CN112001760B - Potential user mining method and device, electronic equipment and storage medium - Google Patents
Potential user mining method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112001760B CN112001760B CN202010884687.5A CN202010884687A CN112001760B CN 112001760 B CN112001760 B CN 112001760B CN 202010884687 A CN202010884687 A CN 202010884687A CN 112001760 B CN112001760 B CN 112001760B
- Authority
- CN
- China
- Prior art keywords
- user
- attribute information
- house
- house source
- unit
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000005065 mining Methods 0.000 title claims abstract description 34
- 239000013598 vector Substances 0.000 claims abstract description 54
- 238000004364 calculation method Methods 0.000 claims abstract description 24
- 239000011159 matrix material Substances 0.000 claims description 66
- 230000006399 behavior Effects 0.000 claims description 63
- 238000010606 normalization Methods 0.000 claims description 46
- 238000004422 calculation algorithm Methods 0.000 claims description 33
- 238000012545 processing Methods 0.000 claims description 31
- 238000004590 computer program Methods 0.000 claims description 5
- 238000010438 heat treatment Methods 0.000 description 12
- 238000005034 decoration Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000003064 k means clustering Methods 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 238000011002 quantification Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/16—Real estate
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a potential user mining method, a potential user mining device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring behavior information and attribute information of a user browsing a house source; calculating a weight vector of the house source in the house source browsed by the user according to the behavior information; acquiring attribute information of the traded house source, and performing clustering calculation on the attribute information of the traded house source to acquire a clustering center; determining the probability of the user becoming a potential user according to the attribute information of the house source browsed by the user, the weight vector and the clustering center; and when the probability is larger than a preset threshold value, determining that the user is a potential user. The scheme can improve the accuracy of potential user mining.
Description
Technical Field
The present invention relates to the field of information processing technologies, and in particular, to a method and an apparatus for mining a potential user, an electronic device, and a storage medium.
Background
At present, in the user mining process, statistical methods such as factor analysis, principal component analysis, joint analysis, regression analysis and the like are mostly adopted.
The user mining is carried out by adopting a statistical method, the characteristic of the house-watching behavior pattern of the user is easily covered, and the classification of the user is not considered, so that the accuracy rate of mining potential users is lower.
Disclosure of Invention
In view of this, the present application provides a method, an apparatus, an electronic device, and a storage medium for potential user mining, which can improve the accuracy of potential user mining.
In order to solve the technical problem, the technical scheme of the application is realized as follows:
in one embodiment, a method for potential user mining is provided, the method comprising:
acquiring behavior information and attribute information of a user browsing a house source;
calculating a weight vector of the house source in the house source browsed by the user according to the behavior information;
acquiring attribute information of the traded house source, and performing clustering calculation on the attribute information of the traded house source to acquire a clustering center;
determining the probability of the user becoming a potential user according to the attribute information of the house source browsed by the user, the weight vector and the clustering center;
and when the probability is larger than a preset threshold value, determining that the user is a potential user.
Wherein, the calculating the weight vector of the house source in the house source browsed by the user according to the behavior information comprises:
obtaining the weight P of the kth set of house resourceskComprises the following steps:
combining the weights of the N sets of room sources into weight vectors of the N sets of room sources;
wherein u iskjIs the value of the kth set of house resources on the jth behavior, unjThe value of the nth set of house resources on the jth behavior is shown, J is the number of behaviors of the user for browsing the house resources, N is the set number of the house resources, and k is more than or equal to 1 and less than or equal to N.
Wherein, the determining the probability of the user becoming a potential user according to the attribute information of the house source browsed by the user, the weight vector and the clustering center comprises:
calculating the probability of the user becoming a potential user by the following formula:
where Q is the probability of a user becoming a potential user, xnRepresenting the attribute information corresponding to the nth set of house sources in the matrix X, wherein the matrix X is the matrix corresponding to the attribute information of the house sources browsed by the user, amThe m-th cluster center in the matrix A corresponding to the cluster center, d (x)n,am) Denotes amAnd xnThe similarity of (2); m is the number of clustering centers, and N is the number of house source sets; p is a radical ofnIs the weight of the nth set of house resources.
Wherein,
the acquiring attribute information of the traded house source, performing clustering calculation on the attribute information of the traded house source, and acquiring a clustering center includes:
acquiring attribute information of a house source which is finished in transaction;
normalizing the attribute information of the traded house source;
performing clustering calculation on the attribute information of the traded house source after normalization processing to obtain a clustering center;
determining the probability of the user becoming a potential user according to the attribute information of the house source browsed by the user, the weight vector and the clustering center, wherein the determining comprises the following steps:
normalizing the attribute information of the house source browsed by the user;
and determining the probability of the user becoming a potential user according to the attribute information of the house source browsed by the user after normalization processing, the weight vector and the clustering center.
Wherein, the determining the probability of the user becoming a potential user according to the attribute information of the house source browsed by the user after the normalization processing, the weight vector and the clustering center comprises:
denoising the normalized attribute information of the user browsed house source by using a clustering algorithm, and determining the probability of the user becoming a potential user according to the denoised attribute information of the user browsed house source, the weight vector and the clustering center.
