease user and each second lease user;
and if the calculated absolute value of the difference value is larger than a third preset threshold value, deleting the lease bias weight vector of the corresponding second lease user.
5. The method of claim 1, wherein prior to obtaining the first weight vector for the rental bias characteristic of the first rental user, the method further comprises:
Determining whether the first spell renter is a blacklist user, and if so, providing whole renting information for the first spell renter; otherwise, a first weight vector of the lease bias characteristics of the first lease user is obtained.
6. The method according to claim 5, wherein the method further comprises:
and storing the rented user into a blacklist according to the received evaluation information of the rented user.
7. A splice renter recommendation device, the device comprising: an acquisition unit and a processing unit;
the acquisition unit is used for acquiring a first weight vector of the lease bias characteristic of the first lease user; acquiring second weight vectors of all second renters in the system;
the processing unit is used for acquiring corresponding renting recommended users according to the first weight vector and the second weight vector acquired by the acquisition unit and sending the corresponding renting recommended users to the first renting users;
the processing unit is specifically configured to determine whether a rental deviation feature with a weight greater than a first preset threshold exists in the first weight vector when the corresponding rental recommendation user is obtained according to the first weight vector and the second weight vector; if yes, judging whether the weight of the corresponding lease deflection feature in the second weight vector is larger than the first preset threshold value; when judging that the weight of the corresponding lease deflection characteristic in the second weight vector is larger than the first preset threshold, determining the corresponding second lease user as the lease recommendation user; when judging that the weight of the corresponding lease deflection feature in the second weight vector is not larger than the first preset threshold, judging whether the difference value between the weight of the corresponding lease deflection feature in the second weight vector and the weight of the lease deflection feature of the first weight vector is smaller than a second preset threshold, and if so, determining the corresponding second lease user as the lease recommendation user.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the program is executed.
9. A computer readable storage medium having stored thereon computer instructions, which when executed by a processor, perform the steps of the method of any of claims 1-6.
CN201911005727.8A 2019-10-22 2019-10-22 Method and device for recommending collage renter, electronic equipment and storage medium Active CN111027999B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911005727.8A CN111027999B (en) 2019-10-22 2019-10-22 Method and device for recommending collage renter, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911005727.8A CN111027999B (en) 2019-10-22 2019-10-22 Method and device for recommending collage renter, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN111027999A CN111027999A (en) 2020-04-17
CN111027999B true CN111027999B (en) 2023-10-20

Family

ID=70201472

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911005727.8A Active CN111027999B (en) 2019-10-22 2019-10-22 Method and device for recommending collage renter, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN111027999B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111597450A (en) * 2020-05-21 2020-08-28 深圳辉煌明天科技有限公司 Intelligent analysis system and method for big data

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102496265A (en) * 2011-11-29 2012-06-13 杭州妙影微电子有限公司 Taxi calling and carpooling method based on mobile terminal and system thereof
CN104065722A (en) * 2014-06-23 2014-09-24 中国联合网络通信集团有限公司 Taxi joint taking taxi calling method and server
CN105976195A (en) * 2015-10-22 2016-09-28 乐视移动智能信息技术（北京）有限公司 Method and device for recommendation of shared accommodation information
CN106528860A (en) * 2016-11-30 2017-03-22 华南师范大学 Recommending method, device and system based on social network and big data analysis
CN106528785A (en) * 2016-11-03 2017-03-22 杜剑峰 Question synthesis based user renting preference capturing method
CN108389106A (en) * 2018-02-07 2018-08-10 链家网（北京）科技有限公司 Method and device is rented in the automatic spelling in whole source of renting a house
CN108985881A (en) * 2018-06-22 2018-12-11 平安科技（深圳）有限公司 Share room-mate's recommended method, device and computer readable storage medium, server
CN109886773A (en) * 2019-01-17 2019-06-14 平安城市建设科技(深圳)有限公司 Recommended method, device, equipment and storage medium based on lessee's credit appraisal
CN109934595A (en) * 2019-01-22 2019-06-25 深圳壹账通智能科技有限公司 House prosperity transaction method, apparatus, equipment and storage medium based on big data
CN110069712A (en) * 2019-04-23 2019-07-30 平安城市建设科技(深圳)有限公司 Source of houses recommended method and relevant device based on source of houses evaluation semantic analysis

