CN113821715A - Method and device for determining push information - Google Patents
Method and device for determining push information Download PDFInfo
- Publication number
- CN113821715A CN113821715A CN202011287791.2A CN202011287791A CN113821715A CN 113821715 A CN113821715 A CN 113821715A CN 202011287791 A CN202011287791 A CN 202011287791A CN 113821715 A CN113821715 A CN 113821715A
- Authority
- CN
- China
- Prior art keywords
- information
- target
- determining
- push
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000012549 training Methods 0.000 claims description 26
- 230000008569 process Effects 0.000 claims description 24
- 238000001914 filtration Methods 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 10
- 238000005457 optimization Methods 0.000 claims description 5
- 235000019580 granularity Nutrition 0.000 description 124
- 238000010586 diagram Methods 0.000 description 21
- 230000006399 behavior Effects 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 238000010276 construction Methods 0.000 description 7
- 238000010801 machine learning Methods 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000000354 decomposition reaction Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 238000012512 characterization method Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000000670 limiting effect Effects 0.000 description 2
- 230000036961 partial effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000007596 consolidation process Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000008450 motivation Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for determining push information, and relates to the technical field of computers. One embodiment of the method comprises: determining a target granularity attribute of a user according to login information under the condition that the user is detected to log in; wherein, the login information comprises the identification information of the target granularity attribute; and determining a target push data table of the user according to the target granularity attribute so as to push information in the target push data table to the user. The method can determine the granularity attribute of the user according to the identification information in the login information, and further can realize information push with various granularity requirements.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method and an apparatus for determining push information.
Background
In the era of data bombs, information push for users is a very important technology. In the prior art, the granularity is generally only performed for a single granularity, where the granularity refers to the thickness of data statistics in the same dimension, such as industries, enterprises, employees, and the like, and one industry generally has multiple enterprises and one enterprise generally has multiple employees. And, in the process of determining push information only for one granularity, the granularity attribute is not taken as a factor for determining the push information. The prior art mainly has the problem that the multi-granularity requirements of users such as industry-level information pushing, employee-level information pushing and the like cannot be met.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for determining push information, which can determine a granularity attribute of a user according to identification information in login information, and further can implement information push with various granularity requirements.
To achieve the above object, according to an aspect of an embodiment of the present invention, there is provided a method.
The method for determining the push information comprises the following steps: determining a target granularity attribute of a user according to login information under the condition that the user is detected to log in; wherein, the login information comprises the identification information of the target granularity attribute; and determining a target push data table of the user according to the target granularity attribute so as to push information in the target push data table to the user.
Optionally, the step of determining the target push data table of the user according to the target granularity attribute includes: determining target scene information of the user; and determining a target push data table of the user according to the target scene information and the target granularity attribute.
Optionally, the step of determining the target scenario information of the user includes: acquiring initial scene information input by the user, and analyzing the initial scene information to obtain target scene information; and/or obtaining target scene information according to the selection operation of the user on the displayed scene information.
Optionally, the step of determining the target push data table of the user according to the target granularity attribute includes: determining a candidate push data table of the user according to the target granularity attribute; the candidate push data table comprises information of at least one object; determining characteristic information of the at least one object; and optimizing the information of at least one object in the candidate pushed data list according to the characteristic information to obtain a target pushed data list.
Optionally, the optimization process includes at least one of: sorting processing, deleting processing and marking processing; and/or the characteristic information at least comprises one of the following: stock quantity information, stock place information, price information.
Optionally, the step of determining the target push data table of the user according to the target granularity attribute includes: determining a target push data table of the user according to a push model corresponding to the target granularity attribute; for each granularity attribute, configuring a corresponding push model; and the push model is obtained by training according to the historical operation data of the corresponding granularity attribute.
Optionally, the step of determining the target granularity attribute of the user according to the login information includes: determining a target granularity attribute of the user from at least one granularity attribute according to login information, wherein the at least one granularity attribute comprises industry, enterprises or individuals;
determining a target push data table of the user according to the target granularity attribute when the target granularity attribute is determined to be an enterprise, wherein the step comprises the following steps: determining industry information and employee information of the user; determining an industry pushing data table and an employee pushing data table according to the industry information and the employee information respectively; determining an enterprise push data table of the user according to the target granularity attribute; and fusing the industry push data sheet, the employee push data sheet and the enterprise push data sheet to obtain a target push data sheet.
Optionally, before determining the target push data table of the user according to the target granularity attribute, the method further includes: and constructing a push model corresponding to the industry, a push model corresponding to the enterprise and a push model corresponding to the individual.
Optionally, the step of constructing a push model corresponding to the industry, a push model corresponding to the enterprise, and a push model corresponding to the individual includes:
acquiring enterprise operation data of a sample enterprise under each scene information and personal operation data of employees in the sample enterprise under each scene information;
determining industry information of the sample enterprise; based on a collaborative filtering model, training to obtain a push model corresponding to the industry according to the enterprise operation data of the sample enterprise under each scene information and the industry information of the sample enterprise;
based on a collaborative filtering model, training to obtain a pushing model corresponding to the enterprise according to enterprise operation data of the sample enterprise under each scene information;
determining employee representations of employees in the sample enterprise, and determining object representations of objects included in the personal operational data; and training to obtain a pushing model corresponding to the individual according to the personal operation data of the employee in the sample enterprise under each scene information, the employee portrait and the object portrait based on a collaborative filtering model and a deep FM model.
To achieve the above object, according to another aspect of the embodiments of the present invention, there is provided an apparatus for determining push information.
The device for determining the push information of the embodiment of the invention comprises the following components:
the target granularity attribute determining module is used for determining the target granularity attribute of the user according to login information under the condition that the user is detected to log in; wherein, the login information comprises the identification information of the target granularity attribute;
and the push data table determining module is used for determining a target push data table of the user according to the target granularity attribute so as to push the information in the target push data table to the user.
Optionally, the pushed data table determining module is further configured to determine target scene information of the user; and determining a target push data table of the user according to the target scene information and the target granularity attribute.
Optionally, the pushed data table determining module is further configured to obtain initial scene information input by the user, and analyze the initial scene information to obtain target scene information; and/or obtaining target scene information according to the selection operation of the user on the displayed scene information.
Optionally, the pushed data table determining module is further configured to determine a candidate pushed data table of the user according to the target granularity attribute; the candidate push data table comprises information of at least one object; determining characteristic information of the at least one object; and optimizing the information of at least one object in the candidate pushed data list according to the characteristic information to obtain a target pushed data list.
Optionally, the optimization process includes at least one of: sorting processing, deleting processing and marking processing; and/or the characteristic information at least comprises one of the following: stock quantity information, stock place information, price information.
Optionally, the pushed data table determining module is further configured to determine a target pushed data table of the user according to a pushing model corresponding to the target granularity attribute;
for each granularity attribute, configuring a corresponding push model; and the push model is obtained by training according to the historical operation data of the corresponding granularity attribute.
Optionally, the step of determining the target granularity attribute of the user according to the login information includes: determining a target granularity attribute of the user from at least one granularity attribute according to login information, wherein the at least one granularity attribute comprises industry, enterprises or individuals;
the push data table determining module is further used for determining industry information and employee information of the user; determining an industry pushing data table and an employee pushing data table according to the industry information and the employee information respectively; determining an enterprise push data table of the user according to the target granularity attribute; and fusing the industry push data sheet, the employee push data sheet and the enterprise push data sheet to obtain a target push data sheet.
Optionally, the system further comprises a push model construction module, configured to construct a push model corresponding to the industry, a push model corresponding to the enterprise, and a push model corresponding to the individual.
Optionally, the push model building module is further configured to obtain enterprise operation data of a sample enterprise under each piece of scenario information, and personal operation data of employees in the sample enterprise under each piece of scenario information; determining industry information of the sample enterprise; based on a collaborative filtering model, training to obtain a push model corresponding to the industry according to the enterprise operation data of the sample enterprise under each scene information and the industry information of the sample enterprise; based on a collaborative filtering model, training to obtain a pushing model corresponding to the enterprise according to enterprise operation data of the sample enterprise under each scene information; determining employee representations of employees in the sample enterprise, and determining object representations of objects included in the personal operational data; and training to obtain a pushing model corresponding to the individual according to the personal operation data of the employee in the sample enterprise under each scene information, the employee portrait and the object portrait based on a collaborative filtering model and a deep FM model.
To achieve the above object, according to still another aspect of an embodiment of the present invention, there is provided an electronic apparatus.
The electronic device of the embodiment of the invention comprises: one or more processors; a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement any of the above methods for determining push information.
To achieve the above object, according to a further aspect of the embodiments of the present invention, there is provided a computer readable medium having a computer program stored thereon, wherein the computer program is configured to implement any one of the above methods for determining push information when executed by a processor.
One embodiment of the above invention has the following advantages or benefits: when the login mode is activated (for example, an account is registered, a login fingerprint is input, and the like), namely, the granularity information is selected, so that when the login of the user is detected, the target granularity attribute of the user can be determined according to the identification information of the granularity attribute in the login information. Furthermore, a data pushing table is determined according to the determined target granularity attribute, all the data pushing tables can be used for recommending selected products aiming at multiple granularities of industries, enterprises, individuals and the like, namely, a user can be a company or an individual, and information pushing with various granularity requirements can be realized. The problem that in the prior art, a user can only be a company or only an individual, and the multi-granularity requirement of the user cannot be met is solved.
Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
fig. 1 is a schematic diagram of a main flow of a method of determining push information according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating a method of determining push information according to an embodiment of the invention;
FIG. 3 is a diagram illustrating a method of determining to push a data table according to an embodiment of the invention;
FIG. 4 is a schematic diagram of determining an option list based on a push model corresponding to enterprises and industries, according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of determining an option list based on a push model corresponding to a person, according to an embodiment of the invention;
FIG. 6 is a schematic diagram of an implementation of a method for determining push information for an enterprise selection according to an embodiment of the invention;
FIG. 7 is a schematic diagram of the main modules of an apparatus for determining push information according to an embodiment of the present invention;
FIG. 8 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;
fig. 9 is a schematic structural diagram of a computer system suitable for implementing a terminal device or a server according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a schematic diagram of a main flow of a method for determining push information according to an embodiment of the present invention, and as shown in fig. 1, the method for determining push information according to the embodiment of the present invention mainly includes:
step S101: determining a target granularity attribute of a user according to login information under the condition that the user is detected to log in; wherein, the login information includes the identification information of the target granularity attribute.
Step S102: and determining a target push data table of the user according to the target granularity attribute so as to push information in the target push data table to the user.
The login by the user is performed by performing an account login operation, a fingerprint recognition login operation, a voice login operation, and the like (only an example) through a login interface of a web page or a login page of an application APP. After the user logs in, the user can browse the interface for displaying the object, and further perform some series of operations on the object in the interface (such as collecting, placing an order, adding a shopping cart, and the like). Therefore, when the user is detected to log in, the information pushing task can be generated. In the process of executing the information pushing task, firstly, the target granularity attribute of the user is determined according to the identification information of the target granularity attribute in the login information. The identification information of the granularity attribute included in the login information may be a name of the granularity attribute, or may be a unique code.
According to the embodiment of the invention, when the login mode is activated (for example, an account is registered, a login fingerprint is input, and the like), the user selects the granularity information, so that when the login of the user is detected, the target granularity attribute of the user can be determined according to the identification information of the granularity attribute in the login information. Furthermore, a data pushing table is determined according to the determined target granularity attribute, all the data pushing tables can be used for recommending selected products aiming at multiple granularities of industries, enterprises, individuals and the like, namely, a user can be a company or an individual, and information pushing with various granularity requirements can be realized. The problem that in the prior art, a user can only be a company or only an individual, and the multi-granularity requirement of the user cannot be met is solved.
Fig. 2 is a schematic diagram of a method for determining push information according to an embodiment of the present invention, and as shown in fig. 2, the method for determining push information according to the embodiment of the present invention mainly includes:
step S201: and under the condition that the user is detected to log in, determining the target granularity attribute of the user according to the login information.
Step S202: and determining target scene information of the user.
Step S203: and determining a target push data table of the user according to the target scene information and the target granularity attribute.
In this embodiment of the present invention, preferably, in the implementation process of step S202, the initial scene information input by the user may be directly obtained, and the initial scene information may be analyzed to obtain the target scene information. And obtaining target scene information according to the selection operation of the user on the displayed scene information. The interface can be configured with a plurality of options of the scene information, and a user can directly click a page to the displayed scene information according to requirements. If the scene information required by the user does not exist in the displayed interface, keywords of the scene information can be input in the input box, or long sentences or voice information of the scene information can be input. According to the embodiment of the invention, in the information recommending process, the object information corresponding to the scene requirement can be screened out according to different scene information such as holidays, labor insurance, motivation and the like, so that the information pushing accuracy is improved, and the function of self-adaption of the scene in the information recommending process is realized.
In an optional embodiment of the present invention, in the process of determining the target pushed data table of the user according to the target granularity attribute, determining a candidate pushed data table of the user according to the target granularity attribute; the candidate push data table comprises information of at least one object. Determining characteristic information of the at least one object; and optimizing the information of at least one object in the candidate pushed data list according to the characteristic information to obtain a target pushed data list. More preferably, the optimization process comprises at least one of: sorting processing, deleting processing and marking processing. The characteristic information includes at least one of: stock quantity information, stock place information, price information. The stock information is the stock quantity of the object, the stock location information is the storage address of the object, and the price information is the price of the object when sold. The sorting process is to sort the information in the candidate push data table, and the specific sorting basis may be that the price is from low to high, or the stock quantity is from high to low, the stock place is from near to far, etc. The deleting process and the marking process refer to deleting or marking partial information in the candidate push data table, wherein the confirmation of the partial information can be according to the stock quantity information, the price information and the like of the object. For example, the object information whose stock quantity is less than a certain threshold value in the candidate push data table is deleted. And marking or deleting the object information with the price higher than a certain threshold value in the candidate push data table. For example, in the case of autumn purchasing in enterprise granularity, by introducing commodity inventory and member price information, commodity sequencing can be adjusted, and commodities with sufficient inventory and price advantage are preferentially displayed.
In an optional embodiment of the present invention, in the process of determining the target push data table of the user according to the target granularity attribute, the target push data table of the user is determined according to a push model corresponding to the target granularity attribute; for each granularity attribute, configuring a corresponding push model; and the push model is obtained by training according to the historical operation data of the corresponding granularity attribute. Optionally, the step of determining the target granularity attribute of the user according to the login information includes: and determining the target granularity attribute of the user from at least one granularity attribute according to the login information, wherein the at least one granularity attribute comprises industry, enterprises or individuals. Furthermore, three granularities of selection (information push) of industry, enterprise and staff are supported.
Fig. 3 is a schematic diagram of a method for determining a pushed data table according to an embodiment of the present invention, and as shown in fig. 3, the method for determining a pushed data table according to an embodiment of the present invention mainly includes:
step S301: and determining the industry information and the employee information of the user. In embodiments of the present invention, granular attributes include industry, business, and personal.
Step S302: and determining an industry pushing data table and an employee pushing data table according to the industry information and the employee information respectively.
Step S303: and determining an enterprise push data table of the user according to the target granularity attribute.
Step S304: and fusing the industry push data sheet, the employee push data sheet and the enterprise push data sheet to obtain a target push data sheet. In this step, the fusion process of the data tables can be performed by machine learning to obtain a process model. Then, a target push data table is obtained based on the model. In the embodiment of the invention, the target push data table is the information in the industry push data table, the employee push data table and the enterprise push data table, namely, in the enterprise granularity information push, the employee-level push results belonging to the enterprise are fused, so that the enterprise-level recommendation can meet the preference of the enterprise employees. And the industrial-level pushing results in the industry of the enterprise are also fused.
Before determining a target push data table of the user according to the target granularity attribute, constructing a push model corresponding to the industry, a push model corresponding to the enterprise and a push model corresponding to the individual. In the process of constructing the push model corresponding to the industry, the push model corresponding to the enterprise and the push model corresponding to the individual, enterprise operation data of the sample enterprise under each scene information and individual operation data of the staff in the sample enterprise under each scene information are obtained. Industry information for the sample enterprise is then determined. And training to obtain a push model corresponding to the industry according to the enterprise operation data of the sample enterprise under each scene information and the industry information of the sample enterprise based on the collaborative filtering model. And training to obtain a push model corresponding to the enterprise according to enterprise operation data of the sample enterprise under each scene information based on the collaborative filtering model. Determining employee representations of employees in the sample enterprise, and determining object representations of objects included in the personal operation data; and training to obtain a pushing model corresponding to the individual according to the personal operation data of the employee in the sample enterprise under each scene information, the employee portrait and the object portrait based on a collaborative filtering model and a deep FM model.
The process of training the model mainly comprises the following steps: 1) data sorting, 2) feature construction, and 3) model construction. Specifically, data consolidation refers to selection schemes of enterprises in different scenes and shopping behaviors of employees on shopping websites. And dividing the selection scheme of the enterprise (namely enterprise operation data, which refers to data information of commodities selected by the enterprise historically) into different data sets according to the scene. The industry-level data set summarizes the enterprise data through the industry to which each enterprise belongs. The conditions of festival, labor protection and the like can be considered in the scene. The shopping behavior (i.e. personal operation data) of the employee includes browsing the goods, joining the shopping cart and placing the order for purchase. The characteristic structure is to construct a user image (i.e. employee image) and a commodity image (i.e. object image), wherein the user image comprises the information of the located industry, the region, the age, the academic calendar and the like, and the commodity image comprises the information of commodity types, the price information and the like. The construction mode of the interactive behavior features is that the commodity is subjected to representation learning, and the feature vectors are input into a neural network after being spliced and pooled. The commodity characterization learning is to combine the interaction behaviors of the user and the commodity into a sequence according to time, learn by using a word2vec method, and finally output a characterization vector for each commodity. For model construction, due to the fact that the number of industry and enterprise products is large, efficiency and expandability become the most important consideration basis of the scheme. Thus, enterprise-level recommendations use a simple but efficient collaborative filtering model to recommend a set of candidate commodities for the corresponding industry and enterprise in a particular scenario. The collaborative filtering model uses industry-level and enterprise-level historical selection data and order data, and different scenes use different models for recommendation. The recommendation of the staff granularity is divided into a recall part and a sorting part, and the technical scheme of the recall part is the same as that of the industry and enterprise level recommendation; the sequencing stage uses a DeepFM model which is divided into an FM part and a DNN part, wherein the FM part uses two portrait characteristics, time information, scene information and the like which are artificially constructed, and the DNN part uses the interaction behavior and the scene information of the user and the commodity to learn.
The recommendation system comprises: a system for providing content information and recommendations to a user by a content provider to assist the user in making selections that simulate the process of a sales person assisting the customer in completing a purchase. It is commonly used in the fields of e-commerce, multimedia content services, etc.
Recall/sort: and two stages of the recommendation system, wherein the recall stage is to primarily screen out a part of all commodities, and the sorting stage is to sort and score the screened candidate set.
Collaborative filtering technology: a recommendation model recommends information of interest to a user by utilizing preferences of interest-cast and common experience groups. The advantage is that the processing speed is faster for the case of larger magnitude. Therefore, aiming at the condition that historical operation data of industries and enterprises are large, a better processing effect can be obtained through the collaborative filtering model. s
DeepFM model: a sorting model comprises an FM part and a DNN part, and can realize refined sorting of a commodity recommendation list. FM (Factorization Machine) is a Machine learning algorithm based on matrix decomposition, and DNN (Deep Neural Networks) is a Neural network structure including a plurality of hidden layers.
Matrix decomposition technique: the matrix decomposition is to decompose and complement a matrix into a product of a plurality of matrices by using the matrix decomposition idea in the field of recommendation systems, and recommend according to the complemented matrix.
A neural network: the artificial neural network is an algorithmic mathematical model which simulates the behavioral characteristics of an animal neural network and performs distributed parallel information processing.
Wide & Deep model: a neural network model issued by Google is commonly used in the field of recommendation systems, and combines a traditional machine learning model and a deep learning model, so that a better recommendation effect is achieved.
Word2Vec model: word2Vec is an efficient tool for Google to open sources in 2013 and characterize words as real-valued vectors, and the adopted models include CBOW and Skip-Gram.
FIG. 4 is a schematic diagram of determining an option list based on a push model corresponding to enterprises and industries, according to an embodiment of the present invention; fig. 5 is a schematic diagram of determining an option list based on a push model corresponding to a person according to an embodiment of the present invention. Fig. 6 is a schematic diagram of an implementation of a method for determining push information of an enterprise option according to an embodiment of the present invention.
