CN105095256A - Information push method and apparatus based on similarity degree between users - Google Patents
Information push method and apparatus based on similarity degree between users Download PDFInfo
- Publication number
- CN105095256A CN105095256A CN201410191101.1A CN201410191101A CN105095256A CN 105095256 A CN105095256 A CN 105095256A CN 201410191101 A CN201410191101 A CN 201410191101A CN 105095256 A CN105095256 A CN 105095256A
- Authority
- CN
- China
- Prior art keywords
- user
- business object
- similarity
- object set
- different
- 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.)
- Granted
Links
Abstract
The present invention provides an information push method and apparatus based on a similarity degree between users. The method comprises: obtaining historical operation information of a plurality of users, and performing clustering processing on service objects comprised in the historical operation information to obtain a service object set; according to information of user operation on the service object in the service object set, obtaining attention degrees of different users to different service object sets; calculating a similarity degree between users according to the attention degrees; receiving a login request of a current user, and obtaining attribute information of the current user ; obtaining a similar user corresponding to the current user according to the attribute information and the similarity degree between users; and recommending a corresponding service object to the current user according to the historical operation information of the similar user. The method and apparatus provided by the present invention can cover more similar users and provide more service object recommendation information for the user so that it is easier for the user to view a related service object according to service object recommendation information.
Description
Technical field
The present invention relates to Internet technical field, particularly relate to a kind of method and the device that carry out information pushing based on similarity between user.
Background technology
In Internet technology, website often needs to recommend various product information to user, and such as e-business network stands on webpage and recommends the interested product of user's possibility etc. to user.By the mode of this recommendation, shorten the path that user finds required product, promote Consumer's Experience.
In current Technologies of Recommendation System in E-Commerce, many employings come to user's recommended products information based on the Collaborative Filtering Recommendation Algorithm of user.This algorithm evaluates and tests the similarity between user by the scoring of analysis different user to same product, makes recommendation based on the similarity between user.When number of users be far longer than product number large, the way of recommendation based on this algorithm can produce good recommendation effect.But present e-commerce website such as Taobao, the number of users of not only access every day is very large, and product number is also very large, and user is very sparse to the behavior on product.The user not setting up direct relation is in a large number had every day to produce the behaviors such as click, collection, purchase on e-commerce website (such as Taobao), they have the features such as different ages, sex, region, also may not be familiar with mutually, but they likely have surprising similar with the purchasing habits of certain user wherein and Shopping Behaviors.In addition, although present product number is very large, a lot of product is had to be actually closely similar.
At present, the Collaborative Filtering Recommendation Algorithm based on user (userbase) comes to the mode of user's recommended products information, even if there are two users to have purchased two closely similar products, the similarity contribution of these two users is also zero.That is, these two users cannot set up similarity relationships.Thus, can find out, the similar users that traditional collaborative filtering based on user can cover is very limited, and the calculating of user's similarity is not accurate enough, thus, and cannot effectively to user's recommended products.
Summary of the invention
The present invention is intended to solve one of technical matters in correlation technique at least to a certain extent.
For this reason, first object of the present invention is to propose a kind of method of carrying out information pushing based on similarity between user, the method can cover more similar users, for user provides more business object recommendation information, user is facilitated to check relevant business object according to business object recommendation information.
Second object of the present invention is to propose a kind of device carrying out information pushing based on similarity between user.
For reaching above-mentioned purpose, first aspect present invention embodiment proposes a kind of method of carrying out information pushing based on similarity between user, comprise: the historical operation information obtaining multiple user, clustering processing is carried out to the business object comprised in described historical operation information, obtain business object set; According to the operation information of user to the business object in business object set, obtain different user to the attention rate of different business object set; According to the attention rate of described different user to different business object set, calculate the similarity between user; Receive the logging request of active user, and obtain the attribute information of described active user; According to the similarity between the attribute information of described active user and user, obtain the similar users that described active user is corresponding; And recommend corresponding business object according to the historical operation information of similar users corresponding to described active user to described active user.
The method of carrying out information pushing based on similarity between user of the embodiment of the present invention, obtain the historical operation information of multiple user, and obtain business object set according to historical operation information, different user is obtained to the attention rate of different business object set according to business object set, calculate the similarity between user, receive the logging request of active user, obtain the attribute information of active user, and obtain similar users corresponding to active user according to attribute information, and recommend corresponding business object according to the historical operation information of similar users to active user, thus, more similar users can be covered, for user provides more business object recommendation information, improve the precision of business object recommendation information, facilitate user and check relevant business object according to business object recommendation information.
For reaching above-mentioned purpose, second aspect present invention embodiment proposes a kind of device carrying out information pushing based on similarity between user, comprise: the first processing module, for obtaining the historical operation information of multiple user, clustering processing is carried out to the business object comprised in described historical operation information, obtains business object set; Second processing module, for according to the operation information of user to the business object in business object set, obtains different user to the attention rate of different business object set; And computing module, for according to the attention rate of described different user to different business object set, calculate the similarity between user; Receiver module, after calculating the similarity between user at described computing module, receives the logging request of active user, and obtains the attribute information of described active user; Obtain module, for according to the similarity between the attribute information of described active user and user, obtain the similar users that described active user is corresponding; And recommending module, recommend corresponding business object for the historical operation information according to similar users corresponding to described active user to described active user.
The device carrying out information pushing based on similarity between user of the embodiment of the present invention, the historical operation information of multiple user is obtained by the first processing module, clustering processing is carried out to the business object comprised in historical operation information, obtain business object set, and obtain different user to the attention rate of different business object set by the second processing module according to business object set, and according to different user, similarity between user is calculated to the attention rate of different business object set by computing module, the logging request of active user is received by receiver module, obtain the attribute information of active user, and obtain similar users corresponding to active user by acquisition module according to attribute information, and recommend corresponding business object according to the historical operation information of similar users to active user by recommending module, thus, more business object recommendation information can be provided for user, provide the precision of business object recommendation information, facilitate user and check relevant business object according to business object recommendation information, improve the experience of user.
Accompanying drawing explanation
The present invention above-mentioned and/or additional aspect and advantage will become obvious and easy understand from the following description of the accompanying drawings of embodiments, wherein,
Fig. 1 is the process flow diagram of the method for the similarity calculated according to an embodiment of the invention between user;
Fig. 2 is the process flow diagram of the method for the similarity calculated in accordance with another embodiment of the present invention between user;
Fig. 3 be according to the calculating user of another embodiment of the present invention between the process flow diagram of method of similarity;
Fig. 4 is the process flow diagram of the method for carrying out information pushing according to an embodiment of the invention based on similarity between user; And
Fig. 5 is the structural representation of the device carrying out information pushing according to an embodiment of the invention based on similarity between user.
Embodiment
Be described below in detail embodiments of the invention, the example of described embodiment is shown in the drawings, and wherein same or similar label represents same or similar element or has element that is identical or similar functions from start to finish.Be exemplary below by the embodiment be described with reference to the drawings, be intended to for explaining the present invention, and can not limitation of the present invention be interpreted as.
In describing the invention, it is to be appreciated that term " first ", " second " etc. are only for describing object, and instruction or hint relative importance can not be interpreted as.In describing the invention, it should be noted that, unless otherwise clearly defined and limited, term " is connected ", " connection " should be interpreted broadly, such as, can be fixedly connected with, also can be removably connect, or connect integratedly; Can be mechanical connection, also can be electrical connection; Can be directly be connected, also indirectly can be connected by intermediary.For the ordinary skill in the art, concrete condition above-mentioned term concrete meaning in the present invention can be understood.In addition, in describing the invention, except as otherwise noted, the implication of " multiple " is two or more.
Describe and can be understood in process flow diagram or in this any process otherwise described or method, represent and comprise one or more for realizing the module of the code of the executable instruction of the step of specific logical function or process, fragment or part, and the scope of the preferred embodiment of the present invention comprises other realization, wherein can not according to order that is shown or that discuss, comprise according to involved function by the mode while of basic or by contrary order, carry out n-back test, this should understand by embodiments of the invention person of ordinary skill in the field.
Below with reference to the accompanying drawings the method and the device that carry out information pushing based on similarity between user of the embodiment of the present invention are described.
Fig. 1 is the process flow diagram of the method obtaining similarity between user according to an embodiment of the invention.As shown in Figure 1, between this acquisition user, the method for similarity comprises:
S101, obtains the historical operation information of multiple user, carries out clustering processing to the business object comprised in historical operation information, obtains business object set.
Wherein, above-mentioned business object can include but not limited to merchandise news, content-data and social network information; Particularly, content-data can be audio-video frequency content, and social network information can be the user profile in social networks, the model etc. also can issued for user or pay close attention to.
Particularly, the historical operation information of multiple user in predetermined amount of time can be obtained, use dimension-reduction algorithm to carry out dimension-reduction treatment to the business object comprised in historical operation information, and according to each business object of the vector representation of default dimension; And use clustering algorithm to representing that the vector of business object carries out clustering processing, obtain business object set, i.e. business object bunch.
Wherein, historical operation information refers to that user after login, the information that operation service object produces.Such as, user is logging in the data message carrying out clicking, collect or buy commodity after e-commerce website and produce.Dimension-reduction algorithm can include but not limited to: word converts vector algorithm, probability latent semantic analysis (PLSA) algorithm and principal component analysis (PCA) (PCA) algorithm to, and clustering algorithm can include but not limited to: hard cluster (K-means) algorithm and spectral clustering.
Specifically, the historical operation information of multiple user in preset time period can be obtained, such as, obtain in preset time period multiple login user on e-commerce website click, buy, the data message of collecting commodities.Wherein, preset time period can be give tacit consent in system, and can also be that keeper is arranged in systems in which according to different demands, such as preset time period can be 30 days.Furthermore, can obtain be kept at each user in such as Hadoop computing platform (it is a kind of Distributed Computing Platform) in 30 days on e-commerce website such as Taobao the data message of the commodity such as click, purchase, collection.
After the historical operation information obtaining multiple user in predetermined amount of time, particularly, such as, Hadoop computing platform can be utilized, by each user in 30 days the commodity clicked condense together, and sort according to the sequence of time, and put in the same row, all behaviors of each user are put in the same row.In order to reduce the noise in some data, the data that also commodity amount that user clicked can be less than predetermined value (such as, predetermined value is 5) abandon.
Afterwards, by the data aggregate of above-mentioned generation in same file, then utilize such as word2vec to train this text.Wherein, word2vec (wordtovector) is one and converts based on word the instrument that vector algorithm develops to, can the vector operation be reduced to the process of content of text in vector space.Word2vec can by relation based on context, such as can according to user click commodity order dimensionality reduction is carried out to commodity, if the context of commodity is similar, so word2vec the vector of commodity of training out also can be similar.Word2vec training need two parameters, the size of training window and the dimension of implicit vector, in an embodiment of the present invention, the size of training window required for Word2vec can being trained and the dimension of implicit vector are set to 5 and 50 respectively.Should be appreciated that and also the dimension of the size of training window and implicit vector can be set to other values, this is not limited here.
Assuming that in data after such as word2vec training, each commodity all can represent with the floating number vector of 50 dimensions.Wherein, cosine (cosine) distance of vector can weigh the similarity of commodity, and the cosine larger expression of distance two commodity are more similar.Then, by such as hard cluster K-means algorithm, cluster is carried out to commodity, wherein, need in K-means algorithm to arrange clustering parameter K, specifically, in an embodiment of the present invention, in order to make to comprise 100 commodity in each class in K-means algorithm, clustering parameter K can be set to k=N/100, wherein, N is the sum of all commodity.
S102, according to the operation information of user to the business object in business object set, obtains different user to the attention rate of different business object set.
Wherein, business object set is the set of several identical business objects or similar business object.
Particularly, different user is determined the scoring of different business object set by obtaining different user the attention rate of different business object set.Specifically, if user clicks certain business object in a business object set, can be understood as the business object set that this user clicks this business object place, that is, this user has paid close attention to the business object set at this business object place.
Particularly, by score calculation formulae discovery different user to the scoring of different business object set.Wherein, score calculation formula is:
R (u, i) represents the scoring of user u to business object i, c
krepresent a kth business object set, R (u, k) represents the scoring of user u to a kth business object set.
S103, according to the attention rate of different user to different business object set, calculates the similarity between user.
Particularly, after acquisition different user is to the attention rate of different business object set, calculate the similarity between user by calculating formula of similarity, wherein, calculating formula of similarity is:
Sim (u, u') represents the similarity between user u and user u', and R (u', k) represents the scoring of user u' to a kth business object set, and K represents total number of business object set, and k is the positive integer being less than K.
By above-mentioned S101-103, can Similarity Measure between completing user.
The embodiment of the method for similarity between above-mentioned acquisition user, by obtaining the historical operation information of multiple user, clustering processing is carried out to the business object in historical operation information, obtain business object set, and obtain different user to the attention rate of different business object set according to business object set, and according to the attention rate of different user to different business object set, calculate the similarity between user, cover more similar users, can be more users and set up similarity relationships, improve the computational accuracy of similarity between user.
Fig. 2 is the process flow diagram of the method obtaining similarity between user in accordance with another embodiment of the present invention, and this embodiment take business object as video content for example is described, and as shown in Figure 2, between this acquisition user, the method for similarity comprises:
S201, obtains the historical operation information of multiple user, carries out clustering processing to the video content comprised in historical operation information, obtains video content set.
In this embodiment, the historical viewing information of multiple login user viewing video content in the schedule time can be obtained, the video content using the historical viewing information of dimension-reduction algorithm to multiple user to comprise carries out dimension-reduction treatment, and according to the video content that each user of the vector representation of default dimension watches; And use the vector of clustering algorithm to the video content representing each user viewing to carry out clustering processing, obtain video content set.
S202, according to the operation information of user to the video content in video content set, obtains different user to the attention rate of different video properties collection.
S203, according to the attention rate of different user to different video properties collection, calculates the similarity between user.
Such as, user 1 have viewed video 1, video 2 and video 3, user 2 have viewed video 1 and video 2, user 3 have viewed video 3, supposes that video 1, video 2 and video 3 are polymerized to a video set, then can according to the attention rate of user to video set, the quantity of the video namely watched in video set according to user calculates the similarity between user 1-user 3, thus, for user 2 and user 3 establish similarity relationships, improve the accuracy calculating similarity between user.
The embodiment of the method for similarity between above-mentioned acquisition user, according to the attention rate of different user to different video properties collection, calculate the similarity between user, two are made not have also can set up similarity relation between the user of viewed identical audio content, more similar users can be covered, can be more users and set up similarity relationships, improve the computational accuracy of similarity between user.
Fig. 3 is the process flow diagram of the method obtaining similarity between user in accordance with another embodiment of the present invention, and this embodiment is that the model example that user pays close attention to is described with business object, and as shown in Figure 3, between this acquisition user, the method for similarity comprises:
S301, obtains the historical operation information of multiple user, carries out clustering processing to the model comprised in historical operation information, obtains model set.
In this embodiment, the history concern information that multiple login user in the schedule time pays close attention to model can be obtained, the model using the history concern packets of information of dimension-reduction algorithm to multiple user to contain carries out dimension-reduction treatment, and according to the model that each user of the vector representation of default dimension pays close attention to; And use clustering algorithm to representing that the vector of the model that each user pays close attention to carries out clustering processing, obtain model set.
S302, according to the operation information of user to the model in model set, obtains different user to the attention rate of different model set.
S303, according to the attention rate of different user to different model set, calculates the similarity between user.
Such as, user 1 has paid close attention to model 1, model 2 and model 3, user 2 has paid close attention to model 1 and model 2, user 3 has paid close attention to model 3, suppose that model 1, model 2 and model 3 are polymerized to a model set, then can according to the attention rate of user to model set, the situation of the model namely paid close attention in model set according to user calculates the similarity between user 1-user 3, thus, the user 3 that can be the user 2 and concern model 3 paying close attention to model 1 and model 2 establishes similarity relationships, improves the accuracy calculating similarity between user.
The embodiment of the method for similarity between above-mentioned acquisition user, according to the attention rate of different user to different model set, calculate the similarity between user, two are made not have also can set up similarity relation between the user of viewed identical audio content, more similar users can be covered, can be more users and set up similarity relationships, improve the computational accuracy of similarity between user.
Fig. 4 is the process flow diagram of the method for carrying out information pushing according to an embodiment of the invention based on similarity between user.As shown in Figure 4, this method of carrying out information pushing based on similarity between user comprises:
S401, obtains the historical operation information of all users, carries out clustering processing to the business object comprised in historical operation information, obtains business object set.
S402, according to the operation information of user to the business object in business object set, obtains different user to the attention rate of different business object set.
S403, according to the attention rate of different user to different business object set, calculates the similarity between user.
Above-mentioned S401-S403 implementation procedure can be identical with S101-S103, also can be identical with S201-S203, and all right and S301-S303, does not repeat herein.
S404, receives the logging request of active user, and obtains the attribute information of active user.
Wherein, the attribute information of user can be the identification information identifying active user, and such as, the ID (Identity, identity code) of user also can be other information, such as, and the account, the pet name, password etc. of user.Specifically, when active user sends logging request, the identity information of active user can be obtained according to the log-on message such as logon account and password of active user's input.
S405, according to the similarity between the attribute information of active user and user, obtains the similar users that active user is corresponding.
After the attribute information obtaining active user, according to the order from high to low of the similarity with active user, predetermined quantity similar users can be obtained.Wherein, predetermined number can be give tacit consent in system, can also arrange according to different needs.Such as, predetermined number can be N, namely obtains the similar users of N before sequencing of similarity.
S406, the historical operation information according to similar users corresponding to active user recommends corresponding business object to active user.
After the N number of similar users of acquisition, commercial product recommending information can be obtained according to the attention rate of this N number of similar users to business object set.Particularly, in this embodiment, by Score on Prediction formulae discovery similar users to the scoring of different business object set, and obtain business object set recommendation information according to similar users to the scoring of different business object set, wherein, Score on Prediction formula is:
R'(u,k)=∑
v∈N(u)R(v,i)sim(u,v)
N (u) represents the predetermined quantity similar users of user u, namely the similar users predetermined quantity of user u is the similarity that N, sim (u, v) represent between user u and user v, R (v, i) represents the scoring of user v to i-th business object set.
Particularly, after acquisition similar users is to the scoring of different business object set, can according to scoring order sequence different business object set from high to low, and the business object set of M before rank is recommended active user as recommendation information, such as, can by before rank 20 business object set recommend active user, active user can check relevant Recommendations according to recommendation information, thus, shorten the path that user searches required commodity, improve the experience of user.
It should be noted that, the business object in this embodiment can be commodity.
Above-mentioned embodiment of the method for carrying out information pushing based on similarity between user, obtain the historical operation information of multiple user, and obtain business object set according to historical operation information, different user is obtained to the attention rate of different business object set according to business object set, calculate the similarity between user, receive the logging request of active user, obtain the attribute information of active user, and obtain similar users corresponding to active user according to attribute information, and recommend corresponding business object according to the historical operation information of similar users to active user, thus, more business object recommendation information can be provided for user, provide the precision of business object recommendation information, facilitate user and check relevant business object according to business object recommendation information.
In order to realize above-described embodiment, the present invention also proposes a kind of device carrying out information pushing based on similarity between user.