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102496265A (en) * 2011-11-29 2012-06-13 杭州妙影微电子有限公司 Taxi calling and carpooling method based on mobile terminal and system thereof
CN104065722A (en) * 2014-06-23 2014-09-24 中国联合网络通信集团有限公司 Taxi joint taking taxi calling method and server
CN105976195A (en) * 2015-10-22 2016-09-28 乐视移动智能信息技术（北京）有限公司 Method and device for recommendation of shared accommodation information
WO2017067222A1 (en) * 2015-10-22 2017-04-27 乐视控股（北京）有限公司 Method and device for recommending joint rent information
CN106528785A (en) * 2016-11-03 2017-03-22 杜剑峰 Question synthesis based user renting preference capturing method
CN106528860A (en) * 2016-11-30 2017-03-22 华南师范大学 Recommending method, device and system based on social network and big data analysis
CN108389106A (en) * 2018-02-07 2018-08-10 链家网（北京）科技有限公司 Method and device is rented in the automatic spelling in whole source of renting a house
CN108985881A (en) * 2018-06-22 2018-12-11 平安科技（深圳）有限公司 Share room-mate's recommended method, device and computer readable storage medium, server
CN109886773A (en) * 2019-01-17 2019-06-14 平安城市建设科技(深圳)有限公司 Recommended method, device, equipment and storage medium based on lessee's credit appraisal
CN109934595A (en) * 2019-01-22 2019-06-25 深圳壹账通智能科技有限公司 House prosperity transaction method, apparatus, equipment and storage medium based on big data
CN110069712A (en) * 2019-04-23 2019-07-30 平安城市建设科技(深圳)有限公司 Source of houses recommended method and relevant device based on source of houses evaluation semantic analysis

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
何佶星 ; 陈汶滨 ; 牟斌皓 ; .流行度划分结合平均偏好权重的协同过滤个性化推荐算法.计算机科学.2017,(第S1期),全文. *
刘旭东 ; 叶长国 ; .一种基于用户偏好序列的协同过滤推荐.泰山学院学报.2009,(第06期),全文. *
胡健 ; 覃慧 ; 梁雪雷 ; .基于用户量化属性的多维相似度的协同过滤推荐算法.江西理工大学学报.2017,(第03期),全文. *

Also Published As

Publication number Publication date
CN111027999A (en) 2020-04-17

Similar Documents

Publication Publication Date Title
US9589025B2 (en) Correlated information recommendation
CN105630977B (en) Application program recommended method, apparatus and system
CN110060090A (en) Method, apparatus, electronic equipment and the readable storage medium storing program for executing of Recommendations combination
CN108460590B (en) Information recommendation method and device and electronic equipment
CN110008973B (en) Model training method, method and device for determining target user based on model
CN111639988B (en) Broker recommendation method, device, electronic equipment and storage medium
CN103890762A (en) Information processing device, information processing method, information processing program, and recording medium
CN111078997B (en) Information recommendation method and device
CN111027999B (en) Method and device for recommending collage renter, electronic equipment and storage medium
CN115271976A (en) Advisory recommendation method and device and computer readable storage medium
CN109829593B (en) Credit determining method and device for target object, storage medium and electronic device
CN110110206B (en) Method, device, computing equipment and storage medium for mining and recommending relationships among articles
US20180129664A1 (en) System and method to recommend a bundle of items based on item/user tagging and co-install graph
CN111782774B (en) Method and device for recommending problems
CN113468886B (en) Work order processing method and device and computer equipment
CN111028044B (en) Renting method and device, electronic equipment and storage medium
CN116415063A (en) Cloud service recommendation method and device
CN110175271B (en) Case random ordering method and device
CN113707282A (en) Candidate doctor sorting method and device, readable storage medium and electronic equipment
CN113486248A (en) Recommendation method and device for functional module in application program
CN112487277A (en) Data distribution method and device, readable storage medium and electronic equipment
CN111324830B (en) Object processing method and device, electronic equipment and computer readable storage medium
CN117217852B (en) Behavior recognition-based purchase willingness prediction method and device
CN114663200B (en) Product recommendation method and device, electronic equipment and storage medium
CN111222052B (en) Searching method and device and electronic equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant