CN115049498B - Financial big data management system and method - Google Patents
Financial big data management system and method Download PDFInfo
- Publication number
- CN115049498B CN115049498B CN202210961269.0A CN202210961269A CN115049498B CN 115049498 B CN115049498 B CN 115049498B CN 202210961269 A CN202210961269 A CN 202210961269A CN 115049498 B CN115049498 B CN 115049498B
- Authority
- CN
- China
- Prior art keywords
- user
- financial transaction
- characteristic
- financial
- period
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Abstract
The invention discloses a financial big data management system and a financial big data management method, which relate to the technical field of financial data management and comprise the following steps of S100: acquiring and storing financial transaction records generated by each user in each online channel by applying for authorized behaviors to each user; step S200: calculating a first user portrait label value for each first type of characteristic user; calculating a first user portrait label value for each second type of characteristic user; step S300: respectively analyzing the ratio of the financial transaction structures of the characteristic users in the first characteristic user set and the second characteristic user set; step S400: capturing a unit acquisition period corresponding to the minimum floating change of the financial transaction structure ratio for each characteristic user in the first characteristic user set and the second characteristic user set respectively; step S500: and respectively acquiring the financial transaction structure ratio of each characteristic user in each final unit acquisition period to obtain a second user portrait label value.
Description
Technical Field
The invention relates to the technical field of financial data management, in particular to a financial big data management system and a financial big data management method.
Background
The coverage range of financial big data is extremely wide, the habits of everyone on financial appeal are different for individuals, and product services provided by financial companies need to be iterated continuously to meet or satisfy the requirements of customers; therefore, the generation of the user financial portrait is necessary, and if the person knows the financial portrait of the person, the person can scientifically grasp the financial appeal of the person; the financial enterprise can learn about the customer and improve the product to meet the customer habit by means of the financial portrait of the user.
Disclosure of Invention
The present invention is directed to a financial big data management system and method, so as to solve the problems mentioned in the background art.
In order to solve the technical problems, the invention provides the following technical scheme: a financial big data management method comprises the following steps:
step S100: the user obtains a personal account after completing identity authentication by filling personal identity information in a user landing page of the management system; the management system collects and stores financial transaction records generated by each user in each online channel by applying for authorized behaviors to each user;
step S200: setting an initial unit acquisition period
In the collection period for each user respectively
The information is sorted based on the collection period of each user
The method comprises the steps of collecting conditions of financial transaction records, and classifying users to obtain a first characteristic user set and a second characteristic user set; collecting period of each first characteristic user in first characteristic user set
The financial transaction record information generated in the database is used for calculating the first user portrait label value of each first characteristic user; collecting period of each second characteristic user in second characteristic user set
Internal financial transaction acquisition conditions, for acquisition period
Adjusting to obtain adjusted acquisition period
Calculating the label value of the first user portrait for each second type of characteristic user;
step S300: respectively analyzing the ratio of the financial transaction structures of the characteristic users in the first characteristic user set and the second characteristic user set; the financial transaction structure ratio is a ratio formed by different corresponding financial transaction amounts generated by users on different types of financial transaction products;
step S400: respectively adjusting the dynamic range of the unit acquisition period for each characteristic user in the first characteristic user set and the second characteristic user set, respectively capturing the corresponding unit acquisition period when the floating change of the financial transaction structure ratio is minimum for each characteristic user in the first characteristic user set and the second characteristic user set, and taking the unit acquisition period as the final unit acquisition period of each characteristic user;
step S500: respectively acquiring the financial transaction structure ratio of each characteristic user in each final unit acquisition period; and taking the financial transaction structure ratio value presented by each characteristic user in each final unit acquisition period as a second user portrait label value presented by each characteristic user in each final unit acquisition period.
Further, step S200 includes:
step S201: setting acquisition period
Respectively collecting the collection periods of the users
All financial transaction records generated in the system are respectively accumulated for each user in the acquisition period
The total number of the financial transaction records generated in the financial transaction system, and the record threshold value is set
；
Step S202: if the collection period of a certain user is accumulated
The total number of internally generated financial transaction records is greater than or equal to the record threshold
Classifying a user into a first type of characteristic users, and collecting all the first type of characteristic users to obtain a first characteristic user set; calculating a first user portrait tag value for each first class of feature users separately
(ii) a Wherein, the first and the second end of the pipe are connected with each other,
indicating each user of the first class of characteristics during the acquisition cycle
The total number of the financial transaction records actually generated in the financial transaction system;
representing users of the first class
The accumulated financial transaction amount;
step S203: if the collection period of a certain user is accumulated
The total number of internally generated financial transaction records is less than the record threshold
Classifying a certain user into a second type of characteristic users, and collecting all the second type of characteristic users to obtain a second characteristic user set; in the second feature user set, to record the bar threshold
For the screening condition, the total number of the financial transaction records of the users with the second type of characteristics is captured when the total number of the financial transaction records is larger than or equal to the record threshold value
The shortest acquisition time period corresponding to each second-class characteristic user
(ii) a The shortest acquisition time period corresponding to all the users with the second type of characteristics
In (1), screening out the minimum value
；
Step S204: respectively accumulating at the minimum value for each user with the second type of characteristics
Total number of financial transaction records generated internally
(ii) a Calculating a first user portrait tag value for each second type of feature user
(ii) a Wherein the content of the first and second substances,
indicating each of the second class of features at
The accumulated financial transaction amount;
the first user portrait value calculated for each characteristic user reflects the frequency degree of the user in financial appeal; for users who have infrequent appeal, the data acquisition period is changed, so that the acquired financial transaction records have personal financial appeal characteristics in the acquisition period.
Further, step S300 includes:
step S301: will collect the cycle
As to each first characteristic user in the first class characteristic user setAn initial unit acquisition period for acquiring financial transaction records; will be minimum value
The initial unit acquisition period is used for acquiring financial transaction records of each second characteristic user in the second type characteristic user set;
step S302: respectively collecting the first characteristic users at intervals of an initial unit collecting period
Is circulated and carried out
Secondary data acquisition, namely, respectively carrying out acquisition on each second characteristic user at intervals of an initial unit acquisition period
Is circulated and carried out
Acquiring secondary data, wherein a financial transaction record set is correspondingly acquired in each unit period;
step S303: extracting the financial transaction product types related in each financial transaction record set for each characteristic user, summarizing the total financial amount corresponding to the financial transaction products of each type to obtain the summarized amount of the financial transaction products of all types, and obtaining the financial transaction structure ratio corresponding to each financial transaction record set:
(ii) a Wherein the content of the first and second substances,
respectively represent the 1 st, 2 nd,
H different categories of financial transaction products;
respectively indicate the characteristic user corresponds to
The total financial amount on the category financial transaction product is a ratio of the financial amount on the aggregated amount.
Further, step S400 includes:
step S401: setting unit acquisition period for each first characteristic user in first characteristic user set
Unit float value of
Unit acquisition period of each first feature user
The floating interval T1 of (a) is:
(ii) a Respectively carrying out the operation on each first characteristic user by adopting each unit acquisition period in the floating interval T1 one by one
The sub-data are collected circularly, and each unit collection period is obtained
A financial transaction structure ratio;
step S402: setting unit floating value of unit acquisition period for each second characteristic user in second characteristic user set
And the floating interval T2 of the unit acquisition cycle of each second characteristic user is as follows:
(ii) a Respectively carrying out the operation of adopting each unit acquisition cycle in the floating interval T2 one by one for each second characteristic user
The sub-data are collected circularly to obtain the data corresponding to each unit collection period
A financial transaction structure ratio;
step S403: respectively comparing the structural deviation between the financial transaction structure ratios corresponding to every two adjacent unit acquisition periods for each characteristic user to obtain a structural deviation set between every two adjacent financial transaction structure ratios; each structure deviation in the structure deviation set is a financial amount ratio deviation presented on a deviation type item between two financial transaction structure ratios or a financial amount ratio deviation presented on the same type item between two financial transaction structure ratios; each first characteristic user is correspondingly obtained by adopting each unit acquisition period
A set of structural deviations; each second characteristic user is obtained by adopting each unit acquisition period
A set of structural deviations;
the dynamic adjustment of the acquisition period of each characteristic user is performed to consider that the financial transaction habits of different users are different and the inertia periods of the financial transactions are different, so that the acquisition period analysis of the optimal matching is performed on different users, and the finally obtained user portrait is more accurate.
