Note: Descriptions are shown in the official language in which they were submitted.
LABEL INFORMATION ACQUISITION METHOD AND APPARATUS, ELECTRONIC
DEVICE AND COMPUTER READABLE MEDIUM
Technical Field
[0001] The present disclosure generally relates to the field of Internet
technology,
specifically to a label information acquisition method and apparatus, an
electronic device and a
computer readable medium.
Background
[0002] In the conventional financial sector, the income level, consumption
power, loan
repayment capacity and other information of a user are obtained generally from
bank statements,
housing provident funds, social insurance, individual income tax certificates,
property ownership
certificates and an employment certificate in combination with the information
filled during
application. However, in an online financial platform, we are unable to
directly obtain
information about occupation and property values.
[0003] Therefore, the technical solutions in the prior art still have a
room to improve.
[0004] The foregoing information disclosed in the section of background art
is only intended
to deepen understanding on the background of the present disclosure, so it may
include
information that does not constitute the prior art known to those of ordinary
skill in the art.
Summary
[0005] The present disclosure provides a label information obtaining method
and apparatus,
an electronic device and a computer readable medium to solve at least one of
the foregoing
problems.
[0006] Other features and advantages of the present disclosure will be
evident through the
following detailed description, or partially learnt through practice of the
present disclosure.
[0007] According to one aspect of the present disclosure, a label
information obtaining
method is provided, comprising:
[0008] classifying performance addresses of a user to obtain classification
results of the
performance addresses, wherein the performance addresses are addresses where
the user
performs orders; and analyzing according to performance behaviors of the user
specific to the
1
CA 3060822 2019-11-01
performance addresses in combination with the classification results to obtain
label information
of the user.
[0009] In an embodiment of the present disclosure, analyzing according to
performance
behaviors of the user specific to the performance addresses in combination
with the classification
results to obtain label information of the user comprises:
[0010] conducting attribute analysis of the classification results in
combination with an
industry information database to obtain attribute information of the
performance addresses;
[0011] analyzing according to performance behaviors of the user specific to
the performance
addresses in combination with the classification results and the attribute
information to obtain
label information of the user.
[0012] In an embodiment of the present disclosure, classifying the
performance addresses to
obtain classification results of the performance addresses comprises:
[0013] conducting classified labeling of historical performance addresses
based on word
vectors to obtain mapping relations between performance addresses and
categories, wherein the
historical performance addresses are addresses where a plurality of users in a
platform perform
historical orders;
[0014] obtaining the classification results specific to the performance
addresses in
combination with the mapping relations between performance addresses and
categories.
[0015] In an embodiment of the present disclosure, conducting classified
labeling of
historical performance addresses based on word vectors comprises:
[0016] extracting trunk information from the historical performance
addresses; conducting
word segmentation of the trunk information by word segmentation technique to
obtain a plurality
of address segments; converting the plurality of address segments into word
vectors; clustering
the word vectors; conducting corresponding classified labeling of
classification results of trunk
information of the performance addresses according to clustering results.
[0017] In an embodiment of the present disclosure, classifying the
performance addresses to
obtain classification results of the performance addresses comprises:
[0018] conducting Softmax training of historical performance addresses
based on word
features to obtain a text classification model, wherein the historical
performance addresses are
addresses where a plurality of users in a platform perform historical orders;
[0019] inputting the performance addresses to the text classification model
and outputting
2
CA 3060822 2019-11-01
the classification results.
[0020] In an embodiment of the present disclosure, conducting Softmax
training of historical
performance addresses based on word features comprises:
[0021] configuring a corresponding rule for address text and
classification; matching the
historical performance addresses by multi-pattern matching, and outputting
corresponding
classification results according to the Corresponding rule if the historical
performance addresses
are matched with the address text; and segmenting the performance addresses,
performing
multiple combination of obtained segments and conducting Softmax training
based on features of
a single segment or a plurality of segments to obtain the text classification
model.
[0022] In an embodiment of the present disclosure, before conducting
attribute analysis of
the classification results in combination with an industry information
database, the method
further comprises:
[0023] pre-processing industry classification information; establishing an
industry
information database according to preprocessed industry classification
information;
[0024] wherein the industry information database contains a plurality of
pieces of
information, each of which comprises:
[0025] a label; classification results; attribute information;
[0026] The classification results include: at least one or more of housing,
hospital, hotel,
office building and leisure and entertainment venue; the attribute information
includes: at least
one or more of housing price, hospital type, hotel star rating, office
building grade and leisure
and entertainment venue grade.