Fig. 5 is the structural representation of the device carrying out information pushing according to an embodiment of the invention based on similarity between user.
As shown in Figure 5, this device carrying out information pushing based on similarity between user comprises: the first processing module 51, second processing module 52 and computing module 53, receiver module 54, acquisition module 55 and recommending module 56, wherein:
First processing module 51, for obtaining the historical operation information of multiple user, carries out clustering processing to the business object comprised in above-mentioned historical operation information, obtains business object set; Second processing module 52, for according to the operation information of user to the business object in business object set, obtains different user to the attention rate of different business object set; Computing module 53, for according to the attention rate of above-mentioned different user to different business object set, calculates the similarity between user; Receiver module 54, for after calculating the similarity between user at above-mentioned computing module 53, receives the logging request of active user, and obtains the attribute information of above-mentioned active user; Obtain module 55 for according to the similarity between the attribute information of above-mentioned active user and user, obtain the similar users that above-mentioned active user is corresponding; And recommending module 56 recommends corresponding business object for the historical operation information according to similar users corresponding to above-mentioned active user to above-mentioned active user.
Wherein, above-mentioned business object can include but not limited to merchandise news, content-data and social network information; Particularly, content-data can be audio-video frequency content, and social network information can be the user profile in social networks, the model etc. also can issued for user or pay close attention to.
Above-mentioned first processing module 51 is specifically for the historical operation information that obtains multiple user in predetermined amount of time, dimension-reduction algorithm is used to carry out dimension-reduction treatment to the business object comprised in above-mentioned historical operation information, and according to each business object of the vector representation of default dimension; And use clustering algorithm to representing that the vector of business object carries out clustering processing.
Wherein, above-mentioned dimension-reduction algorithm can include but not limited to that word converts vector algorithm, PLSA algorithm and PCA algorithm to, and above-mentioned clustering algorithm comprises K-means algorithm and spectral clustering.
Above-mentioned second processing module 52 specifically for: obtain the scoring of above-mentioned different user to different business object set.Specifically, above-mentioned second processing module 52 by score calculation formulae discovery different user to the scoring of different business object set; Wherein, score calculation formula is:
R (u, i) represents the scoring of user u to product i, c
krepresent a kth business object set, R (u, k) represents the scoring of user u to a kth business object set.
Above-mentioned computing module 53 specifically for: calculate the similarity between user by calculating formula of similarity, wherein, above-mentioned calculating formula of similarity is:
Sim (u, u') represents the similarity between user u and user u', and R (u', k) represents the scoring of user u' to a kth business object set, and K represents total number of business object set, and k is the positive integer being less than K.
Wherein, the attribute information of above-mentioned user can be the identification information identifying active user, and such as, the ID (Identity, identity code) of user also can be other information, such as, and the account, the pet name, password etc. of user.
Specifically, when active user sends logging request, above-mentioned receiver module 54 can obtain the identity information of active user according to the log-on message such as logon account and password of active user's input.
Above-mentioned acquisition module 55 specifically for: according to the attribute information of above-mentioned active user, according to the order from high to low of the similarity with active user, obtain predetermined quantity similar users.
Above-mentioned recommending module 56 specifically for: by the above-mentioned similar users of Score on Prediction formulae discovery to the scoring of different business object set, according to above-mentioned similar users, business object set recommendation information is obtained to the scoring of different business object set, wherein, above-mentioned business object recommendation information comprises business object set recommendation information, and above-mentioned Score on Prediction formula is:
R'(u,k)=∑
v∈N(u)R(v,i)sim(u,v)
N (u) represents the predetermined quantity similar users of user u, and sim (u, v) represents the similarity between user u and user v, and R (v, i) represents the scoring of user v to i-th business object set.
Above-mentioned recommending module 56 is after acquisition similar users is to the scoring of different business object set, also can according to scoring order sequence different business object set from high to low, and the business object set of M before rank is recommended active user as recommendation information, such as, above-mentioned recommending module 56 can by before rank 20 business object set recommend active user, active user can check relevant recommendation business object according to recommendation information, shorten the path that user searches required business object, improve the experience of user.
Comprise the first processing module 51, second processing module 52, process that computing module 53, receiver module 54, the device carrying out information pushing based on similarity between user that obtains module 55 and recommending module 56 carry out business object recommendation see Fig. 4, can not repeat herein.
Above-mentioned device embodiment of carrying out information pushing based on similarity between user, the historical operation information of multiple user is obtained by the first processing module, clustering processing is carried out to the business object comprised in historical operation information, obtain business object set, and obtain different user to the attention rate of different business object set by the second processing module according to business object set, and according to different user, similarity between user is calculated to the attention rate of different business object set by computing module, the logging request of active user is received by receiver module, obtain the attribute information of active user, and obtain similar users corresponding to active user by acquisition module according to attribute information, and recommend corresponding business object according to the historical operation information of similar users to active user by recommending module, thus, more business object recommendation information can be provided for user, provide the precision of business object recommendation information, facilitate user and check relevant business object according to business object recommendation information, improve the experience of user.
Should be appreciated that each several part of the present invention can realize with hardware, software, firmware or their combination.In the above-described embodiment, multiple step or method can with to store in memory and the software performed by suitable instruction execution system or firmware realize.Such as, if realized with hardware, the same in another embodiment, can realize by any one in following technology well known in the art or their combination: the discrete logic with the logic gates for realizing logic function to data-signal, there is the special IC of suitable combinational logic gate circuit, programmable gate array (PGA), field programmable gate array (FPGA) etc.
In one typically configuration, computing equipment comprises one or more processor (CPU), input/output interface, network interface and internal memory.
Internal memory may comprise the volatile memory in computer-readable medium, and the forms such as random access memory (RAM) and/or Nonvolatile memory, as ROM (read-only memory) (ROM) or flash memory (flashRAM).Internal memory is the example of computer-readable medium.
Computer-readable medium comprises permanent and impermanency, removable and non-removable media can be stored to realize information by any method or technology.Information can be computer-readable instruction, data structure, the module of program or other data.The example of the storage medium of computing machine comprises, but be not limited to phase transition internal memory (PRAM), static RAM (SRAM), dynamic RAM (DRAM), the random access memory (RAM) of other types, ROM (read-only memory) (ROM), Electrically Erasable Read Only Memory (EEPROM), fast flash memory bank or other memory techniques, read-only optical disc ROM (read-only memory) (CD-ROM), digital versatile disc (DVD) or other optical memory, magnetic magnetic tape cassette, tape magnetic rigid disk stores or other magnetic storage apparatus or any other non-transmitting medium, can be used for storing the information can accessed by computing equipment.According to defining herein, computer-readable medium does not comprise temporary computer readable media (transitorymedia), as data-signal and the carrier wave of modulation.