Further, step S400 further includes:
step S404: respectively corresponding each first characteristic user in each unit acquisition period
The structure deviation sets are arranged according to the comparison sequence to obtain the first characteristic users
A sequence of structural deviation sets consisting of sets of structural deviations:
wherein, the first and the second end of the pipe are connected with each other,
respectively correspondingly represent adjacent 1 st and 2 nd; 2, 3; first, the
、
1 st, 2 nd,
、
A set of structural deviations;
step S405: respectively obtained by the second characteristic users in each unit acquisition cycle
The structural deviation sets are arranged according to the sequence to obtain the users with the second characteristics
A sequence of structural deviation sets consisting of sets of structural deviations:
wherein the content of the first and second substances,
respectively correspondingly represent adjacent 1 st and 2 nd; 2, 3; first, the
、
1 st, 2 nd,
、
A set of structural deviations;
further, step S400 further includes:
step S406: respectively carrying out information investigation on the structure deviation set sequence obtained by each characteristic user in each unit acquisition period; selecting a structural deviation set sequence with the minimum average deviation value among all structural deviation set sequences as a target sequence; the average deviation value comprises an average deviation item value and an average deviation financial transaction amount ratio value;
step S407: and respectively taking the unit acquisition period corresponding to the obtained target sequence as a final unit acquisition period for acquiring the financial transaction records of each characteristic user.
In order to better realize the method, a financial big data management system is also provided, and the system comprises a financial transaction record acquisition and storage module, a financial transaction record information management module, a financial transaction structure ratio analysis module, a unit acquisition period dynamic adjustment module and a user portrait label value calculation module;
the financial transaction record acquisition and storage module is used for receiving the personal account information of the user and acquiring and storing financial transaction records generated by the user in each online channel;
a financial transaction record information management module for each user in an initial acquisition cycle
The financial transaction records generated in the financial transaction system are subjected to information combing, and the users are classified to obtain a first characteristic user set and a second characteristic user set;
the financial transaction structure ratio analysis module is used for receiving the data in the financial transaction record information management module and respectively carrying out financial transaction structure ratio analysis on each feature user in the first feature user set and the second feature user set; the financial transaction structure ratio is the ratio formed by different corresponding financial amounts generated by the user on different types of financial transaction products;
the unit acquisition cycle dynamic adjustment module is used for respectively adjusting the dynamic range of the unit acquisition cycle of each feature user in the first feature user set and the second feature user set, respectively capturing the corresponding unit acquisition cycle when the fluctuation of the ratio of the financial transaction structure is minimum for each feature user in the first feature user set and the second feature user set, and taking the unit acquisition cycle as the final unit acquisition cycle;
and the user portrait label value calculation module is used for receiving data in the financial transaction record information management module, the financial transaction structure ratio analysis module and the unit acquisition period dynamic adjustment module and calculating a first user portrait label value and a second user portrait label value for each characteristic user.
Furthermore, the user portrait label value calculation module comprises a first user portrait label value calculation unit and a second user portrait label value calculation unit;
the first user portrait tag value calculation unit is used for receiving data in the financial transaction record information management module and calculating a first user portrait tag value for each characteristic user;
and the second user portrait label value calculation unit is used for receiving data in the financial transaction structure ratio analysis module and the unit acquisition period dynamic adjustment module and calculating a second user portrait label value for each characteristic user.
Compared with the prior art, the invention has the following beneficial effects: the method carries out user portrait analysis based on financial transaction records generated by each user in different periods; the transaction record acquisition period of the user is dynamically adjusted, the acquisition period which is most adaptive to each user is obtained through analysis, the condition that inertia periods of different people in financial transaction are different is considered, portrait analysis is carried out on data acquired by different users in the acquisition period based on optimal matching, and the user portrait obtaining method is beneficial to enabling users to obtain portrait more accurately finally.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart illustrating a financial big data management method according to the present invention;
fig. 2 is a schematic structural diagram of a financial big data management system according to the present invention.
Detailed Description
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, and 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.
Referring to fig. 1-2, the present invention provides a technical solution: a financial big data management method comprises the following steps:
step S100: the user obtains a personal account after completing identity authentication by filling in personal identity information in a user landing page of the management system; the management system collects and stores financial transaction records generated by each user in each online channel by applying for authorized behaviors to each user;
step S200: setting an initial unit acquisition period
In the collection period for each user respectively
The information is sorted based on the collection period of each user
Acquiring the condition of financial transaction records in the system, and classifying the users to obtain a first characteristic user set and a second characteristic user set; collecting period of each first characteristic user in first characteristic user set
The financial transaction record information generated in the database is used for calculating the first user portrait label value of each first characteristic user; collecting period of each second characteristic user in second characteristic user set
Internal financial transaction acquisition conditions, versus acquisition period
Adjusting to obtain adjusted acquisition period
Calculating the label value of the first user portrait for each second type of characteristic user;
wherein, step S200 includes:
step S201: setting acquisition period
Respectively collecting the collection periods of the users
All financial transaction records generated in the system are respectively accumulated for each user in the collection period
The total number of the financial transaction records generated in the financial transaction system, and the record threshold value is set
；
Step S202: if the collection period of a certain user is accumulated
The total number of internally generated financial transaction records is greater than or equal to the record threshold
Classifying a user into a first type of characteristic users, and collecting all the first type of characteristic users to obtain a first characteristic user set; calculating a first user portrait tag value for each first class of feature users separately
(ii) a Wherein the content of the first and second substances,
indicating each user of the first class of characteristics during the acquisition cycle
The total number of the financial transaction records actually generated in the financial transaction system;
representing users of the first class
The accumulated financial transaction amount;
step S203: if the collection period of a certain user is accumulated
The total number of internally generated financial transaction records is less than the record threshold
Classifying a certain user into a second type of characteristic users, and collecting all the second type of characteristic users to obtain a second characteristic user set; in the second feature user set, to record the bar threshold
For the screening condition, the total number of the financial transaction records of the users with the second type of characteristics is captured when the total number of the financial transaction records is larger than or equal to the record threshold value
The shortest acquisition time period corresponding to each second-class characteristic user
(ii) a The shortest acquisition time period corresponding to all the users with the second type of characteristics
In (1), screening out the minimum value
；
Step S204: respectively accumulating the users with the second type of characteristics at the minimum value
Total number of financial transaction records generated internally
(ii) a Calculating a first user portrait tag value for each second type of feature user
(ii) a Wherein the content of the first and second substances,
indicating each of the second class of features at
The accumulated financial transaction amount;
step S300: respectively analyzing the ratio of the financial transaction structures of the characteristic users in the first characteristic user set and the second characteristic user set; the financial transaction structure ratio is a ratio formed by different corresponding financial transaction amounts generated by users on different types of financial transaction products;
wherein, step S300 includes:
step S301: will collect the cycle
The initial unit acquisition period is used for acquiring financial transaction records of each first characteristic user in the first-class characteristic user set; will be minimum value
The initial unit acquisition period is used for acquiring financial transaction records of each second characteristic user in the second type characteristic user set;
step S302: respectively collecting the first characteristic users at intervals of an initial unit collecting period
Is circulated and carried out
Acquiring secondary data, and respectively carrying out initial unit acquisition period at intervals on each second characteristic user
Is circulated and carried out
Acquiring secondary data, wherein a financial transaction record set is correspondingly acquired in each unit period;
step S303: extracting the financial transaction product types related in each financial transaction record set for each characteristic user, summarizing the total financial amount corresponding to each type of financial transaction product to obtain the summarized amount of all types of financial transaction products, and obtaining the financial transaction structure ratio corresponding to each financial transaction record set:
(ii) a Wherein the content of the first and second substances,
respectively represent the 1 st, 2 nd,
H different categories of financial transaction products;
respectively indicate the characteristic user corresponds to
A financial amount over the aggregated amount for a total financial amount over a category financial transaction product;
step S400: respectively adjusting the dynamic range of a unit acquisition period for each characteristic user in the first characteristic user set and the second characteristic user set, capturing the corresponding unit acquisition period when the floating change of the ratio of the financial transaction structure is minimum, and taking the unit acquisition period as the final unit acquisition period of each characteristic user;
wherein, step S400 includes:
step S401: setting unit acquisition period for each first characteristic user in first characteristic user set
Unit of floating value of
Unit acquisition period of each first feature user
The floating interval T1 of (a) is:
(ii) a Respectively carrying out the operation on each first characteristic user by adopting each unit acquisition period in the floating interval T1 one by one
The sub-data are collected circularly to obtain the data corresponding to each unit collection period
A financial transaction structure ratio;
step S402: setting unit floating value of unit acquisition period for each second characteristic user in second characteristic user set
And the floating interval T2 of the unit acquisition cycle of each second characteristic user is as follows:
(ii) a Respectively carrying out the operation on each second characteristic user by adopting each unit acquisition period in the floating interval T2 one by one
The sub-data are collected circularly to obtain the data corresponding to each unit collection period
A financial transaction structure ratio;
step S403: respectively comparing the structural deviation between the financial transaction structure ratios corresponding to every two adjacent unit acquisition periods for each characteristic user to obtain a structural deviation set between every two adjacent financial transaction structure ratios; each structural deviation in the structural deviation set is a financial amount ratio deviation presented on a deviation category item between two financial transaction structural ratios, or twoThe financial amount represented on the same kind of items between the financial transaction structure ratio accounts for the ratio deviation; each first characteristic user is correspondingly obtained by adopting each unit acquisition period
A set of structural deviations; each second characteristic user is obtained by adopting each unit acquisition period
A set of structural deviations;
for example, a financial transaction structure ratio is
(ii) a A financial transaction structure ratio of
So that the structural deviation between the two financial transaction structure ratios is integrated as
Is concretely provided with
Step S404: respectively corresponding each first characteristic user in each unit acquisition period
The structure deviation sets are arranged according to the comparison sequence to obtain the first characteristic users
A sequence of structural deviation sets consisting of sets of structural deviations:
wherein the content of the first and second substances,
respectively correspondingly represent adjacent 1 st and 2 nd; 2, 3; first, the
、
1 st, 2 nd,
、
A set of structural deviations;
step S405: respectively obtained by the second characteristic users in each unit acquisition cycle
The structural deviation sets are arranged according to the sequence to obtain the users with the second characteristics
A sequence of structural deviation sets consisting of sets of structural deviations:
wherein, the first and the second end of the pipe are connected with each other,
respectively correspondingly represent adjacent 1 st and 2 nd; 2, 3; first, the
、
1 st, 2 nd,
、
A set of structural deviations;
step S406: respectively carrying out information investigation on the structure deviation set sequence obtained by each characteristic user in each unit acquisition period; selecting a structure deviation set sequence with the minimum average deviation value among all structure deviation sets as a target sequence; the average deviation value comprises an average deviation item value and an average deviation financial transaction amount ratio;
step S407: respectively taking the unit acquisition period corresponding to the obtained target sequence as a final unit acquisition period for acquiring financial transaction records of each characteristic user;
step S500: respectively acquiring the financial transaction structure ratio of each characteristic user in each final unit acquisition period; and taking the financial transaction structure ratio value presented by each characteristic user in each final unit acquisition period as a second user portrait label value presented by each characteristic user in each final unit acquisition period.
In order to better realize the method, a financial big data management system is also provided, and the system comprises a financial transaction record acquisition and storage module, a financial transaction record information management module, a financial transaction structure ratio analysis module, a unit acquisition period dynamic adjustment module and a user portrait label value calculation module;
the financial transaction record acquisition and storage module is used for receiving the personal account information of the user and acquiring and storing financial transaction records generated by each user in each online channel;
financial transaction record information management module for each user in initial acquisition period
The internally generated financial transaction records are subjected to information combing, and the users are classified to obtain a first characteristic user setAnd a second set of characteristic users;
the financial transaction structure ratio analysis module is used for receiving the data in the financial transaction record information management module and respectively carrying out financial transaction structure ratio analysis on each feature user in the first feature user set and the second feature user set; the financial transaction structure ratio is the ratio formed by different corresponding financial amounts generated by the user on different types of financial transaction products;
the unit acquisition period dynamic adjustment module is used for respectively adjusting the dynamic range of the unit acquisition period for each characteristic user in the first characteristic user set and the second characteristic user set, respectively capturing the unit acquisition period corresponding to the minimum floating change of the financial transaction structure ratio for each characteristic user in the first characteristic user set and the second characteristic user set, and taking the unit acquisition period as the final unit acquisition period;
and the user portrait label value calculation module is used for receiving data in the financial transaction record information management module, the financial transaction structure ratio analysis module and the unit acquisition period dynamic adjustment module and calculating a first user portrait label value and a second user portrait label value for each characteristic user.
The user portrait label value calculating module comprises a first user portrait label value calculating unit and a second user portrait label value calculating unit;
the first user portrait tag value calculation unit is used for receiving data in the financial transaction record information management module and calculating a first user portrait tag value for each characteristic user;
and the second user portrait label value calculation unit is used for receiving data in the financial transaction structure ratio analysis module and the unit acquisition period dynamic adjustment module and calculating a second user portrait label value for each characteristic user.
It should be noted that, in this document, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," 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.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A financial big data management method is characterized by comprising the following steps:
step S100: the user obtains a personal account after completing identity authentication by filling in personal identity information in a user landing page of the management system; the management system collects and stores financial transaction records generated by each user in each online channel by applying for authorized behaviors to each user;
step S200: setting an initial unit acquisition period
In the collection period for each user respectively
Information combing of internally generated financial transaction records based on each user during the collection period
The financial transaction records in the system are collected, and the users are classified to obtain the first specialA characteristic user set and a second characteristic user set; collecting period of each first type of characteristic user in first characteristic user set
The internally generated financial transaction record information is used for calculating a first user portrait label value for each first-class characteristic user; collecting period of each second type of characteristic user in second characteristic user set
The collection condition of financial transaction, the collection period
Adjusting to obtain adjusted acquisition period
Calculating the label value of the first user portrait for each second type of characteristic user;
step S300: respectively analyzing the ratio of the financial transaction structures of the feature users in the first feature user set and the second feature user set; the financial transaction structure ratio is a ratio formed by different corresponding financial transaction amounts generated by users on different types of financial transaction products;
step S400: respectively adjusting the dynamic range of a unit acquisition period for each characteristic user in the first characteristic user set and the second characteristic user set, capturing the corresponding unit acquisition period when the floating change of the ratio of the financial transaction structure is minimum, and taking the unit acquisition period as the final unit acquisition period of each characteristic user;
step S500: respectively acquiring the financial transaction structure ratio of each characteristic user in each final unit acquisition period; and taking the financial transaction structure ratio value presented by each characteristic user in each final unit acquisition period as a second user portrait label value presented by each characteristic user in each final unit acquisition period.
2. The financial big data management method according to claim 1, wherein the step S200 comprises:
step S201: setting acquisition period
Respectively collecting the user in the collection period
All financial transaction records generated in the device are respectively accumulated in the acquisition period for each user
The total number of financial transaction records generated in the financial transaction system, and the threshold value of the record
；
Step S202: if a user is accumulated in the collection period
The total number of internally generated financial transaction records is greater than or equal to the record threshold
Classifying the certain user as a first type of characteristic user, and collecting all the first type of characteristic users to obtain a first characteristic user set; calculating a first user portrait label value for each of the first class of feature users, respectively
(ii) a Wherein the content of the first and second substances,
indicating each of said first class of feature users during an acquisition cycle
The total number of the financial transaction records actually generated in the financial transaction system;
representing each of said first class of features as a user
The accumulated financial transaction amount;
step S203: if a user is accumulated in the collection period
The total number of internally generated financial transaction records is less than the record threshold
Classifying the certain user into a second type of characteristic user, and collecting all the second type of characteristic users to obtain a second characteristic user set; in the second feature user set, threshold with the record bar
For screening conditions, the total number of the financial transaction records of the users with the second type of characteristics is captured when the total number of the financial transaction records of the users with the second type of characteristics is larger than or equal to the record strip threshold value
The shortest acquisition time period corresponding to each user with the second type of characteristics
(ii) a The shortest acquisition time period corresponding to all the users with the second type of characteristics
In (1), screening out the minimum value
；
Step S204: respectively accumulating at the minimum value for each user with the second type of characteristics
Total number of financial transaction records generated internally
(ii) a Calculating the first user portrait label value for each second type characteristic user respectively
(ii) a Wherein the content of the first and second substances,
representing said second class of feature users in
The accumulated financial transaction amount.
3. The financial big data management method according to claim 2, wherein the step S300 comprises:
step S301: will collect the cycle
The method comprises the steps of taking an initial unit acquisition cycle for acquiring financial transaction records of each first-class characteristic user in a first-class characteristic user set; will be minimum value
The initial unit acquisition period is used for acquiring financial transaction records of each second type characteristic user in the second type characteristic user set;
step S302: respectively collecting the first class characteristic users at intervals of initial unitsIntegration period
Is circulated and carried out
Collecting secondary data, and collecting each second type characteristic user at intervals of initial unit collection period
Is circulated and carried out
Acquiring secondary data, wherein a financial transaction record set is correspondingly acquired in each unit period;
step S303: extracting the financial transaction product types related in each financial transaction record set for each characteristic user, summarizing the total financial amount corresponding to the financial transaction products of each type to obtain the summarized amount of the financial transaction products of all types, and obtaining the financial transaction structure ratio corresponding to each financial transaction record set:
(ii) a Wherein the content of the first and second substances,
respectively represent the 1 st, 2 nd,
H different categories of financial transaction products;
respectively indicate the characteristic user corresponds to
Population on a category financial transaction productFinancial amounts are ratioed to the aggregate amount.
4. The financial big data management method according to claim 3, wherein the step S400 comprises:
step S401: setting unit collection period for each first type of feature user in first feature user set
Unit of floating value of
A unit acquisition period for each of said first feature users
The floating interval T1 of (a) is:
(ii) a Respectively adopting each unit acquisition period in the floating interval T1 to carry out on each first-class characteristic user one by one
The sub-data are collected circularly to obtain the data corresponding to each unit collection period
A financial transaction structure ratio;
step S402: setting unit floating value of unit collection period for each second type of feature users in second feature user set
The floating interval T2 of the unit collecting period of each second-class feature user is:
(ii) a Respectively carrying out the operation of adopting each unit acquisition cycle in the floating interval T2 one by one for each user with the second class of characteristics
The sub-data are collected circularly to obtain the data corresponding to each unit collection period
A financial transaction structure ratio;
step S403: respectively comparing the structural deviation between the financial transaction structure ratios corresponding to every two adjacent unit acquisition periods for each characteristic user to obtain a structural deviation set between every two adjacent financial transaction structure ratios; each structure deviation in the structure deviation set is a financial amount ratio deviation presented on a deviation type item between two financial transaction structure ratios or a financial amount ratio deviation presented on the same type item between two financial transaction structure ratios; all the first kind of characteristic users are correspondingly obtained by adopting each unit acquisition period
A set of structural deviations; all the users with the second kind of characteristics are obtained by adopting each unit acquisition cycle
A set of structural deviations.
5. The method for managing financial big data according to claim 4, wherein said step S400 further comprises:
step S404: respectively corresponding all the first-class characteristic users in each unit acquisition period
The structure deviation sets are arranged according to the comparison sequence to obtain the users with the first type of characteristics
A sequence of structural deviation sets consisting of sets of structural deviations:
wherein the content of the first and second substances,
respectively correspondingly represent adjacent 1 st and 2 nd; 2, 3; first, the
、
1 st, 2 nd,
、
A set of structural deviations;
step S405: respectively obtained by the second type characteristic users under each unit acquisition period
The structural deviation sets are arranged according to the order to obtain the users with the second type of characteristics
A sequence of structural deviation sets consisting of sets of structural deviations:
wherein the content of the first and second substances,
respectively correspondingly represent adjacent 1 st and 2 nd; 2, 3; first, the
、
1 st, 2 nd,
、
A set of structural deviations.
6. The financial big data management method according to claim 5, wherein the step S400 further comprises:
step S406: respectively carrying out information investigation on the structure deviation set sequence obtained by each characteristic user in each unit acquisition period; selecting a structural deviation set sequence with the minimum average deviation value among all structural deviation set sequences as a target sequence; the average deviation value comprises an average deviation item value and an average deviation financial transaction amount ratio value;
step S407: and respectively taking the unit acquisition period corresponding to the obtained target sequence as a final unit acquisition period for acquiring the financial transaction records of each characteristic user.
7. A financial big data management system applied to the financial big data management method of any one of claims 1 to 6, wherein the system comprises a financial transaction record acquisition and storage module, a financial transaction record information management module, a financial transaction structure ratio analysis module, a unit acquisition period dynamic adjustment module, and a user portrait label value calculation module;
the financial transaction record acquisition and storage module is used for receiving the personal account information of the user and acquiring and storing financial transaction records generated by the user in each online channel;
the financial transaction record information management module is used for carrying out initial acquisition period on each user
The financial transaction records generated in the financial transaction system are subjected to information combing, and the users are classified to obtain a first characteristic user set and a second characteristic user set;
the financial transaction structure ratio analysis module is used for receiving the data in the financial transaction record information management module and respectively carrying out financial transaction structure ratio analysis on each feature user in the first feature user set and the second feature user set; the financial transaction structure ratio is a ratio formed by different corresponding financial amounts generated on different types of financial transaction products by a user;
the unit acquisition period dynamic adjustment module is used for respectively adjusting the dynamic range of the unit acquisition period for each characteristic user in the first characteristic user set and the second characteristic user set, respectively capturing the unit acquisition period corresponding to the minimum floating change of the ratio of the financial transaction structure for each characteristic user in the first characteristic user set and the second characteristic user set, and taking the unit acquisition period as the final unit acquisition period;
and the user portrait label value calculation module is used for receiving data in the financial transaction record information management module, the financial transaction structure ratio analysis module and the unit acquisition period dynamic adjustment module and calculating a first user portrait label value and a second user portrait label value for each characteristic user.
8. The financial big data management system of claim 7, wherein the user portrait label value calculation module comprises a first user portrait label value calculation unit, a second user portrait label value calculation unit;
the first user portrait label value calculating unit is used for receiving data in the financial transaction record information management module and calculating a first user portrait label value for each characteristic user;
and the second user portrait label value calculating unit is used for receiving the data in the financial transaction structure ratio analyzing module and the unit acquisition period dynamic adjusting module and calculating a second user portrait label value for each characteristic user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210961269.0A CN115049498B (en) | 2022-08-11 | 2022-08-11 | Financial big data management system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210961269.0A CN115049498B (en) | 2022-08-11 | 2022-08-11 | Financial big data management system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115049498A CN115049498A (en) | 2022-09-13 |
| CN115049498B true CN115049498B (en) | 2022-10-25 |
Family
ID=83167364
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210961269.0A Active CN115049498B (en) | 2022-08-11 | 2022-08-11 | Financial big data management system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115049498B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111861748A (en) * | 2020-07-15 | 2020-10-30 | 郑州博瀚智能科技有限公司 | Financial big data analysis platform based on artificial intelligence |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018000210A1 (en) * | 2016-06-28 | 2018-01-04 | 深圳狗尾草智能科技有限公司 | User portrait-based skill package recommendation device and method |
| CN110399988A (en) * | 2019-07-31 | 2019-11-01 | 中国工商银行股份有限公司 | Equipment portrait generation method and system |
| CN110796354A (en) * | 2019-10-21 | 2020-02-14 | 国网湖南省电力有限公司 | Enterprise electric charge recovery risk portrait method and system |
| CN113240526B (en) * | 2020-12-14 | 2022-07-05 | 山东腾邦国际商务有限公司 | Service recommendation method applied to cloud computing and block chain finance and cloud computing system |
-
2022
- 2022-08-11 CN CN202210961269.0A patent/CN115049498B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111861748A (en) * | 2020-07-15 | 2020-10-30 | 郑州博瀚智能科技有限公司 | Financial big data analysis platform based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115049498A (en) | 2022-09-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11928697B2 (en) | Methods and systems for using multiple data sets to analyze performance metrics of targeted companies | |
| CN110490729B (en) | Financial user classification method based on user portrait model | |
| US6480844B1 (en) | Method for inferring behavioral characteristics based on a large volume of data | |
| CN109408712B (en) | Construction method of multidimensional information portrait of travel agency user | |
| WO2005101265A2 (en) | Systems and methods for investigation of financial reporting information | |
| CN109359868A (en) | A kind of construction method and system of power grid user portrait | |
| CN112308462A (en) | Power consumer classification method and device | |
| CN111738819A (en) | Method, device and equipment for screening characterization data | |
| Glas et al. | Uncertainty measures from partially rounded probabilistic forecast surveys | |
| CN112862585A (en) | Personal loan type bad asset risk rating method based on LightGBM decision tree algorithm | |
| CN110544171A (en) | Investment management service system based on credit system | |
| CN111352976A (en) | Search advertisement conversion rate prediction method and device for shopping nodes | |
| CN112950359B (en) | User identification method and device | |
| CN115049498B (en) | Financial big data management system and method | |
| CN110991744B (en) | Transaction limit setting method and system | |
| Leitner-Hanetseder | Quality and determinants of risk reporting-Evidence from Germany and Austria | |
| KR102336462B1 (en) | Apparatus and method of credit rating | |
| CN115205011A (en) | Bank user portrait model generation method based on LSF-FC algorithm | |
| CN114493686A (en) | Operation content generation and pushing method and device | |
| CN115115157A (en) | Overdue risk prediction method, overdue risk prediction device, computer equipment and storage medium | |
| Nicita et al. | Information and export performance | |
| CN112270595A (en) | Data reconciliation decision method, device, server and storage medium | |
| Alden et al. | Multiple Job Holders-An analysis of second jobs in the European Community. 1982 | |
| CN117764459B (en) | Enterprise management system and method based on intelligent data analysis and processing | |
| CN115204852A (en) | Power transaction multi-market collaborative management system and method based on block chain technology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |