CN116468460A - Consumer finance customer image recognition system and method based on artificial intelligence - Google Patents
Consumer finance customer image recognition system and method based on artificial intelligence Download PDFInfo
- Publication number
- CN116468460A CN116468460A CN202310471500.2A CN202310471500A CN116468460A CN 116468460 A CN116468460 A CN 116468460A CN 202310471500 A CN202310471500 A CN 202310471500A CN 116468460 A CN116468460 A CN 116468460A
- Authority
- CN
- China
- Prior art keywords
- data
- customer
- tag
- classification
- client
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- Technology Law (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an artificial intelligence-based consumer finance customer image recognition system and a method thereof, and relates to the technical field of image recognition. In order to solve the problem that the service scene matching of the developed target customers and the financial products has errors due to different dimensions of customer information and different requirements on image results; the consumer finance customer image recognition system based on artificial intelligence comprises a customer management unit, a customer image construction unit and an intelligent recognition unit; by establishing the user portrait tag, establishing a personalized customer tag according to the portrait tag of the customer, deeply mining the potential value of mass data of the customer based on customer tag modeling and predictive tag, creating differentiated and personalized products and services by means of customer subdivision, accurate marketing and the like, and calculating the mutual demand, the customer portrait tag is convenient to quickly and effectively judge the consumption financial demand of the current individual customer and the marketing object demand of a cooperation mechanism, and meets the demands of different customers.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to a consumer finance customer image recognition system and a method based on artificial intelligence.
Background
For example, chinese patent publication No. CN115422423a discloses a method, apparatus, electronic device and storage medium for determining a customer portrait, where a pre-training corpus is taken from a pre-training corpus, where the pre-training corpus includes at least two pre-training corpora; determining target scales of the at least two pre-training corpuses, and performing text expansion and contraction on different pre-training corpuses of the pre-training corpus according to the target scales; combining the corpus to be determined with at least two telescopic pre-training corpora to obtain at least two target corpora; inputting the at least two target corpus into a unitary recognition model, and obtaining a client image recognition result of the corpus to be determined, which is output by the unitary recognition model, wherein the unitary recognition model is used for recognizing single words in the corpus.
Although the above patent improves the recognition accuracy of the customer portrait, the following problems still exist in the aspect of finance:
the main consumers of the financial enterprises are more and more difficult to touch, the consumer demands are differentiated, the enterprises cannot know the client demands in time, the financial enterprises often perform portraits through statistical information, however, the requirements on the portraits are different due to different dimensions of the client information, and the situation that errors occur in matching of the developed target clients and the business scenes of the financial products is caused.
Disclosure of Invention
The invention aims to provide an artificial intelligence-based consumer finance customer image recognition system and a method thereof, which are used for converging, managing and modeling split data inside and outside an enterprise, eliminating data islands, realizing data capitalization, providing accurate customer stereoscopic images for the enterprise, assisting the enterprise to realize data driving business, and solving the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions:
an artificial intelligence based consumer finance customer image recognition system comprising:
a client management unit for:
respectively establishing a personal customer portrait database and a cooperation portrait database;
establishing a data classification model based on the personal customer portrait and the cooperation portrait database, identifying acquired data, classifying based on the data classification model, generating a plurality of first-level classification data sets, matching corresponding tag algorithm models aiming at data types of different first-level classification data sets, mining characteristic information in the first-level classification data sets, and forming a first-level classification data tag;
subdividing step by step based on the primary classification data labels, respectively mining characteristic information in the classification data to respectively form secondary classification data labels and tertiary classification data labels, constructing a classification data label database, regularly recalculating and mining customer data, and continuously perfecting the customer labels;
a customer portrait construction unit for:
acquiring original data corresponding to the tag based on a multi-stage classification data tag built by the classification data tag database, performing statistical analysis, performing modeling analysis after obtaining a fact tag, determining a model tag based on a modeling analysis result, inputting the model tag into a preset prediction model for prediction, and generating a prediction tag;
performing similarity matching based on the prediction labels and prediction labels of other customer portraits, establishing relevant customer groups according to the similarity of the prediction labels, realizing customer group portraits analysis and clustering of the oriented groups to generate similar customers, and finding potential users;
and the intelligent identification unit is used for determining the client corresponding to the predictive label based on the predictive label, performing bidirectional matching based on the predictive labels of the individual client and the cooperative mechanism, and performing bidirectional recommendation to the individual client side and the cooperative mechanism side after the matching result is determined.