In another embodiment, the present application further provides a potential user mining device, including: the device comprises a first acquisition unit, a calculation unit, a second acquisition unit, a clustering unit, a first determination unit and a second determination unit;
the first acquisition unit is used for acquiring behavior information and attribute information of a user browsing a house source;
the calculating unit is used for calculating a weight vector of the house source in the house source browsed by the user according to the behavior information acquired by the first acquiring unit;
the second acquisition unit is used for acquiring attribute information of the house source which is finished in transaction;
the clustering unit is used for clustering and calculating the attribute information of the traded house source acquired by the second acquiring unit to acquire a clustering center;
the first determining unit is configured to determine, according to the attribute information of the user browsing the house source acquired by the first acquiring unit, the weight vector calculated by the calculating unit and the clustering center acquired by the clustering unit, a probability that the user becomes a potential user;
the second determining unit is used for determining that the user is a potential user when the probability determined by the first unit is greater than a preset threshold.
Wherein,
the computing unit is specifically used for acquiring the weight P of the kth set of room sourceskComprises the following steps:
combining the weights of the N sets of room sources into weight vectors of the N sets of room sources; wherein u iskjIs the value of the kth set of house resources on the jth behavior, unjThe value of the nth set of house resources on the jth behavior is shown, J is the number of behaviors of the user for browsing the house resources, N is the set number of the house resources, and k is more than or equal to 1 and less than or equal to N.
The first determining unit is specifically configured to calculate a probability that the user becomes a potential user according to the following formula:where Q is the probability of a user becoming a potential user, xnRepresenting the attribute information corresponding to the nth set of house sources in the matrix X, wherein the matrix X is the matrix corresponding to the attribute information of the house sources browsed by the user, amThe m-th cluster center in the matrix A corresponding to the cluster center, d (x)n,am) Denotes amAnd xnThe similarity of (2); m is the number of clustering centers, and N is the number of house source sets; p is a radical ofnIs the weight of the nth set of house resources.
Wherein the apparatus further comprises: a normalization unit;
the normalization unit is used for performing normalization processing on the attribute information of the house source which is acquired by the second acquisition unit and has been traded; normalizing the attribute information of the user browsed house source acquired by the first acquisition unit;
the clustering unit is specifically configured to perform clustering calculation on the attribute information of the traded house source after the normalization processing by the normalization unit to obtain a clustering center;
the first determining unit is specifically configured to determine, according to the attribute information of the house source browsed by the user after normalization processing by the normalizing unit, the probability that the user becomes a potential user according to the weight vector and the clustering center.
Wherein the apparatus further comprises: a denoising unit;
the denoising unit is used for denoising the attribute information of the user browsing house source normalized by the normalization unit by using a clustering algorithm;
the first determining unit is specifically configured to determine, according to the attribute information of the user browsing house source after normalization processing by the denoising unit, the probability that the user becomes a potential user according to the weight vector and the clustering center.
In another embodiment, an electronic device is provided 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 potential customer mining method as described when executing the program.
In another embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the potential customer mining method.
According to the technical scheme, the weight vector of the house source browsed by the user is determined by analyzing the behavior information of the house source browsed by the user, the attribute information of the house source which is traded is clustered, the probability that the user becomes a potential user is calculated according to the attribute information and the weight vector of the house source browsed by the user in history and the clustering center, and whether the user can become the potential user can be quantitatively determined. The scheme can improve the accuracy of potential user mining.
In the embodiment of the application, the attribute information of the house source browsed by the user is subjected to normalization processing and denoising processing during specific implementation, and the attribute information of the house source which has completed the transaction is subjected to normalization processing, so that the accuracy of potential user mining can be further improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
Fig. 1 is a schematic diagram illustrating a potential user mining process according to an embodiment of the present application;
fig. 2 is a schematic diagram illustrating a potential user mining process in the second embodiment of the present application;
fig. 3 is a schematic diagram of a potential user mining process in the third embodiment of the present application;
FIG. 4 is a schematic diagram of an apparatus for implementing the above technique in an embodiment of the present application;
fig. 5 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprising" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements explicitly listed, but may include other steps or elements not explicitly listed or inherent to such process, method, article, or apparatus.
The technical solution of the present invention will be described in detail with specific examples. Several of the following embodiments may be combined with each other and some details of the same or similar concepts or processes may not be repeated in some embodiments.
The embodiment of the application provides a potential user mining method which is applied to a potential user mining device and can be called as a mining device for short.
The excavating device can be applied to a server of a house-viewing APP and can also be deployed independently, and the embodiment of the application does not limit the server.
The potential user mining process is described in detail below in conjunction with the figures.
Example one
Referring to fig. 1, fig. 1 is a schematic diagram illustrating a potential user mining process according to a first embodiment of the present application. The method comprises the following specific steps:
In the embodiment of the application, the behavior information and the attribute information of the house source browsed by the user can be acquired through the data of the house source browsed by the user stored in the system database;
the behavior information of the user browsing the house resources can comprise one or any combination of the following information:
searching information, clicking information, consulting times, forwarding information, saving information and page staying time information;
however, the specific implementation may not be limited to the above information.
Searching information, recording the times of searching attribute information, wherein the searched attribute information is house type information, area information, price information and the like;
click information, recording attribute information of the clicked house source, such as area information, house type information and price information;
consultation times, namely consultation times information of house source economic persons and house-looking APP;
forwarding information, recording attribute information of all attributes corresponding to the forwarded house source;
storing information, recording attribute information of all attributes corresponding to the stored house source;
and page stay time information, and recording the duration of browsing attribute information.
