CN108121737A - A kind of generation method, the device and system of business object attribute-bit - Google Patents

A kind of generation method, the device and system of business object attribute-bit Download PDF

Info

Publication number
CN108121737A
CN108121737A CN201611079471.1A CN201611079471A CN108121737A CN 108121737 A CN108121737 A CN 108121737A CN 201611079471 A CN201611079471 A CN 201611079471A CN 108121737 A CN108121737 A CN 108121737A
Authority
CN
China
Prior art keywords
business object
attribute
cluster
bit
user
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
Application number
CN201611079471.1A
Other languages
Chinese (zh)
Other versions
CN108121737B (en
Inventor
郝智恒
李萍
张泽聪
沈晶晶
李江
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Alibaba Group Holding Ltd
Original Assignee
Alibaba Group Holding Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Alibaba Group Holding Ltd filed Critical Alibaba Group Holding Ltd
Priority to CN201611079471.1A priority Critical patent/CN108121737B/en
Priority to TW106127144A priority patent/TWI787196B/en
Priority to PCT/CN2017/111505 priority patent/WO2018099275A1/en
Publication of CN108121737A publication Critical patent/CN108121737A/en
Application granted granted Critical
Publication of CN108121737B publication Critical patent/CN108121737B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • 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
    • 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
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0255—Targeted advertisements based on user history
    • 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
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0269—Targeted advertisements based on user profile or attribute
    • G06Q30/0271—Personalized advertisement
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
    • G06F2216/03—Data mining

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

The embodiment of the present application provides a kind of generation method, the device and system of business object attribute-bit, the described method includes：The behavioural information of business object is directed to according to user, determines the degree of association between different business object；Business object cluster is generated according to the degree of association；Extract the user tag of the business object cluster；The attribute-bit of corresponding business object cluster is generated according to the user tag, the embodiment of the present application is by extracting business object the is contained and relevant information of user behavior in itself, these information are divided not by certain dimension of business object in itself, but the behavioural information of business object is directed to by user, automatic mining identifies, can effectively promote the precision of the identification to the attribute-bit of business object.

Description

A kind of generation method, the device and system of business object attribute-bit
Technical field
This application involves field of computer technology, more particularly to a kind of generation method of business object attribute-bit, one The generating means of kind of business object attribute-bit, it is a kind of for generating the terminal of business object attribute-bit, it is a kind of for generating The server of business object attribute-bit and a kind of generation system of business object attribute-bit.
Background technology
For the website of e-commerce class, each business object can all have some for embodying the category of self-characteristic Property, for example, the style of certain brand article, the targeted consumer group and the brand promote mainly market etc..
When business object reach the standard grade promote when, be typically based on these attributes to formulate the strategy of popularization.A kind of side Formula is to draw a circle to approve target user according to the attribute of business object, for example, attribute of the business object root according to the business object, delineation Target user is lives in a line city, age between 28-35 Sui, the women of certain nearest browsed commodity, then, by business Object recommendation gives above-mentioned drawn a circle to approve user.Another way be according to machine learning algorithm, it is right according to the attribute of business object User predicts the preference of the business object, then will click on or search for the business object or other similar to business object Probability is more than that user's circle of certain threshold value is elected as target user, is then oriented recommendation.
In above-mentioned first way, since business object side oneself being needed to judge the attribute of business object, so Circle selects target user afterwards, therefore is influenced be subject to the subjective factor of business object side, precisely can not select target user by geosphere.And the Two kinds of modes, it is fixed in algorithm object function (such as conversion ratio) due to the use of machine learning algorithm, and calculating Method Feature Engineering to be used for and the attribute extraction of business object it is limited in the case of, be easily trapped into Matthew effect, for example, For the business object newly reached the standard grade, there is no the data of too many user, and machine learning algorithm can not often find proper Target user.
The content of the invention
In view of the above problems, it is proposed that the embodiment of the present application overcomes the above problem or at least partly in order to provide one kind A kind of generation method of the business object attribute-bit to solve the above problems, a kind of generating means of business object attribute-bit, It is a kind of for generating the terminal of business object attribute-bit, it is a kind of for generating the server of business object attribute-bit and corresponding A kind of business object attribute-bit generation system.
To solve the above-mentioned problems, this application discloses a kind of generation system of business object attribute-bit, including：Acquisition Unit, display unit and server；
The collecting unit, acquisition user are directed to the behavioural information of business object, and the behavioural information is sent to clothes Business device；
The server is directed to the behavioural information of business object in the user for receiving the collecting unit transmission Afterwards, determine the degree of association between different business object, business object cluster is generated according to the degree of association；
The display unit extracts the user tag of the business object cluster from server, is marked according to the user Label generate the attribute-bit of corresponding business object cluster.
To solve the above-mentioned problems, disclosed herein as well is a kind of generation method of business object attribute-bit, including：
The behavioural information of business object is directed to according to user, determines the degree of association between different business object；
Business object cluster is generated according to the degree of association；
Extract the user tag of the business object cluster；
The attribute-bit of corresponding business object cluster is generated according to the user tag.
Optionally, the user obtains in the following way for the behavioural information of business object：
Selected initial service object cluster；
Extract the behavioural information that user in preset time range is directed to the initial service object cluster.
Optionally, the behavioural information that business object is directed to according to user, determines the association between different business object The step of spending includes：
The behavioural information of business object is directed to according to user, generates the vector expression of each business object；
Using the vector expression, the similarity and support between different business object are determined；
Using the similarity and support, the degree of association between the different business object is determined.
Optionally, it is described to use the similarity and support, determine the degree of association between the different business object Step includes：
The similarity and support are weighted, obtain the degree of association between different business object.
Optionally, the behavioural information include the first behavioural information and/or, the second behavioural information is described according to user's pin To the behavioural information of business object, the step of determining the similarity between different business object, further includes：
According to first behavioural information, first degree of association between different business object is determined；
According to second behavioural information, second degree of association between the different business object is determined；
First degree of association and second degree of association are weighted, obtain the association between the different business object Degree.
Optionally, described the step of generating business object cluster according to the degree of association, includes：
When the degree of association between different business object is more than the first predetermined threshold value, identify between the different business object With relationship by objective (RBO)；
According to the relationship by objective (RBO) between whole business objects, business object relation map is generated；
Using the business object relation map, the business object is divided into multiple business object clusters.
Optionally, the step of relationship by objective (RBO) according between whole business objects, generation business object relation map Including：
Different business object of the connection with the relationship by objective (RBO) respectively obtains business object relation map.
Optionally, it is described to use the business object relation map, the business object is divided into multiple business objects The step of cluster, includes：
To each business object label allocation in the business object relation map；
The label of each business object is transferred to connected business object；
In the label received from each business object, a label is chosen as the mark possessed according to the quantity of label Label；
Judge in the business object relation map, the label that each business object is possessed whether change or Whether person is currently less than default maximum iteration；
The step of label by each business object is transferred to connected business object is performed if so, returning；
If it is not, the business object for possessing same label is then divided into business object cluster.
Optionally, the business object relation map is used described, the business object is divided into multiple business pair After the step of cluster, further include：
The multiple business object cluster is verified.
Optionally, the multiple business object cluster is respectively provided with corresponding text message, described to the multiple business The step of object cluster is verified includes：
Extract the keyword in the text message of each business object cluster；
According to the keyword, the text similarity between any two business object cluster is determined；
Merge two business object clusters that the text similarity is more than the second predetermined threshold value.
Optionally, the step of user tag of the extraction business object cluster includes：
Obtain the user information of business object cluster；
Using the user information, the core customer in the business object cluster is identified；
Extract the user tag of the core customer.
Optionally, described the step of using the user information, identifying the core customer in the business object cluster, wraps It includes：
According to default dimension, the user in the business object cluster is ranked up；
Identify the core customer of default quantity.
Optionally, the step of attribute-bit for corresponding business object cluster being generated according to the user tag described Afterwards, further include：
Using the attribute-bit of the business object cluster, the target user of the business object cluster is determined；
Recommend target service object to the target user.
To solve the above-mentioned problems, disclosed herein as well is a kind of generation method of business object attribute-bit, including：
Receive the generation instruction of business object attribute-bit；
The generation instruction is committed to server；
The attribute-bit for the business object that the server is sent is received, wherein, the attribute mark of the business object Know and instructed by the server for the generation, marked by the user for extracting the business object cluster belonging to the business object Label obtain；
Show the attribute-bit of the business object.
To solve the above-mentioned problems, disclosed herein as well is a kind of generating means of business object attribute-bit, including：
Degree of association determining module, for according to user be directed to business object behavioural information, determine different business object it Between the degree of association；
Business object cluster generation module, for generating business object cluster according to the degree of association；
User tag extraction module, for extracting the user tag of the business object cluster；
Attribute-bit generation module, for generating the attribute mark of corresponding business object cluster according to the user tag Know.
Optionally, the user is directed to the behavioural information of business object by the way that following submodule is called to obtain：
Selected submodule, for selecting initial service object cluster；
Extracting sub-module, for extracting the behavior that user in preset time range is directed to the initial service object cluster Information.
Optionally, the degree of association determining module includes：
Vector expression generates submodule, for being directed to the behavioural information of business object according to user, generates each business The vector expression of object；
Similarity and support determination sub-module for using the vector expression, are determined between different business object Similarity and support；
Degree of association determination sub-module for using the similarity and support, is determined between the different business object The degree of association.
Optionally, the degree of association determination sub-module includes：
Similarity and support weighted units for being weighted to the similarity and support, obtain different business The degree of association between object.
Optionally, the behavioural information include the first behavioural information and/or, the second behavioural information, the degree of association determines Module further includes：
First degree of association determination sub-module, for according to first behavioural information, determining between different business object First degree of association；
Second degree of association determination sub-module, for according to second behavioural information, determine the different business object it Between second degree of association；
The degree of association weights submodule, for being weighted to first degree of association and second degree of association, described in acquisition not With the degree of association between business object.
Optionally, the business object cluster generation module includes：
Relationship by objective (RBO) identifies submodule, when being more than the first predetermined threshold value for the degree of association between different business object, Identify between the different business object that there is relationship by objective (RBO)；
Business object relation map generates submodule, for according to the relationship by objective (RBO) between whole business objects, generating industry Business object relationship collection of illustrative plates；
For using the business object relation map, the business object is drawn for business object assemblage classification submodule It is divided into multiple business object clusters.
Optionally, the business object relation map generation submodule includes：
Business object connection unit for connecting the different business object with the relationship by objective (RBO) respectively, obtains business Object relationship collection of illustrative plates.
Optionally, the business object assemblage classification submodule includes：
Label dispensing unit, for each business object label allocation in the business object relation map；
Label transfer unit, for the label of each business object to be transferred to connected business object；
Label chooses unit, for from the label that each business object receives, one to be chosen according to the quantity of label Label is as the label possessed；
Judging unit, for judging in the business object relation map, the label that each business object is possessed is It is no to change, alternatively, whether current be less than default maximum iteration；If so, call the label transfer unit；
Business object assemblage classification unit, for the business object for possessing same label to be divided into business object cluster.
Optionally, the business object cluster generation module further includes：
Business object cluster verifies submodule, for being verified to the multiple business object cluster.
Optionally, the multiple business object cluster is respectively provided with corresponding text message, the business object cluster school Testing submodule includes：
Keyword extracting unit, for extracting the keyword in the text message of each business object cluster；
Text similarity determination unit, for according to the keyword, determining between any two business object cluster Text similarity；
Business object cluster combining unit, for merging two business that the text similarity is more than the second predetermined threshold value Object cluster.
Optionally, the user tag extraction module includes：
User information acquisition submodule, for obtaining the user information of business object cluster；
Core customer identifies submodule, for using the user information, identifies the core in the business object cluster User；
User tag extracting sub-module, for extracting the user tag of the core customer.
Optionally, the core customer identifies that submodule includes：
Sequencing unit, for according to default dimension, being ranked up to the user in the business object cluster；
Recognition unit, for identifying the core customer of default quantity.
Optionally, described device further includes：
Target user's determining module, for using the attribute-bit of the business object cluster, determining the business object The target user of cluster；
Target service object recommendation module, for recommending target service object to the target user.
To solve the above-mentioned problems, disclosed herein as well is a kind of generating means of business object attribute-bit, including：
First receiving module, for receiving the generation of business object attribute-bit instruction；
Module is submitted, for the generation instruction to be committed to server；
Second receiving module, for receiving the attribute-bit for the business object that the server is sent, wherein, it is described The attribute-bit of business object is instructed by the server for the generation, by extracting the business belonging to the business object The user tag of object cluster obtains；
Display module, for showing the attribute-bit of the business object.
To solve the above-mentioned problems, disclosed herein as well is a kind of for generating the terminal of business object attribute-bit, bag It includes：
One or more than one processor；
Memory；And
One either more than one program one of them or more than one program storage is in memory, and through matching somebody with somebody It puts and includes to carry out following operate to perform the one or more programs by one or more than one processor Instruction：
Receive the generation instruction of business object attribute-bit；
The generation instruction is committed to server；
The attribute-bit for the business object that the server is sent is received, wherein, the attribute mark of the business object Know and instructed by the server for the generation, marked by the user for extracting the business object cluster belonging to the business object Label obtain；
Show the attribute-bit of the business object.
To solve the above-mentioned problems, disclosed herein as well is a kind of for generating the server of business object attribute-bit, Including：
One or more processors；
Memory；With
One or more modules, one or more of modules are stored in the memory and are configured to by described one A or multiple processors perform, wherein, one or more of modules have the function of as follows：
The behavioural information of business object is directed to according to user, determines the similarity between different business object；
Business object cluster is generated according to the similarity；
Extract the user tag of the business object cluster；
The attribute-bit of corresponding business object cluster is generated according to the user tag.
Compared with background technology, the embodiment of the present application includes advantages below：
The embodiment of the present application, can according to user be directed to business object behavioural information, determine different business object it Between the degree of association, and generate business object cluster according to the degree of association, then extract the user of the business object cluster Label, so as to generate the attribute-bit of corresponding business object cluster according to the user tag, the embodiment of the present application is led to It crosses and extracts business object the is contained and relevant information of user behavior in itself, for example, life style, Demand perference, style category Property etc., these information are divided not by certain dimension of business object in itself, but are directed to business pair by user The behavioural information of elephant, automatic mining identify, can effectively promote the precision of the identification to the attribute-bit of business object.
Secondly, by the attribute-bit of business object cluster in the embodiment of the present application, it may recognize that target user simultaneously Recommend target service object to target user, the efficiency of the identification to target user is further improved, so as to industry It is engaged in the extension process of object, is supplied to relevant information of the business object side more on business object, and can pass through and be The mode of systemization will enclose the user group of choosing for its definition automatically.In addition, the circle choosing side for the target user based on machine learning Method, the attribute-bit for the business object that the embodiment of the present application is generated can also be used as an effective benefit of Feature Engineering in itself It fills, the accuracy rate and recall rate of effective lift scheme.
3rd, when business object is the brand of commodity, the embodiment of the present application can be by determining the association between brand Degree, so as to which multiple brands to be divided into different brand groups, and then the attribute mark by identifying brand group according to the degree of association Know, generate different target user crowds, when brand side is when carrying out brand promotion, the information of relevant brand can be obtained, So as to looking for the user being most interested in this brand, brand master is contributed to quickly and conveniently to navigate to target user, improved pair The accuracy of the positioning of target user helps to realize the maximization of the benefit of brand promotion.
Description of the drawings
Fig. 1 is a kind of step flow chart of the generation method embodiment one of business object attribute-bit of the application；
Fig. 2 is a kind of schematic diagram of business object relation map of the application；
Fig. 3 is a kind of step flow chart of the generation method embodiment two of business object attribute-bit of the application；
Fig. 4 is a kind of generating principle figure of the attribute-bit of Brand of the application；
Fig. 5 is a kind of step flow chart of the generation method embodiment three of business object attribute-bit of the application；
Fig. 6 A-6D are a kind of structure diagrams of the generating means embodiment one of business object attribute-bit of the application；
Fig. 7 is a kind of structure diagram of the generating means embodiment two of business object attribute-bit of the application；
Fig. 8 is a kind of block diagram of the generation system embodiment of business object attribute-bit of the application.
Specific embodiment
It is below in conjunction with the accompanying drawings and specific real to enable the above-mentioned purpose of the application, feature and advantage more obvious understandable Mode is applied to be described in further detail the application.
With reference to Fig. 1, show the application a kind of business object attribute-bit generation method embodiment one the step of flow Cheng Tu specifically may include steps of：
Step 101, the behavioural information of business object is directed to according to user, determines the degree of association between different business object；
In general, can have different business objects in different business scopes, for example, in the field of communications, business Object can be communication data；In news media field, business object can be news data；In search field, business Object can be webpage；In e-commerce field, business object can be commodity or Brand, etc..The application is implemented Example is not construed as limiting the concrete type of business object.Further, user can also be because of for the behavioural information of business object Business scope it is different and different, for example, for news data class business object, the behavioural information of user can be user to certain The reading of news or search behavior, and for commodity or Brand class business object, the behavioural information of user can be then Buying behavior or navigation patterns to a certain commodity, etc..
It in the embodiment of the present application, can be according to the row after behavioural information of the user for business object is collected For information, the degree of association between different business object is calculated, the degree of association can be to the phase between different business object A kind of measurement that mutual relation is made.
In the concrete realization, the degree of association can be by the quantization to the relation between certain dimension, for example, can be with industry Similarity or support between business object is as the degree of association；Can also be the quantization to the relation between multiple dimensions, example Such as, the similarity between business object and support can be uniformly processed, so as to obtain the degree of association.Certainly, this field Technical staff can also determine the degree of association between business object in different ways according to actual needs, and the application is implemented Example is not construed as limiting this.
In the embodiment of the present application, can be by selected initial service object cluster, and extract in preset time range User obtains the behavioural information that user is directed to business object for the behavioural information of the initial service object cluster.
Specifically, can be divided according to specific business objective, the scope of initial service object selected first, for example, right In business object be commodity, if some business specialize in middle and high end brand, can only selected middle and high end brand scope commodity, such as Some business of fruit then only need to select the commodity of women's dress class just for women's dress.It is then possible to will in a certain period of time, user It is extracted for the behavioural information of the business object in the scope, obtains the behavioural information that user is directed to business object.
In the embodiment of the present application, the behavioural information of business object can be directed to according to user first, generates each business The vector expression of object.For example, the behavioural information of a certain number of users can be studied, it is possible to form a use Vector relations expression formula between family behavior and business object.Specifically, using 1000 users whether buy certain brand article as Example, if the 1st, the 3rd and the 6th user has purchased the commodity of the brand, and other users are without buying behavior, then The vector expression generated can be (1,0,1,0,0,1,0 ..., 0).
It is then possible to using the expression formula, the degree of association between business object is further calculated.Specifically, can adopt With the vector expression, the similarity and support between different business object are determined.
In the embodiment of the present application, the similarity can refer to cosine similarity, and the cosine similarity is also known as remaining String similitude can assess their similarity, you can in the hope of two by calculating the included angle cosine value between two vectors Angle between a vector, and draws the corresponding cosine value of angle, this cosine value can be used for characterizing between the two vectors Similitude.In general, the scope of cosine value is between [- 1,1], cosine value more levels off to 1, represents two vectorial directions and more becomes 0 is bordering on, their direction is also just more consistent, corresponding similarity also higher.And support then represents a kind of degree supported, Generally as a percentage.For example, in 1000 users, the user of certain brand article is had purchased as 400, it may be considered that User is 40% to the support of the brand article.
In the embodiment of the present application, cosine similarity between different business object can directly using business object to Expression formula is measured, is calculated according to the calculation formula of well known cosine similarity.For the support between business object, then may be used To extract specific support number from vector expression, using the actual support number of users to different business objects and always Support number of users between ratio determine.For example, to Mr. Yu brand article A and B, wherein supporting (for example, it may be purchase Behavior) brand article A number of users for 10, support the number of users of brand article B as 15, wherein, both propped up including 5 users Brand article A has been held, and has supported brand article B, then it is (10+15- that can determine the support between certain brand article A and B 5)/(10+15) * 100%=80%.
After similarity and support between calculating different business object, the similarity and support can be used Degree, determines the degree of association between the different business object.
In the concrete realization, can be respectively that similarity and support set different weights, then to the similarity It is weighted with support, obtains the degree of association between different business object.The embodiment of the present application is to the similarity and branch of setting The concrete numerical value size of the weight for degree of holding, is not construed as limiting.Certainly, those skilled in the art can also pass through according to actual needs Other modes calculate the degree of association between different business object, for example, can be by calculating the confidence level between business object Or the indexs such as promotion degree, the degree of association between different business object is then obtained, the embodiment of the present application is also not construed as limiting this.
As another example of the application, user can include for the behavioural information of business object it is a variety of, such as can To include the first behavioural information and the second behavioural information.By business object for exemplified by brand article, the first behavioural information can be Buying behavior of the user to certain brand, the second behavioural information can be that user adds shopping cart behavior to the brand, will the product The commodity of board are put into the shopping cart of e-commerce website, but a kind of behavior do not bought temporarily.
The first row is included for exemplified by information and the second behavioural information by user behavior information, definite different business object it Between the degree of association when, can determine first degree of association between different business object first according to first behavioural information, with And according to second behavioural information, determine second degree of association between the different business object；Then closed to described first Connection degree and second degree of association are weighted, and obtain the degree of association between the different business object.Certainly, the behavioural information of user Can also be information including the third line, fourth line is information and other further types of behavioural informations, the embodiment of the present application pair This is not construed as limiting.
Step 102, business object cluster is generated according to the degree of association；
It in the embodiment of the present application, can be according to the degree of association after degree of association between different business object is obtained respectively Difference, whole business objects is divided into multiple and different business objects and is calculated so that in each business object cluster Business object all has higher similitude.
In the concrete realization, a threshold value can be preset, the similitude between business object is distinguished, for example, can be with It is 80% to set the first predetermined threshold value, when the degree of association between different business object is more than the first predetermined threshold value, described in identification There is relationship by objective (RBO) between different business object, when the relationship by objective (RBO) can refer to that the degree of association is more than above-mentioned 80% threshold value, Two different business objects have higher similitude.Certainly, those skilled in the art can set according to actual needs The specific size of one predetermined threshold value, the embodiment of the present application are not construed as limiting this.
It is then possible to according to the relationship by objective (RBO) between whole business objects, business object relation map, the business are generated Object relationship collection of illustrative plates is the relational network figure formed according to the relation between business object.Specifically, can distinguish Different business object of the connection with the relationship by objective (RBO), obtains business object relation map.For example, for business object A, B, C, D, if business object A has above-mentioned relationship by objective (RBO) with C, D, business object B and D has above-mentioned relationship by objective (RBO), business object C Also there is above-mentioned relationship by objective (RBO) with D, then A and C, A and D, B and D, C can be connected two-by-two with D, so as to form a relational graph Spectrum.
Finally, the business object relation map may be employed, the business object is divided into multiple business object collection Group.
It is described to use the business object relation map in a preferred embodiment of the present application, by the business pair As the sub-step for being divided into multiple business object clusters may further include：
S11, to each business object label allocation in the business object relation map；
The label of each business object is transferred to connected business object by S12；
In the label received from each business object, a label is chosen as being possessed according to the quantity of label by S13 Label；
S14 judges in the business object relation map whether the label that each business object is possessed becomes Change, alternatively, whether current be less than default maximum iteration；
S15 performs the step that the label by each business object is transferred to connected business object if so, returning Suddenly；
S16, if it is not, the business object for possessing same label then is divided into business object cluster.
In the concrete realization, for convenience of calculating, the label for being business object configuration can be its ID, it is of course also possible to adopt Label allocation in other ways, such as random arrangement, as long as keeping the uniqueness of label, the embodiment of the present application does not limit this It is fixed.
In iteration for the first time, label can be randomly choosed, since the node of the core in business object relation map is ined succession Other many peripheral nodes, the probability that label is selected at random is larger, in subsequent iterative process, the node of core Number of labels can increase, and progressively reach stabilization.
When label is stable or reaches maximum iteration, the business object with similary label can be regarded as and belong to Same business object cluster, the label of node can be used as the identification label of the business object.
For example, as shown in Fig. 2, be a kind of schematic diagram of business object relation map of the application, it is referred to as with the name of node For the label of business object, i.e. node R, the label of S, T, U is respectively R, S, T, U, then it is as follows in the process of iteration：
After the 3rd wheel iteration, the label that business object is possessed all is R, is no longer changed, it is therefore contemplated that section The corresponding business objects of point R, S, T, U belong to identical cluster, can be divided in same business object cluster.
It is relatively simple to the description of business object relation map above, divide business as just the embodiment of the present application is introduced One example of object cluster, in actual use, the quantity of business object included in business object relation map can be with It is extremely huge.Certainly, those skilled in the art are also an option that other modes and draw business object relation map to realize It is divided into multiple and different business object clusters, for example, clustering procedure, community's partitioning algorithm etc., the embodiment of the present application does not make this It limits.
In the embodiment of the present application, after business object to be divided into multiple and different business object clusters, in order to determine Whether obtained division result is rationally and accurate, and the multiple business object cluster can also be verified.
In general, business object cluster can include corresponding text message, for example, using business object cluster as some phases As exemplified by brand, text message can be the advertising slogan of each business object (i.e. each brand) in the cluster, consumer Evaluation information, brand slogan, brand culture information etc..
In the concrete realization, the keyword in the text message of each business object cluster, Ran Houyi can be extracted first According to the keyword, the text similarity between any two business object cluster is determined.
For example, for text message " I loves Beijing Tian An-men ", after keyword extraction, can be " I ", " love ", " Beijing ", " Tian An-men ", the mode that many similar texts can be in this way become some crucial contaminations；It is and right In other text message " I loves the Yellow River ", through participle and keyword extraction after can be " I ", " love ", " the Yellow River ", then There are two keyword it is identical, three word differences between above two text message, then the similitude between them is exactly 2/5=0.4.
Certainly, above example is only to illustrate keyword extraction and the calculating process of text similarity, those skilled in the art Other modes can also be selected to carry out the item above process, the embodiment of the present application is not construed as limiting this.
In the embodiment of the present application, text similarity that can be between business object cluster sets a threshold value, such as can It, can be with after text similarity between obtaining any two business object cluster to set the second predetermined threshold value as 90% Merge two business object clusters that the text similarity is more than the second predetermined threshold value.
Step 103, the user tag of the business object cluster is extracted；
In the embodiment of the present application, after multiple business objects are divided into different business object clusters, can be directed to The business object cluster to be studied, further obtains the user information of the business object cluster, and the user information can be with It is come definite, for example, business can be identified first according to the user that each business object is possessed in business object cluster The user group of each business object in object cluster, then using the information of the user group of whole business objects as the business The user information of object cluster.
It is then possible to using the user information, the core customer in the business object cluster is identified.Specifically, may be used According to default dimension, to be ranked up to the user in the business object cluster, then identify the core of default quantity User.
For example, what if a certain business object cluster was made of multiple similar Brands, the business object collection Core customer in group is it may be considered that be a kind of user more to the commodity consumption of above-mentioned brand.It therefore, can be according to disappearing Take the amount of money this dimension, count spending amount of each user to whole brands in the business object cluster first, then It is ranked up according to the size of spending amount, spending amount is identified as core customer in preceding 20% user.Certainly, for not The business object of same type or business object cluster, the criterion of identification of core customer also can be different, and those skilled in the art can be with According to actual needs, setting identifies the concrete mode of core customer in business object cluster, and the embodiment of the present application does not limit this It is fixed.
In general, user can have the user tag of oneself, for example, age, job information, city of residence, consumption preferences etc. Deng.After the core customer in business object cluster is identified, the user tag of the core customer can be further extracted.
Step 104, the attribute-bit of corresponding business object cluster is generated according to the user tag.
It in the embodiment of the present application, can be using the user tag of core customer in business object cluster as the business object The attribute-bit of cluster.
In the embodiment of the present application, the behavioural information of business object can be directed to according to user, determines different business pair The degree of association as between, and business object cluster is generated according to the degree of association, then extract the business object cluster User tag, so as to generate the attribute-bit of corresponding business object cluster according to the user tag, the application is implemented Example is by extracting business object the is contained and relevant information of user behavior in itself, such as life style, Demand perference, wind Lattice attribute etc., these information are divided not by certain dimension of business object in itself, but are directed to industry by user The behavioural information of business object, automatic mining identifies, can effectively promote the essence of the identification to the attribute-bit of business object Accuracy.
In the embodiment of the present application, after the attribute-bit of business object cluster is generated, the business pair can also be used As the attribute-bit of cluster, the target user of the business object cluster is determined, and then recommend target industry to the target user Business object.
In general, the attribute-bit of the business object generated can have it is multiple, therefore, generation business object cluster category Property mark after, some or multiple attribute-bits therein may be employed, determine the target user of business object cluster, example Such as, for business object cluster attribute-bit for " male, 18-22 Sui, a tier 2 cities, consume level it is medium on the upper side ", can To choose two attribute-bits of " male, 18-22 " therein, so as to which the user with above-mentioned two attribute-bit be identified as Target user, and then recommend target service object to the target user.
In the concrete realization, target service object can be some business object in the business object cluster, also may be used Not to be the business object in the business object cluster, but there is higher similitude with the business object in the business object cluster Other business objects, the embodiment of the present application is not construed as limiting this.
In the embodiment of the present application, by the attribute-bit of business object cluster, may recognize that target user and to Target user recommends target service object, the efficiency of the identification to target user is further improved, so as to business In the extension process of object, relevant information of the business object side more on business object is supplied to, and system can be passed through The mode of change will enclose the user group of choosing for its definition automatically.In addition, the circle choosing side for the target user based on machine learning Method, the attribute-bit for the business object that the embodiment of the present application is generated can also be used as an effective benefit of Feature Engineering in itself It fills, the accuracy rate and recall rate of effective lift scheme.
In order to make it easy to understand, below by taking business object is the brand of commodity as an example, to the business object attribute mark of the application The generation method of knowledge makes a presentation.
With reference to Fig. 3, show the application a kind of business object attribute-bit generation method embodiment two the step of flow Cheng Tu specifically may include steps of：
Step 301, the behavioural information of business object is directed to according to user, determines the degree of association between different business object；
When business object is the brand of commodity, user is business of the user to the brand for the behavioural information of business object The buying behaviors of product, navigation patterns, search behavior and it is put into shopping cart etc..
As shown in figure 4, it is a kind of generating principle figure of the attribute-bit of Brand of the application.In Fig. 4, user Behavioural information includes buying behavior, navigation patterns and is put into shopping cart three classes.
In the concrete realization, the information that user buys the commodity of all kinds of brands can be directed to, is calculated between different brands The purchase degree of association；The information of the commodity of all kinds of brands is browsed for user, calculates the browsing degree of association between different brands； The commodity of all kinds of brands for user are put into the information of shopping cart, calculate between the different brands plus purchase degree of association.
In the concrete realization, exemplified by buying the degree of association, if in 1000 users, 500 users have purchased brand A Commodity, then can generate the vector expression A of buying behavior of the user to brand A；If there are 700 in 1000 users User has purchased the commodity of brand B, then can similarly generate the vector expression B, Ran Houke of buying behavior of the user to brand B To use vector expression A and vector expression B, the similarity between brand A and brand B is calculated.
Further, it is also possible to using vector expression A and vector expression B, the support between brand A and brand B is calculated Degree, confidence level and promotion degree etc., and then above-mentioned similarity, support, confidence level and promotion degree are weighted, from And obtain the purchase degree of association between brand A and brand B.Certainly, those skilled in the art can be specific to select according to actual needs Be weighted object is selected, for example, can be only using similarity result as the purchase degree of association or on the basis of similarity Upper increase support, be then weighted again, etc., the embodiment of the present application is not construed as limiting this.
Similarly, the browsing degree of association between brand A and brand B and the calculating process of the purchase degree of association and the purchase degree of association are added Calculating process is similar, and the embodiment of the present application repeats no more this.After above-mentioned three classes similarity is obtained, purchase can be closed respectively Connection degree browses the degree of association and the purchase degree of association is added to be weighted, so as to obtain the degree of association between brand A and brand B.
Step 302, business object cluster is generated according to the similarity；
In the embodiment of the present application, when business object is the brand of commodity, business object cluster is different brands Group.
It in the concrete realization, can be by the degree of association after the similarity of the whole brands of acquisition between any two is calculated respectively Two brands more than the first predetermined threshold value are attached, and generate Brand Relationship collection of illustrative plates, and then iteration hierarchical clustering may be employed Algorithm or other community find that algorithm divides the Brand Relationship collection of illustrative plates, obtain multiple brand groups, and make each brand Include multiple and different brands of reasonable quantity in group.For example, the different product for there are 6-8 or so in each brand group can be made Board.
Step 303, the multiple business object cluster is verified；
In the embodiment of the present application, after multiple brand groups are obtained, each brand group can also be verified, to determine It is whether rationally and effective according to the division to Brand Relationship collection of illustrative plates completed in step 302.
It in the concrete realization, can be according to the advertising slogan of each brand in brand group, consumer evaluation's information, brand mouth Number, brand culture information etc. generates the text message of the brand group, and then by extracting the keyword in text message, calculates Text similarity between brand group two-by-two.If text similarity is more than default second threshold, it may be considered that two Similitude between brand group is higher, can be with merging treatment.
Step 304, the user tag of the business object cluster is extracted；
In the embodiment of the present application, when extracting the user tag of brand group, the core of the brand group can be identified first Heart user, for example, core customer can be use of the spending amount preceding 20% for buying the commodity of each brand in the brand group Family.Then, user tag of the user tag of above-mentioned preceding 20% user as the brand group is extracted.
Step 305, the attribute-bit of corresponding business object cluster is generated according to the user tag；
After the label of core customer of each brand group is obtained, can corresponding product be generated according to the user tag The attribute-bit of board group.For example, for some brand group, attribute-bit can be " young, male, a tier 2 cities, middle height End consumption, movement is outdoor, fashion " etc..
Step 306, using the attribute-bit of the business object cluster, determine that the target of the business object cluster is used Family；
In the concrete realization, after the attribute-bit of each brand group is generated, so as to when carrying out brand promotion, root According to the actual demand of brand side, dispensing demand is such as oriented, can target user crowd's knot be generated according to the attribute-bit of brand group Fruit, for example, it may be " European style furniture crowd ", " smart home enthusiast crowd ", " light luxurious damp product intelligent crowd " is " high The mother and baby crowd of end ", then " good-for-nothing family " etc. therefrom selects oneself suitable target user crowd.
Step 307, target service object is recommended to the target user.
In the embodiment of the present application, when business object is Brand, target service object is specific a certain commodity Brand.Specifically, which can be a certain Brand in brand group or the commodity product in non-brand group Board, the embodiment of the present application are not construed as limiting this.So as to by the commercial product recommending of target brand to target user.
It in the embodiment of the present application, can be by determining the similarity between brand, so as to will be more according to the similarity A brand is divided into different brand groups, and then the attribute-bit by identifying brand group, generates different target user crowds, When brand side is when carrying out brand promotion, the information of relevant brand can be obtained, so as to look for what this brand was most interested in User contributes to brand master quickly and conveniently to navigate to target user, improves the accuracy of the positioning to target user, has Help realize the maximization of the benefit of brand promotion.
With reference to Fig. 5, show the application a kind of business object attribute-bit generation method embodiment three the step of flow Cheng Tu specifically may include steps of：
Step 501, the generation instruction of business object attribute-bit is received；
Step 502, the generation instruction is committed to server；
Step 503, the attribute-bit for the business object that the server is sent is received, wherein, the business object Attribute-bit by the server for it is described generation instruct, by extracting the business object cluster belonging to the business object User tag obtain；
Step 504, the attribute-bit of the business object is showed.
In the embodiment of the present application, when needing to generate the attribute-bit of business object, business pair can be sent to terminal As the generation instruction of attribute-bit, the generation instruction can be committed to service by terminal after above-mentioned generation instruction is received Device is obtained the attribute mark of the business object as server according to the user tag of the business object cluster belonging to business object Know, and then feed back to terminal, terminal, can be in terminal after the attribute-bit of the business object of server feedback is received User interface on show the attribute-bit.
By a kind of step 101 of process and method embodiment of the generation business object attribute-bit of server in this present embodiment Into step 104 and embodiment of the method two, step 301 is similar to step 305, can mutually refer to, the present embodiment to this not It repeats again.
It should be noted that for embodiment of the method, in order to be briefly described, therefore it is all expressed as to a series of action group It closes, but those skilled in the art should know, the embodiment of the present application and from the limitation of described sequence of movement, because according to According to the embodiment of the present application, some steps may be employed other orders or be carried out at the same time.Secondly, those skilled in the art also should Know, embodiment described in this description belongs to preferred embodiment, and involved action not necessarily the application is implemented Necessary to example.
Reference Fig. 6 A show a kind of structural frames of the generating means embodiment one of business object attribute-bit of the application One of figure, can specifically include following module：
Degree of association determining module 601 for being directed to the behavioural information of business object according to user, determines different business object Between the degree of association；
Business object cluster generation module 602, for generating business object cluster according to the degree of association；
User tag extraction module 603, for extracting the user tag of the business object cluster；
Attribute-bit generation module 604, for generating the attribute of corresponding business object cluster according to the user tag Mark.
Reference Fig. 6 B show a kind of structural frames of the generating means embodiment one of business object attribute-bit of the application The two of figure, the user can be by calling following submodule to obtain for the behavioural information of business object：
Selected submodule 6011, for selecting initial service object cluster；
Extracting sub-module 6012 is directed to the initial service object cluster for extracting user in preset time range Behavioural information.
In the embodiment of the present application, the degree of association determining module 601 can also include following submodule：
Vector expression generates submodule 6013, and for being directed to the behavioural information of business object according to user, generation is each The vector expression of business object；
Similarity and support determination sub-module 6014 for using the vector expression, determine different business object Between similarity and support；
Degree of association determination sub-module 6015 for using the similarity and support, determines the different business object Between the degree of association.
In the embodiment of the present application, the degree of association determination sub-module 6015 can specifically include such as lower unit：
Similarity and support weighted units for being weighted to the similarity and support, obtain different business The degree of association between object.
In the embodiment of the present application, the behavioural information can include the first behavioural information and/or, the second behavioural information, The degree of association determining module 601 can also include following submodule：
First degree of association determination sub-module 6016, for according to first behavioural information, determine different business object it Between first degree of association；
Second degree of association determination sub-module 6017, for according to second behavioural information, determining the different business pair Second degree of association as between；
The degree of association weights submodule 6018, for being weighted to first degree of association and second degree of association, obtains institute State the degree of association between different business object.
Reference Fig. 6 C show a kind of structural frames of the generating means embodiment one of business object attribute-bit of the application The three of figure, the business object cluster generation module 602 can specifically include following submodule：
Relationship by objective (RBO) identifies submodule 6021, is more than the first predetermined threshold value for the degree of association between different business object When, identify between the different business object that there is relationship by objective (RBO)；
Business object relation map generates submodule 6022, for according to the relationship by objective (RBO) between whole business objects, life Into business object relation map；
Business object assemblage classification submodule 6023, for using the business object relation map, by the business pair As being divided into multiple business object clusters.
In the embodiment of the present application, the business object relation map generation submodule 6022 can specifically include such as placing an order Member：
Business object connection unit for connecting the different business object with the relationship by objective (RBO) respectively, obtains business Object relationship collection of illustrative plates.
In the embodiment of the present application, the business object assemblage classification submodule 6023 can specifically include such as lower unit：
Label dispensing unit, for each business object label allocation in the business object relation map；
Label transfer unit, for the label of each business object to be transferred to connected business object；
Label chooses unit, for from the label that each business object receives, one to be chosen according to the quantity of label Label is as the label possessed；
Judging unit, for judging in the business object relation map, the label that each business object is possessed is It is no to change, alternatively, whether current be less than default maximum iteration；If so, call the label transfer unit；
Business object assemblage classification unit, for the business object for possessing same label to be divided into business object cluster.
In the embodiment of the present application, the business object cluster generation module 602 can also include following submodule：
Business object cluster verifies submodule 6024, for being verified to the multiple business object cluster.
In the embodiment of the present application, the multiple business object cluster can be respectively provided with corresponding text message, described Business object cluster verification submodule 6024 can specifically include such as lower unit：
Keyword extracting unit, for extracting the keyword in the text message of each business object cluster；
Text similarity determination unit, for according to the keyword, determining between any two business object cluster Text similarity；
Business object cluster combining unit, for merging two business that the text similarity is more than the second predetermined threshold value Object cluster.
Reference Fig. 6 D show a kind of structural frames of the generating means embodiment one of business object attribute-bit of the application The four of figure, the user tag extraction module 603 can specifically include following submodule：
User information acquisition submodule 6031, for obtaining the user information of business object cluster；
Core customer identifies submodule 6032, for using the user information, identifies in the business object cluster Core customer；
User tag extracting sub-module 6033, for extracting the user tag of the core customer.
In the embodiment of the present application, the core customer identifies that submodule 6032 can specifically include such as lower unit：
Sequencing unit, for according to default dimension, being ranked up to the user in the business object cluster；
Recognition unit, for identifying the core customer of default quantity.
In the embodiment of the present application, described device can also include following module：
Target user's determining module, for using the attribute-bit of the business object cluster, determining the business object The target user of cluster；
Target service object recommendation module, for recommending target service object to the target user.
Reference Fig. 7 shows a kind of structural frames of the generating means embodiment two of business object attribute-bit of the application Figure, can specifically include following module：
First receiving module 701, for receiving the generation of business object attribute-bit instruction；
Module 702 is submitted, for the generation instruction to be committed to server；
Second receiving module 703, for receiving the attribute-bit for the business object that the server is sent, wherein, The attribute-bit of the business object is instructed by the server for the generation, by extracting belonging to the business object The user tag of business object cluster obtains；
Display module 704, for showing the attribute-bit of the business object.
For device embodiment, since it is basicly similar to embodiment of the method, so description is fairly simple, it is related Part illustrates referring to the part of embodiment of the method.
Referring to Fig. 8, a kind of block diagram of the generation system of business object attribute-bit of the application, the system tool are shown Body can include：Collecting unit 801, server 802 and display unit 803；
The collecting unit 801, acquisition user are directed to the behavioural information of business object, and the behavioural information is sent to Server 802；
The server 802 is directed to the behavioural information of business object in the user for receiving the transmission of collecting unit 801 Afterwards, determine the degree of association between different business object, business object cluster is generated according to the degree of association；
The display unit 803 extracts the user tag of the business object cluster, according to described from server 802 User tag generates the attribute-bit of corresponding business object cluster.
The embodiment of the present application also discloses a kind of terminal for being used to generate business object attribute-bit, including：
One or more than one processor；
Memory；And
One either more than one program one of them or more than one program storage is in memory, and through matching somebody with somebody It puts and includes to carry out following operate to perform the one or more programs by one or more than one processor Instruction：
Receive the generation instruction of business object attribute-bit；
The generation instruction is committed to server；
The attribute-bit for the business object that the server is sent is received, wherein, the attribute mark of the business object Know and instructed by the server for the generation, marked by the user for extracting the business object cluster belonging to the business object Label obtain；
Show the attribute-bit of the business object.
The embodiment of the present application also discloses a kind of server for being used to generate business object attribute-bit, including：
One or more processors；
Memory；With
One or more modules, one or more of modules are stored in the memory and are configured to by described one A or multiple processors perform, wherein, one or more of modules have the function of as follows：
The behavioural information of business object is directed to according to user, determines the similarity between different business object；
Business object cluster is generated according to the similarity；
Extract the user tag of the business object cluster；
The attribute-bit of corresponding business object cluster is generated according to the user tag.
Each embodiment in this specification is described by the way of progressive, the highlights of each of the examples are with The difference of other embodiment, just to refer each other for identical similar part between each embodiment.
It should be understood by those skilled in the art that, the embodiment of the embodiment of the present application can be provided as method, apparatus or calculate Machine program product.Therefore, the embodiment of the present application can be used complete hardware embodiment, complete software embodiment or combine software and The form of the embodiment of hardware aspect.Moreover, the embodiment of the present application can be used one or more wherein include computer can With in the computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) of program code The form of the computer program product of implementation.
In a typical configuration, the computer equipment includes one or more processors (CPU), input/output Interface, network interface and memory.Memory may include the volatile memory in computer-readable medium, random access memory The forms such as device (RAM) and/or Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is to calculate The example of machine readable medium.Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be with Realize that information stores by any method or technique.Information can be computer-readable instruction, data structure, the module of program or Other data.The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM (SRAM), dynamic random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), fast flash memory bank or other memory techniques, read-only optical disc are read-only Memory (CD-ROM), digital versatile disc (DVD) or other optical storages, magnetic tape cassette, tape magnetic rigid disk storage or Other magnetic storage apparatus or any other non-transmission medium, the information that can be accessed by a computing device available for storage.According to Herein defines, and computer-readable medium does not include the computer readable media (transitory media) of non-standing, such as The data-signal and carrier wave of modulation.
The embodiment of the present application is with reference to according to the method for the embodiment of the present application, terminal device (system) and computer program The flowchart and/or the block diagram of product describes.It should be understood that it can realize flowchart and/or the block diagram by computer program instructions In each flow and/or block and flowchart and/or the block diagram in flow and/or box combination.These can be provided Computer program instructions are set to all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing terminals Standby processor is to generate a machine so that is held by the processor of computer or other programmable data processing terminal equipments Capable instruction generation is used to implement in one flow of flow chart or multiple flows and/or one box of block diagram or multiple boxes The device for the function of specifying.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing terminal equipments In the computer-readable memory to work in a specific way so that the instruction being stored in the computer-readable memory generates bag The manufacture of command device is included, which realizes in one flow of flow chart or multiple flows and/or one side of block diagram The function of being specified in frame or multiple boxes.
These computer program instructions can be also loaded into computer or other programmable data processing terminal equipments so that Series of operation steps is performed on computer or other programmable terminal equipments to generate computer implemented processing, thus The instruction offer performed on computer or other programmable terminal equipments is used to implement in one flow of flow chart or multiple flows And/or specified in one box of block diagram or multiple boxes function the step of.
Although the preferred embodiment of the embodiment of the present application has been described, those skilled in the art once know base This creative concept can then make these embodiments other change and modification.So appended claims are intended to be construed to Including preferred embodiment and fall into all change and modification of the embodiment of the present application scope.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation Between there are any actual relationship or orders.Moreover, term " comprising ", "comprising" or its any other variant meaning Covering non-exclusive inclusion, so that process, method, article or terminal device including a series of elements are not only wrapped Those elements are included, but also including other elements that are not explicitly listed or are further included as this process, method, article Or the element that terminal device is intrinsic.In the absence of more restrictions, it is wanted by what sentence "including a ..." limited Element, it is not excluded that also there are other identical elements in the process including the element, method, article or terminal device.
Generation method to a kind of business object attribute-bit provided herein, a kind of business object attribute mark above The generating means of knowledge, it is a kind of for generating the terminal of business object attribute-bit, it is a kind of for generating business object attribute-bit Server and a kind of generation system of business object attribute-bit, be described in detail, specific case used herein The principle and implementation of this application are described, and the explanation of above example is only intended to the sides that help understands the application Method and its core concept；Meanwhile for those of ordinary skill in the art, according to the thought of the application, in specific embodiment And there will be changes in application range, in conclusion this specification content should not be construed as the limitation to the application.

Claims (19)

1. a kind of generation system of business object attribute-bit, which is characterized in that including：Collecting unit, display unit and service Device；
The collecting unit, acquisition user are directed to the behavioural information of business object, and the behavioural information is sent to server；
The server, after behavioural information of the user of the collecting unit transmission for business object is received, really Determine the degree of association between different business object, business object cluster is generated according to the degree of association；
The display unit extracts the user tag of the business object cluster from server, is given birth to according to the user tag Into the attribute-bit of corresponding business object cluster.
2. a kind of generation method of business object attribute-bit, which is characterized in that including：
The behavioural information of business object is directed to according to user, determines the degree of association between different business object；
Business object cluster is generated according to the degree of association；
Extract the user tag of the business object cluster；
The attribute-bit of corresponding business object cluster is generated according to the user tag.
3. according to the method described in claim 2, it is characterized in that, the user passes through such as the behavioural information of business object Under type obtains：
Selected initial service object cluster；
Extract the behavioural information that user in preset time range is directed to the initial service object cluster.
4. according to the method described in claim 2, it is characterized in that, it is described according to user be directed to business object behavioural information, The step of determining the degree of association between different business object includes：
The behavioural information of business object is directed to according to user, generates the vector expression of each business object；
Using the vector expression, the similarity and support between different business object are determined；
Using the similarity and support, the degree of association between the different business object is determined.
5. according to the method described in claim 4, it is characterized in that, the use similarity and the support, determine described The step of degree of association between different business object, includes：
The similarity and support are weighted, obtain the degree of association between different business object.
6. according to any methods of claim 2-5, which is characterized in that the behavioural information includes the first behavioural information, And/or second behavioural information, the behavioural information that business object is directed to according to user, it determines between different business object The step of similarity, further includes：
According to first behavioural information, first degree of association between different business object is determined；
According to second behavioural information, second degree of association between the different business object is determined；
First degree of association and second degree of association are weighted, obtain the degree of association between the different business object.
7. according to the method described in claim 2, it is characterized in that, described generate business object cluster according to the degree of association Step includes：
When the degree of association between different business object is more than the first predetermined threshold value, identifying between the different business object has Relationship by objective (RBO)；
According to the relationship by objective (RBO) between whole business objects, business object relation map is generated；
Using the business object relation map, the business object is divided into multiple business object clusters.
8. the method according to the description of claim 7 is characterized in that the relationship by objective (RBO) according between whole business objects, The step of generating business object relation map includes：
Different business object of the connection with the relationship by objective (RBO) respectively obtains business object relation map.
9. according to the method described in claim 8, it is characterized in that, described use the business object relation map, by described in Business object, which is divided into the step of multiple business object clusters, to be included：
To each business object label allocation in the business object relation map；
The label of each business object is transferred to connected business object；
In the label received from each business object, a label is chosen as the label possessed according to the quantity of label；
Judge in the business object relation map, whether the label that each business object is possessed changes, alternatively, working as It is preceding whether to be less than default maximum iteration；
The step of label by each business object is transferred to connected business object is performed if so, returning；
If it is not, the business object for possessing same label is then divided into business object cluster.
10. according to any methods of claim 7-9, which is characterized in that use the business object relational graph described After the step of composing, the business object is divided into multiple business object clusters, further include：
The multiple business object cluster is verified.
11. according to the method described in claim 10, it is characterized in that, the multiple business object cluster be respectively provided with it is corresponding Text message, described the step of being verified to the multiple business object cluster, include：
Extract the keyword in the text message of each business object cluster；
According to the keyword, the text similarity between any two business object cluster is determined；
Merge two business object clusters that the text similarity is more than the second predetermined threshold value.
12. the according to the method described in claim 2, it is characterized in that, user tag of the extraction business object cluster The step of include：
Obtain the user information of business object cluster；
Using the user information, the core customer in the business object cluster is identified；
Extract the user tag of the core customer.
13. according to the method for claim 12, which is characterized in that it is described to use the user information, identify the business The step of core customer in object cluster, includes：
According to default dimension, the user in the business object cluster is ranked up；
Identify the core customer of default quantity.
14. according to the method described in claim 2, it is characterized in that, corresponding industry is generated according to the user tag described After the step of attribute-bit of business object cluster, further include：
Using the attribute-bit of the business object cluster, the target user of the business object cluster is determined；
Recommend target service object to the target user.
15. a kind of generation method of business object attribute-bit, which is characterized in that including：
Receive the generation instruction of business object attribute-bit；
The generation instruction is committed to server；
Receive the attribute-bit for the business object that the server is sent, wherein, the attribute-bit of the business object by The server is instructed for the generation, is obtained by the user tag for extracting the business object cluster belonging to the business object ；
Show the attribute-bit of the business object.
16. a kind of generating means of business object attribute-bit, which is characterized in that including：
Degree of association determining module for being directed to the behavioural information of business object according to user, is determined between different business object The degree of association；
Business object cluster generation module, for generating business object cluster according to the degree of association；
User tag extraction module, for extracting the user tag of the business object cluster；
Attribute-bit generation module, for generating the attribute-bit of corresponding business object cluster according to the user tag.
17. a kind of generating means of business object attribute-bit, which is characterized in that including：
First receiving module, for receiving the generation of business object attribute-bit instruction；
Module is submitted, for the generation instruction to be committed to server；
Second receiving module, for receiving the attribute-bit for the business object that the server is sent, wherein, the business The attribute-bit of object is instructed by the server for the generation, by extracting the business object belonging to the business object The user tag of cluster obtains；
Display module, for showing the attribute-bit of the business object.
18. a kind of terminal for being used to generate business object attribute-bit, which is characterized in that including：
One or more than one processor；
Memory；And
One either more than one program one of them or more than one program storage in memory, and be configured to The one or more programs are performed by one or more than one processor and include the finger operated below Order：
Receive the generation instruction of business object attribute-bit；
The generation instruction is committed to server；
Receive the attribute-bit for the business object that the server is sent, wherein, the attribute-bit of the business object by The server is instructed for the generation, is obtained by the user tag for extracting the business object cluster belonging to the business object ；
Show the attribute-bit of the business object.
19. a kind of server for being used to generate business object attribute-bit, which is characterized in that including：
One or more processors；
Memory；With
One or more modules, one or more of modules be stored in the memory and be configured to by one or Multiple processors perform, wherein, one or more of modules have the function of as follows：
The behavioural information of business object is directed to according to user, determines the similarity between different business object；
Business object cluster is generated according to the similarity；
Extract the user tag of the business object cluster；
The attribute-bit of corresponding business object cluster is generated according to the user tag.
CN201611079471.1A 2016-11-29 2016-11-29 Method, device and system for generating business object attribute identifier Active CN108121737B (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
CN201611079471.1A CN108121737B (en) 2016-11-29 2016-11-29 Method, device and system for generating business object attribute identifier
TW106127144A TWI787196B (en) 2016-11-29 2017-08-10 Method, device and system for generating business object attribute identification
PCT/CN2017/111505 WO2018099275A1 (en) 2016-11-29 2017-11-17 Method, apparatus, and system for generating business object attribute identifier

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611079471.1A CN108121737B (en) 2016-11-29 2016-11-29 Method, device and system for generating business object attribute identifier

Publications (2)

Publication Number Publication Date
CN108121737A true CN108121737A (en) 2018-06-05
CN108121737B CN108121737B (en) 2022-04-26

Family

ID=62227071

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611079471.1A Active CN108121737B (en) 2016-11-29 2016-11-29 Method, device and system for generating business object attribute identifier

Country Status (3)

Country Link
CN (1) CN108121737B (en)
TW (1) TWI787196B (en)
WO (1) WO2018099275A1 (en)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109062955A (en) * 2018-06-25 2018-12-21 广东神马搜索科技有限公司 Incidence relation method for digging, device, calculating equipment and storage medium between project
CN110852778A (en) * 2019-09-30 2020-02-28 口口相传(北京)网络技术有限公司 Data processing method and device for business object
CN111292154A (en) * 2018-12-10 2020-06-16 阿里巴巴集团控股有限公司 Information obtaining method and device
CN111522606A (en) * 2020-04-26 2020-08-11 广东优特云科技有限公司 Data processing method, device, equipment and storage medium
CN111598541A (en) * 2020-05-14 2020-08-28 深圳易伙科技有限责任公司 Enterprise business reporting method, device, equipment and storage medium
CN111611504A (en) * 2019-02-26 2020-09-01 深圳云天励飞技术有限公司 Processing method, device, equipment and system
CN112445916A (en) * 2019-08-28 2021-03-05 阿里巴巴集团控股有限公司 Business object issuing method, entity issuing method and device
CN112632405A (en) * 2020-12-31 2021-04-09 数字广东网络建设有限公司 Recommendation method, device, equipment and storage medium
US20210358042A1 (en) * 2020-05-13 2021-11-18 Hunan Fumi Information Technology Co., Ltd. Stock recommendation method based on item attribute identification and the system thereof
CN114143165A (en) * 2020-08-14 2022-03-04 北京达佳互联信息技术有限公司 Service alarm method, device, server, storage medium and program product
CN114418012A (en) * 2022-01-21 2022-04-29 建信金融科技有限责任公司 Object association relation determining method, device and equipment and computer storage medium

Families Citing this family (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109447674A (en) * 2018-09-03 2019-03-08 中国平安人寿保险股份有限公司 Electronic device, insurance agent target service area determine method and storage medium
CN109670848A (en) * 2018-09-11 2019-04-23 深圳平安财富宝投资咨询有限公司 Customer segmentation method, user equipment, storage medium and device based on big data
CN109670852A (en) * 2018-09-26 2019-04-23 平安普惠企业管理有限公司 User classification method, device, terminal and storage medium
CN111291019B (en) * 2018-12-07 2023-09-29 中国移动通信集团陕西有限公司 Similarity discrimination method and device for data model
CN111382343B (en) * 2018-12-27 2023-11-28 方正国际软件(北京)有限公司 Label system generation method and device
CN110032878B (en) * 2019-03-04 2021-11-02 创新先进技术有限公司 Safety feature engineering method and device
CN112100391B (en) * 2019-05-31 2023-06-13 阿里巴巴集团控股有限公司 User intention recognition method, device, service end, client and terminal equipment
CN110188357B (en) * 2019-05-31 2023-06-20 创新先进技术有限公司 Industry identification method and device for objects
CN112307213B (en) * 2019-07-26 2024-08-23 第四范式（北京）技术有限公司 Method and system for predicting state of target entity
CN110737834B (en) * 2019-10-14 2024-04-02 腾讯科技（深圳）有限公司 Recommendation method and device for business objects, storage medium and computer equipment
CN112749292B (en) * 2019-10-31 2024-05-03 深圳云天励飞技术有限公司 User tag generation method and device, computer device and storage medium
CN111309614B (en) * 2020-02-17 2022-10-18 支付宝(杭州)信息技术有限公司 A/B test method and device and electronic equipment
CN111353779B (en) * 2020-02-25 2023-05-16 中国银联股份有限公司 Determination method, device, equipment and storage medium of abnormal service provider
CN111880989B (en) * 2020-07-14 2024-05-17 中国银联股份有限公司 Configuration item management method and device
CN112632143A (en) * 2020-12-30 2021-04-09 中国农业银行股份有限公司 Data label generation method and device
CN112613917B (en) * 2020-12-30 2024-09-06 平安壹钱包电子商务有限公司 Information pushing method, device, equipment and storage medium based on user portrait
CN113220838B (en) * 2021-05-12 2024-09-17 北京百度网讯科技有限公司 Method, device, electronic equipment and storage medium for determining key information
CN115169850B (en) * 2022-06-28 2024-08-02 飞鸟鱼信息科技有限公司 Method and device for determining resource attribute
CN116308683B (en) * 2023-05-17 2023-08-04 武汉纺织大学 Knowledge-graph-based clothing brand positioning recommendation method, equipment and storage medium
CN116431319B (en) * 2023-06-14 2023-09-12 云阵(杭州)互联网技术有限公司 Task processing method and device

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102456203A (en) * 2010-10-22 2012-05-16 阿里巴巴集团控股有限公司 Method for determining candidate product linked list as well as related device
US8489596B1 (en) * 2013-01-04 2013-07-16 PlaceIQ, Inc. Apparatus and method for profiling users
CN103577549A (en) * 2013-10-16 2014-02-12 复旦大学 Crowd portrayal system and method based on microblog label
CN104025130A (en) * 2011-02-22 2014-09-03 汤姆森路透社全球资源公司 Association Significance
CN104077337A (en) * 2013-05-20 2014-10-01 腾讯科技（深圳）有限公司 Searching method and device
CN104199849A (en) * 2014-08-08 2014-12-10 亿赞普(北京)科技有限公司 Advertisement injecting method and device
CN104252679A (en) * 2013-06-30 2014-12-31 北京百度网讯科技有限公司 Construction method and system of brand advertisement evaluation system
CN104915377A (en) * 2015-05-07 2015-09-16 亿赞普(北京)科技有限公司 Method and device for adding foreign language business object category labels
CN104965863A (en) * 2015-06-05 2015-10-07 北京奇虎科技有限公司 Object clustering method and apparatus
CN105095306A (en) * 2014-05-20 2015-11-25 阿里巴巴集团控股有限公司 Operating method and device based on associated objects
CN105354202A (en) * 2014-08-20 2016-02-24 阿里巴巴集团控股有限公司 Data pushing method and apparatus
CN105678578A (en) * 2016-01-05 2016-06-15 重庆邮电大学 Method for measuring user brand preference on the basis of online shopping behavior data

Family Cites Families (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101206752A (en) * 2007-12-25 2008-06-25 北京科文书业信息技术有限公司 Electric commerce website related products recommendation system and method
US8812543B2 (en) * 2011-03-31 2014-08-19 Infosys Limited Methods and systems for mining association rules
CN102789615B (en) * 2011-05-17 2015-09-09 阿里巴巴集团控股有限公司 Book information correlation recommendation method, server and system
CN102789462B (en) * 2011-05-18 2015-12-16 阿里巴巴集团控股有限公司 A kind of item recommendation method and system
CN102254028A (en) * 2011-07-22 2011-11-23 青岛理工大学 Personalized commodity recommendation method and system integrating attributes and structural similarity
US9524522B2 (en) * 2012-08-31 2016-12-20 Accenture Global Services Limited Hybrid recommendation system
US20140180808A1 (en) * 2012-12-22 2014-06-26 Coupons.Com Incorporated Generation and management of dynamic electronic offers
JP6060833B2 (en) * 2013-06-28 2017-01-18 株式会社Ｊｖｃケンウッド Information processing apparatus, information processing method, and information processing program
CN104572782A (en) * 2013-10-29 2015-04-29 中兴通讯股份有限公司 Method and system for directional information pushing based on browser search
CN104636402B (en) * 2013-11-13 2018-05-01 阿里巴巴集团控股有限公司 A kind of classification of business object, search, method for pushing and system
US20150287091A1 (en) * 2014-04-08 2015-10-08 Turn Inc. User similarity groups for on-line marketing
CN105095256B (en) * 2014-05-07 2019-06-11 阿里巴巴集团控股有限公司 The method and device of information push is carried out based on similarity between user
CN103942712A (en) * 2014-05-09 2014-07-23 北京联时空网络通信设备有限公司 Product similarity based e-commerce recommendation system and method thereof
CN104050295B (en) * 2014-07-01 2018-01-02 彩带网络科技（北京）有限公司 A kind of exchange method and system
US20160063544A1 (en) * 2014-08-29 2016-03-03 Verizon Patent And Licensing Inc. Marketing platform that determines a target user segment based on third party information
KR102393154B1 (en) * 2015-01-02 2022-04-29 에스케이플래닛 주식회사 Contents recommending service system, and apparatus and control method applied to the same
US11157955B2 (en) * 2015-03-18 2021-10-26 Facebook, Inc. Selecting content for presentation to online system users based on correlations between content accessed by users via third party systems and interactions with online system content
SG10201502187RA (en) * 2015-03-20 2016-10-28 Mastercard Asia Pacific Pte Ltd Method and system for comparing merchants, and predicting the compatibility of a merchant with a potential customer
CN105809479A (en) * 2016-03-07 2016-07-27 海信集团有限公司 Item recommending method and device
CN106055566B (en) * 2016-05-19 2019-06-18 华南理工大学 Mobile phone games recommended method towards mobile advertising user

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102456203A (en) * 2010-10-22 2012-05-16 阿里巴巴集团控股有限公司 Method for determining candidate product linked list as well as related device
CN104025130A (en) * 2011-02-22 2014-09-03 汤姆森路透社全球资源公司 Association Significance
US8489596B1 (en) * 2013-01-04 2013-07-16 PlaceIQ, Inc. Apparatus and method for profiling users
CN104077337A (en) * 2013-05-20 2014-10-01 腾讯科技（深圳）有限公司 Searching method and device
CN104252679A (en) * 2013-06-30 2014-12-31 北京百度网讯科技有限公司 Construction method and system of brand advertisement evaluation system
CN103577549A (en) * 2013-10-16 2014-02-12 复旦大学 Crowd portrayal system and method based on microblog label
CN105095306A (en) * 2014-05-20 2015-11-25 阿里巴巴集团控股有限公司 Operating method and device based on associated objects
CN104199849A (en) * 2014-08-08 2014-12-10 亿赞普(北京)科技有限公司 Advertisement injecting method and device
CN105354202A (en) * 2014-08-20 2016-02-24 阿里巴巴集团控股有限公司 Data pushing method and apparatus
CN104915377A (en) * 2015-05-07 2015-09-16 亿赞普(北京)科技有限公司 Method and device for adding foreign language business object category labels
CN104965863A (en) * 2015-06-05 2015-10-07 北京奇虎科技有限公司 Object clustering method and apparatus
CN105678578A (en) * 2016-01-05 2016-06-15 重庆邮电大学 Method for measuring user brand preference on the basis of online shopping behavior data

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
刘巍等: "基于机构知识库的知识分析及可视化功能实现", 《图书与情报》 *
汪沛等: "一种结合词向量和图模型的特定领域实体消歧方法", 《智能系统学报》 *

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109062955A (en) * 2018-06-25 2018-12-21 广东神马搜索科技有限公司 Incidence relation method for digging, device, calculating equipment and storage medium between project
CN111292154A (en) * 2018-12-10 2020-06-16 阿里巴巴集团控股有限公司 Information obtaining method and device
CN111611504A (en) * 2019-02-26 2020-09-01 深圳云天励飞技术有限公司 Processing method, device, equipment and system
CN112445916A (en) * 2019-08-28 2021-03-05 阿里巴巴集团控股有限公司 Business object issuing method, entity issuing method and device
CN110852778A (en) * 2019-09-30 2020-02-28 口口相传(北京)网络技术有限公司 Data processing method and device for business object
CN111522606A (en) * 2020-04-26 2020-08-11 广东优特云科技有限公司 Data processing method, device, equipment and storage medium
CN111522606B (en) * 2020-04-26 2023-08-04 广东优特云科技有限公司 Data processing method, device, equipment and storage medium
US20210358042A1 (en) * 2020-05-13 2021-11-18 Hunan Fumi Information Technology Co., Ltd. Stock recommendation method based on item attribute identification and the system thereof
CN111598541A (en) * 2020-05-14 2020-08-28 深圳易伙科技有限责任公司 Enterprise business reporting method, device, equipment and storage medium
CN114143165A (en) * 2020-08-14 2022-03-04 北京达佳互联信息技术有限公司 Service alarm method, device, server, storage medium and program product
CN112632405A (en) * 2020-12-31 2021-04-09 数字广东网络建设有限公司 Recommendation method, device, equipment and storage medium
CN112632405B (en) * 2020-12-31 2024-05-10 数字广东网络建设有限公司 Recommendation method, recommendation device, recommendation equipment and storage medium
CN114418012A (en) * 2022-01-21 2022-04-29 建信金融科技有限责任公司 Object association relation determining method, device and equipment and computer storage medium
CN114418012B (en) * 2022-01-21 2024-08-23 建信金融科技有限责任公司 Object association relation determining method, device, equipment and computer storage medium

Also Published As

Publication number Publication date
WO2018099275A1 (en) 2018-06-07
CN108121737B (en) 2022-04-26
TWI787196B (en) 2022-12-21
TW201820230A (en) 2018-06-01

Similar Documents

Publication Publication Date Title
CN108121737A (en) A kind of generation method, the device and system of business object attribute-bit
Guo et al. Application of an improved Apriori algorithm in a mobile e-commerce recommendation system
US10095771B1 (en) Clustering and recommending items based upon keyword analysis
US10410138B2 (en) System and method for automatic generation of features from datasets for use in an automated machine learning process
CN108287864B (en) Interest group dividing method, device, medium and computing equipment
CN104866474B (en) Individuation data searching method and device
CN104239324B (en) A kind of feature extraction based on user behavior, personalized recommendation method and system
CN107632984A (en) A kind of cluster data table shows methods, devices and systems
CN105718184A (en) Data processing method and apparatus
JP5859606B2 (en) Ad source and keyword set adaptation in online commerce platforms
CN105183733A (en) Methods for matching text information and pushing business object, and devices for matching text information and pushing business object
CN104679771A (en) Individual data searching method and device
CN104636402A (en) Classification, search and push methods and systems of service objects
US12086820B2 (en) Technology opportunity mapping
CN103778553A (en) Commodity attribute recommendation method and commodity attribute recommendation system
CN107911448A (en) Content pushing method and device
CN107633416A (en) A kind of recommendation methods, devices and systems of business object
CN107133811A (en) The recognition methods of targeted customer a kind of and device
Baby et al. A hybrid product recommendation system based on weather analysis
CN104572932A (en) Method and device for determining interest label
CN107239456A (en) Age bracket recognition methods and device
CN111651456B (en) Potential user determination method, service pushing method and device
Kumar et al. A Deep Ranking Weighted Multihashing Recommender System for Item Recommendation
US20160148095A1 (en) Electronic calculating apparatus, method thereof and non-transitory machine-readable medium thereof for sensing context and recommending information
CN110020136B (en) Object recommendation method and related equipment

Legal Events

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