CN115170212B - Private domain operation data management method based on chain brands and related device - Google Patents
Private domain operation data management method based on chain brands and related device Download PDFInfo
- Publication number
- CN115170212B CN115170212B CN202211095475.4A CN202211095475A CN115170212B CN 115170212 B CN115170212 B CN 115170212B CN 202211095475 A CN202211095475 A CN 202211095475A CN 115170212 B CN115170212 B CN 115170212B
- Authority
- CN
- China
- Prior art keywords
- user
- brand
- data
- users
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Abstract
The invention relates to the field of data processing, and discloses a private area operation data management method based on chain brands and a related device, which are used for improving the accuracy of private area operation data management of chain brands. The method comprises the following steps: extracting characteristic information of the user private domain data to obtain user characteristic information corresponding to each brand user; calculating the user group distribution of the target linked brands according to the user characteristic information corresponding to each brand user; dividing the user groups of the plurality of brand users based on the user group distribution to obtain a plurality of user groups; respectively obtaining group interaction data of the user groups, generating a user preference model according to the group interaction data, and performing user preference management on the brand users through the user preference model.
Description
Technical Field
The invention relates to the field of data processing, in particular to a private domain operation data management method based on chain brands and a related device.
Background
In recent years, off-line brick-and-mortar merchants, traditional e-commerce, short video e-commerce, live e-commerce, or private-domain-based social e-commerce have been slowing down in the face of traffic growth and rising user traffic costs. Under new trends, linked brands are required to have the ability to be systematically marketed in the global traffic pool of public and private domains.
At present, more and more chain brands try private domain marketing, and merchants can better systematically manage the user marketing system by self-building a private domain flow operation system and combining a public domain flow centralized merchant platform, but at present, the accuracy rate of recommending commodities to users is lower in the aspect of private domain operation data management of chain brands.
Disclosure of Invention
The invention provides a private domain operation data management method based on chain brands and a related device, which are used for improving the accuracy of the private domain operation data management of the chain brands.
The invention provides a private domain operation data management method based on chain brands, which comprises the following steps: acquiring target operation data corresponding to a target chain brand from a preset private operation data management platform; extracting a plurality of brand users in the target operation data according to preset user information identification, and respectively determining user private domain data corresponding to each brand user; extracting feature information of the user private domain data to obtain user feature information corresponding to each brand user; calculating the user group distribution of the target linked brands according to the user characteristic information corresponding to each brand user; performing user group division on the plurality of brand users based on the user group distribution to obtain a plurality of user groups; respectively obtaining group interaction data of the user groups, generating a user preference model according to the group interaction data, and performing user preference management on the brand users through the user preference model.
Optionally, in a first implementation manner of the first aspect of the present invention, the calculating, according to the user characteristic information corresponding to each brand user, a user group distribution of the target linked brand, includes: calculating target association degrees among the plurality of brand users based on a preset association degree calculation strategy and user characteristic information corresponding to each brand user; generating a probability distribution diagram according to the target relevance among the plurality of brand users; and generating the user group distribution of the target linked brands according to the probability distribution map.
Optionally, in a second implementation manner of the first aspect of the present invention, the calculating a target association degree between the plurality of brand users based on a preset association degree calculation policy and user characteristic information corresponding to each brand user includes: acquiring target material information of preset index values from user characteristic information corresponding to each brand user based on a preset association degree calculation strategy; and calling a preset relevance model to calculate the relevance of the target material information to obtain the target relevance among the plurality of brand users.
Optionally, in a third implementation manner of the first aspect of the present invention, the method for managing the private domain operation data based on the linked brands further includes: and creating a target association model corresponding to the plurality of brand users according to the target association degree.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the dividing the user groups of the plurality of brand users based on the user group distribution to obtain a plurality of user groups includes: analyzing the characteristic points of the user group distribution based on the correlation model to obtain a plurality of characteristic distribution points corresponding to the user group distribution; respectively calculating the distribution weight of the plurality of characteristic distribution points to obtain the distribution weight corresponding to each characteristic distribution point; and carrying out user group division on the plurality of brand users according to the distribution weight corresponding to each feature distribution point to obtain a plurality of user groups.
Optionally, in a fifth implementation manner of the first aspect of the present invention, the respectively obtaining group interaction data of the multiple user groups, generating a user preference model according to the group interaction data, and performing user preference management on the multiple brand users through the user preference model includes: respectively acquiring group interaction data of the user groups, wherein the group interaction data comprises: the method comprises the following steps of (1) carrying out social customer proportion, social transaction data, social data arrangement, social marketing data and a social activity trend; generating a user preference model according to the group interaction data; and pushing the user preference of the plurality of brand users through the user preference model so as to manage the user preference of the plurality of brand users.
Optionally, in a sixth implementation manner of the first aspect of the present invention, the performing, by the user preference model, user preference pushing on the multiple brand users to perform user preference management on the multiple brand users includes: inquiring the purchasing data of the chain brand materials corresponding to each brand user; matching materials to be pushed to the plurality of brand users according to the chain brand material purchasing data to obtain the materials to be pushed; calculating the preference value of the material to be pushed based on the user preference model, and pushing the user preference of the plurality of brand users according to the preference value so as to manage the user preference of the plurality of brand users.
A second aspect of the present invention provides a linked brand-based private operation data management apparatus, including: the acquisition module is used for acquiring target operation data corresponding to the target chain brand from a preset private operation data management platform; the analysis module is used for extracting a plurality of brand users in the target operation data according to preset user information identification, and respectively determining user private domain data corresponding to each brand user; the extraction module is used for extracting the characteristic information of the user private domain data to obtain the user characteristic information corresponding to each brand user; the computing module is used for computing the user group distribution of the target linked brands according to the user characteristic information corresponding to each brand user; the dividing module is used for dividing the user groups of the brand users based on the user group distribution to obtain a plurality of user groups; and the generating module is used for respectively acquiring group interaction data of the user groups, generating a user preference model according to the group interaction data, and performing user preference management on the brand users through the user preference model.
Optionally, in a first implementation manner of the second aspect of the present invention, the calculation module further includes: the calculating unit is used for calculating target association degrees among the plurality of brand users based on a preset association degree calculating strategy and user characteristic information corresponding to each brand user; the generating unit is used for generating a probability distribution map according to the target relevance among the plurality of brand users; and the processing unit is used for generating the user group distribution of the target linked brands according to the probability distribution map.
Optionally, in a second implementation manner of the second aspect of the present invention, the computing unit is specifically configured to: acquiring target material information of preset index values from user characteristic information corresponding to each brand user based on a preset association degree calculation strategy; and calling a preset relevance model to calculate the relevance of the target material information to obtain the target relevance among the plurality of brand users.
Optionally, in a third implementation manner of the second aspect of the present invention, the device for managing linked brands based on private domain operation data further includes: and the creating module is used for creating a target association model corresponding to the plurality of brand users according to the target association degree.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the dividing module is specifically configured to: analyzing the characteristic points of the user group distribution based on the correlation model to obtain a plurality of characteristic distribution points corresponding to the user group distribution; respectively calculating the distribution weight of the plurality of characteristic distribution points to obtain the distribution weight corresponding to each characteristic distribution point; and carrying out user group division on the plurality of brand users according to the distribution weight corresponding to each feature distribution point to obtain a plurality of user groups.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the generating module further includes: an obtaining unit, configured to obtain group interaction data of the plurality of user groups, respectively, where the group interaction data includes: the method comprises the steps of (1) carrying out social customer proportion, social transaction data, social data arrangement, social marketing data and social activity trend; generating a user preference model according to the group interaction data; and the pushing unit is used for pushing the user preferences of the plurality of brand users through the user preference model so as to manage the user preferences of the plurality of brand users.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the pushing unit is specifically configured to: inquiring the purchasing data of the chain brand materials corresponding to each brand user; matching materials to be pushed to the plurality of brand users according to the chain brand material purchase data to obtain the materials to be pushed; calculating the preference value of the material to be pushed based on the user preference model, and pushing the user preference of the plurality of brand users according to the preference value so as to manage the user preference of the plurality of brand users.
The third aspect of the present invention provides a private domain operation data management device based on chain brands, including: a memory and at least one processor, the memory having instructions stored therein; the at least one processor calls the instructions in the memory to enable the linked brand-based private area operation data management device to execute the linked brand-based private area operation data management method.
A fourth aspect of the present invention provides a computer-readable storage medium, which stores instructions that, when executed on a computer, cause the computer to perform the above-mentioned linked-brand-based private business data management method.
In the technical scheme provided by the invention, the characteristic information of the private domain data of the user is extracted to obtain the user characteristic information corresponding to each brand user; calculating user group distribution of the target linked brands according to the user characteristic information corresponding to each brand user; dividing a plurality of brand users into user groups based on user group distribution to obtain a plurality of user groups; the method comprises the steps of respectively obtaining group interaction data of a plurality of user groups, generating a user preference model according to the group interaction data, and carrying out user preference management on a plurality of brand users through the user preference model. According to the invention, the user private domain data is subjected to characteristic analysis, then the characteristic information of the user on the private domain is obtained, then the user group division is carried out according to the characteristic information, so that the group interaction data of the user can be more accurately obtained, and finally, the user preference model is constructed through the group interaction data to carry out user preference pushing and management, so that the accuracy of user preference pushing is improved, and further, the accuracy of private domain management data management of linked brands is improved.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a method for managing linked-brand-based private domain operation data according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of another embodiment of a method for managing linked-brand-based private domain operation data according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an embodiment of a linked-brand-based private-domain-operation data management apparatus according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of another embodiment of a private domain operation data management apparatus based on linked brands according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of an embodiment of a linked-brand-based private-domain-operation data management device in the embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a method and a related device for managing private domain operation data based on chain brands, which are used for improving the accuracy of the private domain operation data management of the chain brands. The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be implemented in other sequences than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For convenience of understanding, a specific flow of the embodiment of the present invention is described below, and referring to fig. 1, an embodiment of the method for managing the private domain operation data based on the linked brands in the embodiment of the present invention includes:
101. acquiring target operation data corresponding to a target chain brand from a preset private operation data management platform;
it is understood that the execution subject of the present invention may be a private operation data management device based on linked brands, and may also be a terminal or a server, which is not limited herein. The embodiment of the present invention is described by taking a server as an execution subject.
Specifically, the online access amount of the product of the corresponding linked brand in a preset unit time is obtained from the private domain data management platform. The unit time may be hourly, daily, weekly, monthly, or the like. When the operation data is obtained, the server firstly carries out data identification matching on target chain brands, determines corresponding data identifications, extracts the operation data through the data identifications, and obtains the corresponding target operation data.
102. Extracting a plurality of brand users in the target operation data according to preset user information identification, and respectively determining user private domain data corresponding to each brand user;
specifically, the server matches the current target operation data with a predetermined user information identifier, determines a brand user according to a matching result, extracts signaling information for determining user private domain data from a database according to the determined brand user, or extracts signaling information for determining user private domain data from the current database according to the brand user, and finally extracts user private domain data corresponding to each brand user respectively according to the signaling information.
103. Extracting characteristic information of the private domain data of the user to obtain user characteristic information corresponding to each brand user;
specifically, feature extraction is performed on user private domain data corresponding to each device identifier, the extracted feature information is input into a pre-trained recognition model associated with a designated user attribute, a recognition result is obtained, the recognition result includes a probability that an attribute value of the designated user attribute of a user to which the device belongs, the attribute value being indicated by the device identifier, is a preset attribute value, based on the probability in the obtained recognition result, whether an attribute value of the designated user attribute of the user to which the device belongs, the attribute value being indicated by at least one device identifier, is a preset attribute value is determined, and user feature information corresponding to each brand user is determined according to the attribute value.
104. Calculating user group distribution of the target linked brands according to the user characteristic information corresponding to each brand user;
specifically, the method includes the steps of obtaining current feature information of each brand user, enabling the feature information to include an identity of the brand user, conducting unsupervised classification on the brand users according to feature data, dividing the brand users into a preset number of brand user groups, analyzing preference information of the brand user groups according to the feature information of each brand user in the brand user groups, inquiring preference information of the brand users corresponding to a target identity after the target identity is received in a current period, and calculating user group distribution of target linked brands according to the preference information, so that occupation of computing resources can be reduced, and cost is reduced.
105. Dividing a plurality of brand users into user groups based on user group distribution to obtain a plurality of user groups;
specifically, the server determines user group distribution of the division rules, trains to obtain a classification model according to the user group distribution, determines a target user feature set and an optimal division point corresponding to each user feature in the target user feature set according to the user group distribution and the classification model, and finally obtains the target division rules according to the optimal division points corresponding to each user feature in the target user feature set, so as to perform group division on the users to obtain a plurality of user groups.
106. The method comprises the steps of respectively obtaining group interaction data of a plurality of user groups, generating a user preference model according to the group interaction data, and carrying out user preference management on a plurality of brand users through the user preference model.
Specifically, the server constructs a scoring matrix of the user to the group interaction data, processes a user group interaction data set to obtain a group interaction data embedding matrix, constructs a bipartite graph based on content attributes according to the scoring matrix, inputs the constructed bipartite graph into a graph convolution network, continuously updates the group interaction data embedding matrix, calculates a preference predicted value of the user to a segment by using the graph convolution network, generates a user preference model according to the group interaction data, performs user preference management on a plurality of brand users through the user preference model, and can perform more accurate recommendation on the user.
In the embodiment of the invention, the characteristic information of the private domain data of the user is extracted to obtain the user characteristic information corresponding to each brand user; calculating user group distribution of the target linked brands according to the user characteristic information corresponding to each brand user; dividing a plurality of brand users into user groups based on user group distribution to obtain a plurality of user groups; the method comprises the steps of respectively obtaining group interaction data of a plurality of user groups, generating a user preference model according to the group interaction data, and carrying out user preference management on a plurality of brand users through the user preference model. According to the invention, the user private domain data is subjected to characteristic analysis, then the characteristic information of the user on the private domain is obtained, then the user group division is carried out according to the characteristic information, so that the group interaction data of the user can be more accurately obtained, and finally, the user preference model is constructed through the group interaction data to carry out user preference pushing and management, so that the accuracy of user preference pushing is improved, and further, the accuracy of private domain management data management of linked brands is improved.
Referring to fig. 2, another embodiment of the method for managing the private domain operation data based on the linked brands according to the embodiment of the present invention includes:
201. acquiring target operation data corresponding to a target chain brand from a preset private operation data management platform;
202. extracting a plurality of brand users in the target operation data according to preset user information identification, and respectively determining user private domain data corresponding to each brand user;
203. extracting characteristic information of the private domain data of the user to obtain user characteristic information corresponding to each brand user;
specifically, the online visit volume of the product of the corresponding linked brand in a preset unit time is obtained from the private domain data management platform. The preset unit time may be every hour, every day, every week, every month, or the like. The method comprises the steps that currently, the latest acquired online access amount is obtained, when operation data are acquired, a server firstly performs data identification matching on a target chain brand, determines a corresponding data identification, extracts operation data through the data identification, acquires the corresponding target operation data, matches the current target operation data with a predetermined user information identification, determines brand users according to matching results, extracts signaling information used for determining user private domain data from a database according to the determined brand users, or extracts signaling information used for determining the user private domain data from the current database according to the brand users, and respectively extracts user private domain data corresponding to each brand user according to the signaling information.
204. Calculating target association degrees among a plurality of brand users based on a preset association degree calculation strategy and user characteristic information corresponding to each brand user;
specifically, target material information of a preset index value is obtained from user characteristic information corresponding to each brand user based on a preset association degree calculation strategy; and calling a preset relevance model to calculate the relevance of the target material information to obtain the target relevance among a plurality of brand users.
The server acquires feature data, consumption behavior data and marketing strategy data of brand clients from a preset database, determines target material information with preset index values between different features and consumption behaviors according to the feature data and the consumption behavior data, determines target features from the different features according to the target material information, determines clients with the target features in the brand clients as target clients, determines sensitivity data of the target clients to different marketing strategies according to the feature data, the consumption behavior data and the marketing strategy data, and determines target relevance between the target clients and a plurality of brand users from the different marketing strategies according to the sensitivity data.
Optionally, the server may also create a target association model corresponding to multiple brand users according to the target association degree.
It should be noted that when the server creates a model according to the target association degree, the server determines a corresponding convolutional network according to the target association degree, further obtains multiple groups of training data to train the convolutional network, and simultaneously calls a preset loss function to optimize the trained convolutional network, so as to finally obtain target association models corresponding to multiple brand users.
205. Generating a probability distribution map according to the target relevance among the plurality of brand users;
206. generating user group distribution of the target linked brands according to the probability distribution map;
specifically, the server obtains the target association degree of the brand users and carries out initialization processing, the Markov chain method is adopted to calculate the steady-state probability of data with the association degree, the linear Kriging method is adopted to carry out interpolation estimation on the steady-state probability of other data association, the brand user association probability space distribution map is drawn according to all the data association steady-state probabilities, the probability distribution map is generated at the same time, the user group distribution of the target linked brands is generated according to the probability distribution map, and the probability distribution of data association can be efficiently obtained while high precision is guaranteed.
207. Dividing a plurality of brand users into user groups based on user group distribution to obtain a plurality of user groups;
specifically, feature point analysis is carried out on the user group distribution based on the association model to obtain a plurality of feature distribution points corresponding to the user group distribution; respectively calculating the distribution weight of the plurality of characteristic distribution points to obtain the distribution weight corresponding to each characteristic distribution point; and carrying out user group division on the plurality of brand users according to the distribution weight corresponding to each feature distribution point to obtain a plurality of user groups.
Optionally, the server may further divide the user group distribution into a plurality of groups, and quantize the active feature points in each group, where the server obtains feature points and an account set participating in feature propagation based on a keyword of a specific event, constructs a participating account table by inputting the feature points of a single feature and the account set participating in the feature, generates a model for each feature in the sample library based on a subject probability, extracts words and participating accounts from the constructed vocabulary table and the participating account table according to a group-subject, a subject-word and a group-person in the model, performs calculation by using a gibbs sampling method, sorts words included under each subject and accounts included in each group by using a merge-sort algorithm, and performs user group division on a plurality of brand users according to a distribution weight corresponding to each feature distribution point, thereby obtaining a plurality of user groups.
208. The method comprises the steps of respectively obtaining group interaction data of a plurality of user groups, generating a user preference model according to the group interaction data, and carrying out user preference management on a plurality of brand users through the user preference model.
Specifically, group interaction data of a plurality of user groups are respectively obtained, wherein the group interaction data include: the method comprises the steps of (1) carrying out social customer proportion, social transaction data, social data arrangement, social marketing data and social activity trend; generating a user preference model according to group interaction data; and carrying out user preference pushing on a plurality of brand users through a user preference model so as to carry out user preference management on the plurality of brand users.
The method comprises the steps that a server determines a preset number of task response active users, respectively obtains historical push data sets of all the task response active users, establishes an acceptance probability logistic regression model according to the historical push data sets, estimates historical task acceptance probability according to the active user data and the historical task data by using the acceptance probability logistic regression model, estimates user likelihood degree of the task response active users according to the historical task acceptance probability and response result label data, determines a high-preference target user from the preset number of task response active users according to the user likelihood degree corresponding to the preset number of task response active users, and pushes user preference of a plurality of brand users through a user preference model so as to manage the user preference of the plurality of brand users.
Specifically, inquiring the chain brand material purchasing data corresponding to each brand user; matching materials to be pushed to a plurality of brand users according to the chain brand material purchase data to obtain the materials to be pushed; calculating a preference value of the material to be pushed based on a user preference model, and pushing user preference of a plurality of brand users according to the preference value so as to manage the user preference of the plurality of brand users.
The method comprises the steps of obtaining preference characteristic data and correlation characteristic data of brand users, respectively carrying out quantization processing on the preference characteristic data and the correlation characteristic data to obtain preference quantization data and correlation quantization data, inputting the preference quantization data and the correlation quantization data characteristic data into a preset user behavior model to obtain a material to be pushed; calculating a preference value of the material to be pushed based on a user preference model, and pushing user preference of a plurality of brand users according to the preference value so as to manage the user preference of the brand users.
In the embodiment of the invention, the characteristic information of the private domain data of the user is extracted to obtain the user characteristic information corresponding to each brand user; calculating user group distribution of the target linked brands according to the user characteristic information corresponding to each brand user; dividing a plurality of brand users into user groups based on user group distribution to obtain a plurality of user groups; the method comprises the steps of respectively obtaining group interaction data of a plurality of user groups, generating a user preference model according to the group interaction data, and carrying out user preference management on a plurality of brand users through the user preference model. According to the invention, the user private domain data is subjected to characteristic analysis, then the characteristic information of the user on the private domain is obtained, then the user group division is carried out according to the characteristic information, so that the group interaction data of the user can be more accurately obtained, and finally, the user preference model is constructed through the group interaction data to carry out user preference pushing and management, so that the accuracy of user preference pushing is improved, and further, the accuracy of private domain management data management of linked brands is improved.
In the above description of the method for managing the private domain operation data based on the linked brands in the embodiment of the present invention, referring to fig. 3, a device for managing the private domain operation data based on the linked brands in the embodiment of the present invention is described below, and an embodiment of the device for managing the private domain operation data based on the linked brands in the embodiment of the present invention includes:
an obtaining module 301, configured to obtain target operation data corresponding to a target chain brand from a preset private domain operation data management platform;
an analysis module 302, configured to extract multiple brand users in the target operation data according to preset user information identifiers, and determine user private domain data corresponding to each brand user respectively;
an extracting module 303, configured to perform feature information extraction on the user private domain data to obtain user feature information corresponding to each brand user;
the calculating module 304 is configured to calculate user group distribution of the target linked brands according to user characteristic information corresponding to each brand user;
a dividing module 305, configured to divide the user groups of the multiple brand users based on the user group distribution to obtain multiple user groups;
the generating module 306 is configured to obtain group interaction data of the plurality of user groups, generate a user preference model according to the group interaction data, and perform user preference management on the plurality of brand users through the user preference model.
In the embodiment of the invention, the characteristic information of the private domain data of the user is extracted to obtain the user characteristic information corresponding to each brand user; calculating user group distribution of the target linked brands according to the user characteristic information corresponding to each brand user; dividing a plurality of brand users into user groups based on user group distribution to obtain a plurality of user groups; the method comprises the steps of respectively obtaining group interaction data of a plurality of user groups, generating a user preference model according to the group interaction data, and carrying out user preference management on a plurality of brand users through the user preference model. According to the invention, the user private domain data is subjected to characteristic analysis, then the characteristic information of the user on the private domain is obtained, then the user group division is carried out according to the characteristic information, so that the group interaction data of the user can be more accurately obtained, and finally, the user preference model is constructed through the group interaction data to carry out user preference pushing and management, so that the accuracy of user preference pushing is improved, and further, the accuracy of private domain management data management of linked brands is improved.
Referring to fig. 4, another embodiment of the device for managing private domain operation data based on linked brands according to the present invention includes:
an obtaining module 301, configured to obtain target operation data corresponding to a target chain brand from a preset private operation data management platform;
an analysis module 302, configured to extract multiple brand users in the target operation data according to preset user information identifiers, and determine user private domain data corresponding to each brand user respectively;
an extracting module 303, configured to perform feature information extraction on the user private domain data to obtain user feature information corresponding to each brand user;
the calculating module 304 is configured to calculate user group distribution of the target linked brands according to user characteristic information corresponding to each brand user;
a dividing module 305, configured to divide the user groups of the multiple brand users based on the user group distribution to obtain multiple user groups;
the generating module 306 is configured to obtain group interaction data of the plurality of user groups, generate a user preference model according to the group interaction data, and perform user preference management on the plurality of brand users through the user preference model.
Optionally, the calculating module 304 further includes:
the calculating unit is used for calculating target association degrees among the plurality of brand users based on a preset association degree calculating strategy and user characteristic information corresponding to each brand user;
the generating unit is used for generating a probability distribution graph according to the target association degree among the plurality of brand users;
and the processing unit is used for generating the user group distribution of the target linked brands according to the probability distribution map.
Optionally, the computing unit is specifically configured to:
acquiring target material information of preset index values from user characteristic information corresponding to each brand user based on a preset association degree calculation strategy; and calling a preset relevance model to calculate the relevance of the target material information to obtain the target relevance among the plurality of brand users.
Optionally, the chain brand-based private area operation data management apparatus further includes:
a creating module 307, configured to create a target association model corresponding to the plurality of brand users according to the target association degree.
Optionally, the dividing module 305 is specifically configured to:
analyzing the characteristic points of the user group distribution based on the correlation model to obtain a plurality of characteristic distribution points corresponding to the user group distribution; respectively calculating the distribution weight of the plurality of characteristic distribution points to obtain the distribution weight corresponding to each characteristic distribution point; and carrying out user group division on the plurality of brand users according to the distribution weight corresponding to each feature distribution point to obtain a plurality of user groups.
Optionally, the generating module 306 further includes:
an obtaining unit, configured to obtain group interaction data of the plurality of user groups, respectively, where the group interaction data includes: the method comprises the steps of (1) carrying out social customer proportion, social transaction data, social data arrangement, social marketing data and social activity trend; generating a user preference model according to the group interaction data;
and the pushing unit is used for pushing the user preferences of the plurality of brand users through the user preference model so as to manage the user preferences of the plurality of brand users.
Optionally, the pushing unit is specifically configured to:
inquiring chain brand material purchasing data corresponding to each brand user; matching materials to be pushed to the plurality of brand users according to the chain brand material purchasing data to obtain the materials to be pushed; calculating the preference value of the material to be pushed based on the user preference model, and pushing the user preference of the plurality of brand users according to the preference value so as to manage the user preference of the plurality of brand users.
In the embodiment of the invention, the characteristic information of the private domain data of the user is extracted to obtain the user characteristic information corresponding to each brand user; calculating user group distribution of the target linked brands according to the user characteristic information corresponding to each brand user; dividing a plurality of brand users into user groups based on user group distribution to obtain a plurality of user groups; the method comprises the steps of respectively obtaining group interaction data of a plurality of user groups, generating a user preference model according to the group interaction data, and carrying out user preference management on a plurality of brand users through the user preference model. According to the invention, the user private domain data is subjected to characteristic analysis, then the characteristic information of the user on the private domain is obtained, then the user group division is carried out according to the characteristic information, so that the group interaction data of the user can be more accurately obtained, and finally, the user preference model is constructed through the group interaction data to carry out user preference pushing and management, so that the accuracy of user preference pushing is improved, and further, the accuracy of private domain management data management of linked brands is improved.
Fig. 3 and fig. 4 describe the chain-brands-based private domain operation data management apparatus in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the chain-brands-based private domain operation data management apparatus in the embodiment of the present invention is described in detail from the perspective of hardware processing.
Fig. 5 is a schematic structural diagram of a chained brand-based private area administration data management apparatus 500 according to an embodiment of the present invention, which may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 510 (e.g., one or more processors) and a memory 520, and one or more storage media 530 (e.g., one or more mass storage devices) storing applications 533 or data 532. Memory 520 and storage media 530 may be, among other things, transient or persistent storage. The program stored on the storage medium 530 may include one or more modules (not shown), each of which may include a series of instructions for operating on the linked brand-based private domain administration data management apparatus 500. Still further, the processor 510 may be configured to communicate with the storage medium 530 to execute a series of instruction operations in the storage medium 530 on the linked brand-based private territory administration data management device 500.
The chain brand-based private domain operation data management apparatus 500 may further include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input-output interfaces 560, and/or one or more operating systems 531, such as Windows server, mac OS X, unix, linux, freeBSD, and the like. Those skilled in the art will appreciate that the linked brand-based private area operation data management device structure shown in fig. 5 does not constitute a limitation of the linked brand-based private area operation data management device, and may include more or less components than those shown, or some components in combination, or different component arrangements.
The invention also provides a linked brand-based private area operation data management device, which comprises a memory and a processor, wherein the memory stores computer readable instructions, and when the computer readable instructions are executed by the processor, the processor executes the steps of the linked brand-based private area operation data management method in the embodiments.
The invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, or a volatile computer readable storage medium, having stored therein instructions, which when run on a computer, cause the computer to perform the steps of the linked-brand-based private-domain-management-data-management method.
Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention, which is substantially or partly contributed by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (6)
1. A method for managing private domain operation data based on chain brands is characterized by comprising the following steps:
acquiring target operation data corresponding to a target chain brand from a preset private operation data management platform;
extracting a plurality of brand users in the target operation data according to preset user information identification, and respectively determining user private domain data corresponding to each brand user;
extracting characteristic information of the user private domain data to obtain user characteristic information corresponding to each brand user;
calculating the user group distribution of the target linked brands according to the user characteristic information corresponding to each brand user; wherein, the calculating the user group distribution of the target linked brands according to the user characteristic information corresponding to each brand user comprises: calculating target association degrees among the plurality of brand users based on a preset association degree calculation strategy and user characteristic information corresponding to each brand user; generating a probability distribution diagram according to the target relevance among the plurality of brand users; generating user group distribution of the target linked brands according to the probability distribution map; wherein the calculating of the target relevance between the plurality of brand users based on the preset relevance calculating strategy and the user characteristic information corresponding to each brand user comprises: acquiring target material information of preset index values from user characteristic information corresponding to each brand user based on a preset association degree calculation strategy; calling a preset relevance model to calculate the relevance of the target material information to obtain the target relevance among the plurality of brand users; specifically, feature data, consumption behavior data and marketing strategy data of brand clients are obtained from a preset database, target material information of preset index values between different features and consumption behaviors is determined according to the feature data and the consumption behavior data, target features are determined from the different features according to the target material information, the clients with the target features in the brand clients are determined as target clients, sensitivity data of the target clients to different marketing strategies is determined according to the feature data, the consumption behavior data and the marketing strategy data, and target association degrees with multiple brand users are determined from the different marketing strategies according to the sensitivity data;
performing user group division on the plurality of brand users based on the user group distribution to obtain a plurality of user groups;
respectively acquiring group interaction data of the user groups, generating a user preference model according to the group interaction data, and performing user preference management on the brand users through the user preference model; the method for respectively acquiring group interaction data of the plurality of user groups, generating a user preference model according to the group interaction data, and performing user preference management on the plurality of brand users through the user preference model comprises the following steps: respectively acquiring group interaction data of the plurality of user groups, wherein the group interaction data comprises: the method comprises the steps of (1) carrying out social customer proportion, social transaction data, social data arrangement, social marketing data and social activity trend; generating a user preference model according to the group interaction data; performing user preference pushing on the plurality of brand users through the user preference model so as to perform user preference management on the plurality of brand users; the method comprises the steps that a server determines a preset number of task response active users, respectively obtains a history push data set of each task response active user, establishes an acceptance probability logistic regression model according to the history push data set, estimates a history task acceptance probability according to active user data and history task data by using the acceptance probability logistic regression model, estimates a user likelihood degree of the task response active users according to the history task acceptance probability and response result label data, determines a high-preference target user from the preset number of task response active users according to the user likelihood degree corresponding to each preset number of task response active users, and pushes user preferences of a plurality of brand users through a user preference model so as to manage the user preferences of the plurality of brand users; the pushing of the user preference of the plurality of brand users through the user preference model to perform user preference management on the plurality of brand users comprises the following steps: inquiring the purchasing data of the chain brand materials corresponding to each brand user; matching materials to be pushed to the plurality of brand users according to the chain brand material purchase data to obtain the materials to be pushed; calculating preference values of the materials to be pushed based on the user preference model, and pushing user preferences of the plurality of brand users according to the preference values so as to manage the user preferences of the plurality of brand users; the method comprises the steps of obtaining preference characteristic data and correlation characteristic data of brand users, respectively carrying out quantization processing on the preference characteristic data and the correlation characteristic data to obtain preference quantization data and correlation quantization data, inputting the preference quantization data and the correlation quantization data characteristic data into a preset user behavior model to obtain a material to be pushed; calculating a preference value of the material to be pushed based on a user preference model, and pushing user preference of a plurality of brand users according to the preference value so as to manage the user preference of the plurality of brand users.
2. The linked-brand-based private domain operation data management method according to claim 1, further comprising:
and creating a target association model corresponding to the plurality of brand users according to the target association degree.
3. The method according to claim 2, wherein the dividing the user groups of the plurality of brand users based on the user group distribution to obtain a plurality of user groups comprises:
analyzing the characteristic points of the user group distribution based on the correlation model to obtain a plurality of characteristic distribution points corresponding to the user group distribution;
respectively calculating the distribution weight of the plurality of characteristic distribution points to obtain the distribution weight corresponding to each characteristic distribution point;
and carrying out user group division on the plurality of brand users according to the distribution weight corresponding to each feature distribution point to obtain a plurality of user groups.
4. A chain-brand-based private operation data management device is characterized by comprising:
the acquisition module is used for acquiring target operation data corresponding to the target chain brand from a preset private operation data management platform;
the analysis module is used for extracting a plurality of brand users in the target operation data according to preset user information identification and respectively determining user private domain data corresponding to each brand user;
the extraction module is used for extracting the characteristic information of the user private domain data to obtain the user characteristic information corresponding to each brand user;
the calculation module is used for calculating the user group distribution of the target linked brands according to the user characteristic information corresponding to each brand user; wherein, the calculating the user group distribution of the target linked brands according to the user characteristic information corresponding to each brand user comprises: calculating target association degrees among the plurality of brand users based on a preset association degree calculation strategy and user characteristic information corresponding to each brand user; generating a probability distribution diagram according to the target relevance among the plurality of brand users; generating user group distribution of the target linked brands according to the probability distribution map; wherein the calculating of the target relevance between the plurality of brand users based on the preset relevance calculating strategy and the user characteristic information corresponding to each brand user comprises: acquiring target material information of preset index values from user characteristic information corresponding to each brand user based on a preset association degree calculation strategy; calling a preset relevance model to calculate the relevance of the target material information to obtain the target relevance among the plurality of brand users; specifically, feature data, consumption behavior data and marketing strategy data of brand clients are obtained from a preset database, target material information with preset index values between different features and consumption behaviors is determined according to the feature data and the consumption behavior data, target features are determined from the different features according to the target material information, clients with the target features in the brand clients are determined as target clients, sensitivity data of the target clients to different marketing strategies is determined according to the feature data, the consumption behavior data and the marketing strategy data, and target relevance between the target clients and a plurality of brand users is determined from the different marketing strategies according to the sensitivity data;
the dividing module is used for dividing the user groups of the brand users based on the user group distribution to obtain a plurality of user groups;
the generating module is used for respectively acquiring group interaction data of the plurality of user groups, generating a user preference model according to the group interaction data, and performing user preference management on the plurality of brand users through the user preference model; the method for respectively acquiring group interaction data of the plurality of user groups, generating a user preference model according to the group interaction data, and performing user preference management on the plurality of brand users through the user preference model comprises the following steps: respectively acquiring group interaction data of the user groups, wherein the group interaction data comprises: the method comprises the steps of (1) carrying out social customer proportion, social transaction data, social data arrangement, social marketing data and social activity trend; generating a user preference model according to the group interaction data; performing user preference pushing on the plurality of brand users through the user preference model so as to perform user preference management on the plurality of brand users; the method comprises the steps that a server determines a preset number of task response active users, respectively obtains a history push data set of each task response active user, establishes an acceptance probability logistic regression model according to the history push data set, estimates a history task acceptance probability according to active user data and history task data by using the acceptance probability logistic regression model, estimates a user likelihood degree of the task response active users according to the history task acceptance probability and response result label data, determines a high-preference target user from the preset number of task response active users according to the user likelihood degree corresponding to each preset number of task response active users, and pushes user preferences of a plurality of brand users through a user preference model so as to manage the user preferences of the plurality of brand users; the pushing of the user preference of the plurality of brand users through the user preference model to perform user preference management on the plurality of brand users comprises the following steps: inquiring the purchasing data of the chain brand materials corresponding to each brand user; matching materials to be pushed to the plurality of brand users according to the chain brand material purchase data to obtain the materials to be pushed; calculating preference values of the materials to be pushed based on the user preference model, and pushing user preferences of the plurality of brand users according to the preference values so as to manage the user preferences of the plurality of brand users; the method comprises the steps of obtaining preference characteristic data and correlation characteristic data of brand users, respectively carrying out quantization processing on the preference characteristic data and the correlation characteristic data to obtain preference quantization data and correlation quantization data, inputting the preference quantization data and the correlation quantization data characteristic data into a preset user behavior model to obtain a material to be pushed; calculating a preference value of the material to be pushed based on a user preference model, and pushing user preference of a plurality of brand users according to the preference value so as to manage the user preference of the plurality of brand users.
5. A chain-brand-based private operation data management device is characterized by comprising: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invokes the instructions in the memory to cause the linked-brand private domain operation data management apparatus to perform the linked-brand private domain operation data management method according to any one of claims 1 to 3.
6. A computer readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, implement the linked brand-based private domain operation data management method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211095475.4A CN115170212B (en) | 2022-09-08 | 2022-09-08 | Private domain operation data management method based on chain brands and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211095475.4A CN115170212B (en) | 2022-09-08 | 2022-09-08 | Private domain operation data management method based on chain brands and related device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115170212A CN115170212A (en) | 2022-10-11 |
| CN115170212B true CN115170212B (en) | 2022-11-25 |
Family
ID=83482338
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211095475.4A Active CN115170212B (en) | 2022-09-08 | 2022-09-08 | Private domain operation data management method based on chain brands and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115170212B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019149021A1 (en) * | 2018-02-01 | 2019-08-08 | 阿里巴巴集团控股有限公司 | Data processing method and apparatus for claims settlement service, and electronic device and server |
| CN111598648A (en) * | 2020-04-16 | 2020-08-28 | 上海源慧信息科技股份有限公司 | Full-link online marketing method based on fast-moving industrial commodities |
| CN112365285A (en) * | 2020-11-13 | 2021-02-12 | 上海源慧信息科技股份有限公司 | Full link marketing method based on private domain flow pool data |
| CN112465598A (en) * | 2020-12-04 | 2021-03-09 | 中国移动通信集团黑龙江有限公司 | User portrait generation method, device and equipment and computer storage medium |
| CN114926228A (en) * | 2022-06-14 | 2022-08-19 | 上海天擎天拓软件技术有限公司 | Group marketing method and group marketing system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114663186A (en) * | 2022-03-24 | 2022-06-24 | 鲸灵云(杭州)智能有限公司 | Commodity recommendation method, system and storage medium applied to private domain and e-commerce platform |
-
2022
- 2022-09-08 CN CN202211095475.4A patent/CN115170212B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019149021A1 (en) * | 2018-02-01 | 2019-08-08 | 阿里巴巴集团控股有限公司 | Data processing method and apparatus for claims settlement service, and electronic device and server |
| CN111598648A (en) * | 2020-04-16 | 2020-08-28 | 上海源慧信息科技股份有限公司 | Full-link online marketing method based on fast-moving industrial commodities |
| CN112365285A (en) * | 2020-11-13 | 2021-02-12 | 上海源慧信息科技股份有限公司 | Full link marketing method based on private domain flow pool data |
| CN112465598A (en) * | 2020-12-04 | 2021-03-09 | 中国移动通信集团黑龙江有限公司 | User portrait generation method, device and equipment and computer storage medium |
| CN114926228A (en) * | 2022-06-14 | 2022-08-19 | 上海天擎天拓软件技术有限公司 | Group marketing method and group marketing system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115170212A (en) | 2022-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107689008A (en) | A kind of user insures the method and device of behavior prediction | |
| CN108399564B (en) | Credit scoring method and device | |
| CN110992167A (en) | Bank client business intention identification method and device | |
| CN106651213B (en) | Service order processing method and device | |
| CN110609935A (en) | User identity tag generation method and device, computer equipment and storage medium | |
| Abbasimehr et al. | A new framework for predicting customer behavior in terms of RFM by considering the temporal aspect based on time series techniques | |
| CN110942338A (en) | Marketing enabling strategy recommendation method and device and electronic equipment | |
| CN108921587B (en) | Data processing method and device and server | |
| CN107657357B (en) | Data processing method and device | |
| CN111400613A (en) | Article recommendation method, device, medium and computer equipment | |
| CN114817746A (en) | Insurance product recommendation method, device, equipment and storage medium | |
| CN111861605A (en) | Business object recommendation method | |
| CN115098650A (en) | Comment information analysis method based on historical data model and related device | |
| WO2019032239A1 (en) | Systems and methods for distributing data to node devices for real time scoring, based on accounts for the data | |
| CN111882399A (en) | Service information recommendation method, device, computer system and readable storage medium | |
| CN115170212B (en) | Private domain operation data management method based on chain brands and related device | |
| CN110796379A (en) | Risk assessment method, device and equipment of business channel and storage medium | |
| CN114372199A (en) | Business pushing method and device, storage medium and electronic equipment | |
| CN113138977A (en) | Transaction conversion analysis method, device, equipment and storage medium | |
| Kalyanakrishnan et al. | On building decision trees from large-scale data in applications of on-line advertising | |
| CN112581281A (en) | Product recommendation method and device, storage medium and electronic equipment | |
| CN112765449A (en) | Application program display method and device and storage medium | |
| US20200160408A1 (en) | Systems and methods for secure distributed crowdfunding | |
| CN111967966B (en) | Automatic wake-up method and system for sleep clients of mobile phone banks | |
| CN110059248B (en) | Recommendation method and device and server |
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 |