The behavior information of the user browsing the house resources can be represented by a matrix U, rows of the matrix U represent the house resources (each row represents a set of house resources), and columns correspond to the behaviors (each column corresponds to one behavior).
If 10 sets of house sources are used totally, 6 behavior information is obtained, in a matrix U corresponding to the behavior information, 10 sets of house sources are corresponding to the house sources from the first row to the 10 th row, 6 house source attributes are corresponding to the house sources from the first column to the 6 th column, and the process sequentially comprises the following steps: searching information, clicking information, consulting times, forwarding information, saving information and page staying time information; then u is13Indicating the number of consultations with the first set of house resources.
The attribute information of the user browsing the house source may include any combination of the following information, but is not limited to the attribute information given below:
region information, price information, area information, house type information, orientation information, floor information, building age information, decoration information, elevator information, heating information, right information, type information, house source characteristic information.
The meaning of each house source attribute, and the specific quantification mode are given below:
such as the hai lake area of Beijing, the sunny area, etc.; in specific implementation, a type value is set for each region in advance to quantify region information, such as setting the hai lake region to be 2, setting the sun ward region to be 5, and the like;
the price information refers to the expected house selling price marked by the house source, such as 500 (ten thousand) and the like;
the area information refers to the actual area of the house source, such as 100 (square meters);
the house type information refers to actual house types of house sources, such as one-room-one-hall, two-room-one-hall, three-room-one-hall and the like, and in specific implementation, a type value is set for each house type in advance to quantify the house type information, such as one-room-one-hall setting 1, two-room-one-hall setting 2 and three-room-one-hall setting 3.
The orientation information refers to the orientation of the house source, such as the south direction, the southeast direction, the northwest direction, and the like, and in a specific implementation, an orientation value is set for each orientation in advance to quantify the orientation information, such as setting the south direction to 1, setting the northwest direction to 2, and the like.
The floor information refers to the floor where the house source is located, namely the specific number of floors;
the building age information refers to the construction period displayed by the house book of the house source, and the construction period of the house source can be converted from the current time, such as 1998 or 22 years.
The decoration information refers to decoration conditions of a house source, such as finish decoration, simplified decoration, blanks and the like, and during specific implementation, a device value can be set to quantify the decoration information, such as 11 for finish decoration, 12 for simplified decoration, 13 for blanks and the like;
the elevator information indicates whether an elevator exists in a room source, and specific numerical values are set for quantifying the elevator information according to the existence of the elevator, such as 1 and 2, and can also be 1 and 0;
the heating information indicates whether the room source has heating or not, and can be further subdivided, whether the heating is collective heating or self-heating, and the like; different values are set for different conditions, such as no heating is 1, collective heating is 2, self heating is 3, and the like;
the ownership information indicates whether the ownership of the house source exists or not, and whether the ownership information quantifies the ownership of the house source or not is determined by respectively setting different values;
the type information refers to ownership of the house source, such as public houses, commodity houses, business and residential dual-purpose houses, and different values are set respectively for quantification;
the house source characteristic information refers to information with characteristics of house sources, such as near subways, study rooms, VR house watching and the like, and different values are set respectively for quantification.
The attribute information of the house source browsed by the user can be represented by a matrix X, wherein rows in the matrix X represent house sources (each row represents a set of house sources), and columns represent attribute information (each column corresponds to one attribute information of the house source).
If there are 10 sets of house sources and 13 attribute information, in the matrix X of attribute information, the house sources correspond to 10 sets of house sources from the first row to the 10 th row, and correspond to 13 house source attributes from the first column to the 13 th column, which sequentially is: region information, price information, area information, house type information, orientation information, floor information, building age information, decoration information, elevator information, heating information, right information, type information and house source characteristic information; x is then13Representing the value of the 3 rd attribute information of the first set of house resources, if the area information is 100, x13Is 100.
And 102, calculating a weight vector of the house source in the house source browsed by the user according to the behavior information.
Obtaining the weight P of the kth set of house resourceskComprises the following steps:
wherein u iskjIs the value of the kth set of house resources on the jth behavior, unjThe value of the nth set of house resources on the jth behavior is shown, J is the number of behaviors of the user for browsing the house resources, N is the set number of the house resources, and k is more than or equal to 1 and less than or equal to N.
And combining the weights of the N sets of room sources into weight vectors of the N sets of room sources.
And 103, acquiring attribute information of the traded house source, and performing clustering calculation on the attribute information of the traded house source to acquire a clustering center.
During specific implementation, the attribute information of the house source which is traded and completed within preset time can be set and acquired, and the preset time can be set according to actual needs;
the attribute information of the house source which is traded is consistent with the number and the content of the acquired attribute information of the house source browsed by the user, that is, which attribute information of the house source which is traded is, which attribute information of the house source browsed by the user is acquired, and if the attribute information of the house source which is traded comprises region information, price information and area information, the information of the house source browsed by the user only comprises the region information, the price information and the area information.
The attribute information of the traded property sources can be represented by a matrix Y, the rows of the matrix Y representing the property sources (each row representing a set of property sources), and the columns representing the property of the property sources (each column representing a property of the property source).
The clustering algorithm used when clustering calculation is performed on the attribute information of the traded house source is not limited, for example, a DBSCAn clustering algorithm, an expectation-maximization (EM) clustering algorithm based on a Gaussian Mixture Model (GMM), a K-means clustering algorithm and the like can be used, preferably, the DBSCAn clustering algorithm is used, and the clustering algorithm does not need to input the number of clusters;
the cluster center is denoted as matrix a.
And step 104, determining the probability of the user becoming a potential user according to the attribute information of the house source browsed by the user, the weight vector and the clustering center.
Calculating the probability of the user becoming a potential user by the following formula:
wherein x isnRepresenting the attribute information corresponding to the nth set of house sources in the matrix X, wherein the matrix X is the matrix corresponding to the attribute information of the house sources browsed by the user, amM-th cluster center in the matrix A of cluster centers, d (x)n,am) Denotes amAnd xnThe similarity of (2); m is the number of clustering centers, and N is the number of house source sets; p is a radical ofnAnd Q is the probability of the user becoming a potential user, wherein the larger the probability value is, the larger the probability of becoming a potential user is.
In the calculation of amAnd xnThe similarity of (2) is not limited to specific similarity algorithms, such as cosine similarity algorithm, euclidean distance, hamming distance, and other similarity algorithms.
And 105, when the probability is greater than a preset threshold value, determining that the user is a potential user.
According to the embodiment of the application, the weight vector of the house source browsed by the user is determined by analyzing the behavior information of the house source browsed by the user, the attribute information of the house source which is traded is clustered, the probability that the user becomes a potential user is calculated according to the attribute information and the weight vector of the house source browsed by the user in history and the clustering center, and whether the user can become the potential user or not can be quantitatively determined. The scheme can improve the accuracy rate of potential user mining; and further, a house source recommendation strategy can be formulated according to the related requirements of the user, so that the conversion rate of potential users is improved.
Example two
Referring to fig. 2, fig. 2 is a schematic diagram of a potential user mining process in the second embodiment of the present application. The method comprises the following specific steps:
In the embodiment of the application, the behavior information and the attribute information of the house source browsed by the user can be automatically acquired from the system database;
the behavior information of the user browsing the house resources can comprise one or any combination of the following information:
searching information, clicking information, consulting times, forwarding information, saving information and page staying time information;
however, the specific implementation may not be limited to the above information.
The behavior information of the user browsing the house resources can be represented by a matrix U, rows of the matrix U represent the house resources (each row represents a set of house resources), and columns correspond to the behaviors (each column corresponds to one behavior).
The attribute information of the user browsing the house source may include any combination of the following information, but is not limited to the attribute information given below:
region information, price information, area information, house type information, orientation information, floor information, building age information, decoration information, elevator information, heating information, right information, type information, house source characteristic information.
The attribute information of the house source browsed by the user can be represented by a matrix X, wherein rows in the matrix X represent house sources (each row represents a set of house sources), and columns represent attribute information (each column corresponds to one attribute information of the house source).
Obtaining the weight P of the kth set of house resourceskComprises the following steps:
wherein u iskjIs the value of the kth set of house resources on the jth behavior, unjThe value of the nth set of house resources on the jth behavior is shown, J is the number of behaviors for browsing the house resources, N is the set number of the house resources, and k is more than or equal to 1 and less than or equal to N.
And combining the weights of the N sets of room sources into weight vectors of the N sets of room sources.
Performing normalization processing on the matrix X corresponding to the attribute information of the house source browsed by the user through the following formula, and recording the processed matrix as X':
wherein x isni' represents the value of the nth set of room sources on the ith attribute after normalization, xniThe value of the nth set of room sources on the ith attribute is represented,represents the mean value of the values of the N sets of room sources on the ith attribute, max (x)i) The maximum value of the ith room source attribute, min (x), of the N sets of room sourcesi) And the minimum value of the values of the N sets of house sources on the ith house source attribute is represented.
In the embodiment of the present application, the execution of step 203 may be performed after step 205, before step 204, or in parallel with step 204, or before step 202, which is not limited to this, as long as the execution is performed after step 201 and before step 206.
And step 204, acquiring the attribute information of the house source which is finished in transaction, and carrying out normalization processing.
During specific implementation, the attribute information of the house source which is traded and completed within preset time can be set and acquired, and the preset time can be set according to actual needs;
the attribute information of the house source which is finished by transaction is consistent with the number and the content of the acquired attribute information of the house source browsed by the user, namely, which attribute information is provided and which attribute information is provided.
The attribute information of the traded property sources can be represented by a matrix Y, the rows of the matrix Y representing the property sources (each row representing a set of property sources), and the columns representing the property of the property sources (each column representing a property of the property source).
Performing normalization processing on a matrix Y corresponding to the attribute information of the house source which is finished by trading according to the following formula, and recording the processed matrix as Y':
wherein, ywi' represents the value of the w set of room sources on the ith attribute after normalization, ywiThe value of the w set of room sources on the ith attribute is represented,represents the mean value of the values of the W sets of room sources on the ith attribute, max (x)i) The maximum value of the W set of house resources on the ith house resource attribute is represented, min (x)i) And the minimum value of the W sets of house resources on the ith house resource attribute is represented.
The clustering algorithm used when the matrix Y' corresponding to the attribute information of the house source which is subjected to the normalized transaction is subjected to clustering calculation is not limited, for example, a DBSCAn clustering algorithm, an Expectation Maximization (EM) clustering algorithm based on a Gaussian Mixture Model (GMM), a K-means clustering algorithm and the like can be used, the DBSCAn clustering algorithm is preferred, and the clustering algorithm does not need to input the number of clusters;
wherein, the cluster center is marked as a matrix A'.
And step 206, determining the probability of the user becoming a potential user according to the normalized attribute information of the house source browsed by the user, the weight vector and the clustering center.
Calculating the probability of the user becoming a potential user by the following formula:
wherein x isn' represents the attribute information corresponding to the nth set of house sources in the matrix X ', the matrix X ' is the matrix corresponding to the attribute information of the house sources browsed by the user after normalization, am'm-th cluster center in the matrix A' of cluster centers, d (x)n,am) Denotes am' and xn' similarity; m is the number of cluster centers, pnAnd Q is the probability of the user becoming a potential user, wherein the larger the probability value is, the larger the probability of becoming a potential user is.
In the calculation of am' and xnThe similarity of' is not limited to a specific similarity algorithm, such as a cosine similarity algorithm, a euclidean distance, a hamming distance, and other similarity algorithms.
And step 207, when the probability is greater than a preset threshold value, determining that the user is a potential user.
According to the embodiment of the application, the weight vector of the house source browsed by the user is determined by analyzing the behavior information of the house source browsed by the user, the attribute information of the house source browsed by the user and the attribute information of the house source traded and completed by trading are normalized, the normalized attribute information of the house source traded and completed by trading is clustered, the probability that the user becomes a potential user is calculated according to the normalized attribute information, weight vector and clustering center of the user browsing the house source historically, and whether the user can become a potential user can be quantitatively determined. The scheme can improve the accuracy rate of potential user mining; and further, a house source recommendation strategy can be formulated according to the related requirements of the user, so that the conversion rate of potential users is improved.
EXAMPLE III
Referring to fig. 3, fig. 3 is a schematic diagram of a potential user mining process in the third embodiment of the present application. The method comprises the following specific steps:
In the embodiment of the application, the behavior information and the attribute information of the house source browsed by the user can be automatically acquired from the system database;
the behavior information of the user browsing the house resources can comprise one or any combination of the following information:
searching information, clicking information, consulting times, forwarding information, saving information and page staying time information;
however, the specific implementation may not be limited to the above information.
The behavior information of the user browsing the house resources can be represented by a matrix U, rows of the matrix U represent the house resources (each row represents a set of house resources), and columns correspond to the behaviors (each column corresponds to one behavior).
The attribute information of the user browsing the house source may include any combination of the following information, but is not limited to the attribute information given below:
region information, price information, area information, house type information, orientation information, floor information, building age information, decoration information, elevator information, heating information, right information, type information, house source characteristic information.
The attribute information of the house source browsed by the user can be represented by a matrix X, wherein rows in the matrix X represent house sources (each row represents a set of house sources), and columns represent attribute information (each column corresponds to one attribute information of the house source).
Obtaining the weight P of the kth set of house resourceskComprises the following steps:
wherein u iskjIs the value of the kth set of house resources on the jth behavior, unjThe value of the nth set of house resources on the jth behavior is shown, J is the number of behaviors for browsing the house resources, N is the set number of the house resources, and k is more than or equal to 1 and less than or equal to N.
The weight vector is the weight vector corresponding to the weight of the N sets of room sources.
Performing normalization processing on the matrix X corresponding to the attribute information of the house source browsed by the user through the following formula, and recording the processed matrix as X':
wherein x isni' represents the value of the nth set of room sources on the ith attribute after normalization, xniThe value of the nth set of room sources on the ith attribute is represented,represents the mean value of the values of the N sets of room sources on the ith attribute, max (x)i) The maximum value of the ith room source attribute, min (x), of the N sets of room sourcesi) And the minimum value of the values of the N sets of house sources on the ith house source attribute is represented.
And 304, denoising the normalized attribute information of the user browsing house source.
And taking the matrix X' as a training sample, denoising attribute information of the house source browsed by the user by using a clustering algorithm, wherein a clustering result comprises clustered data and non-clustered data, and sample points of any cluster divided by the non-clustered data are recorded as noise.
And 305, acquiring the attribute information of the house source which is finished in transaction, and performing normalization processing.
During specific implementation, the attribute information of the house source which is traded and completed within preset time can be set and acquired, and the preset time can be set according to actual needs;
the attribute information of the house source which is finished by transaction is consistent with the number and the content of the acquired attribute information of the house source browsed by the user, namely, which attribute information is provided and which attribute information is provided.
The attribute information of the traded property sources can be represented by a matrix Y, the rows of the matrix Y representing the property sources (each row representing a set of property sources), and the columns representing the property of the property sources (each column representing a property of the property source).
Performing normalization processing on a matrix Y corresponding to the attribute information of the house source which is finished by trading according to the following formula, and recording the processed matrix as Y':
wherein, ywi' represents the value of the w set of room sources on the ith attribute after normalization, ywiThe value of the w set of room sources on the ith attribute is represented,represents the mean value of the values of the W sets of room sources on the ith attribute, max (x)i) The maximum value of the W set of house resources on the ith house resource attribute is represented, min (x)i) And the minimum value of the W sets of house resources on the ith house resource attribute is represented.
And step 306, performing clustering calculation on the attribute information of the house source after the normalization processing and after the transaction is completed, and acquiring a clustering center.
The clustering algorithm used when the matrix Y' corresponding to the attribute information of the house source which is subjected to the normalized transaction is subjected to clustering calculation is not limited, for example, a DBSCAn clustering algorithm, an Expectation Maximization (EM) clustering algorithm based on a Gaussian Mixture Model (GMM), a K-means clustering algorithm and the like can be used, the DBSCAn clustering algorithm is preferred, and the clustering algorithm does not need to input the number of clusters;
wherein, the cluster center is marked as a matrix A'.
Calculating the probability of the user becoming a potential user by the following formula:
wherein x isn' represents the attribute information corresponding to the nth set of house sources in the matrix X ', the matrix X ' is the matrix corresponding to the attribute information of the house sources browsed by the user after normalization, am'm-th cluster center in the matrix A' of cluster centers, d (x)n,am) Denotes am' and xn' similarity; m is the number of cluster centers, pnAnd Q is the probability of the user becoming a potential user, wherein the larger the probability value is, the larger the probability of becoming a potential user is.
In the calculation of am' and xnThe similarity of' is not limited to a specific similarity algorithm, such as a cosine similarity algorithm, a euclidean distance, a hamming distance, and other similarity algorithms.
And 308, when the probability is greater than a preset threshold value, determining that the user is a potential user.
According to the embodiment of the application, the weight vector of the house source browsed by the user is determined by analyzing the behavior information of the house source browsed by the user, the attribute information of the house source browsed by the user and the attribute information of the house source traded and finished are subjected to normalization processing and denoising processing, the normalized attribute information of the house source traded and finished is clustered, the probability that the user becomes a potential user is calculated according to the normalized attribute information and weight vector of the house source browsed by the user and the clustering center, and whether the user can become the potential user can be quantitatively determined. The scheme can improve the accuracy rate of potential user mining; and further, a house source recommendation strategy can be formulated according to the related requirements of the user, so that the conversion rate of potential users is improved.
Based on the same inventive concept, the embodiment of the application also provides a potential user excavating device. Referring to fig. 4, fig. 4 is a schematic structural diagram of an apparatus applied to the above technology in the embodiment of the present application. The device comprises: a first acquisition unit 401, a calculation unit 402, a second acquisition unit 403, a clustering unit 404, a first determination unit 405, and a second determination unit 406;
a first obtaining unit 401, configured to obtain behavior information and attribute information of a user browsing a house source;
a calculating unit 402, configured to calculate a weight vector of the house source in the house source browsed by the user according to the behavior information acquired by the first acquiring unit 401;
a second obtaining unit 403, configured to obtain attribute information of a house source that has completed a transaction;
a clustering unit 404, configured to perform clustering calculation on the attribute information of the traded house source acquired by the second acquiring unit 403, so as to acquire a clustering center;
a first determining unit 405, configured to determine, according to the attribute information of the user browsing the house source acquired by the first acquiring unit 401, the probability that the user becomes a potential user according to the weight vector calculated by the calculating unit 402 and the clustering center acquired by the clustering unit 404;
a second determining unit 406, configured to determine that the user is a potential user when the probability determined by the first unit is greater than a preset threshold.
Wherein,
a calculating unit 402, specifically configured to obtain the weight P of the kth set of room sourceskComprises the following steps:
combining the weights of the N sets of room sources into weight vectors of the N sets of room sources; wherein u iskjIs the value of the kth set of house resources on the jth behavior, unjThe value of the nth set of house resources on the jth behavior is shown, J is the number of behaviors of the user for browsing the house resources, N is the set number of the house resources, and k is more than or equal to 1 and less than or equal to N.
The first determining unit 405 is specifically configured to calculate the probability that the user becomes a potential user according to the following formula:where Q is the probability of a user becoming a potential user, xnRepresenting the attribute information corresponding to the nth set of house sources in the matrix X, wherein the matrix X is the matrix corresponding to the attribute information of the house sources browsed by the user, amThe m-th cluster center in the matrix A corresponding to the cluster center, d (x)n,am) Denotes amAnd xnThe similarity of (2); m is the number of clustering centers, and N is the number of house source sets; p is a radical ofnIs the weight of the nth set of house resources.
Wherein the apparatus further comprises: a normalization unit 407;
a normalizing unit 407, configured to perform normalization processing on the attribute information of the house source that has been traded and acquired by the second acquiring unit 403; normalizing the attribute information of the user browsed house source acquired by the first acquisition unit 401;
a clustering unit 404, configured to perform clustering calculation on the attribute information of the traded house source after the normalization processing by the normalization unit, so as to obtain a clustering center;
the first determining unit 405 is specifically configured to determine, according to the attribute information of the house source browsed by the user after normalization processing by the normalizing unit, the probability that the user becomes a potential user according to the weight vector and the clustering center.
Wherein the apparatus further comprises: a denoising unit 408;
the denoising unit 408 is configured to denoise the attribute information of the user browsing house source normalized by the normalization unit 407 by using a clustering algorithm;
the first determining unit 405 is specifically configured to determine, according to the attribute information of the user browsing the house source after the normalization processing by the denoising unit, the probability that the user becomes a potential user through the weight vector and the clustering center.
The units of the above embodiments may be integrated into one body, or may be separately deployed; may be combined into one unit or further divided into a plurality of sub-units.
In another embodiment, an electronic device is also provided, 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 potential user mining method when executing the program.
In another embodiment, a computer readable storage medium is also provided having stored thereon computer instructions that, when executed by a processor, may implement the steps in the potential user mining method.
Fig. 5 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention. As shown in fig. 5, the electronic device may include: a Processor (Processor)510, a communication Interface (Communications Interface)520, a Memory (Memory)530 and a communication bus 540, wherein the Processor 510, the communication Interface 520 and the Memory 530 communicate with each other via the communication bus 540. Processor 510 may call logic instructions in memory 530 to perform the following method:
acquiring behavior information and attribute information of a user browsing a house source;
calculating a weight vector of the house source in the house source browsed by the user according to the behavior information;
acquiring attribute information of the traded house source, and performing clustering calculation on the attribute information of the traded house source to acquire a clustering center;
determining the probability of the user becoming a potential user according to the attribute information of the house source browsed by the user, the weight vector and the clustering center;
and when the probability is larger than a preset threshold value, determining that the user is a potential user.
Furthermore, the logic instructions in the memory 530 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute 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), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (9)
1. A method for potential user mining, the method comprising:
acquiring behavior information and attribute information of a user browsing a house source;
calculating a weight vector of the house source in the house source browsed by the user according to the behavior information;
acquiring attribute information of the traded house source, and performing clustering calculation on the attribute information of the traded house source to acquire a clustering center;
determining the probability of the user becoming a potential user according to the attribute information of the house source browsed by the user, the weight vector and the clustering center;
when the probability is larger than a preset threshold value, determining that the user is a potential user;
wherein, the determining the probability of the user becoming a potential user according to the attribute information of the house source browsed by the user, the weight vector and the clustering center comprises:
calculating the probability of the user becoming a potential user by the following formula:
where Q is the probability of a user becoming a potential user, xnRepresenting the attribute information corresponding to the nth set of house sources in the matrix X, wherein the matrix X is the matrix corresponding to the attribute information of the house sources browsed by the user, amThe mth cluster center in the matrix A corresponding to the cluster center,d(xn,am) Denotes amAnd xnThe similarity of (2); m is the number of clustering centers, and N is the number of house source sets; p is a radical ofnIs the weight of the nth set of house resources.
2. The method of claim 1, wherein calculating a weight vector of the house resources in the user-browsed house resources according to the behavior information comprises:
obtaining the weight P of the kth set of house resourceskComprises the following steps:
combining the weights of the N sets of room sources into weight vectors of the N sets of room sources;
wherein u iskjIs the value of the kth set of house resources on the jth behavior, unjThe value of the nth set of house resources on the jth behavior is shown, J is the number of behaviors of the user for browsing the house resources, N is the set number of the house resources, and k is more than or equal to 1 and less than or equal to N.
3. The method of claim 1,
the acquiring attribute information of the traded house source, performing clustering calculation on the attribute information of the traded house source, and acquiring a clustering center includes:
acquiring attribute information of a house source which is finished in transaction;
normalizing the attribute information of the traded house source;
performing clustering calculation on the attribute information of the traded house source after normalization processing to obtain a clustering center;
determining the probability of the user becoming a potential user according to the attribute information of the house source browsed by the user, the weight vector and the clustering center, wherein the determining comprises the following steps:
normalizing the attribute information of the house source browsed by the user;
and determining the probability of the user becoming a potential user according to the attribute information of the house source browsed by the user after normalization processing, the weight vector and the clustering center.
4. The method of claim 3, wherein the determining the probability of the user becoming a potential user according to the normalized attribute information of the user browsing the house resources, the weight vector and the clustering center comprises:
denoising the normalized attribute information of the user browsed house source by using a clustering algorithm, and determining the probability of the user becoming a potential user according to the denoised attribute information of the user browsed house source, the weight vector and the clustering center.
5. A potential user mining device, the device comprising: the device comprises a first acquisition unit, a calculation unit, a second acquisition unit, a clustering unit, a first determination unit and a second determination unit;
the first acquisition unit is used for acquiring behavior information and attribute information of a user browsing a house source;
the calculating unit is used for calculating a weight vector of the house source in the house source browsed by the user according to the behavior information acquired by the first acquiring unit;
the second acquisition unit is used for acquiring attribute information of the house source which is finished in transaction;
the clustering unit is used for clustering and calculating the attribute information of the traded house source acquired by the second acquiring unit to acquire a clustering center;
the first determining unit is configured to determine, according to the attribute information of the user browsing the house source acquired by the first acquiring unit, the weight vector calculated by the calculating unit and the clustering center acquired by the clustering unit, a probability that the user becomes a potential user;
the second determining unit is used for determining that the user is a potential user when the probability determined by the first determining unit is greater than a preset threshold;
wherein,
the first determining unit is specifically configured to calculate a probability that the user becomes a potential user according to the following formula:
where Q is the probability of a user becoming a potential user, xnRepresenting the attribute information corresponding to the nth set of house sources in the matrix X, wherein the matrix X is the matrix corresponding to the attribute information of the house sources browsed by the user, amThe m-th cluster center in the matrix A corresponding to the cluster center, d (x)n,am) Denotes amAnd xnThe similarity of (2); m is the number of clustering centers, and N is the number of house source sets; p is a radical ofnIs the weight of the nth set of house resources.
6. The apparatus of claim 5, further comprising: a normalization unit;
the normalization unit is used for performing normalization processing on the attribute information of the house source which is acquired by the second acquisition unit and has been traded; normalizing the attribute information of the user browsed house source acquired by the first acquisition unit;
the clustering unit is specifically configured to perform clustering calculation on the attribute information of the traded house source after the normalization processing by the normalization unit to obtain a clustering center;
the first determining unit is specifically configured to determine, according to the attribute information of the house source browsed by the user after normalization processing by the normalizing unit, the probability that the user becomes a potential user according to the weight vector and the clustering center.
7. The apparatus of claim 6, further comprising: a denoising unit;
the denoising unit is used for denoising the attribute information of the user browsing house source normalized by the normalization unit by using a clustering algorithm;
the first determining unit is specifically configured to determine, according to the attribute information of the user browsing house source after normalization processing by the denoising unit, the probability that the user becomes a potential user according to the weight vector and the clustering center.
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 method according to any of claims 1-4 when executing the program.
9. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the method of any one of claims 1 to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010884687.5A CN112001760B (en) | 2020-08-28 | 2020-08-28 | Potential user mining method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010884687.5A CN112001760B (en) | 2020-08-28 | 2020-08-28 | Potential user mining method and device, electronic equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112001760A CN112001760A (en) | 2020-11-27 |
CN112001760B true CN112001760B (en) | 2021-10-12 |
Family
ID=73465975
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010884687.5A Active CN112001760B (en) | 2020-08-28 | 2020-08-28 | Potential user mining method and device, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112001760B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112561571A (en) * | 2020-12-07 | 2021-03-26 | 深圳市思为软件技术有限公司 | House purchasing intention evaluation method and related equipment |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110992124A (en) * | 2019-10-31 | 2020-04-10 | 贝壳技术有限公司 | House resource recommendation method and system |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106355449B (en) * | 2016-08-31 | 2021-09-07 | 腾讯科技(深圳)有限公司 | User selection method and device |
CN108288179B (en) * | 2018-01-25 | 2021-02-02 | 贝壳找房(北京)科技有限公司 | User preference house source calculation method and system |
CN108510321A (en) * | 2018-03-23 | 2018-09-07 | 北京焦点新干线信息技术有限公司 | A kind of construction method and device of house property user portrait |
US10972298B2 (en) * | 2018-08-21 | 2021-04-06 | International Business Machines Corporation | Proactively managing collisions of multiple clustering groups for collaborative messaging platforms |
CN109670113A (en) * | 2018-12-20 | 2019-04-23 | 重庆锐云科技有限公司 | A kind of source of houses recommended method, device and server |
CN110688553A (en) * | 2019-08-13 | 2020-01-14 | 平安科技(深圳)有限公司 | Information pushing method and device based on data analysis, computer equipment and storage medium |
-
2020
- 2020-08-28 CN CN202010884687.5A patent/CN112001760B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110992124A (en) * | 2019-10-31 | 2020-04-10 | 贝壳技术有限公司 | House resource recommendation method and system |
Also Published As
Publication number | Publication date |
---|---|
CN112001760A (en) | 2020-11-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Kim et al. | Improved churn prediction in telecommunication industry by analyzing a large network | |
CN110659318B (en) | Big data-based policy pushing method, system and computer equipment | |
CN108345587B (en) | Method and system for detecting authenticity of comments | |
CN110689457A (en) | Intelligent reception method for online clients in real estate industry, server and storage medium | |
CN108427708A (en) | Data processing method, device, storage medium and electronic device | |
CN109784848B (en) | Hotel order processing method and related product | |
CN111062444B (en) | Credit risk prediction method, credit risk prediction system, credit risk prediction terminal and storage medium | |
CN108804577B (en) | Method for estimating interest degree of information tag | |
CN111639988A (en) | Broker recommendation method, device, electronic equipment and storage medium | |
CN110458644A (en) | A kind of information processing method and relevant device | |
CN111754044A (en) | Employee behavior auditing method, device, equipment and readable storage medium | |
CN111428217A (en) | Method and device for identifying cheat group, electronic equipment and computer readable storage medium | |
CN112487284A (en) | Bank customer portrait generation method, equipment, storage medium and device | |
CN112348321A (en) | Risk user identification method and device and electronic equipment | |
CN112001760B (en) | Potential user mining method and device, electronic equipment and storage medium | |
CN117608650B (en) | Business flow chart generation method, processing device and storage medium | |
CN112053245B (en) | Information evaluation method and system | |
CN117253287B (en) | Action prediction model training method based on domain generalization, related method and product | |
CN108073567B (en) | Feature word extraction processing method, system and server | |
CN111225009A (en) | Method and apparatus for generating information | |
CN111476446A (en) | Service state monitoring processing method, device, equipment and storage medium | |
CN111400663B (en) | Model training method, device, equipment and computer readable storage medium | |
CN107609921A (en) | A kind of data processing method and server | |
CN112183946A (en) | Multimedia content evaluation method, device and training method thereof | |
CN116501979A (en) | Information recommendation method, information recommendation device, computer equipment and computer readable storage medium |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20210323 Address after: 100085 Floor 101 102-1, No. 35 Building, No. 2 Hospital, Xierqi West Road, Haidian District, Beijing Applicant after: Seashell Housing (Beijing) Technology Co.,Ltd. Address before: Unit 05, room 112, 1 / F, block C, comprehensive service area, Nangang Industrial Zone, Tianjin Economic and Technological Development Zone, 300280 Applicant before: BEIKE TECHNOLOGY Co.,Ltd. |
|
TA01 | Transfer of patent application right | ||
GR01 | Patent grant | ||
GR01 | Patent grant |