CN114443952A - User preference processing method and system based on electronic commerce - Google Patents
User preference processing method and system based on electronic commerce Download PDFInfo
- Publication number
- CN114443952A CN114443952A CN202111653140.5A CN202111653140A CN114443952A CN 114443952 A CN114443952 A CN 114443952A CN 202111653140 A CN202111653140 A CN 202111653140A CN 114443952 A CN114443952 A CN 114443952A
- Authority
- CN
- China
- Prior art keywords
- user preference
- distribution
- preference
- live broadcast
- feature
- 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.)
- Withdrawn
Links
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/242—Query formulation
- G06F16/2433—Query languages
- G06F16/244—Grouping and aggregation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/048—Fuzzy inferencing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Fuzzy Systems (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
According to the user preference processing method and system based on electronic commerce, provided by the embodiment of the invention, the user preference prediction is carried out on the E-commerce live broadcast interaction log to obtain the first user preference distribution, and the current live broadcast optimization component in the E-commerce live broadcast interaction log is identified by combining the treatments of preference fuzzy derivation, preference distribution aggregation, preference intention matching and the like. Thus, tracking identification can be realized for the current live broadcast optimization component, so that the live broadcast optimization index can be determined conveniently.
Description
Technical Field
The invention relates to the technical field of electronic commerce, in particular to a user preference processing method and a user preference processing system based on electronic commerce.
Background
How to realize tracking identification aiming at the current live broadcast optimization component so as to be convenient for determining the live broadcast optimization index is a technical problem to be solved urgently.
Disclosure of Invention
In view of the above, an embodiment of the present invention provides an e-commerce-based user preference processing method, including:
carrying out user preference prediction on live E-commerce interactive logs to obtain first user preference distribution, and carrying out preference fuzzy derivation on the first user preference distribution to obtain second user preference distribution;
performing first preference intention matching aiming at the current live broadcast optimization component based on the second user preference distribution to obtain a first preference intention member representing the current live broadcast optimization component, aggregating the first user preference distribution and the second user preference distribution, and performing preference fuzzy derivation on the aggregated user preference distribution to obtain a third user preference distribution;
acquiring release related metric values corresponding to member feature components in the first preference intention members; removing the member feature component of which the release related metric value is smaller than the target related metric value to obtain a removed member feature component, and performing member node distribution on the removed member feature component based on the presentation data of the removed member feature component and the presentation data corresponding to the second user preference distribution to obtain a member feature component after member node distribution;
and performing second preference intention matching on the current live broadcast optimization component based on the third user preference distribution and the member characteristic components distributed by the member nodes so as to update the member characteristic components distributed by the member nodes, and determining the current live broadcast optimization component in the E-commerce live broadcast interaction log based on the updated member characteristic components.
Optionally, the performing fuzzy preference derivation on the first user preference distribution to obtain a second user preference distribution includes:
based on a first feature mining layer of a user preference processing model, performing first user preference prediction on the first user preference distribution to obtain feature mining information of the first user preference distribution;
and performing fuzzy preference derivation on the feature mining information based on a first fuzzy preference derivation layer of the user preference processing model to obtain the second user preference distribution.
Optionally, the performing, based on the second user preference distribution, a first preference intention matching for a current live broadcast optimization component to obtain a first preference intention member characterizing the current live broadcast optimization component includes:
extracting member feature components aiming at a current live broadcast optimization component in the E-commerce live broadcast interaction log based on the second user preference distribution on the basis of a first member feature component mining layer of a user preference processing model;
clustering member characteristic components of the current live broadcast optimization component to obtain a first preference intention member representing the current live broadcast optimization component.
Optionally, the aggregating the first user preference distribution and the second user preference distribution, and performing fuzzy preference derivation on the aggregated user preference distribution to obtain a third user preference distribution includes:
loading the first user preference distribution and the second user preference distribution into a second feature mining layer of a user preference processing model;
updating the weight information of the second feature mining layer based on the first user preference distribution and the second user preference distribution to obtain updated weight information;
aggregating the first user preference distribution and the second user preference distribution to obtain an aggregated user preference distribution;
based on the updated weight information, performing first user preference prediction on the aggregated user preference distribution to obtain feature mining information corresponding to the aggregated user preference distribution;
and performing fuzzy preference derivation on the feature mining information based on a second fuzzy preference derivation layer of the user preference processing model to obtain a third user preference distribution.
Optionally, the performing, by the server, member node distribution on the removed member feature component based on the presentation data of the removed member feature component and the presentation data corresponding to the second user preference distribution to obtain a member feature component after member node distribution includes:
acquiring connected presentation data of the removed member feature components in a live broadcast function presenting process corresponding to the second user preference distribution;
and performing member node distribution on the removed member characteristic components based on the communication presentation data to obtain member characteristic components after member node distribution.
The embodiment of the invention also provides a user preference processing system based on the electronic commerce, which comprises a processor, a memory and the user preference processing system based on the electronic commerce, wherein the user preference processing system based on the electronic commerce comprises:
the prediction module is used for predicting user preference of the E-commerce live broadcast interaction log to obtain first user preference distribution, and performing preference fuzzy derivation on the first user preference distribution to obtain second user preference distribution;
the aggregation module is used for matching a first preference intention aiming at the current live broadcast optimization component based on the second user preference distribution to obtain a first preference intention member representing the current live broadcast optimization component, aggregating the first user preference distribution and the second user preference distribution, and performing preference fuzzy derivation on the aggregated user preference distribution to obtain a third user preference distribution;
the distribution module is used for acquiring launching related metric values corresponding to the characteristic components of all members in the first preference intention members; removing the member feature component of which the release related metric value is smaller than the target related metric value to obtain a removed member feature component, and performing member node distribution on the removed member feature component based on the presentation data of the removed member feature component and the presentation data corresponding to the second user preference distribution to obtain a member feature component after member node distribution;
and the updating module is used for performing second preference intention matching on the current live broadcast optimization component based on the third user preference distribution and the member characteristic components distributed by the member nodes so as to update the member characteristic components distributed by the member nodes, and determining the current live broadcast optimization component in the E-commerce live broadcast interaction log based on the updated member characteristic components.
Optionally, the prediction module is further configured to:
based on a first feature mining layer of a user preference processing model, performing first user preference prediction on the first user preference distribution to obtain feature mining information of the first user preference distribution;
and performing fuzzy preference derivation on the feature mining information based on a first fuzzy preference derivation layer of the user preference processing model to obtain second user preference distribution.
Optionally, the aggregation module is further configured to:
extracting member feature components aiming at a current live broadcast optimization component in the E-commerce live broadcast interaction log based on the second user preference distribution on the basis of a first member feature component mining layer of a user preference processing model;
clustering member characteristic components of the current live broadcast optimization component to obtain a first preference intention member representing the current live broadcast optimization component.
Optionally, the aggregation module is further configured to:
loading the first user preference distribution and the second user preference distribution into a second feature mining layer of a user preference processing model;
updating the weight information of the second feature mining layer based on the first user preference distribution and the second user preference distribution to obtain updated weight information;
aggregating the first user preference distribution and the second user preference distribution to obtain an aggregated user preference distribution;
based on the updated weight information, performing first user preference prediction on the aggregated user preference distribution to obtain feature mining information corresponding to the aggregated user preference distribution;
and performing fuzzy preference derivation on the feature mining information based on a second fuzzy preference derivation layer of the user preference processing model to obtain a third user preference distribution.
Optionally, the allocation module is further configured to:
acquiring connected presentation data of the removed member feature components in a live broadcast function presenting process corresponding to the second user preference distribution;
and performing member node distribution on the removed member characteristic components based on the communication presentation data to obtain member characteristic components after member node distribution.
In summary, the method and system for processing user preference based on e-commerce according to the embodiments of the present invention first perform user preference prediction on live broadcast interactive logs of e-commerce to obtain a first user preference distribution, and perform fuzzy preference derivation on the first user preference distribution to obtain a second user preference distribution; then, performing first preference intention matching aiming at the current live broadcast optimization component based on the second user preference distribution to obtain a first preference intention member representing the current live broadcast optimization component, aggregating the first user preference distribution and the second user preference distribution, and performing preference fuzzy derivation on the aggregated user preference distribution to obtain a third user preference distribution; secondly, acquiring a launching correlation metric value corresponding to each member characteristic component in the first preference intention member; removing the member feature component of which the delivery related metric value is smaller than the target related metric value to obtain a removed member feature component, and performing member node distribution on the removed member feature component based on the presentation data of the removed member feature component and the presentation data corresponding to the second user preference distribution to obtain a member feature component after member node distribution; and finally, performing second preference intention matching on the current live broadcast optimization component based on the third user preference distribution and the member characteristic components distributed by the member nodes so as to update the member characteristic components distributed by the member nodes, and determining the current live broadcast optimization component in the E-commerce live broadcast interaction log based on the updated member characteristic components. Thus, tracking identification can be realized for the current live broadcast optimization component, so that the live broadcast optimization index can be determined conveniently.
In order to make the aforementioned objects, features and advantages of the embodiments of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings are only some embodiments of the present invention, and therefore should not be considered as limiting the scope, and it is obvious for those skilled in the art that other related drawings can be obtained based on these drawings without inventive efforts.
Fig. 1 is a schematic diagram of an e-commerce based user preference processing system for implementing an e-commerce based user preference processing method according to an embodiment of the present invention.
Fig. 2 is a flowchart illustrating a method for processing user preferences based on e-commerce according to an embodiment of the present invention.
Fig. 3 is a functional block diagram of a user preference processing system based on e-commerce according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood by the scholars in the technical field, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic diagram of an e-commerce based user preference processing system 1 for implementing an e-commerce based user preference processing method according to an embodiment of the present invention. Fig. 2 is a flowchart illustrating a method for processing user preferences based on e-commerce according to an embodiment of the present invention. Preferably, the method is implemented by the e-commerce based user preference processing system 1, and the steps of the method are described in detail below.
And 2, matching a first preference intention aiming at the current live broadcast optimization component based on the second user preference distribution to obtain a first preference intention member representing the current live broadcast optimization component, aggregating the first user preference distribution and the second user preference distribution, and performing preference fuzzy derivation on the aggregated user preference distribution to obtain a third user preference distribution.
And 4, performing second preference intention matching on the current live broadcast optimization component based on the third user preference distribution and the member characteristic components distributed by the member nodes so as to update the member characteristic components distributed by the member nodes, and determining the current live broadcast optimization component in the E-commerce live broadcast interaction log based on the updated member characteristic components.
Preferably, in step 1, the performing fuzzy preference derivation on the first user preference distribution to obtain a second user preference distribution includes:
based on a first feature mining layer of a user preference processing model, performing first user preference prediction on the first user preference distribution to obtain feature mining information of the first user preference distribution;
and performing fuzzy preference derivation on the feature mining information based on a first fuzzy preference derivation layer of the user preference processing model to obtain the second user preference distribution.
Preferably, in step 2, the performing, based on the second user preference distribution, a first preference intention matching for the current live broadcast optimization component to obtain a first preference intention member characterizing the current live broadcast optimization component includes:
extracting member feature components aiming at a current live broadcast optimization component in the E-commerce live broadcast interaction log based on the second user preference distribution on the basis of a first member feature component mining layer of a user preference processing model;
clustering member characteristic components of the current live broadcast optimization component to obtain a first preference intention member representing the current live broadcast optimization component.
Preferably, in step 3, the aggregating the first user preference distribution and the second user preference distribution, and performing fuzzy preference derivation on the aggregated user preference distribution to obtain a third user preference distribution includes:
loading the first user preference distribution and the second user preference distribution into a second feature mining layer of a user preference processing model;
updating the weight information of the second feature mining layer based on the first user preference distribution and the second user preference distribution to obtain updated weight information;
aggregating the first user preference distribution and the second user preference distribution to obtain an aggregated user preference distribution;
based on the updated weight information, performing first user preference prediction on the aggregated user preference distribution to obtain feature mining information corresponding to the aggregated user preference distribution;
and performing fuzzy preference derivation on the feature mining information based on a second fuzzy preference derivation layer of the user preference processing model to obtain a third user preference distribution.
Preferably, in step 3, the performing member node assignment on the removed member feature component based on the presentation data of the removed member feature component and the presentation data corresponding to the second user preference distribution to obtain a member feature component after member node assignment includes:
acquiring connected presentation data of the removed member feature components in a live broadcast function presenting process corresponding to the second user preference distribution;
and performing member node distribution on the removed member characteristic components based on the communication presentation data to obtain member characteristic components after member node distribution.
Further, referring to fig. 2, in this embodiment, the e-commerce based user preference processing system 1 may be a server, or may be a server cluster, a computer device, a cloud service center, or other devices with information processing and analyzing capabilities, and the e-commerce based user preference processing system 1 may include one or more processors 10, such as one or more Central Processing Units (CPUs), each of which may implement one or more hardware threads. The e-commerce based user preference processing system may also include a machine-readable storage medium 20 for storing any kind of information such as code, settings, data, etc. Non-limiting examples of the machine-readable storage medium include any one or more of the following in combination: any type of RAM, any type of ROM, flash memory devices, hard disks, optical disks, etc. More generally, machine-readable storage media may store information using any technology. Further, the machine-readable storage medium may provide volatile or non-volatile retention of information. Further, the machine-readable storage medium may represent fixed or removable components of the e-commerce based user preference processing system 1. In one case, when processor 10 executes the associated instructions stored in machine-readable storage medium 20 or a combination of storage media, e-commerce based user preference processing system 1 may perform any of the operations of the associated instructions. The e-commerce based user preference processing system 1 further comprises one or more drive units, such as a hard disk drive unit, an optical disk drive unit, etc., for interacting with the machine-readable storage medium.
Further, the e-commerce based user preference processing system 1 may also include input/output (I/O) for receiving various inputs (via the input unit) and for providing various outputs (via the output unit)). One particular output mechanism may include a presentation device and an associated Graphical User Interface (GUI). The e-commerce based user preference processing system 1 may further comprise one or more network interfaces for exchanging data with other devices via one or more communication units. One or more communication buses couple the above-described components together.
The communication unit may be implemented in any manner, e.g., based on a local area network, a wide area network (e.g., the internet), a point-to-point connection, etc., or any combination thereof. The communication units may comprise any combination of hardwired links, wireless links, routers, gateway functions, etc., governed by any protocol or combination of protocols.
Fig. 3 is a functional block diagram of an e-commerce based user preference processing system 30 (as shown in fig. 1) according to an embodiment of the present invention, where the functions implemented by the e-commerce based user preference processing system 30 may correspond to the steps executed by the method described above. In other embodiments, the e-commerce based user preference processing system 30 may be understood as the e-commerce based user preference processing system 1 or the processor 10 of the e-commerce based user preference processing system, or may be understood as a component which is independent of the e-commerce based user preference processing system 1 or the processor 10 and implements the functions of the present invention under the control of the e-commerce based user preference processing system 1, as shown in fig. 3, and the functions of the functional modules of the e-commerce based user preference processing system are described in detail below.
The prediction module 301 is configured to perform user preference prediction on the e-commerce live broadcast interaction log to obtain first user preference distribution, and perform preference fuzzy derivation on the first user preference distribution to obtain second user preference distribution;
an aggregation module 302, configured to perform first preference intention matching for a current live broadcast optimization component based on the second user preference distribution to obtain a first preference intention member representing the current live broadcast optimization component, aggregate the first user preference distribution and the second user preference distribution, and perform preference fuzzy derivation on the aggregated user preference distribution to obtain a third user preference distribution;
the distribution module 303 is configured to obtain a launch related metric value corresponding to each member feature component in the first preference intention member, remove a member feature component of which the launch related metric value is smaller than a target related metric value to obtain a removed member feature component, and perform member node distribution on the removed member feature component based on presentation data of the removed member feature component and presentation data corresponding to the second user preference distribution to obtain a member feature component after member node distribution;
an updating module 304, configured to perform second preference intention matching on the current live broadcast optimization component based on the third user preference distribution and the member feature component allocated by the member node, so as to update the member feature component allocated by the member node, and determine the current live broadcast optimization component in the e-commerce live broadcast interaction log based on the updated member feature component.
Optionally, the prediction module 301 is further configured to:
based on a first feature mining layer of a user preference processing model, performing first user preference prediction on the first user preference distribution to obtain feature mining information of the first user preference distribution;
and performing fuzzy preference derivation on the feature mining information based on a first fuzzy preference derivation layer of the user preference processing model to obtain the second user preference distribution.
Optionally, the aggregation module 302 is further configured to:
extracting member feature components aiming at a current live broadcast optimization component in the E-commerce live broadcast interaction log based on the second user preference distribution on the basis of a first member feature component mining layer of a user preference processing model;
clustering member characteristic components of the current live broadcast optimization component to obtain a first preference intention member representing the current live broadcast optimization component.
Optionally, the aggregation module 302 is further configured to:
loading the first user preference distribution and the second user preference distribution into a second feature mining layer of a user preference processing model;
updating the weight information of the second feature mining layer based on the first user preference distribution and the second user preference distribution to obtain updated weight information;
aggregating the first user preference distribution and the second user preference distribution to obtain an aggregated user preference distribution;
based on the updated weight information, performing first user preference prediction on the aggregated user preference distribution to obtain feature mining information corresponding to the aggregated user preference distribution;
and performing fuzzy preference derivation on the feature mining information based on a second fuzzy preference derivation layer of the user preference processing model to obtain a third user preference distribution.
Optionally, the allocating module 303 is further configured to:
acquiring connected presentation data of the removed member feature components in a live broadcast function presenting process corresponding to the second user preference distribution;
and performing member node distribution on the removed member characteristic components based on the communication presentation data to obtain member characteristic components after member node distribution.
In summary, the method and system for processing user preference based on e-commerce provided by the embodiments of the present invention first predict user preference for e-commerce live broadcast interaction logs to obtain a first user preference distribution, and perform fuzzy derivation on the first user preference distribution to obtain a second user preference distribution; then, performing first preference intention matching aiming at the current live broadcast optimization component based on the second user preference distribution to obtain a first preference intention member representing the current live broadcast optimization component, aggregating the first user preference distribution and the second user preference distribution, and performing preference fuzzy derivation on the aggregated user preference distribution to obtain a third user preference distribution; secondly, acquiring a launching correlation metric value corresponding to each member characteristic component in the first preference intention member; removing the member feature component of which the release related metric value is smaller than the target related metric value to obtain a removed member feature component, and performing member node distribution on the removed member feature component based on the presentation data of the removed member feature component and the presentation data corresponding to the second user preference distribution to obtain a member feature component after member node distribution; and finally, performing second preference intention matching on the current live broadcast optimization component based on the third user preference distribution and the member characteristic components distributed by the member nodes so as to update the member characteristic components distributed by the member nodes, and determining the current live broadcast optimization component in the E-commerce live broadcast interaction log based on the updated member characteristic components. Thus, tracking identification can be realized for the current live broadcast optimization component, so that the live broadcast optimization index can be determined conveniently.
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 functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
Alternatively, it may be implemented in whole or in part based on software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, or data center to another website site, computer, or data center based on wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. having one or more of the available media integrated therewith. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It should be noted that, in this document, the terms "comprises," "comprising," "has," "having," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any drawing credit or debit acknowledgement in the claims should not be construed as limiting the claim concerned.
Claims (10)
1. A user preference processing method based on electronic commerce is characterized by comprising the following steps:
carrying out user preference prediction on live E-commerce interactive logs to obtain first user preference distribution, and carrying out preference fuzzy derivation on the first user preference distribution to obtain second user preference distribution;
performing first preference intention matching aiming at the current live broadcast optimization component based on the second user preference distribution to obtain a first preference intention member representing the current live broadcast optimization component, aggregating the first user preference distribution and the second user preference distribution, and performing preference fuzzy derivation on the aggregated user preference distribution to obtain a third user preference distribution;
acquiring release related metric values corresponding to member feature components in the first preference intention members; removing the member feature component of which the release related metric value is smaller than the target related metric value to obtain a removed member feature component, and performing member node distribution on the removed member feature component based on the presentation data of the removed member feature component and the presentation data corresponding to the second user preference distribution to obtain a member feature component after member node distribution;
and performing second preference intention matching on the current live broadcast optimization component based on the third user preference distribution and the member characteristic components distributed by the member nodes so as to update the member characteristic components distributed by the member nodes, and determining the current live broadcast optimization component in the E-commerce live broadcast interaction log based on the updated member characteristic components.
2. The method of claim 1, wherein the deriving the first user preference distribution with fuzzy preference to obtain a second user preference distribution comprises:
based on a first feature mining layer of a user preference processing model, performing first user preference prediction on the first user preference distribution to obtain feature mining information of the first user preference distribution;
and performing fuzzy preference derivation on the feature mining information based on a first fuzzy preference derivation layer of the user preference processing model to obtain the second user preference distribution.
3. The method of claim 1, wherein the matching a first preference intention for a current live optimization component based on the second user preference distribution results in a first preference intention member characterizing the current live optimization component, comprising:
extracting member feature components aiming at a current live broadcast optimization component in the E-commerce live broadcast interaction log based on the second user preference distribution on the basis of a first member feature component mining layer of a user preference processing model;
clustering member characteristic components of the current live broadcast optimization component to obtain a first preference intention member representing the current live broadcast optimization component.
4. The method of claim 1, wherein the aggregating the first user preference distribution and the second user preference distribution and performing a preference fuzzy derivation on the aggregated user preference distribution to obtain a third user preference distribution comprises:
loading the first user preference distribution and the second user preference distribution into a second feature mining layer of a user preference processing model;
updating the weight information of the second feature mining layer based on the first user preference distribution and the second user preference distribution to obtain updated weight information;
aggregating the first user preference distribution and the second user preference distribution to obtain an aggregated user preference distribution;
based on the updated weight information, performing first user preference prediction on the aggregated user preference distribution to obtain feature mining information corresponding to the aggregated user preference distribution;
and performing fuzzy preference derivation on the feature mining information based on a second fuzzy preference derivation layer of the user preference processing model to obtain a third user preference distribution.
5. The method according to claim 1, wherein the performing member node assignment on the removed member feature component based on the presentation data of the removed member feature component and the presentation data corresponding to the second user preference distribution to obtain a member feature component after member node assignment comprises:
acquiring connected presentation data of the removed member feature components in a live broadcast function presenting process corresponding to the second user preference distribution;
and performing member node distribution on the removed member characteristic components based on the communication presentation data to obtain member characteristic components after member node distribution.
6. An e-commerce based user preference processing system comprising a processor, a memory, and an e-commerce based user preference processing system, wherein the e-commerce based user preference processing system comprises:
the prediction module is used for predicting user preference of the E-commerce live broadcast interaction log to obtain first user preference distribution, and performing preference fuzzy derivation on the first user preference distribution to obtain second user preference distribution;
the aggregation module is used for matching a first preference intention aiming at the current live broadcast optimization component based on the second user preference distribution to obtain a first preference intention member representing the current live broadcast optimization component, aggregating the first user preference distribution and the second user preference distribution, and performing preference fuzzy derivation on the aggregated user preference distribution to obtain a third user preference distribution;
the distribution module is used for acquiring launching related metric values corresponding to the characteristic components of all members in the first preference intention members; removing the member feature component of which the release related metric value is smaller than the target related metric value to obtain a removed member feature component, and performing member node distribution on the removed member feature component based on the presentation data of the removed member feature component and the presentation data corresponding to the second user preference distribution to obtain a member feature component after member node distribution;
and the updating module is used for performing second preference intention matching on the current live broadcast optimization component based on the third user preference distribution and the member characteristic components distributed by the member nodes so as to update the member characteristic components distributed by the member nodes, and determining the current live broadcast optimization component in the E-commerce live broadcast interaction log based on the updated member characteristic components.
7. The e-commerce based user preference processing system of claim 6, wherein the prediction module is further configured to:
based on a first feature mining layer of a user preference processing model, performing first user preference prediction on the first user preference distribution to obtain feature mining information of the first user preference distribution;
and performing fuzzy preference derivation on the feature mining information based on a first fuzzy preference derivation layer of the user preference processing model to obtain the second user preference distribution.
8. The e-commerce based user preference processing system of claim 6, wherein the aggregation module is further configured to:
extracting member feature components aiming at a current live broadcast optimization component in the E-commerce live broadcast interaction log based on the second user preference distribution on the basis of a first member feature component mining layer of a user preference processing model;
clustering member characteristic components of the current live broadcast optimization component to obtain a first preference intention member representing the current live broadcast optimization component.
9. The e-commerce based user preference processing system of claim 6, wherein the aggregation module is further configured to:
loading the first user preference distribution and the second user preference distribution into a second feature mining layer of a user preference processing model;
updating the weight information of the second feature mining layer based on the first user preference distribution and the second user preference distribution to obtain updated weight information;
aggregating the first user preference distribution and the second user preference distribution to obtain an aggregated user preference distribution;
based on the updated weight information, performing first user preference prediction on the aggregated user preference distribution to obtain feature mining information corresponding to the aggregated user preference distribution;
and performing fuzzy preference derivation on the feature mining information based on a second fuzzy preference derivation layer of the user preference processing model to obtain a third user preference distribution.
10. The e-commerce based user preference processing system of claim 6, wherein the assignment module is further configured to:
acquiring connected presentation data of the removed member feature components in a live broadcast function presenting process corresponding to the second user preference distribution;
and performing member node distribution on the removed member characteristic components based on the communication presentation data to obtain member characteristic components after member node distribution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111653140.5A CN114443952A (en) | 2021-12-31 | 2021-12-31 | User preference processing method and system based on electronic commerce |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111653140.5A CN114443952A (en) | 2021-12-31 | 2021-12-31 | User preference processing method and system based on electronic commerce |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114443952A true CN114443952A (en) | 2022-05-06 |
Family
ID=81366604
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111653140.5A Withdrawn CN114443952A (en) | 2021-12-31 | 2021-12-31 | User preference processing method and system based on electronic commerce |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114443952A (en) |
-
2021
- 2021-12-31 CN CN202111653140.5A patent/CN114443952A/en not_active Withdrawn
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9552232B2 (en) | System and process to recommend cloud service cloud configuration based on service similarity | |
| US9053004B2 (en) | Virtual data storage service with sparse provisioning | |
| US10437470B1 (en) | Disk space manager | |
| CN112148468A (en) | Resource scheduling method and device, electronic equipment and storage medium | |
| US11474809B2 (en) | Upgrades based on analytics from multiple sources | |
| CN113761526A (en) | Attack intention analysis method and system based on big data | |
| CN113779409A (en) | Intention mining method and system based on big data | |
| CN114443952A (en) | User preference processing method and system based on electronic commerce | |
| KR101810180B1 (en) | Method and apparatus for distributed processing of big data based on user equipment | |
| CN111274437B (en) | Video material resource management method and system based on Internet | |
| WO2016069621A1 (en) | System and method to recommend a bundle of items based on item/user tagging and co-install graph | |
| CN113297491A (en) | Service subscription information pushing method and system based on social network | |
| CN111948967B (en) | Power data acquisition method and system based on big data | |
| CN111324753B (en) | Media information publishing management method and system | |
| US11132235B2 (en) | Data processing method, distributed data processing system and storage medium | |
| CN113297445A (en) | Hot topic identification method and data analysis server | |
| CN114063879B (en) | Method for processing operation command, electronic device and storage medium | |
| CN114448676A (en) | Information interception method and system applied to electronic commerce live broadcast | |
| WO2024113184A1 (en) | Optimizing allocation of graphical processing unit (gpu) resources in a production workspace | |
| CN113905046A (en) | Cloud server remote monitoring method and system | |
| CN114444119A (en) | Security protection method and system based on electronic commerce | |
| CN113900792A (en) | Information classification method and system based on cloud computing service | |
| CN113706221A (en) | Big data-based user interest prediction method and system | |
| CN113282823A (en) | Hot topic tracking method and system based on artificial intelligence | |
| CN114810109A (en) | Control strategy distribution method and system for shield machine control |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220506 |
|
| WW01 | Invention patent application withdrawn after publication |