Also it should be noted that, term " comprises ", " comprising " or its any other variant are intended to contain comprising of nonexcludability, thus make to comprise the process of a series of key element, method, commodity or equipment and not only comprise those key elements, but also comprise other key elements clearly do not listed, or also comprise by the intrinsic key element of this process, method, commodity or equipment.When not more restrictions, the key element limited by statement " comprising ... ", and be not precluded within process, method, commodity or the equipment comprising described key element and also there is other identical element.
It will be understood by those skilled in the art that the embodiment of the application can be provided as method, system or computer program.Therefore, the application can adopt the form of complete hardware embodiment, completely software implementation or the embodiment in conjunction with software and hardware aspect.And the application can adopt in one or more form wherein including the upper computer program implemented of computer-usable storage medium (including but not limited to magnetic disk memory, CD-ROM, optical memory etc.) of computer usable program code.
In the description of this instructions, specific features, structure, material or feature that the description of reference term " embodiment ", " some embodiments ", " example ", " concrete example " or " some examples " etc. means to describe in conjunction with this embodiment or example are contained at least one embodiment of the present invention or example.In this manual, identical embodiment or example are not necessarily referred to the schematic representation of above-mentioned term.And the specific features of description, structure, material or feature can combine in an appropriate manner in any one or more embodiment or example.
Although illustrate and describe embodiments of the invention, those having ordinary skill in the art will appreciate that: can carry out multiple change, amendment, replacement and modification to these embodiments when not departing from principle of the present invention and aim, scope of the present invention is by claim and equivalency thereof.
Claims (16)
1. carry out a method for information pushing based on similarity between user, it is characterized in that, comprising:
Obtain the historical operation information of multiple user, clustering processing is carried out to the business object comprised in described historical operation information, obtain business object set;
According to the operation information of user to the business object in business object set, obtain different user to the attention rate of different business object set;
According to the attention rate of described different user to different business object set, calculate the similarity between user;
Receive the logging request of active user, and obtain the attribute information of described active user;
According to the similarity between the attribute information of described active user and user, obtain the similar users that described active user is corresponding; And
Historical operation information according to similar users corresponding to described active user recommends corresponding business object to described active user.
2. method according to claim 1, is characterized in that, describedly comprises according to the attention rate of described different user to different business object set:
Obtain the scoring of described different user to different business object set.
3. method according to claim 2, is characterized in that, the scoring of described acquisition different user to different business object set comprises:
By score calculation formulae discovery different user to the scoring of different business object set; Wherein, described score calculation formula is:
R (u, i) represents the scoring of user u to business object i, c
krepresent a kth business object set, R (u, k) represents the scoring of user u to a kth business object set.
4. method according to claim 3, is characterized in that, described according to the attention rate of described different user to different business object set, calculates the similarity between user, comprising:
Calculate the similarity between user by calculating formula of similarity, wherein, described calculating formula of similarity is:
Sim (u, u') represents the similarity between user u and user u', and R (u', k) represents the scoring of user u' to a kth business object set, and K represents total number of business object set, and k is the positive integer being less than K.
5. method according to claim 1, is characterized in that, the historical operation information of the multiple user of described acquisition, carries out clustering processing, comprising the business object comprised in described historical operation information:
Obtain the historical operation information of multiple user in predetermined amount of time, use dimension-reduction algorithm to carry out dimension-reduction treatment to the business object comprised in described historical operation information, and according to each business object of the vector representation of default dimension; And
Use clustering algorithm to representing that the vector of business object carries out clustering processing.
6. method according to claim 5, it is characterized in that, described dimension-reduction algorithm comprises word and converts vector algorithm, probability latent semantic analysis PLSA algorithm and principal component analysis (PCA) PCA algorithm to, and described clustering algorithm comprises hard cluster K-means algorithm and spectral clustering.
7. method according to claim 1, is characterized in that, the similarity between the described attribute information according to described active user and user, obtains the similar users that described active user is corresponding, comprising:
According to the attribute information of described active user, according to the order from high to low of the similarity with active user, obtain predetermined quantity similar users.
8. method according to claim 7, is characterized in that, the historical operation information of the described similar users corresponding according to described active user recommends corresponding business object to described active user, comprising:
By similar users described in Score on Prediction formulae discovery to the scoring of different business object set, obtain business object set recommendation information according to described similar users to the scoring of different business object set, wherein, described Score on Prediction formula is:
R'(u,k)=∑
v∈N(u)R(v,i)sim(u,v)
N (u) represents the predetermined quantity similar users of user u, and sim (u, v) represents the similarity between user u and user v, and R (v, i) represents the scoring of user v to i-th business object set.
9. carry out a device for information pushing based on similarity between user, it is characterized in that, comprising:
First processing module, for obtaining the historical operation information of multiple user, carries out clustering processing to the business object comprised in described historical operation information, obtains business object set;
Second processing module, for according to the operation information of user to the business object in business object set, obtains different user to the attention rate of different business object set;
Computing module, for according to the attention rate of described different user to different business object set, calculates the similarity between user;
Receiver module, after calculating the similarity between user at described computing module, receives the logging request of active user, and obtains the attribute information of described active user;
Obtain module, for according to the similarity between the attribute information of described active user and user, obtain the similar users that described active user is corresponding; And
Recommending module, recommends corresponding business object for the historical operation information according to similar users corresponding to described active user to described active user.
10. device according to claim 9, is characterized in that, described second processing module, specifically for:
Obtain the scoring of described different user to different business object set.
11. devices according to claim 10, is characterized in that, described second processing module, specifically for:
By score calculation formulae discovery different user to the scoring of different business object set; Wherein, described score calculation formula is:
R (u, i) represents the scoring of user u to business object i, c
krepresent a kth business object set, R (u, k) represents the scoring of user u to a kth business object set.
12. devices according to claim 11, is characterized in that, described computing module, specifically for:
Calculate the similarity between user by calculating formula of similarity, wherein, described calculating formula of similarity is:
Sim (u, u') represents the similarity between user u and user u', and R (u', k) represents the scoring of user u' to a kth business object set, and K represents total number of business object set, and k is the positive integer being less than K.
13. devices according to claim 9, is characterized in that, described first processing module, specifically for:
Obtain the historical operation information of multiple user in predetermined amount of time, use dimension-reduction algorithm to carry out dimension-reduction treatment to the business object comprised in described historical operation information, and according to each business object of the vector representation of default dimension; And use clustering algorithm to representing that the vector of business object carries out clustering processing.
14. devices according to claim 13, it is characterized in that, described dimension-reduction algorithm comprises word and converts vector algorithm, probability latent semantic analysis PLSA algorithm and principal component analysis (PCA) PCA algorithm to, and described clustering algorithm comprises hard cluster K-means algorithm and spectral clustering.
15. devices according to claim 9, is characterized in that, described acquisition module, specifically for:
According to the attribute information of described active user, according to the order from high to low of the similarity with active user, obtain predetermined quantity similar users.
16. devices according to claim 15, is characterized in that, described recommending module, specifically for:
By similar users described in Score on Prediction formulae discovery to the scoring of different business object set, obtain business object set recommendation information according to described similar users to the scoring of different business object set, wherein, described Score on Prediction formula is:
R'(u,k)=∑
v∈N(u)R(v,i)sim(u,v)
N (u) represents the predetermined quantity similar users of user u, and sim (u, v) represents the similarity between user u and user v, and R (v, i) represents the scoring of user v to i-th business object set.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410191101.1A CN105095256B (en) | 2014-05-07 | 2014-05-07 | The method and device of information push is carried out based on similarity between user |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410191101.1A CN105095256B (en) | 2014-05-07 | 2014-05-07 | The method and device of information push is carried out based on similarity between user |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105095256A true CN105095256A (en) | 2015-11-25 |
CN105095256B CN105095256B (en) | 2019-06-11 |
Family
ID=54575710
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410191101.1A Active CN105095256B (en) | 2014-05-07 | 2014-05-07 | The method and device of information push is carried out based on similarity between user |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105095256B (en) |
Cited By (39)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105912708A (en) * | 2016-04-28 | 2016-08-31 | 南京信息工程大学 | Meso-and micro-scale meteorological product integration display platform and recommendation method thereof |
CN106604068A (en) * | 2016-12-30 | 2017-04-26 | 中广热点云科技有限公司 | Method and system for updating media program |
CN106815217A (en) * | 2015-11-30 | 2017-06-09 | 北京云莱坞文化传媒有限公司 | Story recommends method and story recommendation apparatus |
CN106909594A (en) * | 2016-06-06 | 2017-06-30 | 阿里巴巴集团控股有限公司 | Information-pushing method and device |
CN107194814A (en) * | 2016-03-15 | 2017-09-22 | 阿里巴巴集团控股有限公司 | The method and apparatus of recommended user |
CN107247786A (en) * | 2017-06-15 | 2017-10-13 | 北京小度信息科技有限公司 | Method, device and server for determining similar users |
CN107292646A (en) * | 2016-04-01 | 2017-10-24 | 中国移动通信集团河北有限公司 | A kind of method and apparatus of generation business |
CN107343036A (en) * | 2017-06-30 | 2017-11-10 | 广州优视网络科技有限公司 | Information-pushing method, device and server |
CN107730284A (en) * | 2016-08-10 | 2018-02-23 | 腾讯科技(深圳)有限公司 | A kind of information-pushing method and device |
CN107766446A (en) * | 2017-09-22 | 2018-03-06 | 北京网众共创科技有限公司 | Method for pushing, device, storage medium and the processor of information |
CN107798567A (en) * | 2017-11-21 | 2018-03-13 | 成都高德唯斯科技股份有限公司 | Brand message method for pushing, device and electronic equipment |
CN107818491A (en) * | 2017-09-30 | 2018-03-20 | 平安科技(深圳)有限公司 | Electronic installation, Products Show method and storage medium based on user's Internet data |
CN107885846A (en) * | 2017-11-10 | 2018-04-06 | 西安交通大学 | Recommend method in a kind of knowledge point excavated based on implicit attribute and implicit relationship |
CN108038647A (en) * | 2017-12-22 | 2018-05-15 | 江苏满运软件科技有限公司 | A kind of source of goods of arterial highway logistics recommends method |
CN108198058A (en) * | 2018-03-31 | 2018-06-22 | 丁超 | Method of Commodity Recommendation and device |
CN108241630A (en) * | 2016-12-23 | 2018-07-03 | 武汉四维图新科技有限公司 | Recommend method and device in a kind of driving destination |
CN108268584A (en) * | 2017-08-25 | 2018-07-10 | 广州市动景计算机科技有限公司 | Message push method, device and server |
CN108346067A (en) * | 2018-01-23 | 2018-07-31 | 中国科学技术大学苏州研究院 | Social networks advertisement sending method based on natural language processing |
CN108491527A (en) * | 2018-03-28 | 2018-09-04 | 百度在线网络技术(北京)有限公司 | Information recommendation method, device and electronic equipment |
CN108876644A (en) * | 2018-05-24 | 2018-11-23 | 微梦创科网络科技(中国)有限公司 | A kind of similar account calculation method and device based on social networks |
CN109087138A (en) * | 2018-07-26 | 2018-12-25 | 北京京东金融科技控股有限公司 | Data processing method and system, computer system and readable storage medium storing program for executing |
CN109345175A (en) * | 2018-10-10 | 2019-02-15 | 江苏满运软件科技有限公司 | Source of goods method for pushing, system, equipment and storage medium based on driver's matching degree |
CN109636479A (en) * | 2018-12-19 | 2019-04-16 | 武汉斗鱼鱼乐网络科技有限公司 | A kind of advertisement recommended method, device, electronic equipment and storage medium |
CN110223093A (en) * | 2018-03-02 | 2019-09-10 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus of commodity promotion |
CN110569446A (en) * | 2019-09-04 | 2019-12-13 | 第四范式(北京)技术有限公司 | Method and system for constructing recommended object candidate set |
CN110580259A (en) * | 2018-05-22 | 2019-12-17 | 上海大学 | Customer demand mining method and equipment based on process management big data |
CN111192161A (en) * | 2019-12-19 | 2020-05-22 | 广东电网有限责任公司电力调度控制中心 | Electric power market trading object recommendation method and device |
CN111327704A (en) * | 2020-02-28 | 2020-06-23 | 中国科学院计算机网络信息中心 | IPv6 user-based business object requirement mapping method |