[0027] In an embodiment of the present disclosure, conducting attribute
analysis of the
classification results in combination with an industry information database to
obtain attribute
information:
[0028] obtaining corresponding attribute information of the performance
addresses through
forward maximum matching of information in the classification results and the
industry
information database.
[0029] In an embodiment of the present disclosure, before analyzing
according to
performance behaviors of a user specific to the performance addresses in
combination with the
classification results, the method further comprises:
[0030] obtaining performance behaviors of the user specific to the
performance addresses;
3
CA 3060822 2019-11-01
=
wherein the performance behaviors include: at least one of the following
information, including
workday performance times, non-workday performance times, time span of
performance, and
labeling of performance addresses by the user.
[0031] In an embodiment of the present disclosure, analyzing according to
performance
behaviors of the user specific to the performance addresses in combination
with the classification
results to obtain label information of the user comprises:
[0032] if workday performance times of the user are greater than or equal
to a first threshold
value, and the classification result is hospital, then obtained label
information of the user is
occupation, which is medical staff.
[0033] In an embodiment of the present disclosure, analyzing according to
performance
behaviors of the user specific to the performance addresses in combination
with the classification
results and the attribute information to obtain label information of the user
comprises:
[0034] if non-workday performance times of the user are greater than or
equal to a second
threshold value, and the classification result is housing, and a housing price
in the attribute
information is greater than or equal to a third threshold value, then obtained
label information of
the user is a high-end living quarter.
[0035] According to another aspect of the present disclosure, a label
information obtaining
apparatus is provided, comprising: an address classification module,
configured to classify
performance addresses of a user to obtain classification results of the
performance addresses,
wherein the performance addresses are addresses where the user performs
orders; and a label
analysis module, configured to analyze according to performance behaviors of
the user specific
to the performance addresses in combination with the classification results to
obtain label
information of the user.
[0036] According to another aspect of the present disclosure, an electronic
device is
provided, comprising a processor; and a memory, storing instructions for
controlling steps of the
foregoing method by the processor.
[0037] According to another aspect of the present disclosure, a computer
readable medium
is provided, and stores computer executable instructions, which achieve steps
of the foregoing
method when being executed.
[0038] The label information obtaining method and apparatus, electronic
device and
computer readable medium provided by embodiments of the present disclosure
obtain label
4
CA 3060822 2019-11-01
information of a user, such as occupation, housing values, living habits and
other relatively
strong financial attributes by classifying performance addresses of the user
7268 and analyzing
in combination with performance behaviors of the user, and evaluate
consumption power of the
user under the precondition of not obtaining sensitive information of the
user.
[0039] It should be understood that the foregoing general description and
subsequent
detailed description are only exemplary and cannot limit the present
disclosure.
Brief Description of The Drawings
[0040] Through detailed description of exemplary embodiments of the present
disclosure
with reference to accompanying drawings, the foregoing and other objectives,
features and
advantages of the present disclosure will be evident.
[0041] FIG. 1 is a flow chart of a label information obtaining method
provided in an
embodiment of the present disclosure.
[0042] FIG. 2 is a flow chart of an alternative label information obtaining
method provided
in an embodiment of the present disclosure.
[0043] FIG. 3 is a flow chart of classified labeling based on word vectors
in an
embodiment of the present disclosure.
[0044] FIG. 4 is a flow chart of text classification training based on word
features in an
embodiment of the present disclosure.
[0045] FIG. 5 is a flow chart of classifying performance addresses of a
user in an
embodiment of the present disclosure.
[0046] FIG. 6 is a schematic diagram of a label information obtaining
apparatus in another
embodiment of the present disclosure.
[0047] FIG. 7 is a schematic diagram of an alternative label information
obtaining apparatus
provided in another embodiment of the present disclosure.
[0048] FIG. 8 is a structural schematic diagram of an electronic device
provided by an
embodiment of the present disclosure and suitable to achieve embodiments of
the present
application.
Detailed Description
[0049] Now, exemplary implementation manners are more comprehensively
described with
CA 3060822 2019-11-01
reference to accompanying drawings. However, exemplary implementation manners
can be
implemented in various forms and should not be understood that they are
limited to the examples
set forth herein; on the contrary, provision of these implementation manners
makes the present
disclosure more comprehensive and complete and comprehensively conveys the
conception of
the exemplary implementation manners to those skilled in the art. The
accompanying drawings
are only schematic diagrams of the present disclosure and not drawn definitely
in proportion. The
same reference signs in the drawings denote the same or similar parts, so the
repetitive
description on them will be omitted here.
[0050] Further, the described characteristics, structures or features can
be combined in one
or more implementation manners in any appropriate way. In the following
description, many
details are provided to fully understand the implementation manners of the
present disclosure.
However, those skilled in the art will be aware that the technical solution of
the present
disclosure can be practiced while omitting one or more of the specific
details, or other methods,
components, apparatuses and steps can be adopted. Under other circumstances,
well-known
structures, methods, apparatuses, realizations, materials or operations are
not stated or described
in detail to avoid stealing the show and blur various aspects of the present
disclosure.
[0051] Some block diagrams shown in the accompanying drawings are
functional entities
and do not have to correspond to physically or logically independent entities.
These functional
entities can be achieved in form of software, or in one or more hardware
modules or integrated
circuits, or in different networks and/or processor devices and /or
microprocessor devices.
[0052] In order to make the objectives, technical solutions and advantages
of the present
invention clearer and more comprehensible, the present invention is further
elaborated in
combination with specific embodiments and with reference to accompanying
drawings.
[0053] In relevant embodiments of the present invention, some attributes of
a user can be
portrayed in a platform typically according to direct consuming behaviors of
the user (such as
group buying, take-away, reservation, movies and tickets). For example,
according to behaviors
of a customer in a platform, such as the movies or tickets that the customer
has browsed or
transacted, the age and likings of the user can be analyzed and portrayed.
However, excavating
financial attributes of a user simply from transactions, browsing and other
behaviors of the user
is likely to be limited by platform category, resulting in inadequate
excavation of financial
attributes of the user.
6
CA 3060822 2019-11-01
[0054] Based on the foregoing problems, some embodiments of the present
disclosure
provide a label information obtaining method and apparatus, an electronic
device and a computer
readable medium, structuralize performance addresses by natural language
processing
technology based on performance addresses of a user, and further obtain
housing values,
occupation, living habits and so on of the user from structuralized
information, thereby
extracting relatively strong financial attributes.
[0055] FIG. 1 is a flow chart of a label information obtaining method
provided in an
embodiment of the present disclosure, comprising the following steps:
[0056] As shown in FIG. 1, at step S110, classifying performance addresses
of a user to
obtain classification results of the performance addresses, wherein the
performance addresses are
addresses where the user performs orders.
[0057] As shown in FIG. 1, at step S120, analyzing according to performance
behaviors of
the user specific to the performance addresses in combination with the
classification results to
obtain label information of the user.
[0058] FIG. 2 is a flow chart of an alternative label information obtaining
method provided
in an embodiment of the present disclosure, comprising the following steps:
[0059] As shown in FIG. 2, at step S210, classifying performance addresses
of a user to
obtain classification results of the performance addresses, wherein the
performance addresses are
addresses where the user performs orders.
[0060] As shown in FIG. 2, at step S220, conducting attribute analysis of
the classification
results in combination with an industry information database to obtain
attribute information of
the performance addresses.
[0061] As shown in FIG. 2, at step S230, analyzing according to performance
behaviors of
the user specific to the performance addresses in combination with the
classification results and
the attribute information to obtain label information of the user.
[0062] Different from the method flow shown in FIG. 1, the flow shown in
FIG. 2 further
conducts attribute analysis according to classification results in combination
with an industry
information database so that user's label can be deeply analyzed according to
performance
behaviors of the user in combination with classification results and attribute
information of the
user to obtain label information of the user.
[0063] The label information obtaining method in this exemplary embodiment
obtains label
7
CA 3060822 2019-11-01
information of a user, such as occupation, housing values, living habits and
other relatively
strong financial attributes through classification and attribute recognition
of performance
addresses of the user and through analysis in combination with performance
behaviors of the
user, and evaluates consumption power of the user under the precondition of
not obtaining
sensitive information of the user.
[0064] Below the flow shown in FIG. 2 is taken as an example to further
describe every step
of the label information obtaining method in embodiments of the present
disclosure.
[0065] At step S210, classifying performance addresses of a user to obtain
classification
results of the performance addresses.
[0066] In an embodiment of the present disclosure, the performance
addresses are addresses
provided by the user to perform orders. For example, addresses written by a
user for order
performance when the user places orders under 020, such as addresses relating
to take-away or
online taxi hailing and other orders, are performance addresses. One take-away
order contains a
performance address, and one online taxi hailing order contains two
performance addresses
(departure place and destination). The performance addresses in this
embodiment mainly take the
performance address in the take-away order as an example, while the two
performance addresses
in the online taxi hailing order, including departure place and destination,
are also applicable.
