Note : Les descriptions sont présentées dans la langue officielle dans laquelle elles ont été soumises.
COMMODITY INFORMATION PUSHING METHOD, DEVICE, AND SYSTEM
Technical Field
[0001] The present invention relates to the field of data mining technologies,
in particular, to a
method, a device, and a system for pushing commodity information.
Background
[0002] Nowadays, sales of a certain commodity are not only related to the
price, customer
reviews, the brand, advertisement, and other factors, but also greatly
affected by hot news
outbreaks on the internet and other public opinions. Public opinions may
provide positive
information to customers, promoting customers to purchase the commodity. On
the other hand,
public opinions may provide negative information that suppresses customers'
willingness to
purchase. From the perspective of e-commerce marketing, based on the positive
or negative
effects by public opinions, the promoting strategies can be adjusted in time,
to improve
commodity sales and reduce marketing risks. However, in the current
technologies, the research
of commodity marketing plans generally focus on strategies to generate
customized and
individualized recommendations based on the data mining technique, wherein the
effects from
public opinions are ignored.
Summary
[0003] In order to solve the limitations of the current commodity marketing
modes due to
ignorance of public opinions, the present invention provides a method, a
device, and a system for
pushing commodity information based on data mining technologies. The described
technical
proposal comprises:
[0004] From the first perspective, a commodity information pushing method is
provided in the
present invention, comprising:
[0005] collecting public opinions to generate at least one information tag for
the public opinions;
[0006] calculating correlation between the commodity and the information tag
according to the
acquired commodity information, to determine correlation between the commodity
and the
public opinions;
1
Date Recue/Date Received 2021-10-18
[0007] comparing the correlations with a primary correlation threshold
condition, to connect the
commodity satisfying the primary correlation threshold condition with the
public opinions; and
[0008] sending the connection information of the commodity and the public
opinions to a target
service system.
[0009] Furthermore, the described method further includes:
[0010] classifying the described collected public opinions into positive
information and negative
information;
[0011] generate risk warning information based on the connection between the
described
commodity and the described negative information; and
[0012] sending the described risk warning information to the described target
service system.
[0013] Furthermore, information tags of the described public opinions are
generated, comprises:
[0014] classifying the described public opinions into types of fields
according to information
contents;
[0015] acquiring hot indices of the described public opinions in each type of
field; and
[0016] sorting the described public opinions within each type of field
according to the described
hot indices, to generate information tags for the described public opinions
satisfying ranking
conditions.
[0017] Furthermore, the described method further includes:
[0018] sending the hot indices of the described public opinions satisfying
ranking conditions to
the described target service system.
[0019] Furthermore, the described method further includes:
[0020] predicting evolution trends of the described hot indices; and
[0021] where if the described evolution trends of the described hot indices
are increasing during
a pre-set time period, keeping monitoring and collecting public opinions.
[0022] From the second perspective, a commodity information pushing device is
provided,
comprising:
[0023] a public opinion collecting module, configured to collect public
opinions;
[0024] an information tag generation module, configured to generate at least
one information tag
for the public opinions;
[0025] a commodity information acquisition module, configured to acquire
commodity
information;
2
Date Recue/Date Received 2021-10-18
[0026] a correlation calculation module, configured to calculate correlation
between the
commodity and the information tag according to the acquired commodity
information, for
determining correlation between the commodity and the public opinions;
[0027] a connection linking module, configured to compare the correlations
with a primary
correlation threshold condition, to connect the commodity satisfying the
primary correlation
threshold condition with the public opinions; and
[0028] a communication module, configured to send the connection information
of the
commodity and the public opinions to a target service system.
[0029] Furthermore, the described device further includes:
[0030] a primary classification module, configured to classify the described
collected public
opinions into positive information and negative information;
[0031] a risk warning information generation module, configured to generate
risk warning
information based on the connection between the described commodity and the
described
negative information; and
[0032] the described communication module, configured to send the described
risk warning
information to the described target service system.
[0033] Furthermore, the described device further includes:
[0034] a secondary classification module, configured to classify the described
public opinions
into types of fields according to information contents;
[0035] a hot index calculation module, configured to acquire hot indices of
the described public
opinions in each type of field; and
[0036] the described information tag generation module, configured to sort the
described public
opinions within each type of field according to the described hot indices, for
generating
information tags for the described public opinions satisfying ranking
conditions.
[0037] Furthermore, the described communication device, is further configured
to send the hot
indices of the described public opinions satisfying ranking conditions to the
described target
service system.
[0038] Furthermore, the described device further includes:
[0039] a trend prediction module, configured to predict evolution trends of
the described hot
indices; and
3
Date Recue/Date Received 2021-10-18
[0040] the described public opinion collection module, configured to keep
monitoring and
collecting public opinions, where if the described evolution trends of the
described hot indices
are increasing during a pre-set time period.
[0041] From the third perspective, a computer system is provided in the
present invention,
comprising:
[0042] one or more processors; and
[0043] a memory connected to the described one or more processors, wherein the
described
memory is used to store program commands, for implementing the forementioned
methods in the
first perspective when the described program commands are executed on the
described one or
more processors.
[0044] The technical proposal in the present invention provides benefits of:
[0045] The technical proposal disclosed in the present invention provides
reference marketing
plans for commodities selected by target service systems by constructing
connections between
public opinions and commodities, to solve the problem of low commodity
promotion efficiency
affected by ignoring public opinions for commodity marketing, and to prevent
potential
operation risks by public opinions during commodity marketing.
Brief descriptions of the drawings
[0046] In order to make the technical strategies of the present invention
clearer, the
accompanying drawings for the present invention will be briefly introduced
below. Obviously,
the following drawings in the descriptions are only a portion of embodiments
of the present
invention. Those skilled in the art are able to generate other configurations
according to the
provided drawings without requiring any creative works.
[0047] Fig. 1 is a flow diagram of the commodity information pushing method
provided in the
present invention.
[0048] Fig. 2 is a structure diagram of the commodity information pushing
device provided in
the present invention.
[0049] Fig. 3 is a structure diagram of a computer system provided in the
present invention.
4
Date Recue/Date Received 2021-10-18
Detailed descriptions
[0050] In order to make the objective, the technical protocol, and the
advantages of the present
invention clearer, the present invention will be explained further in detail
precisely below with
references to the accompanying drawings. Obviously, the embodiments described
below are only
a portion of embodiments of the present invention and cannot represent all
possible embodiments.
Based on the embodiments in the present invention, the other applications by
those skilled in the
art without any creative works are falling within the scope of the present
invention.
[0051] With the development and maturity of internet media, customers receive
more and more
public opinions. Public opinions are directly or indirectly connected to a
certain type of
commodities or a certain brand, wherein public opinions can significantly
influence the
commodity marketing activities due to the forementioned connections. With
immediately
accessed public opinions to analyze connections between the public opinions
and the
commodities, important references can be provided for customizing commodity
marketing plans.
Accordingly, the present invention provides a method, a device, and a system
for pushing
commodity information. The detailed specifications of the technical proposal
are provided as the
following:
[0052] As shown in Fig. 1, a commodity information pushing method is provided
in the present
invention, comprising:
[0053] S01, collecting public opinions to generate at least one information
tag for the public
opinions.
[0054] In particular, the forementioned public opinion collection can use web
crawlers to
monitor and browse public opinions from the news web portals, social media and
other third-
party public opinion platforms, wherein hot news, topics, and commodity
activities are collected.
In detail, the information collected can include titles, abstracts, contents,
and other text data of
news related to hot events.
[0055] In particular, the forementioned information tag can be generated via
text keyword
extraction, wherein the extracted keywords are assigned as tags of the public
opinions. With
multiple keywords of a public opinion related to a hot event, the information
tag of the public
opinion may include multiple dimensions, wherein the multi-dimensional
information tag helps
to connect the public opinion to multiple commodities. The text keyword
extraction methods
include TF-IDF algorithm, statistical language model based on semantic
compositions, TF-IWF
Date Recue/Date Received 2021-10-18
automated file keyword extraction algorithm, keyword extraction algorithm
based on the
separation model, keyword extraction algorithm based on high-dimensional
cluster technologies,
keyword extraction algorithm based on Naive Bayes model, and so on, wherein
the particular
question keyword extraction algorithms are not limited or restricted in the
present embodiment
of the present dimension.
[0056] To clarify, in order to store information tags, a tag index database
can be constructed,
wherein the information tags are stored according to the public opinions
associated with the hot
events and corresponding connections.
[0057] In an embodiment of the present invention, the hot public opinions can
be found in
several fields. Therefore, in order to match connected commodities for the
public opinions
associated with the hot events, when the information tags of public opinions
are generated, the
step SO1 further includes:
[0058] S011, classifying the described public opinions into types of fields
according to
information contents.
[0059] In particular, the contents of public opinions may relate to different
types of fields, such
as entertainment, economics, society, technology, etc. The public opinions are
classified
according to types of fields. In detail, the classification of the public
opinions can be determined
by resources of the public opinions, or the keywords extracted from the
forementioned keyword
extraction algorithms. The particular determination methods are not limited or
restricted in the
present embodiment of the present dimension.
[0060] S012, acquiring hot indices of the described public opinions in each
type of field.
[0061] In particular, the forementioned hot indices can include click rates,
play volumes, read
volumes, comment volumes, liked volumes, etc. The forementioned hot indices
can be used to
determine the extent of public attention of the public opinions from each
field. Associated data
can be directly obtained from public opinion platforms for obtaining hot
indices. On the other
hand, different data to measure public attention can be obtained from public
opinion platforms,
wherein multi-angled comprehensive hot indices can be obtained by weighted
calculation. The
particular attainment methods are not limited or restricted in the present
embodiment of the
present dimension.
6
Date Recue/Date Received 2021-10-18
[0062] S013, sorting the described public opinions within each type of field
according to the
described hot indices, to generate information tags for the described public
opinions satisfying
ranking conditions.
[0063] In particular, the forementioned ranking conditions are generally pre-
set ranking
thresholds. By generating information tags for the public opinions satisfying
ranking conditions,
the public opinions connected to the commodities in the present invention are
guaranteed with
considerable public attention, to provide reference marketing plans for
commodities selected by
target service systems.
[0064] S02, calculating correlation between the commodity and the information
tag according to
the acquired commodity information, to determine correlation between the
commodity and the
public opinions.
[0065] In particular, the forementioned commodity information can be stored in
the target
service system, wherein the commodity information can be collected from the
target service
system. The commodity information can include names, brands, types, brand
ambassadors,
places of origin, dealers of the commodities. In the meanwhile, the commodity
information can
be collected from third-party public opinion platforms.
[0066] In particular, the forementioned calculation for the correlation
between the commodity
and the information tag can include TF/IDF algorithm, Euclidean evaluation,
Pearson correlation
evaluation, neural network models, etc. The particular attainment methods are
not limited or
restricted in the present embodiment of the present dimension.
[0067] S03, comparing the correlations with a primary correlation threshold
condition, to
connect the commodity satisfying the primary correlation threshold condition
with the public
opinions.
[0068] In particular, the forementioned correlation between the commodity and
the information
tag should exceed a certain threshold, wherein a small correlation indicates
little influence on the
commodity marketing by the public opinions without requiring focuses.
[0069] SO4, sending the connection information of the commodity and the public
opinions to a
target service system.
[0070] In particular, the forementioned connection of the commodity and the
public opinions can
include mapping relationships between the public opinions and commodities and
magnitude of
connection between the commodity and the public opinions, assigned as
marketing information
7
Date Recue/Date Received 2021-10-18
to be sent to the target service system. The target service system refers to
the forementioned
correlation relationships, and publishes marketing advertisements on the
website marketing spots
based on the number of website marketing spots associated with the public
opinions. For
example, when one event corresponds to multiple marketing spots, different
commodity
combinations are sent to different marketing spots according to different
correlations of the
public opinions and the commodities. The target service system can be a
marketing system.
[0071] In an embodiment of the present invention, the forementioned production
information
pushing method further includes:
[0072] S05, classifying the described collected public opinions into positive
information and
negative information.
[0073] In particular, the forementioned positive information promotes customer
to purchase the
commodities, while the negative information suppresses customers' willingness
to purchase and
further puts risks on marketing systems. Therefore, the present invention
classifies the public
opinions into positive and negative information, wherein the commodities
associated with the
negative information are filtered, so as to propose marketing plans for the
marketing systems
accordingly and reduce risks.
[0074] To clarify, the step S05 can be performed directly after collecting
public opinions in the
step S01.
[0075] S06, generate risk warning information based on the connection between
the described
commodity and the described negative information.
[0076] S07, sending the described risk warning information to the described
target service
system.
[0077] In particular, the forementioned risk warning information includes
connections between
the negative information and the commodities. The risk warning information can
provide
reference marketing plans for commodities selected by target service systems.
For example, a
public opinion is about negative news for a brand ambassador. Hence, the
target service system
can refer to the risk warning information to stop selling the commodity for
reducing risks.
[0078] In an embodiment of the present invention, based on the step S011 ¨
S013, the
commodity information pushing method further includes:
[0079] S08, sending the hot indices of the described public opinions
satisfying ranking
conditions to the described target service system.
8
Date Recue/Date Received 2021-10-18
[0080] In particular, the hot indices can be used to determine the extent of
public attention of the
public opinions from each field. Therefore, the hot indices are sent to the
target service system,
wherein the target service system can compile commodity marketing plans
according to the hot
indices and the connection of the public opinions and commodities.
[0081] In an embodiment of the present invention, the forementioned commodity
information
pushing method further includes:
[0082] S09, predicting evolution trends of the described hot indices.
[0083] In particular, the forementioned trend prediction method can adopt
ARIMA model
predicting method, neural network model predicting method, Prophet model
predicting method,
and so on. The particular attainment methods are not limited or restricted in
the present
embodiment of the present dimension.
[0084] S10, keeping monitoring and collecting public opinions, where if the
described evolution
trends of the described hot indices are increasing during a pre-set time
period.
[0085] In particular, the multiple types of public opinions can be collected.
If all public opinions
are monitored, the service resources can be wasted. Therefore, the present
invention judges that
if continuous monitoring of the public opinions is required based on the
evolution trends of the
hot indices.
[0086] As shown in Fig. 2, based on the forementioned commodity information
pushing method,
a commodity information pushing device is also provided in the present
invention, comprising:
[0087] a public opinion collecting module 201, configured to collect public
opinions.
[0088] In particular, the forementioned public opinion collection module can
use web crawlers
to monitor and browse public opinions from the news web portals, social media
and other third-
party public opinion platforms, wherein hot news, topics, and commodity
activities are collected.
[0089] An information tag generation module 202, configured to generate at
least one
information tag for the public opinions.
[0090] In particular, the forementioned information tag generation module can
implement one or
more text keyword extraction algorithms for extracting information tags of the
public opinions.
[0091] To clarify, in order to store information tags, a tag index database
can be constructed,
wherein the information tags are stored according to the public opinions
associated with the hot
events and corresponding connections.
[0092] In an embodiment of the present invention, the forementioned device
further includes:
9
Date Recue/Date Received 2021-10-18
[0093] A secondary classification module 209, configured to classify the
described public
opinions into types of fields according to information contents.
[0094] A hot index calculation module 210, configured to acquire hot indices
of the described
public opinions in each type of field.
[0095] The information tag generation module 202, configured to sort the
described public
opinions within each type of field according to the described hot indices, for
generating
information tags for the described public opinions satisfying ranking
conditions.
[0096] A commodity information acquisition module 203, configured to acquire
commodity
information;
[0097] In particular, the forementioned commodity information acquisition
module can acquire
commodity information from the target service system, the third-party public
opinion
information platforms, as well as reports associated with the commodities on
third-party public
opinion information platforms.
[0098] A correlation calculation module 204, configured to calculate
correlation between the
commodity and the information tag according to the acquired commodity
information, for
determining correlation between the commodity and the public opinions.
[0099] In particular, the forementioned correlation calculation module can
implement TF/IDF
algorithm, Euclidean evaluation, Pearson correlation evaluation, neural
network models, etc. The
particular attainment methods are not limited or restricted in the present
embodiment of the
present dimension.
[0100] A connection linking module 205, configured to compare the correlations
with a primary
correlation threshold condition, to connect the commodity satisfying the
primary correlation
threshold condition with the public opinions; and
[0101] A communication module 206, configured to send the connection
information of the
commodity and the public opinions to a target service system.
[0102] In an embodiment of the present invention, the forementioned device
further includes:
[0103] A primary classification module 207, configured to classify the
described collected public
opinions into positive information and negative information.
[0104] A risk warning information generation module 208, configured to
generate risk warning
information based on the connection between the described commodity and the
described
negative information.
Date Recue/Date Received 2021-10-18
[0105] The described communication module 206, configured to send the
described risk warning
information to the described target service system.
[0106] In an embodiment of the present invention, based on the secondary
classification module
and the hot index calculation module 210, the forementioned communication
module 206, is
further configured to send the hot indices of the described public opinions
satisfying ranking
conditions to the described target service system.
[0107] In an embodiment of the present invention, the forementioned device
further includes:
[0108] a trend prediction module 211, configured to predict evolution trends
of the described hot
indices; and
[0109] the described public opinion collection module 201, configured to keep
monitoring and
collecting public opinions, where if the described evolution trends of the
described hot indices
are increasing during a pre-set time period.
[0110] The technical proposal in the present invention provides benefits of:
[0111] The technical proposal disclosed in the present invention provides
reference marketing
plans for commodities selected by target service systems by constructing
connections between
public opinions and commodities, to solve the problem of low commodity
promotion efficiency
affected by ignoring public opinions for commodity marketing, and to prevent
potential
operation risks by public opinions during commodity marketing.
[0112] Based on the forementioned method embodiment, a computer system is
provided in the
present invention, comprising:
[0113] one or more processors; and
[0114] a memory connected to the described one or more processors, wherein the
described
memory is used to store program commands, for implementing the forementioned
commodity
information pushing method when the described program commands are executed on
the
described one or more processors.
[0115] In particular, a schematic of the computer system structure, shown in
Fig. 3, comprises a
processor 310, a video display adapter 311, a disk driver 312, an input/output
connection port
313, an internet connection port 314, and a memory 320. The forementioned
processor 310,
video display adapter 311, disk driver 312, input/output connection port 313,
and internet
connection port 314 are connected and communicated via the system bus control
330.
11
Date Recue/Date Received 2021-10-18
[0116] In particular, the processor 310 can adopt a universal CPU (central
processing unit), a
microprocessor, an ASIC (application specific integrated circuit) or the use
of one or more
integrated circuits. The processor is used for executing associated programmes
to achieve the
technical strategies provided in the present invention.
[0117] The memory 320 can adopt a read-only memory (ROM), a random access
memory
(RAM), a static memory, a dynamic memory, etc. The memory 320 is used to store
the operating
system 321 for controlling the electronic apparatus 300, and the basic input
output system (BIOS)
322 for controlling the low-level operations of the electronic apparatus 300.
In the meanwhile,
the memory can also store the internet browser 324, data storage management
system 324, the
device label information processing system 325, etc. The described device
label information
processing system 325 can be a program to achieve the forementioned methods
and procedures
in the present invention. In summary, when the technical strategies are
performed via software or
hardware, the codes for associated programs are stored in the memory 320, then
called and
executed by the processor 310.
[0118] The input/output connection port 313 is used to connect with the
input/output modules
for information input and output. The input/output modules can be used as
components that are
installed in the devices (not included in the drawings), or can be externally
connected to the
devices to provide the described functionalities. In particular, the input
devices may include
keyboards, mouse, touch screens, microphones, various types of sensors, etc.
The output devices
may include monitors, speakers, vibrators, signal lights, etc.
[0119] The internet connection port 314 is used to connect with a
communication module (not
included in the drawings), to achieve the communication and interaction
between the described
device and other equipment. In particular, the communication module may be
connected by wire
connection (such as USB cables or internet cables), or wireless connection
(such as mobile data,
WIFI, Bluetooth, etc.)
[0120] The system bus control 330 includes a path to transfer data across each
component of the
device (such as the processor 310, the video display adapter 311, the disk
driver 312, the
input/output connection port 313, the internet connection port 314 and the
memory 320).
[0121] Besides, the described electronic device 300 can access the collection
condition
information from the collection condition information database 341 via a
virtual resource object,
so as for conditional statements and other purposes.
12
Date Recue/Date Received 2021-10-18
[0122] To clarify, although the schematic of the forementioned device only
includes the
processor 310, the video display adapter 311, the disk driver 312, the
input/output connection
port 313, the internet connection port 314, the memory 320 and the system bus
control 330, the
practical applications may include the other necessary components to achieve
successful
operations. It is comprehensible for those skilled in the art that the
structure of the device may
comprise of less components than that in the drawings, to achieve successful
operations.
[0123] By the forementioned descriptions of the applications and embodiments,
those skilled in
the art can understand that the present invention can be achieved by
combination of software and
necessary hardware platforms. Based on this concept, the present invention is
considered as
providing the technical benefits in the means of software commodities. The
mentioned computer
software commodities are stored in the storage media such as ROM/RAM, magnetic
disks,
compact disks, etc. The mentioned computer software commodities also include
using several
commands to have a computer device (such as a personal computer, a server, or
a network device)
to perform portions of the methods described in each or some of the
embodiments in the present
invention.
[0124] The embodiments in the description of the present invention are
explained step-by-step.
The similar contents can be referred amongst the embodiments, while the
differences amongst
the embodiments are emphasized. In particular, the system and the
corresponding embodiments
have similar contents to the method embodiments. Hence, the system and the
corresponding
embodiments are described concisely, and the related contents can be referred
to the method
embodiments. The described system and system embodiments are for demonstration
only, where
the components that are described separately can be physically separated or
not. The components
shown in individual units can be physical units or not. In other words, the
mentioned components
can be at a single location or distributed onto multiple network units. All or
portions of the
modules can be used to achieve the purposes of embodiments of the present
invention based on
the practical scenarios. Those skilled in the art can understand and apply the
associated strategies
without creative works.
[0125] All the forementioned technical applications can be combined as
possible for available
embodiments and not explained in detail herein.
13
Date Recue/Date Received 2021-10-18
[0126] The forementioned contents of preferred embodiments of the present
invention shall not
limit the applications of the present invention. Therefore, all alterations,
modifications,
equivalence, improvements of the present invention fall within the scope of
the present invention.
14
Date Recue/Date Received 2021-10-18