Further, the building of the personal customer representation and collaboration organization representation database further comprises:
a personal customer representation comprising: demographic characteristics of the individual, consumption capability data, interest data, risk preferences, and daily habits;
a collaboration organization representation, comprising: enterprise production, circulation, operation, finance, sales, and customer data, related industry chain upstream and downstream data.
Further, the client management unit includes:
the data reading module is used for reading the acquired multi-source data, determining the data type of the multi-source data and generating a personal client data set and a cooperation data set based on the data type;
the data source analysis module is used for acquiring a personal client data set and a cooperation data set and dividing the personal client data set and the cooperation data set into static information data and dynamic information data respectively;
the data classification storage module is used for acquiring the data characteristics of the static information data and the dynamic information data, determining a data classification identifier based on the data characteristics, inputting the data classification identifier into a neural network for learning, and determining the classification expression of the data classification identifier;
the data updating module is used for setting a timing calculation model, performing full-quantity calculation based on the calculation model, comparing the acquired label with the history label, determining updating data and generating an updating list.
Further, the data classification storage module is further configured to:
constructing tag storage nodes in a storage database, converging the tag storage nodes based on each level of classification, and respectively forming a plurality of storage domains from the storage database;
and in the storage process, determining the use intensity of each label based on a plurality of storages and analyzing the labels, and sorting storage nodes based on the use intensity.
Further, the client portrait construction unit includes:
the data center constructing module is used for forming a corresponding excavation model for each storage domain respectively and carrying out deep stubborn excavation on a large amount of data in the storage domains;
a customer representation modeling module for customer representation modeling based on mining data, the customer representation modeling comprising: user identification, timestamp, user contact point, subject content, and user behavior type;
and the customer portrait prediction module is used for carrying out deduction prediction based on the modeling result and determining a prediction label of the customer portrait.
Further, deep stubborn digging is carried out on a large amount of data in the storage domain, specifically:
acquiring a data set corresponding to a tag in each storage domain, performing large data behavior analysis by a related algorithm, removing duplicate and null values of numerical values in the data set, converting the data set to form a unified data structure, unifying formats of digital class data in the data set, and unifying timestamp formats;
and acquiring a cleaning mode in a cleaning database, matching a cleaning strategy based on the cleaning mode, matching cleaning methods in the cleaning database according to different types of data, and cleaning the data in the data set based on the cleaning methods to obtain target data.
Further, after the matching result is determined, bidirectional recommendation is performed to the client side and the partner side, and the method further comprises the following steps:
obtaining predictive labels of the individual clients and the cooperative mechanisms, carrying out one-to-one matching based on weight values of the predictive labels, and calculating mutual demand degrees of the individual clients and the cooperative mechanisms based on the weight values;
comparing the mutual demand degree with the preset demand similarity, and if the mutual demand degree is smaller than the preset demand similarity, judging that the individual client does not meet the marketing object demand of the cooperation mechanism and the cooperation mechanism does not meet the demand intention of the individual client;
otherwise, the personal client is judged to meet the marketing object requirement of the cooperative mechanism, and relevant financial products are recommended to the personal client based on a recommendation engine.
The invention provides another technical scheme, which is based on an artificial intelligence, of a consumer finance customer image recognition method, comprising the following steps:
step one: acquiring population attribute information of a customer in a personal customer portrait, describing income potential, income condition and payment capability of the customer, and acquiring behavior habits of the customer in real time, wherein the behavior habits comprise consumption behaviors and consumption amount;
step two: acquiring information related to a business scene and a target client from the image of the cooperation institution, matching personal client images, determining client groups corresponding to enterprises based on matching results, and finding potential user groups;
step three: and establishing a bidirectional recommendation algorithm of the client side and the partner, and respectively recommending the user and the financial product to the client side and the partner based on a recommendation engine.
Compared with the prior art, the invention has the beneficial effects that:
1. the personalized customer label is established according to the customer portrait label, the potential value of mass data of the customer label is deeply mined based on customer label modeling and prediction label, differentiated and personalized products and services are created through means of customer subdivision, accurate marketing and the like, the weight value of the predicted label of the individual customer and the weight value of the cooperation mechanism are calculated, the mutual demand degree of the individual customer and the cooperation mechanism is calculated based on the weight value, the current consumption financial demand of the individual customer and the marketing object demand of the cooperation mechanism are conveniently and effectively judged through the calculation of the mutual demand degree, and a financial enterprise customizes products for different customers to meet the demands of different customers.
2. The method comprises the steps of automatically re-mining data in a plurality of storage domains based on multi-level tags at regular intervals, updating historical tags in real time to form a tag system with complete structure, determining the use strength of each tag, continuously analyzing the core demands and the potential demands of insight users, refining the characteristic preference of a user group through data analysis, exploring potential users, and enabling business expansion and automatic marketing.
3. The data center is used for optimizing data management to improve service, the service is changed into an enterprise data asset management center, a data API is formed, various data services are efficiently provided for enterprises and clients, data islands are eliminated by gathering, managing and modeling processing of the data split inside and outside the enterprises, data capitalization is achieved, accurate client stereoscopic images are provided for the enterprises, data driving service is achieved by assisting the enterprises, single-class data in a single level are cleaned, a targeted cleaning method is selected according to different types of the data by combining multi-level labels, the cleaned target data is finally determined, potential requirements of users in the data are deeply mined, continuous enumeration and iteration supplement of missing information dimension are facilitated, and the problem that the dimension is omitted and hidden danger is left is avoided.
Drawings
FIG. 1 is a block diagram of an artificial intelligence based consumer finance customer image recognition system of the present invention;
FIG. 2 is a block diagram of a customer management unit and customer representation construction unit of the present invention;
FIG. 3 is a diagram of a user image tag frame of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order to solve the technical problem of errors in matching the developed business scenario of the target customer and the financial product due to different dimensions of customer information and different requirements on the image result, referring to fig. 1-3, the present embodiment provides the following technical scheme:
an artificial intelligence based consumer finance customer image recognition system comprising:
a client management unit for:
respectively establishing a personal customer portrait database and a cooperation portrait database; a personal customer representation comprising: demographic characteristics of the individual, consumption capability data, interest data, risk preferences, and daily habits; a collaboration organization representation, comprising: production, circulation, operation, finance, sales and customer data of enterprises, related industry chain upstream and downstream data;
establishing a data classification model based on the personal customer portrait and the cooperation portrait database, identifying acquired data, classifying based on the data classification model, generating a plurality of first-level classification data sets, matching corresponding tag algorithm models aiming at data types of different first-level classification data sets, mining characteristic information in the first-level classification data sets, and forming a first-level classification data tag;
subdividing step by step based on the primary classification data labels, respectively mining characteristic information in the classification data to respectively form secondary classification data labels and tertiary classification data labels, constructing a classification data label database, regularly recalculating and mining customer data, and continuously perfecting the customer labels;
a customer portrait construction unit for:
acquiring original data corresponding to the tag based on a multi-stage classification data tag built by the classification data tag database, performing statistical analysis, performing modeling analysis after obtaining a fact tag, determining a model tag based on a modeling analysis result, inputting the model tag into a preset prediction model for prediction, and generating a prediction tag;
performing similarity matching based on the prediction labels and prediction labels of other customer portraits, establishing relevant customer groups according to the similarity of the prediction labels, realizing customer group portraits analysis and clustering of the oriented groups to generate similar customers, and finding potential users;
the intelligent identification unit is used for determining clients corresponding to the predictive tags based on the predictive tags, performing bidirectional matching based on the predictive tags of the individual clients and the cooperative mechanism, and performing bidirectional recommendation to the individual clients and the cooperative mechanism after determining matching results;
after the matching result is determined, bidirectional recommendation is carried out to the client side and the partner side, and the method further comprises the following steps:
obtaining predictive labels of the individual clients and the cooperative mechanisms, carrying out one-to-one matching based on weight values of the predictive labels, and calculating mutual demand degrees of the individual clients and the cooperative mechanisms based on the weight values;
comparing the mutual demand degree with the preset demand similarity, and if the mutual demand degree is smaller than the preset demand similarity, judging that the individual client does not meet the marketing object demand of the cooperation mechanism and the cooperation mechanism does not meet the demand intention of the individual client;
otherwise, the personal client is judged to meet the marketing object requirement of the cooperative mechanism, and relevant financial products are recommended to the personal client based on a recommendation engine.
Specifically, a personalized customer label is created according to the customer portrait label, potential values of mass data of the customer label are deeply mined based on customer label modeling and prediction label, differentiated and personalized products and services are created through means of customer subdivision, accurate marketing and the like, weight values of the individual customers and the cooperation mechanism prediction labels are calculated, mutual demand degrees of the individual customers and the cooperation mechanism are calculated based on the weight values, the mutual demand degrees are calculated, and the current consumption financial demands of the individual customers and marketing object demands of the cooperation mechanism are conveniently, rapidly and effectively judged, and financial enterprises customize products for different customers to meet the demands of different customers.
In order to solve the technical problem that the construction of the client portrait by the multi-source data causes complex client portrait, effective data cannot be quickly obtained from the client portrait, and the portrait construction efficiency is affected, referring to fig. 1-3, the following technical scheme is provided in this embodiment:
a client management unit comprising:
the data reading module is used for reading the acquired multi-source data, determining the data type of the multi-source data and generating a personal client data set and a cooperation data set based on the data type;
the data source analysis module is used for acquiring a personal client data set and a cooperation data set and dividing the personal client data set and the cooperation data set into static information data and dynamic information data respectively;
the data classification storage module is used for acquiring the data characteristics of the static information data and the dynamic information data, determining a data classification identifier based on the data characteristics, inputting the data classification identifier into a neural network for learning, and determining the classification expression of the data classification identifier;
the data classification storage module is further used for:
constructing tag storage nodes in a storage database, converging the tag storage nodes based on each level of classification, and respectively forming a plurality of storage domains from the storage database;
in the storage process, based on a plurality of storages and analysis of each label, determining the use intensity of each label, and sorting storage nodes based on the use intensity;
the data updating module is used for setting a timing calculation model, performing full-quantity calculation based on the calculation model, comparing the acquired label with the history label, determining updating data and generating an updating list.
Specifically, data in a plurality of storage domains is automatically and re-mined on the basis of multi-level labels at regular intervals, historical labels are updated in real time to form a label system with complete structure, the use intensity of each label is determined, the core demands and the potential demands of insight users are continuously analyzed, the characteristic preference of a user group is refined through data analysis, potential users are discovered, and service expansion and automatic marketing are enabled.
In order to solve the technical problem that each layer of classification is not considered complete under the multi-layer classification, thereby causing dimension omission and leaving hidden danger of expansibility, please refer to fig. 1-3, the present embodiment provides the following technical scheme:
a customer representation construction unit comprising:
the data center constructing module is used for forming a corresponding excavation model for each storage domain respectively and carrying out deep stubborn excavation on a large amount of data in the storage domains;
carrying out deep digging on a large amount of data in a storage domain, and specifically:
acquiring a data set corresponding to a tag in each storage domain, performing large data behavior analysis by a related algorithm, removing duplicate and null values of numerical values in the data set, converting the data set to form a unified data structure, unifying formats of digital class data in the data set, and unifying timestamp formats;
acquiring a cleaning mode in a cleaning database, matching a cleaning strategy based on the cleaning mode, and matching cleaning methods in the cleaning database according to different types of data, and cleaning the data in the data set based on the cleaning methods to obtain target data;
a customer representation modeling module for customer representation modeling based on mining data, the customer representation modeling comprising: user identification, timestamp, user contact point, subject content, and user behavior type;
and the customer portrait prediction module is used for carrying out deduction prediction based on the modeling result and determining a prediction label of the customer portrait.
Specifically, the data management is optimized through the data center to improve the service, the enterprise data asset management center is formed, the data API is formed, various data services are efficiently provided for enterprises and clients, data split inside and outside the enterprises are subjected to aggregation, treatment and modeling processing, data islands are eliminated, data capitalization is achieved, accurate client stereoscopic portraits are provided for the enterprises, the power-assisted enterprises realize data driving service, single-class data in a single level are cleaned, a targeted cleaning method is selected according to different types of the data by combining a multi-level label, the cleaned target data is finally determined, potential demands of users in the data are deeply mined, continuous enumeration and iteration supplement of missing information dimension are facilitated, and the problem that the dimension is missed and the expansibility hidden trouble is avoided.
In order to better show the consumer finance customer image recognition system based on artificial intelligence, the embodiment provides a consumer finance customer image recognition method based on artificial intelligence, which comprises the following steps:
step one: acquiring population attribute information of a customer in an individual customer portrait, describing income potential, income condition and payment capability of the customer, and acquiring behavior habits of the customer in real time, wherein the behavior habits comprise consumption behaviors and consumption amount, so as to provide classified data for financial enterprises, and facilitate the enterprises to screen target users according to business scenes;
step two: information related to business scenes and target clients is obtained from the images of the cooperation institutions, personal client images are matched, client groups corresponding to enterprises are determined based on matching results, potential user groups are found, and the product conversion rate is improved;
step three: and establishing a bidirectional recommendation algorithm of the client side and the partner, and recommending the user and the financial product to the client side and the partner respectively based on a recommendation engine, so that the information of the client side and the partner can be effectively communicated in time.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should be covered by the protection scope of the present invention by making equivalents and modifications to the technical solution and the inventive concept thereof.
Claims (8)
1. Consumer finance customer image recognition system based on artificial intelligence, its characterized in that: comprising the following steps:
a client management unit for:
respectively establishing a personal customer portrait database and a cooperation portrait database;
establishing a data classification model based on the personal customer portrait and the cooperation portrait database, identifying acquired data, classifying based on the data classification model, generating a plurality of first-level classification data sets, matching corresponding tag algorithm models aiming at data types of different first-level classification data sets, mining characteristic information in the first-level classification data sets, and forming a first-level classification data tag;
subdividing step by step based on the primary classification data labels, respectively mining characteristic information in the classification data to respectively form secondary classification data labels and tertiary classification data labels, constructing a classification data label database, regularly recalculating and mining customer data, and continuously perfecting the customer labels;
a customer portrait construction unit for:
acquiring original data corresponding to the tag based on a multi-stage classification data tag built by the classification data tag database, performing statistical analysis, performing modeling analysis after obtaining a fact tag, determining a model tag based on a modeling analysis result, inputting the model tag into a preset prediction model for prediction, and generating a prediction tag;
performing similarity matching based on the prediction labels and prediction labels of other customer portraits, establishing relevant customer groups according to the similarity of the prediction labels, realizing customer group portraits analysis and clustering of the oriented groups to generate similar customers, and finding potential users;
and the intelligent identification unit is used for determining the client corresponding to the predictive label based on the predictive label, performing bidirectional matching based on the predictive labels of the individual client and the cooperative mechanism, and performing bidirectional recommendation to the individual client side and the cooperative mechanism side after the matching result is determined.
2. The artificial intelligence based consumer finance customer image recognition system of claim 1, wherein: establishing a personal customer representation and collaboration institution representation database, further comprising:
a personal customer representation comprising: demographic characteristics of the individual, consumption capability data, interest data, risk preferences, and daily habits;
a collaboration organization representation, comprising: enterprise production, circulation, operation, finance, sales, and customer data, related industry chain upstream and downstream data.