[0067] In an embodiment of the present disclosure, at step S210,
classifying the performance
addresses to obtain classification results of the performance addresses can be
achieved by the
following two methods for offline model training, to be specific:
[0068] Methods for offline model training may include:
[0069] 1) conducting classified labeling of the historical performance
addresses based on
word vectors to obtain mapping relations between performance addresses and
categories;
[0070] obtaining the classification results specific to the performance
addresses in
combination with the mapping relations between performance addresses and
categories; or
[0071] 2) conducting Softmax training of the historical performance
addresses based on
word features to obtain a text classification model;
[0072] inputting the performance addresses to the text classification model
and outputting
the classification results.
[0073] The foregoing historical performance addresses are addresses where a
plurality of
users in a platform perform historical orders.
8
CA 3060822 2019-11-01
[0074] FIG. 3 is a flow chart of classified labeling based on word vectors
in an embodiment
of the present disclosure, comprising the following steps:
[0075] As shown in FIG. 3, at step S301, extracting trunk information from
the historical
performance addresses.
[0076] In an embodiment of the present disclosure, before this step, the
method further
comprises filtering all historical performance addresses obtained from the
platform. Filtering
methods include deduplication and other operations.
[0077] For example, a complete performance address can be as follows:
[0078] Zhaofeng Plaza, Changning Road, Shanghai City (Fangtang Town
opposite to Xiao
Nan Guo on Floor 4)
[0079] The trunk information in the foregoing performance address is
"Zhaofeng Plaza,
Changning Road, Shanghai City". At this step, information in the brackets is
not considered for
the time being.
[0080] As shown in FIG. 3, at step S302, conducting word segmentation of
the trunk
information by word segmentation technique to obtain a plurality of address
segments.
[0081] In an embodiment of the present disclosure, for English addresses,
space is used as a
separator during word segmentation, and there are many word segmentation
techniques for
Chinese addresses and in general, word segmentation based on dictionary
matching and Markov
model can be selected according to the requirements.
[0082] Still taking the foregoing performance address as an example,
address segments
obtained from step S202 are:
[0083] Zhaofeng Plaza, Changning Road, Shanghai City
[0084] As shown in FIG. 3, at step S303, converting the plurality of
address segments into
word vectors.
[0085] In an embodiment of the present disclosure, at this step, word2vec
technique (e.g.,
skipNgram model) is adopted to convert address segments into word vectors, and
the word
vector technique trains a neutral network model through context between words.
[0086] Still taking the foregoing performance address as an example, each
of address
segments "Shanghai City", "Changning Road" and "Zhaofeng Plaza" will obtain a
word vector.
In the end, these word vectors are accumulated to obtain word vectors to which
this address text
corresponds.
9
CA 3060822 2019-11-01
[0087] As shown in FIG. 3, at step S304, clustering the word vectors.
[0088] In an embodiment of the present disclosure, clustering can be
conducted through
kmeans. For example, performance addresses are clustered into 1000 clusters.
The number of
clusters obtained from clustering is set according to the need. The more the
clusters are, the
larger the workload of needed subsequent labeling will be.
[0089] As shown in FIG. 3, at step S305, conducting corresponding
classified labeling of
classification results of trunk information of the performance addresses
according to clustering
results.
[0090] In an embodiment of the present disclosure, performance addresses in
each cluster
are labeled according to clustering results. For example, 1000 clusters of
performance addresses
closest to the clustering center are artificially labeled, thereby labeling
trunks of all performance
addresses. For example, classified labeling of Zhaofeng Plaza is shopping
mall, classified
labeling of Longemont Hotel is hotel, and classified labeling of Regents Park
is housing.
[0091] FIG. 4 is a flow chart of text classification training based on word
features,
comprising the following steps:
[0092] As shown in FIG. 4, at step S401, configuring a corresponding rule
for address text
and classification.
[0093] In an embodiment of the present disclosure, an artificial dictionary
can be configured.
The artificial dictionary contains a corresponding rule for address text and
classification, and a
format can be: text ¨>classification.
[0094] As shown in FIG. 4, at step S402, matching the historical
performance addresses by
multi-pattern matching, and outputting corresponding classification results
according to the
corresponding rule if the historical performance addresses are matched with
the address text.
[0095] In an embodiment of the present disclosure, multi-pattern matching
is to judge
whether the antecedent of the rule has an inclusion relation in the address
text. Such inclusion
relation is multi-pattern matching, using the foregoing corresponding rule and
multi-pattern
matching can handle some failure cases or bad cases, the antecedent of the
rule is address text,
and the consequent of the rule is hotel, i.e., category.
[0096] For example, a rule in an artificial dictionary is guesthouse
¨>hotel. Based on this
corresponding rule, if text **guesthouse is given, because "guesthouse" is
contained, it is
concluded that the category of "**guesthouse" is hotel.
CA 3060822 2019-11-01
[0097] As shown in FIG. 4, at step S403, segmenting the performance
addresses, performing
multiple combination of obtained segments and conducting Softmax training
based on features of
a single segment or a plurality of segments to obtain the text classification
model.
[0098] In an embodiment of the present disclosure, for corpus obtained from
artificial
labeling, performance addresses are subjected to word segmentation and
combination of bigram
(2 segments) and trigram (3 segments). Based on features of unigram (one
segment), bigram and
trigram, Softmax training is used to obtain a text classification model.
[0099] After training based on the offline model shown in FIG. 3 and FIG.
4, obtained
performance addresses are classified. This process is a process of online
prediction. FIG. 5 is a
flow chart of classifying performance addresses of a user, comprising the
following steps:
[0100] As shown in FIG. 5, at step S501, extracting trunk information from
performance
addresses. Classified labeling can be obtained from address labeling based on
word vectors,
through a flow shown in FIG. 3.
[0101] As shown in FIG. 5, at step S502, predicting using a word feature
model, and
predicting trunk information of performance addresses and content except trunk
information (e.g.,
content in brackets) in turn to obtain prediction results. For example,
prediction is conducted
using a flow shown in the foregoing FIG. 4. If a µrule in the artificial
dictionary can be hit, then
classification results are returned directly according to a corresponding
rule, otherwise the
Softmax model is used to train obtained classification results.
[0102] In a process of online prediction, a prediction method based on word
vectors and
clustering does not consider content except trunk information (e.g., content
in brackets) because
the content in the brackets has many distracters, affecting clustering
results. However, during
online prediction, the offline training model will act upon trunk information
and non-trunk
information in turn, and then prediction results to which the content in the
brackets corresponds
are adopted because the address in the brackets is more accurate and concrete.
[0103] For example, when only trunk information is considered, the
classification result is:
[0104] Zhaofeng Plaza, Changning Road, Shanghai City shopping mall
[0105] If the non-trunk information in the brackets is considered, the
classification result is:
[0106] Zhaofeng Plaza, Changning Road, Shanghai City (Fangtang Town
opposite to Xiao
Nan Guo on Floor 4) incorporated business
[0107] As Fangtang Town is a mass-innovation space, its corresponding
category should be
11
CA 3060822 2019-11-01
incorporated business rather than a shopping mall. Apparently, the latter
classification result is
more accurate.
[0108] Before prediction at step S502, localizers of performance addresses
are processed.
For example, if a performance address contains "opposite to...", localizer
"opposite to" will be
omitted.
[0109] At step S220, conducting attribute analysis of the classification
results in
combination with an industry information database to obtain attribute
information of the
performance addresses.
[0110] In an embodiment of the present disclosure, before conducting
attribute analysis of
the classification results in combination with an industry information
database, this step further
comprises:
[0111] a step of establishing an industry information database,
specifically comprising the
following steps:
[0112] firstly, pre-processing industry classification information;
secondly, establishing an
industry information database according to preprocessed industry
classification information.
[0113] The pre-processing can obtain, clean and structuralize address,
industry and other
information by means of external trading and/or crawling of public data to
obtain information in
a triple form.
[0114] The established industry information database contains a plurality
of pieces of
information, and each piece of triple information comprises:
[0115] a label; classification results; attribute information;
[0116] The classification results include: at least one or more of housing,
hospital, hotel,
office building and leisure and entertainment venue; the attribute information
includes: at least
one or more of housing price, hospital type, hotel star rating, office
building grade and leisure
and entertainment venue grade.
[0117] For example, information in an industry information database is as
follows:
[0118] Property = Regents Park; housing; housing price = Y 100,000/m2;
[0119] Hotel = Shangri-La; hotel; hotel star rating = 5 stars;
[0120] Hospital = Zhongshan Hospital; hospital; hospital category = Grade-A
tertiary
hospital
[0121] In an embodiment of the present disclosure, at this step, conducting
attribute analysis
12
CA 3060822 2019-11-01
of the classification results in combination with an industry information
database to obtain
attribute information specifically comprises:
[0122] obtaining corresponding attribute information, of the performance
addresses through
forward maximum matching of information in the classification results and the
industry
information database.
[0123] Here, an algorithm of forward maximum matching is to separate a
character string,
with a limitation to separation length, then match separated character sub-
strings with the words
in a dictionary, and if the matching is successful, then a next round of
matching is conducted
until all character strings are processed; if the matching is not successful,
then a word is removed
from the tail of the character sub-string and matching is conducted again ,
and the above
operation is repeated.
[0124] For example, a performance address is:
[0125] Regents Park (306, BLK 12)
[0126] Firstly, an obtained classification result is housing, then
screening is conducted
according to the second row in the industry information database, which is
housing, to obtain
housing-related entities, and then an entity containing Regents Park is
obtained through forward
maximum matching, and an attribute to which the performance address
corresponds, i.e., an
entity of housing price information, is obtained. That is, the housing price
is Y 100,000/m2.
[0127] At step S230, analyzing according to performance behaviors of the
user specific to
the performance addresses in combination with the classification results and
the attribute
information to obtain label information of the user.
[0128] In an embodiment of the present disclosure, before specific
analysis, this step further
comprises:
[0129] obtaining performance behaviors of the user specific to the
performance addresses;
wherein the performance behaviors include: at least one of the following
information, including
workday performance times, non-workday performance times, time span of
performance, and
labeling of performance addresses by the user.
[0130] In an embodiment of the present disclosure, analyzing according to
performance
behaviors of the user specific to the performance addresses in combination
with the classification
results and/or the attribute information to obtain label information of the
user comprises:
[0131] if workday performance times of the user are greater than or equal
to a first threshold
13
CA 3060822 2019-11-01
value, and the classification result is hospital, then obtained label
information of the user is
occupation, which is medical staff; or if non-workday performance times of the
user are greater
than or equal to a second threshold value, and the classification result is
housing, and a housing
price in the attribute information is greater than or equal to a third
threshold value, then obtained
label information of the user is a high-end living quarter.
[0132] The threshold values referred to in the foregoing mapping process
can be set
according to the need. For example, the first threshold value to which the
workday performance
times correspond can be set to be five times, and the third threshold value to
which the housing
price corresponds needs to be set in consideration of various cities.
[0133] Analysis and mapping is conducted according to text extracted from
given
performance addresses by the user and performance behaviors of the user
specific to the
performance addresses (workday performance times, holiday performance times,
time span of
performance, labeling of performance addresses by the user, and other
information) to obtain
label information of the user.
[0134] Example: If performance address category = office building, and the
performance
address is labeled as a place of work by the user, then it is speculated that
the user is a
white-collar worker, i.e., the label information is white-collar worker.
[0135] If address category = housing, and developer = Vanke, and housing
price =
Y 75,635.0/m2, the time span of performance at this address is >1 year, and
the holiday
performance times at this address are >=5, then it is speculated that the user
lives in a high-end
living quarter, i.e., the label is high-end living quarter.
[0136] A group fact label obtained from structuralized information of
performance addresses
has certain sequencing ability in quota and risk of the user and can be used
as a strong financial
attribute of the user.
[0137] Based on the foregoing flow, without directly obtaining information
of the user and
classifying performance addresses of the user, the present disclosure can
judge if the user
performs in a place of residence (the performance address category is housing)
or in a place of
work (the address category is office building or incorporated business) or in
any other place.
Then on the basis of classification, attribute information of performance
addresses of the user
can be further analyzed by associating the established industry information
database with
performance addresses, and label information of the user, such as housing
values, occupation,
14
CA 3060822 2019-11-01
living habits and other information, is obtained in combination with
performance behaviors of
the user (performance frequency, workday performance frequency, holiday
performance
frequency, time span of performance dates, etc.), thereby extracting strong
financial attributes of
the user.
[0138] To sum up, the label information obtaining method provided by this
embodiment
obtains label information of a user, such as occupation, housing values,
living habits and other
relatively strong financial attributes through classification and attribute
recognition of
performance addresses of the user and through analysis in combination with
performance
behaviors of the user, and evaluates consumption power of the user under the
precondition of not
obtaining sensitive information of the user.
[0139] FIG. 6 is a schematic diagram of a label information obtaining
apparatus provided in
another embodiment of the present disclosure. As shown in FIG. 6, this
apparatus 600 comprises:
an address classification module 610 and a label analysis module 620.
[0140] The address classification module 610 is configured to classify
performance
addresses of a user to obtain classification results of the performance
addresses, wherein the
performance addresses are addresses where the user performs orders; and the
label analysis
module 620 is configured to analyze according to performance behaviors of the
user specific to
the performance addresses in combination with the classification results to
obtain label
information of the user.
[0141] FIG. 7 is a schematic diagram of an alternative label information
obtaining apparatus
provided in another embodiment of the present disclosure. As shown in FIG. 7,
this apparatus
700 comprises: an address classification module 710, an attribute recognition
module 720 and a
label analysis module 730.
[0142] The address classification modu1e710 is configured to classify
performance
addresses of a user to obtain classification results of the performance
addresses, wherein the
performance addresses are addresses provided by the user to perform orders;
the attribute
recognition module 720 is configured to conduct attribute analysis of the
classification results in
combination with an industry information database to obtain attribute
information of the
performance addresses; and the label analysis module 730 is configured to
analyze according to
performance behaviors of the user specific to the performance addresses in
combination with the
classification results and the attribute information to obtain label
information of the user.
CA 3060822 2019-11-01
[0143] For the functions of the modules in this apparatus, please refer to
relevant
descriptions in the foregoing method embodiments. They are not described again
here.
[0144] To sum up, the label information obtaining apparatus in this
embodiment obtains
label information of a user, such as occupation, housing values, living habits
and other relatively
strong financial attributes through classification and attribute recognition
of performance
addresses of the user and through analysis in combination with performance
behaviors of the
user, and evaluates consumption power of the user under the precondition of
not obtaining
sensitive information of the user.
[0145] On the other hand, the present disclosure further provides an
electronic device,
comprising a processor and a memory, storing operation instructions for
controlling the
following method by the foregoing processor:
[0146] classifying performance addresses of a user to obtain classification
results Of the
performance addresses, wherein the performance addresses are addresses where
the user
performs orders; analyzing according to performance behaviors of the user
specific to the
performance addresses in combination with the classification results to obtain
label information
of the user. Or
[0147] classifying performance addresses of a user to obtain classification
results of the
performance addresses, wherein the performance addresses are addresses where
the user
performs orders; conducting attribute analysis of the classification results
in combination with an
industry information database to obtain attribute information of the
performance addresses;
analyzing according to performance behaviors of the user specific to the
performance addresses
in combination with, the classification results and the attribute information
to obtain label
information of the user.
[0148] Below FIG. 8 is referred to. FIG. 8 is a structural schematic
diagram of a computer
system 800 of an electronic device suitable to achieve embodiments of the
present application.
The electronic device shown in FIG. 8 is only an example and should not impose
any restriction
on functions and use scope of embodiments of the present application.
[0149] As shown in FIG. 8, the computer system 800 comprises a central
processing unit
(CPU) 801, which can execute various appropriate actions and processing
according to programs
stored in a read only memory (ROM) 802 or programs loaded from a storage unit
805 to a
random access memory (RAM) 803. The RAM 803 also stores all kinds of programs
and data
16
CA 3060822 2019-11-01
that operation of the system 800 needs. The CPU 801, the ROM 802 and the RAM
803 are
mutually, connected via a bus 804. An input/output (I/0) interface 805 is also
connected to the
bus 804.
[0150] The following components are connected to the I/0 interface 805: an
input unit 806
comprising a keyboard, a mouse, etc.; an output unit 808 comprising for
example a cathode ray
tube (CRT), a liquid crystal display (LCD), a loudspeaker, etc.; a storage
unit 808 comprising a
hard disk, etc.; as well as a communication unit 809 comprising for example an
LAN card,
Modem and other network interface cards. The communication unit 809 performs
communication processing via a network such as the Internet. The driver 810 is
also connected to
the I/0 interface 805 according to the need. A detachable medium 811, such as
magnetic disk,
optical disk, magnetic optical disc and semiconductor memory, is installed on
the driver 810
according to the need so that computer programs read from the detachable
medium 811 are
installed and saved in the storage unit 808 as needed.
[0151] Specially, according to embodiments of the present disclosure, the
process described
with reference to a flow chart in the preceding part of the text can be
achieved as a computer
software program. For example, an embodiment of the present disclosure
includes a computer
program product, comprising a computer program loaded on a computer readable
medium. This
computer program contains a program code used to implement the method shown in
the flow
chart. In such embodiment, this computer program can be downloaded and
installed from the
network via the communication unit 809, and/or installed from the detachable
medium 811.
When this computer program is executed by the CPU 801, the foregoing functions
defined in the
system of the present application are executed.
[0152] It needs to be explained that the computer readable medium shown in
the present
application can be a computer readable signal medium or a computer readable
medium or any
combination of the foregoing two. The computer readable medium for example can
be ¨ without
limitation ¨ an electric, magnetic, optical, electromagnetic, infrared or
semiconductor system,
apparatus or device, or any combination thereof. More concrete examples of the
readable
memory media may include without limitation: electric connection with one or
more conductors,
portable computer magnetic disk, hard disk, random access memory (RAM), read
only memory
(ROM), erasable programmable read-only memory (EPROM or flash memory), optical
fiber,
portable compact disk read only memory (CD-ROM), optical memory module,
magnetic
17
CA 3060822 2019-11-01
memory module or any appropriate combination thereof. In the present
application, a readable
memory medium can be any tangible medium containing or storing programs, which
can be used
by an instruction execution system, apparatus or device or can be used in
combination with an
instruction execution system, apparatus or device. In the present application,
computer readable
signal media may include data signals transmitted in base band or as part of
carriers, and carry
computer readable program codes. Such transmitted data signals can adopt
various forms,
including but not limited to: electromagnetic signals, optical signals or any
appropriate
combination thereof. The computer readable signal media may also be any
computer readable
media except readable memory media. Such computer readable media can send,
transmit or
transfer programs used by an instruction execution system, apparatus or device
or used in
combination with an instruction execution system, apparatus or device. The
program codes
contained on a computer readable medium can be transferred by any appropriate
medium,
including but not limited to: wireless, wired, optical cable and RF, or any
appropriate
combination thereof
[0153] The flow charts and block diagrams in the accompanying drawings show
system
architectures, functions and operations likely achieved according to the
systems, methods and
computer program products of various embodiments of the present application.
At this point,
every box in the flow charts or block diagrams can represent a part of a
module, a program
segment or a code. The foregoing part of a module, a program segment or a code
comprises one
or more executable instructions used to achieve a specified logical function.
It should also be
noted that in the realization of some replacements, functions marked in boxes
may also occur in
a sequence different from that marked in the accompanying drawings. For
example, two boxes
expressed successively can be executed basically in parallel in fact, and
sometimes, they can be
executed in a reverse sequence, depending on involved functions. It should
also be noted that
each box in block diagrams or flow charts and combinations of boxes in the
block diagrams or
flow charts can be achieved using a special hardware-based system that
executes specified
functions, or can be achieved using a combination of special hardware and
computer
instructions.
[0154] Description of units involved in embodiments of the present
application can be
achieved in form of software, or in form of hardware. The described units may
also be arranged
in a processor. For example, it can be described as: a processor comprising a
sending unit, an
18
CA 3060822 2019-11-01
obtaining unit, a determining unit and a first processing unit. Names of these
units do pot
constitute limitation to these units under some circumstances. For example,
the sending unit may
also be described as "a unit sending a picture obtaining request to a
connected server".
[0155] On the other hand, the present disclosure further provides a
computer readable
medium, which may be included in a device described in the foregoing
embodiments; or may
exist separately, and is not assembled into the device. The foregoing computer
readable medium
carries one or more programs. When the foregoing one or more programs are
executed by one of
such devices, the device includes the following method steps:
[0156] classifying performance addresses of a user to obtain classification
results of the
performance addresses, wherein the performance addresses are addresses
provided by the user to
perform orders; and analyzing according to performance behaviors of the user
specific to the
performance addresses in combination with the classification results to obtain
label information
of the user. Or
[0157] classifying performance addresses of a user to obtain classification
results of the
performance addresses, wherein the performance addresses are addresses where
the user
performs orders; conducting attribute analysis of the classification results
in combination with an
industry information database to obtain attribute information of the
performance addresses;
analyzing according to performance behaviors of the user specific to the
performance addresses
in combination with the classification results and the attribute information
to obtain label
information of the user.
[0158] It should be clearly understood that the present disclosure
describes how to form and
use specific examples, but the principles of the present disclosure are not
limited to any details of
these examples. On the contrary, based on teaching of the content disclosed by
the present
disclosure, these principles can be applied in many other implementation
manners.
[0159] Exemplary implementation manners of the present disclosure are
presented and
described above. It should be understood that the present disclosure is not
limited to the detailed
structures, setting modes or implementation methods described here; on the
contrary, the present
disclosure intends to cover all modifications and equivalent settings included
in the spirit and
scope of the claims.
19
CA 3060822 2019-11-01