For a traditional enterprise selection system, the recommendation granularity is generally a single enterprise granularity, that is, only the enterprise user can be recommended to select the product, and the main implementation scheme in the prior art includes: (1) a rule-based selection system. And uniform commodity recommendation logic, such as popularity, new-class degree and the like, is adopted for all enterprises. (2) And (4) a selection system based on manual experience. The operators communicate with the enterprises and select proper commodities for each enterprise by combining own experience. (3) An item selection system based on machine learning and deep learning. And automatically recommending personalized commodities for each enterprise through a machine learning method such as collaborative filtering and matrix decomposition and a Deep learning method such as Wide & Deep. The problems that exist mainly include:
1. rule-based selection system:
1) personalized selection cannot be made for different enterprises, hot-market commodities or new products can be simply displayed, the batch commercial purchasing requirements of the enterprises cannot be met, and the screening cost of enterprise users is still high;
2) flexible adjustment cannot be made according to real-time feedback of enterprises;
2. selection system based on manual operation:
1) the labor cost is high, and the time consumption is long. It is necessary to communicate with the enterprise in advance. When the number of enterprise users is too large, the problems of high operation cost and long user waiting time are caused. The information of the user comprises the company and the industry;
2) the experience level of operators is uneven, and it is difficult to ensure that the proper commodities can be selected for enterprises each time;
3. the selection system based on machine learning and deep learning comprises:
1) timely commodities cannot be selected for enterprises according to scenes such as current festivals. Because the traditional recommendation system based on machine learning and deep learning mainly carries out recommendation according to the historical behaviors of users, the recommendation accuracy is reduced due to the fact that the frequency of the user behaviors is low in an enterprise selection scene and the association degree with the scene is high;
2) because the quantity of the selected products of the enterprise is generally large, the traditional recommendation system does not consider the factors such as inventory and the like, so that the problems that the recommended commodities cannot meet the purchasing quantity of the enterprise and the like are caused;
3) the recommendation granularity of the traditional enterprise selection system is generally single enterprise granularity, and cannot adapt to various requirements of users, such as industry-level recommendation, employee-level recommendation and the like.
As shown in fig. 6, the method for determining pushing information of enterprise selections in the embodiment of the present invention is implemented mainly by:
s601: and receiving the option information input by the user on the front page. In embodiments of the present invention, the user is only a business user and does not represent an individual. The option information is information which can represent the requirements of the user, and the information input by the user on the front end page mainly comprises scene descriptors and option willingness. If the user does not input the selection information, the information can be pushed to the user according to the historical data or the current nearest festival.
S602: and determining scene information according to the option information input by the user. According to the scene directly selected by the user or corresponding the input keywords to a certain scene.
S603: whether the industry to which the user belongs needs to be determined. The user can select own industry during registration, the background can maintain a data table, and the industry to which the enterprise belongs can be automatically obtained after the user logs in. If the industry to which the user belongs does not need to be determined, and the information of the enterprise and the employee under the enterprise can be pushed directly, the two pieces of granularity information are integrated in S608.
S604: and judging whether the user is the enterprise granularity attribute. The enterprise account number has two types, one is a super account number of an enterprise buyer, the account number represents an enterprise, and the user logs in and displays a selection result of the whole enterprise; the other is an account number of the enterprise employee, which represents an employee, and the account number is recommended after logging in to recommend results of the enterprise employee. This step is used to determine which account is the logged-in account.
S605: and calling a push model corresponding to the enterprise granularity attribute, and acquiring a selection list of the enterprise. As shown in fig. 4, a push model is obtained according to enterprise selections and order data (historical operation data), and training according to scene information and sample operation data, and a selection list under different granularities is determined. Such as collaborative filtering model 1 (push model for spring festival scenario), collaborative filtering model 2 (push model for labor insurance scenario) in fig. 4.
S606: and calling a push model corresponding to the staff granularity attribute, and acquiring a selection list of the staff. As shown in fig. 5, scene information and time information can be obtained according to a user portrait, a commodity portrait of an employee, and a scene requirement input by a user, which are stored in a database or generated in real time, and further, a candidate set of employee selections can be preliminarily obtained according to the rice shopping behavior of the employee through a collaborative filtering model 3 obtained through training. And based on the deep FM model, obtaining a selection list of the staff according to the staff selection candidate set, the staff shopping behavior data, the commodity portrait, the user portrait, the scene information and the time information.
S607: and calling a push model corresponding to the industry granularity attribute to obtain an industry selection list. As shown in fig. 4, the selection list of the same enterprise is obtained by obtaining a push model according to industry selection and order data (historical operation data), and training according to scene information and sample operation data, and determining the selection list under different granularities.
S608: and performing result fusion on the selection lists of enterprises, employees and industries.
S609: and displaying the commodities according to the fusion result.
Fig. 7 is a schematic diagram of main modules of an apparatus for determining push information according to an embodiment of the present invention, and as shown in fig. 7, an apparatus 700 for determining push information according to an embodiment of the present invention includes a target granularity attribute determining module 701 and a push data table determining module 702.
The target granularity attribute determining module 701 is configured to, when it is detected that the user logs in, determine the target granularity attribute of the user according to login information.
The pushed data table determining module 702 is configured to determine a target pushed data table of the user according to the target granularity attribute, so as to push information in the target pushed data table to the user.
In an optional embodiment of the present invention, the pushed data table determining module is further configured to determine target scene information of the user; and determining a target push data table of the user according to the target scene information and the target granularity attribute.
In an optional embodiment of the present invention, the pushed data table determining module is further configured to obtain initial scene information input by the user, and analyze the initial scene information to obtain target scene information. In an optional embodiment of the present invention, the pushed data table determining module is further configured to obtain the target scene information according to a selection operation of the user on the displayed scene information.
In an optional embodiment of the present invention, the pushed data table determining module is further configured to determine, according to the target granularity attribute, a candidate pushed data table of the user; the candidate push data table comprises information of at least one object; determining characteristic information of the at least one object; and optimizing the information of at least one object in the candidate pushed data list according to the characteristic information to obtain a target pushed data list. Preferably, in an optional embodiment of the present invention, the optimization process includes at least one of: sorting processing, deleting processing and marking processing; and/or the characteristic information at least comprises one of the following: stock quantity information, stock place information, price information.
In an optional embodiment of the present invention, the pushed data table determining module is further configured to determine the target pushed data table of the user according to a pushing model corresponding to the target granularity attribute. For each granularity attribute, configuring a corresponding push model; and the push model is obtained by training according to the historical operation data of the corresponding granularity attribute.
In an optional embodiment of the present invention, the step of determining the target granularity attribute of the user according to the login information includes: and determining the target granularity attribute of the user from at least one granularity attribute according to the login information, wherein the at least one granularity attribute comprises industry, enterprises or individuals. Preferably, the push data table determining module is further configured to determine industry information and employee information of the user; determining an industry pushing data table and an employee pushing data table according to the industry information and the employee information respectively; determining an enterprise push data table of the user according to the target granularity attribute; and fusing the industry push data sheet, the employee push data sheet and the enterprise push data sheet to obtain a target push data sheet.
In an optional embodiment of the present invention, the apparatus for determining push information further includes a push model construction module, configured to construct a push model corresponding to the industry, a push model corresponding to the enterprise, and a push model corresponding to the individual.
In an optional embodiment of the present invention, the push model building module is further configured to obtain enterprise operation data of a sample enterprise under each piece of scenario information, and personal operation data of employees in the sample enterprise under each piece of scenario information; determining industry information of the sample enterprise; based on a collaborative filtering model, training to obtain a push model corresponding to the industry according to the enterprise operation data of the sample enterprise under each scene information and the industry information of the sample enterprise; based on a collaborative filtering model, training to obtain a pushing model corresponding to the enterprise according to enterprise operation data of the sample enterprise under each scene information; determining employee representations of employees in the sample enterprise, and determining object representations of objects included in the personal operational data; and training to obtain a pushing model corresponding to the individual according to the personal operation data of the employee in the sample enterprise under each scene information, the employee portrait and the object portrait based on a collaborative filtering model and a deep FM model.
According to the embodiment of the invention, when the login mode is activated (for example, an account is registered, a login fingerprint is input, and the like), the user selects the granularity information, so that when the login of the user is detected, the target granularity attribute of the user can be determined according to the identification information of the granularity attribute in the login information. Furthermore, a data pushing table is determined according to the determined target granularity attribute, all the data pushing tables can be used for recommending selected products aiming at multiple granularities of industries, enterprises, individuals and the like, namely, a user can be a company or an individual, and information pushing with various granularity requirements can be realized. The problem that in the prior art, a user can only be a company or only an individual, and the multi-granularity requirement of the user cannot be met is solved. And in the process of determining the push information, the function of self-adapting to scenes in the information push process can be realized by introducing scene information such as festivals, labor insurance, incentives and the like. And the information pushing considers the inventory factor, and ensures that the recommended objects (such as commodities) can meet the enterprise granularity purchase quantity. And for each granularity, different pushing models can be adopted to determine pushing information, and the different pushing models are obtained by training according to historical operation data of the granularity, so that the recommendation accuracy is improved, and the personalized recommendation of each granularity is realized.
Fig. 8 illustrates an exemplary system architecture 800 of a method of determining push information or an apparatus for determining push information to which embodiments of the invention may be applied.
As shown in fig. 8, the system architecture 800 may include terminal devices 801, 802, 803, a network 804, and a server 805. The network 804 serves to provide a medium for communication links between the terminal devices 801, 802, 803 and the server 805. Network 804 may include various types of connections, such as wire, wireless communication links, or fiber optic cables, to name a few.
A user may use the terminal devices 801, 802, 803 to interact with a server 805 over a network 804 to receive or send messages or the like. The terminal devices 801, 802, 803 may have installed thereon various communication client applications, such as shopping-like applications, web browser applications, search-like applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).
The terminal devices 801, 802, 803 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 805 may be a server that provides various services, such as a back-office management server (for example only) that supports shopping-like websites browsed by users using the terminal devices 801, 802, 803. The background management server can analyze and process the received data such as the product information inquiry request and feed back the processing result to the terminal equipment.
It should be noted that the method for determining push information provided by the embodiment of the present invention is generally performed by the server 805, and accordingly, the device for determining push information is generally disposed in the server 805.
It should be understood that the number of terminal devices, networks, and servers in fig. 8 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 9, shown is a block diagram of a computer system 900 suitable for use with a terminal device implementing an embodiment of the present invention. The terminal device shown in fig. 9 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 9, the computer system 900 includes a Central Processing Unit (CPU)901 that can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)902 or a program loaded from a storage section 908 into a Random Access Memory (RAM) 903. In the RAM 903, various programs and data necessary for the operation of the system 900 are also stored. The CPU 901, ROM 902, and RAM 903 are connected to each other via a bus 904. An input/output (I/O) interface 905 is also connected to bus 904.
The following components are connected to the I/O interface 909: an input portion 906 including a keyboard, a mouse, and the like; an output section 907 including components such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 908 including a hard disk and the like; and a communication section 909 including a network interface card such as a LAN card, a modem, or the like. The communication section 909 performs communication processing via a network such as the internet. The drive 910 is also connected to the I/O interface 905 as necessary. A removable medium 911 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 910 as necessary, so that a computer program read out therefrom is mounted into the storage section 908 as necessary.
In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 909, and/or installed from the removable medium 911. The above-described functions defined in the system of the present invention are executed when the computer program is executed by a Central Processing Unit (CPU) 901.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor comprises a target granularity attribute determining module and a pushed data table determining module. The names of these modules do not form a limitation on the modules themselves in some cases, for example, the target granularity attribute determination module may also be described as a "module that determines the target granularity attribute of a user according to login information in the case that the user is detected to log in".
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise: determining a target granularity attribute of a user according to login information under the condition that the user is detected to log in; wherein, the login information comprises the identification information of the target granularity attribute; and determining a target push data table of the user according to the target granularity attribute so as to push information in the target push data table to the user.
According to the embodiment of the invention, when the login mode is activated (for example, an account is registered, a login fingerprint is input, and the like), the user selects the granularity information, so that when the login of the user is detected, the target granularity attribute of the user can be determined according to the identification information of the granularity attribute in the login information. Furthermore, a data pushing table is determined according to the determined target granularity attribute, all the data pushing tables can be used for recommending selected products aiming at multiple granularities of industries, enterprises, individuals and the like, namely, a user can be a company or an individual, and information pushing with various granularity requirements can be realized. The problem that in the prior art, a user can only be a company or only an individual, and the multi-granularity requirement of the user cannot be met is solved.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (15)
1. A method for determining push information, comprising:
determining a target granularity attribute of a user according to login information under the condition that the user is detected to log in; wherein, the login information comprises the identification information of the target granularity attribute;
and determining a target push data table of the user according to the target granularity attribute so as to push information in the target push data table to the user.
2. The method of claim 1, wherein the step of determining the target push data table of the user according to the target granularity attribute comprises:
determining target scene information of the user;
and determining a target push data table of the user according to the target scene information and the target granularity attribute.
3. The method of claim 2, wherein the step of determining the target context information of the user comprises:
acquiring initial scene information input by the user, and analyzing the initial scene information to obtain target scene information; and/or
And obtaining target scene information according to the selection operation of the user on the displayed scene information.
4. The method of claim 1, wherein the step of determining the target push data table of the user according to the target granularity attribute comprises:
determining a candidate push data table of the user according to the target granularity attribute; the candidate push data table comprises information of at least one object;
determining characteristic information of the at least one object;
and optimizing the information of at least one object in the candidate pushed data list according to the characteristic information to obtain a target pushed data list.
5. The method of claim 4, wherein the optimization process comprises at least one of: sorting processing, deleting processing and marking processing; and/or
The characteristic information includes at least one of: stock quantity information, stock place information, price information.
6. The method of any of claims 1-5, wherein determining the user's target push data table based on the target granularity attribute comprises:
determining a target push data table of the user according to a push model corresponding to the target granularity attribute;
for each granularity attribute, configuring a corresponding push model; and the push model is obtained by training according to the historical operation data of the corresponding granularity attribute.
7. The method of claim 6, wherein the step of determining the target granularity attribute of the user based on the login information comprises: determining a target granularity attribute of the user from at least one granularity attribute according to login information, wherein the at least one granularity attribute comprises industry, enterprises or individuals;
determining a target push data table of the user according to the target granularity attribute when the target granularity attribute is determined to be an enterprise, wherein the step comprises the following steps:
determining industry information and employee information of the user;
determining an industry pushing data table and an employee pushing data table according to the industry information and the employee information respectively;
determining an enterprise push data table of the user according to the target granularity attribute;
and fusing the industry push data sheet, the employee push data sheet and the enterprise push data sheet to obtain a target push data sheet.
8. The method of claim 7, further comprising, prior to determining the user's target push data table based on the target granularity attribute:
and constructing a push model corresponding to the industry, a push model corresponding to the enterprise and a push model corresponding to the individual.
9. The method of claim 8, wherein the step of constructing the industry-specific push model, the enterprise-specific push model, and the individual-specific push model comprises:
acquiring enterprise operation data of a sample enterprise under each scene information and personal operation data of employees in the sample enterprise under each scene information;
determining industry information of the sample enterprise; based on a collaborative filtering model, training to obtain a push model corresponding to the industry according to the enterprise operation data of the sample enterprise under each scene information and the industry information of the sample enterprise;
based on a collaborative filtering model, training to obtain a pushing model corresponding to the enterprise according to enterprise operation data of the sample enterprise under each scene information;
determining employee representations of employees in the sample enterprise, and determining object representations of objects included in the personal operational data; and training to obtain a pushing model corresponding to the individual according to the personal operation data of the employee in the sample enterprise under each scene information, the employee portrait and the object portrait based on a collaborative filtering model and a deep FM model.
10. An apparatus for determining push information, comprising:
the target granularity attribute determining module is used for determining the target granularity attribute of the user according to login information under the condition that the user is detected to log in; wherein, the login information comprises the identification information of the target granularity attribute;
and the push data table determining module is used for determining a target push data table of the user according to the target granularity attribute so as to push the information in the target push data table to the user.
11. The apparatus of claim 10, wherein the pushed data table determining module is further configured to determine target scenario information of the user; and determining a target push data table of the user according to the target scene information and the target granularity attribute.
12. The apparatus according to any one of claims 10 to 11, wherein the pushed data table determining module is further configured to determine a target pushed data table of the user according to a pushing model corresponding to the target granularity attribute; for each granularity attribute, configuring a corresponding push model; and the push model is obtained by training according to the historical operation data of the corresponding granularity attribute.
13. The apparatus of claim 12, wherein the step of determining the target granularity attribute of the user based on the login information comprises: determining a target granularity attribute of the user from at least one granularity attribute according to login information, wherein the at least one granularity attribute comprises industry, enterprises or individuals;
the push data table determining module is further used for determining industry information and employee information of the user; determining an industry pushing data table and an employee pushing data table according to the industry information and the employee information respectively; determining an enterprise push data table of the user according to the target granularity attribute; and fusing the industry push data sheet, the employee push data sheet and the enterprise push data sheet to obtain a target push data sheet.
14. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-9.
15. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011287791.2A CN113821715A (en) | 2020-11-17 | 2020-11-17 | Method and device for determining push information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011287791.2A CN113821715A (en) | 2020-11-17 | 2020-11-17 | Method and device for determining push information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113821715A true CN113821715A (en) | 2021-12-21 |
Family
ID=78924944
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011287791.2A Pending CN113821715A (en) | 2020-11-17 | 2020-11-17 | Method and device for determining push information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113821715A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108960975A (en) * | 2018-06-15 | 2018-12-07 | 广州麦优网络科技有限公司 | Personalized Precision Marketing Method, server and storage medium based on user's portrait |
| CN109040300A (en) * | 2018-09-04 | 2018-12-18 | 航天信息股份有限公司 | The method, apparatus and storage medium of PUSH message |
| CN109831684A (en) * | 2019-03-11 | 2019-05-31 | 深圳前海微众银行股份有限公司 | Video optimized recommended method, device and readable storage medium storing program for executing |
| CN109981712A (en) * | 2017-12-28 | 2019-07-05 | 北京京东尚科信息技术有限公司 | Method and apparatus for pushed information |
| CN110442790A (en) * | 2019-08-07 | 2019-11-12 | 腾讯科技（深圳）有限公司 | Recommend method, apparatus, server and the storage medium of multi-medium data |
| CN111143681A (en) * | 2019-12-27 | 2020-05-12 | 中国银行股份有限公司 | Information recommendation device, method, equipment and system |
-
2020
- 2020-11-17 CN CN202011287791.2A patent/CN113821715A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109981712A (en) * | 2017-12-28 | 2019-07-05 | 北京京东尚科信息技术有限公司 | Method and apparatus for pushed information |
| CN108960975A (en) * | 2018-06-15 | 2018-12-07 | 广州麦优网络科技有限公司 | Personalized Precision Marketing Method, server and storage medium based on user's portrait |
| CN109040300A (en) * | 2018-09-04 | 2018-12-18 | 航天信息股份有限公司 | The method, apparatus and storage medium of PUSH message |
| CN109831684A (en) * | 2019-03-11 | 2019-05-31 | 深圳前海微众银行股份有限公司 | Video optimized recommended method, device and readable storage medium storing program for executing |
| CN110442790A (en) * | 2019-08-07 | 2019-11-12 | 腾讯科技（深圳）有限公司 | Recommend method, apparatus, server and the storage medium of multi-medium data |
| CN111143681A (en) * | 2019-12-27 | 2020-05-12 | 中国银行股份有限公司 | Information recommendation device, method, equipment and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110020162B (en) | User identification method and device | |
| US20130185106A1 (en) | Using social media objects for content curation, management, and engagement facilitation | |
| US20210263978A1 (en) | Intelligent interface accelerating | |
| CN107517251B (en) | Information pushing method and device | |
| CN112925973B (en) | Data processing method and device | |
| CN109155041A (en) | The recommendation based on travelling or promotion associated with socialgram is provided | |
| CN112256977B (en) | Componentized commodity recommendation method, computing device and computer storage medium | |
| CN115423555A (en) | Commodity recommendation method and device, electronic equipment and storage medium | |
| CN112749323A (en) | Method and device for constructing user portrait | |
| CN112650942A (en) | Product recommendation method, device, computer system and computer-readable storage medium | |
| CN113780915A (en) | Service docking method and device | |
| CN113744009A (en) | Target object output method and device, computer readable medium and electronic equipment | |
| CN112784861A (en) | Similarity determination method and device, electronic equipment and storage medium | |
| CN110544140A (en) | method and device for processing browsing data | |
| CN113313542B (en) | Method and device for pushing channel pages | |
| US11500950B2 (en) | Digital search results generation | |
| CN114677174A (en) | Method and device for calculating sales volume of unladen articles | |
| CN113821715A (en) | Method and device for determining push information | |
| CN110838019A (en) | Method and device for determining trial supply distribution crowd | |
| CN115115313A (en) | Order aging management method and device | |
| CN113762994B (en) | User operation management method and device | |
| EP3449454A1 (en) | Emphasizing communication based on past interaction related to promoted items | |
| CN111488537A (en) | Page display method and device | |
| CN113159877A (en) | Data processing method, device, system and computer readable storage medium | |
| CN110738538A (en) | Method and device for identifying similar articles |
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 |