3. The artificial intelligence based consumer finance customer image recognition system of claim 2, wherein: the client management unit includes:
the data reading module is used for reading the acquired multi-source data, determining the data type of the multi-source data and generating a personal client data set and a cooperation data set based on the data type;
the data source analysis module is used for acquiring a personal client data set and a cooperation data set and dividing the personal client data set and the cooperation data set into static information data and dynamic information data respectively;
the data classification storage module is used for acquiring the data characteristics of the static information data and the dynamic information data, determining a data classification identifier based on the data characteristics, inputting the data classification identifier into a neural network for learning, and determining the classification expression of the data classification identifier;
the data updating module is used for setting a timing calculation model, performing full-quantity calculation based on the calculation model, comparing the acquired label with the history label, determining updating data and generating an updating list.
4. The artificial intelligence based consumer finance customer image recognition system of claim 3, wherein: the data classification storage module is further used for:
constructing tag storage nodes in a storage database, converging the tag storage nodes based on each level of classification, and respectively forming a plurality of storage domains from the storage database;
and in the storage process, determining the use intensity of each label based on a plurality of storages and analyzing the labels, and sorting storage nodes based on the use intensity.
5. The artificial intelligence based consumer finance customer image recognition system of claim 4, wherein: the customer portrait construction unit includes:
the data center constructing module is used for forming a corresponding excavation model for each storage domain respectively and carrying out deep stubborn excavation on a large amount of data in the storage domains;
a customer representation modeling module for customer representation modeling based on mining data, the customer representation modeling comprising: user identification, timestamp, user contact point, subject content, and user behavior type;
and the customer portrait prediction module is used for carrying out deduction prediction based on the modeling result and determining a prediction label of the customer portrait.
6. The artificial intelligence based consumer finance customer image recognition system of claim 5, wherein: carrying out deep digging on a large amount of data in a storage domain, and specifically:
acquiring a data set corresponding to a tag in each storage domain, performing large data behavior analysis by a related algorithm, removing duplicate and null values of numerical values in the data set, converting the data set to form a unified data structure, unifying formats of digital class data in the data set, and unifying timestamp formats;
and acquiring a cleaning mode in a cleaning database, matching a cleaning strategy based on the cleaning mode, matching cleaning methods in the cleaning database according to different types of data, and cleaning the data in the data set based on the cleaning methods to obtain target data.
7. The artificial intelligence based consumer finance customer image recognition system of claim 1, wherein: after the matching result is determined, bidirectional recommendation is carried out to the client side and the partner side, and the method further comprises the following steps:
obtaining predictive labels of the individual clients and the cooperative mechanisms, carrying out one-to-one matching based on weight values of the predictive labels, and calculating mutual demand degrees of the individual clients and the cooperative mechanisms based on the weight values;
comparing the mutual demand degree with the preset demand similarity, and if the mutual demand degree is smaller than the preset demand similarity, judging that the individual client does not meet the marketing object demand of the cooperation mechanism and the cooperation mechanism does not meet the demand intention of the individual client;
otherwise, the personal client is judged to meet the marketing object requirement of the cooperative mechanism, and relevant financial products are recommended to the personal client based on a recommendation engine.
8. An artificial intelligence based consumer finance customer image recognition method, based on the implementation of the artificial intelligence based consumer finance customer image recognition system as claimed in any one of claims 1-7, characterized in that: the method comprises the following steps:
step one: acquiring population attribute information of a customer in a personal customer portrait, describing income potential, income condition and payment capability of the customer, and acquiring behavior habits of the customer in real time, wherein the behavior habits comprise consumption behaviors and consumption amount;
step two: acquiring information related to a business scene and a target client from the image of the cooperation institution, matching personal client images, determining client groups corresponding to enterprises based on matching results, and finding potential user groups;
step three: and establishing a bidirectional recommendation algorithm of the client side and the partner, and respectively recommending the user and the financial product to the client side and the partner based on a recommendation engine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310471500.2A CN116468460B (en) | 2023-04-27 | 2023-04-27 | Consumer finance customer image recognition system and method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310471500.2A CN116468460B (en) | 2023-04-27 | 2023-04-27 | Consumer finance customer image recognition system and method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116468460A true CN116468460A (en) | 2023-07-21 |
| CN116468460B CN116468460B (en) | 2024-06-11 |
Family
ID=87182369
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310471500.2A Active CN116468460B (en) | 2023-04-27 | 2023-04-27 | Consumer finance customer image recognition system and method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116468460B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117333275A (en) * | 2023-10-12 | 2024-01-02 | 中国农业银行股份有限公司江苏省分行 | Marketing platform construction method based on big data |
| CN117593096A (en) * | 2024-01-19 | 2024-02-23 | 朴道征信有限公司 | Intelligent pushing method and device for product information, electronic equipment and computer medium |
| CN117807302A (en) * | 2023-09-26 | 2024-04-02 | 交通银行股份有限公司北京市分行 | Customer information processing method and device |
| CN118780837A (en) * | 2024-07-12 | 2024-10-15 | 湖北公众信息产业有限责任公司 | A method and system for constructing a personalized traffic user portrait application based on big data processing and multi-dimensional features |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107403335A (en) * | 2017-06-19 | 2017-11-28 | 北京至信普林科技有限公司 | A kind of drawn a portrait based on depth user carries out the system and implementation method of precision marketing |
| CN110490729A (en) * | 2019-08-16 | 2019-11-22 | 南京汇银迅信息技术有限公司 | A kind of financial user classification method based on user's portrait model |
| US20200184556A1 (en) * | 2018-05-06 | 2020-06-11 | Strong Force TX Portfolio 2018, LLC | Adaptive intelligence and shared infrastructure lending transaction enablement platform responsive to crowd sourced information |
| CN112541706A (en) * | 2020-12-24 | 2021-03-23 | 四川享宇金信金融科技有限公司 | Big data wind control model construction method |
| CN112861003A (en) * | 2021-02-19 | 2021-05-28 | 杭州谐云科技有限公司 | User portrait construction method and system based on cloud edge collaboration |
| CA3160715A1 (en) * | 2019-12-30 | 2021-07-08 | Loren Roger Marti | Systems and methods for business analytics model scoring and selection |
| CN113516500A (en) * | 2021-04-23 | 2021-10-19 | 深圳市威斯登信息科技有限公司 | A realization method and system of a business travel operation platform based on big data |
| CN114266492A (en) * | 2021-12-27 | 2022-04-01 | 天元大数据信用管理有限公司 | A Data Mining-Based Enterprise Financing Fund Matching Method |
| CN115130811A (en) * | 2022-04-12 | 2022-09-30 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | Method and device for establishing power user portrait and electronic equipment |
-
2023
- 2023-04-27 CN CN202310471500.2A patent/CN116468460B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107403335A (en) * | 2017-06-19 | 2017-11-28 | 北京至信普林科技有限公司 | A kind of drawn a portrait based on depth user carries out the system and implementation method of precision marketing |
| US20200184556A1 (en) * | 2018-05-06 | 2020-06-11 | Strong Force TX Portfolio 2018, LLC | Adaptive intelligence and shared infrastructure lending transaction enablement platform responsive to crowd sourced information |
| CN110490729A (en) * | 2019-08-16 | 2019-11-22 | 南京汇银迅信息技术有限公司 | A kind of financial user classification method based on user's portrait model |
| CA3160715A1 (en) * | 2019-12-30 | 2021-07-08 | Loren Roger Marti | Systems and methods for business analytics model scoring and selection |
| CN112541706A (en) * | 2020-12-24 | 2021-03-23 | 四川享宇金信金融科技有限公司 | Big data wind control model construction method |
| CN112861003A (en) * | 2021-02-19 | 2021-05-28 | 杭州谐云科技有限公司 | User portrait construction method and system based on cloud edge collaboration |
| CN113516500A (en) * | 2021-04-23 | 2021-10-19 | 深圳市威斯登信息科技有限公司 | A realization method and system of a business travel operation platform based on big data |
| CN114266492A (en) * | 2021-12-27 | 2022-04-01 | 天元大数据信用管理有限公司 | A Data Mining-Based Enterprise Financing Fund Matching Method |
| CN115130811A (en) * | 2022-04-12 | 2022-09-30 | 内蒙古电力(集团)有限责任公司内蒙古电力科学研究院分公司 | Method and device for establishing power user portrait and electronic equipment |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117807302A (en) * | 2023-09-26 | 2024-04-02 | 交通银行股份有限公司北京市分行 | Customer information processing method and device |
| CN117807302B (en) * | 2023-09-26 | 2024-05-31 | 交通银行股份有限公司北京市分行 | Customer information processing method and device |
| CN117333275A (en) * | 2023-10-12 | 2024-01-02 | 中国农业银行股份有限公司江苏省分行 | Marketing platform construction method based on big data |
| CN117333275B (en) * | 2023-10-12 | 2024-03-19 | 中国农业银行股份有限公司江苏省分行 | Marketing platform construction method based on big data |
| CN117593096A (en) * | 2024-01-19 | 2024-02-23 | 朴道征信有限公司 | Intelligent pushing method and device for product information, electronic equipment and computer medium |
| CN117593096B (en) * | 2024-01-19 | 2024-04-12 | 朴道征信有限公司 | Intelligent pushing method and device for product information, electronic equipment and computer medium |
| CN118780837A (en) * | 2024-07-12 | 2024-10-15 | 湖北公众信息产业有限责任公司 | A method and system for constructing a personalized traffic user portrait application based on big data processing and multi-dimensional features |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116468460B (en) | 2024-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110751261B (en) | Training method and system of neural network model and prediction method and system | |
| CN116468460B (en) | Consumer finance customer image recognition system and method based on artificial intelligence | |
| Ngai et al. | Application of data mining techniques in customer relationship management: A literature review and classification | |
| WO2020249125A1 (en) | Method and system for automatically training machine learning model | |
| WO2020020088A1 (en) | Neural network model training method and system, and prediction method and system | |
| Al Montaser et al. | Sentiment analysis of social media data: Business insights and consumer behavior trends in the USA | |
| CN118941365B (en) | Commodity pushing method and system based on user preference analysis | |
| KR20230099822A (en) | System of making market report based on ai and method thereof | |
| CN113254775A (en) | Credit card product recommendation method based on client browsing behavior sequence | |
| Ogunleye | The concept of data mining | |
| Nanayakkara et al. | A survey of finding trends in data mining techniques for social media analysis | |
| CN117911079A (en) | Personalized merchant marketing intelligent recommendation method and system | |
| CN117746546A (en) | Service business processing method and system based on caller | |
| CN117235811A (en) | Internet finance-based payment big data analysis method and big data analysis system | |
| Boyko et al. | Using artificial intelligence algorithms in advertising | |
| Thakur et al. | Enhancing customer experience through ai-powered personalization: A data science perspective in e-commerce | |
| WO2025147770A1 (en) | Apparatus and a method for the generation of exploitation data | |
| CN114862506A (en) | Financial product recommendation method based on deep reinforcement learning | |
| CN119515558A (en) | Method, device, computer equipment and storage medium for generating personalized copy | |
| CN118154235A (en) | Method, device and storage medium for predicting commodity marketing topic communication behavior | |
| CN116823321A (en) | Method and system for analyzing economic management data of electric business | |
| Gummadi et al. | NLP Based TAG Algorithm for Enhancing Customer Data Platform and Personalized Marketing | |
| Josephine VL et al. | Optimising lead qualification through machine learning: A customer data-driven approach | |
| Mohammed et al. | Social Media Data-Based Business Intelligence Analysis Using Deep Learning. | |
| Alaei et al. | A brief introduction to ‘big data’and its application in tourism |
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 |