CN111582905A (en) * | 2020-03-26 | 2020-08-25 | 口碑(上海)信息技术有限公司 | Target object acquisition method and device, electronic equipment and storage medium |
CN111694906A (en) * | 2019-03-14 | 2020-09-22 | 北京搜狗科技发展有限公司 | Method, device and equipment for displaying POI in map |
CN112434140A (en) * | 2020-11-10 | 2021-03-02 | 杭州博联智能科技股份有限公司 | Reply information processing method and system |
CN112667919A (en) * | 2020-12-28 | 2021-04-16 | 山东大学 | Personalized community correction scheme recommendation system based on text data and working method thereof |
CN112765230A (en) * | 2020-12-30 | 2021-05-07 | 陈非 | Payment big data analysis method and big data analysis system based on internet finance |
CN112785443A (en) * | 2021-01-25 | 2021-05-11 | 中国工商银行股份有限公司 | Financial product pushing method and device based on client group |
CN113139767A (en) * | 2020-01-20 | 2021-07-20 | 菜鸟智能物流控股有限公司 | Logistics object allocation method and device, electronic equipment and computer-readable storage medium |
CN113298587A (en) * | 2020-05-25 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Shop commodity information display method, electronic equipment and client |
CN113486249A (en) * | 2021-07-27 | 2021-10-08 | 中国银行股份有限公司 | Mobile banking business recommendation method and device |
TWI787196B (en) * | 2016-11-29 | 2022-12-21 | 香港商阿里巴巴集團服務有限公司 | Method, device and system for generating business object attribute identification |
CN115577167A (en) * | 2022-08-29 | 2023-01-06 | 建信金融科技有限责任公司 | WebAssemly-based content recommendation method, device, equipment and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102609523A (en) * | 2012-02-10 | 2012-07-25 | 上海视畅信息科技有限公司 | Collaborative filtering recommendation algorithm based on article sorting and user sorting |
CN102654860A (en) * | 2011-03-01 | 2012-09-05 | 北京彩云在线技术开发有限公司 | Personalized music recommendation method and system |
CN102780920A (en) * | 2011-07-05 | 2012-11-14 | 上海奂讯通信安装工程有限公司 | Television program recommending method and system |
CN103246672A (en) * | 2012-02-09 | 2013-08-14 | 中国科学技术大学 | Method and device for performing personalized recommendation on users |
CN103366009A (en) * | 2013-07-24 | 2013-10-23 | 杭州东信北邮信息技术有限公司 | Book recommendation method based on self-adaption clustering |
CN103678672A (en) * | 2013-12-25 | 2014-03-26 | 北京中兴通软件科技股份有限公司 | Method for recommending information |
-
2014
- 2014-05-07 CN CN201410191101.1A patent/CN105095256B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102654860A (en) * | 2011-03-01 | 2012-09-05 | 北京彩云在线技术开发有限公司 | Personalized music recommendation method and system |
CN102780920A (en) * | 2011-07-05 | 2012-11-14 | 上海奂讯通信安装工程有限公司 | Television program recommending method and system |
CN103246672A (en) * | 2012-02-09 | 2013-08-14 | 中国科学技术大学 | Method and device for performing personalized recommendation on users |
CN102609523A (en) * | 2012-02-10 | 2012-07-25 | 上海视畅信息科技有限公司 | Collaborative filtering recommendation algorithm based on article sorting and user sorting |
CN103366009A (en) * | 2013-07-24 | 2013-10-23 | 杭州东信北邮信息技术有限公司 | Book recommendation method based on self-adaption clustering |
CN103678672A (en) * | 2013-12-25 | 2014-03-26 | 北京中兴通软件科技股份有限公司 | Method for recommending information |
Cited By (52)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106815217A (en) * | 2015-11-30 | 2017-06-09 | 北京云莱坞文化传媒有限公司 | Story recommends method and story recommendation apparatus |
CN107194814A (en) * | 2016-03-15 | 2017-09-22 | 阿里巴巴集团控股有限公司 | The method and apparatus of recommended user |
CN107292646A (en) * | 2016-04-01 | 2017-10-24 | 中国移动通信集团河北有限公司 | A kind of method and apparatus of generation business |
CN105912708A (en) * | 2016-04-28 | 2016-08-31 | 南京信息工程大学 | Meso-and micro-scale meteorological product integration display platform and recommendation method thereof |
US11074623B2 (en) | 2016-06-06 | 2021-07-27 | Advanced New Technologies Co., Ltd. | Method and device for pushing information |
CN106909594A (en) * | 2016-06-06 | 2017-06-30 | 阿里巴巴集团控股有限公司 | Information-pushing method and device |
WO2017211191A1 (en) * | 2016-06-06 | 2017-12-14 | 阿里巴巴集团控股有限公司 | Method and device for pushing information |
CN106909594B (en) * | 2016-06-06 | 2020-05-05 | 阿里巴巴集团控股有限公司 | Information pushing method and device |
CN107730284A (en) * | 2016-08-10 | 2018-02-23 | 腾讯科技(深圳)有限公司 | A kind of information-pushing method and device |
TWI787196B (en) * | 2016-11-29 | 2022-12-21 | 香港商阿里巴巴集團服務有限公司 | Method, device and system for generating business object attribute identification |
CN108241630A (en) * | 2016-12-23 | 2018-07-03 | 武汉四维图新科技有限公司 | Recommend method and device in a kind of driving destination |
CN106604068A (en) * | 2016-12-30 | 2017-04-26 | 中广热点云科技有限公司 | Method and system for updating media program |
CN106604068B (en) * | 2016-12-30 | 2019-11-05 | 中广热点云科技有限公司 | A kind of method and its system of more new media program |
CN107247786A (en) * | 2017-06-15 | 2017-10-13 | 北京小度信息科技有限公司 | Method, device and server for determining similar users |
CN107343036A (en) * | 2017-06-30 | 2017-11-10 | 广州优视网络科技有限公司 | Information-pushing method, device and server |
CN108268584A (en) * | 2017-08-25 | 2018-07-10 | 广州市动景计算机科技有限公司 | Message push method, device and server |
CN107766446A (en) * | 2017-09-22 | 2018-03-06 | 北京网众共创科技有限公司 | Method for pushing, device, storage medium and the processor of information |
CN107818491A (en) * | 2017-09-30 | 2018-03-20 | 平安科技(深圳)有限公司 | Electronic installation, Products Show method and storage medium based on user's Internet data |
CN107885846A (en) * | 2017-11-10 | 2018-04-06 | 西安交通大学 | Recommend method in a kind of knowledge point excavated based on implicit attribute and implicit relationship |
CN107798567B (en) * | 2017-11-21 | 2023-06-20 | 成都高德唯斯科技股份有限公司 | Brand information pushing method and device and electronic equipment |
CN107798567A (en) * | 2017-11-21 | 2018-03-13 | 成都高德唯斯科技股份有限公司 | Brand message method for pushing, device and electronic equipment |
CN108038647A (en) * | 2017-12-22 | 2018-05-15 | 江苏满运软件科技有限公司 | A kind of source of goods of arterial highway logistics recommends method |
CN108346067A (en) * | 2018-01-23 | 2018-07-31 | 中国科学技术大学苏州研究院 | Social networks advertisement sending method based on natural language processing |
CN110223093B (en) * | 2018-03-02 | 2024-04-16 | 北京京东尚科信息技术有限公司 | Commodity recommendation method and device |
CN110223093A (en) * | 2018-03-02 | 2019-09-10 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus of commodity promotion |
CN108491527A (en) * | 2018-03-28 | 2018-09-04 | 百度在线网络技术(北京)有限公司 | Information recommendation method, device and electronic equipment |
CN108198058A (en) * | 2018-03-31 | 2018-06-22 | 丁超 | Method of Commodity Recommendation and device |
CN110580259A (en) * | 2018-05-22 | 2019-12-17 | 上海大学 | Customer demand mining method and equipment based on process management big data |
CN108876644B (en) * | 2018-05-24 | 2022-02-22 | 微梦创科网络科技(中国)有限公司 | Similar account calculation method and device based on social network |
CN108876644A (en) * | 2018-05-24 | 2018-11-23 | 微梦创科网络科技(中国)有限公司 | A kind of similar account calculation method and device based on social networks |
CN109087138A (en) * | 2018-07-26 | 2018-12-25 | 北京京东金融科技控股有限公司 | Data processing method and system, computer system and readable storage medium storing program for executing |
CN109345175B (en) * | 2018-10-10 | 2021-08-03 | 江苏满运软件科技有限公司 | Goods source pushing method, system, equipment and storage medium based on driver matching degree |
CN109345175A (en) * | 2018-10-10 | 2019-02-15 | 江苏满运软件科技有限公司 | Source of goods method for pushing, system, equipment and storage medium based on driver's matching degree |
CN109636479A (en) * | 2018-12-19 | 2019-04-16 | 武汉斗鱼鱼乐网络科技有限公司 | A kind of advertisement recommended method, device, electronic equipment and storage medium |
CN111694906A (en) * | 2019-03-14 | 2020-09-22 | 北京搜狗科技发展有限公司 | Method, device and equipment for displaying POI in map |
CN110569446B (en) * | 2019-09-04 | 2022-05-17 | 第四范式(北京)技术有限公司 | Method and system for constructing recommended object candidate set |
CN110569446A (en) * | 2019-09-04 | 2019-12-13 | 第四范式(北京)技术有限公司 | Method and system for constructing recommended object candidate set |
CN111192161A (en) * | 2019-12-19 | 2020-05-22 | 广东电网有限责任公司电力调度控制中心 | Electric power market trading object recommendation method and device |
CN113139767A (en) * | 2020-01-20 | 2021-07-20 | 菜鸟智能物流控股有限公司 | Logistics object allocation method and device, electronic equipment and computer-readable storage medium |
CN111327704A (en) * | 2020-02-28 | 2020-06-23 | 中国科学院计算机网络信息中心 | IPv6 user-based business object requirement mapping method |
CN111582905A (en) * | 2020-03-26 | 2020-08-25 | 口碑(上海)信息技术有限公司 | Target object acquisition method and device, electronic equipment and storage medium |
CN113298587A (en) * | 2020-05-25 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Shop commodity information display method, electronic equipment and client |
CN112434140B (en) * | 2020-11-10 | 2024-02-09 | 杭州博联智能科技股份有限公司 | Reply information processing method and system |
CN112434140A (en) * | 2020-11-10 | 2021-03-02 | 杭州博联智能科技股份有限公司 | Reply information processing method and system |
CN112667919A (en) * | 2020-12-28 | 2021-04-16 | 山东大学 | Personalized community correction scheme recommendation system based on text data and working method thereof |
CN112765230B (en) * | 2020-12-30 | 2021-09-21 | 深圳钱盒信息技术有限公司 | Payment big data analysis method and big data analysis system based on internet finance |
CN112765230A (en) * | 2020-12-30 | 2021-05-07 | 陈非 | Payment big data analysis method and big data analysis system based on internet finance |
CN112785443A (en) * | 2021-01-25 | 2021-05-11 | 中国工商银行股份有限公司 | Financial product pushing method and device based on client group |
CN113486249A (en) * | 2021-07-27 | 2021-10-08 | 中国银行股份有限公司 | Mobile banking business recommendation method and device |
CN113486249B (en) * | 2021-07-27 | 2024-02-27 | 中国银行股份有限公司 | Mobile banking business recommendation method and device |
CN115577167A (en) * | 2022-08-29 | 2023-01-06 | 建信金融科技有限责任公司 | WebAssemly-based content recommendation method, device, equipment and storage medium |
CN115577167B (en) * | 2022-08-29 | 2023-11-21 | 建信金融科技有限责任公司 | Webassembl-based content recommendation method, device, equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN105095256B (en) | 2019-06-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105095256A (en) | Information push method and apparatus based on similarity degree between users | |
US11861628B2 (en) | Method, system and computer readable medium for creating a profile of a user based on user behavior | |
US9858586B2 (en) | Methods and systems for creating rules for assigning attribution credit across a plurality of events | |
US8732015B1 (en) | Social media pricing engine | |
US10324960B1 (en) | Determining a number of unique viewers of a content item | |
US9589025B2 (en) | Correlated information recommendation | |
US8583471B1 (en) | Inferring household income for users of a social networking system | |
US8639575B2 (en) | Audience segment estimation | |
US20160188734A1 (en) | Method and apparatus for programmatically synthesizing multiple sources of data for providing a recommendation | |
US20160098735A1 (en) | Marketing channel attribution | |
US20170011420A1 (en) | Methods and apparatus to analyze and adjust age demographic information | |
US20160321711A1 (en) | Indicating unreliable reviews on a website | |
US11188678B2 (en) | Detection and prevention of privacy violation due to database release | |
Ballestar et al. | Social networks on cashback websites | |
CN103853789A (en) | Method and equipment used for recommending information to user | |
US11924487B2 (en) | Synthetic total audience ratings | |
CN104199843A (en) | Service sorting and recommending method and system based on social network interactive data | |
US20170076339A1 (en) | Method, Apparatus, Computer Program Product and System for Reputation Generation | |
US20190171955A1 (en) | System and method for inferring anonymized publishers | |
CN112862617A (en) | Data processing method, system, storage medium and electronic device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |