CN113836215B - Financial scene user perception information processing method, system, equipment and application - Google Patents

Financial scene user perception information processing method, system, equipment and application Download PDF

Info

Publication number
CN113836215B
CN113836215B CN202111317763.5A CN202111317763A CN113836215B CN 113836215 B CN113836215 B CN 113836215B CN 202111317763 A CN202111317763 A CN 202111317763A CN 113836215 B CN113836215 B CN 113836215B
Authority
CN
China
Prior art keywords
data
unified
line
service
construction
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
Application number
CN202111317763.5A
Other languages
Chinese (zh)
Other versions
CN113836215A (en
Inventor
孙国辛
于晓雪
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
DIGITAL CHINA ADVANCED SYSTEMS SERVICES CO LTD
Original Assignee
DIGITAL CHINA ADVANCED SYSTEMS SERVICES CO LTD
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by DIGITAL CHINA ADVANCED SYSTEMS SERVICES CO LTD filed Critical DIGITAL CHINA ADVANCED SYSTEMS SERVICES CO LTD
Priority to CN202111317763.5A priority Critical patent/CN113836215B/en
Publication of CN113836215A publication Critical patent/CN113836215A/en
Application granted granted Critical
Publication of CN113836215B publication Critical patent/CN113836215B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/25Integrating or interfacing systems involving database management systems
    • G06F16/254Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/10File systems; File servers
    • G06F16/18File system types
    • G06F16/182Distributed file systems
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/21Design, administration or maintenance of databases
    • G06F16/211Schema design and management
    • G06F16/212Schema design and management with details for data modelling support
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/25Fusion techniques
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q40/00Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16YINFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y30/00IoT infrastructure

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Economics (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Strategic Management (AREA)
  • Technology Law (AREA)
  • General Business, Economics & Management (AREA)
  • Computing Systems (AREA)
  • Development Economics (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention belongs to the technical field of computer information processing, and discloses a financial scene user perception information processing method, a system, equipment and application, wherein acquisition of off-line network point various Internet of things terminal sensor data, on-line open bank buried point data, third party system push information and other in-line platform or business flow data is performed; calculating and analyzing ETL, off-line calculation, real-time calculation, AI algorithm analysis and the like of the data; hierarchical data fusion is carried out through data modeling, so that data asset construction is realized; the construction of a data service system is realized through unified service opening, unified authority management, unified operation and maintenance management and a unified alarm center; supporting online and offline website digital operation for data application; the application scene of the user is mined, more intelligent personalized service is provided, and the perception of the user is improved. The invention provides more accurate personalized service, thereby improving user perception experience, assisting digital transformation of the city business and construction of intelligent network points.

Description

Financial scene user perception information processing method, system, equipment and application
Technical Field
The invention belongs to the technical field of computer information processing, and particularly relates to a financial scene user perception information processing method, system, equipment and application.
Background
At present: from the perspective of informatization, epidemic situation accelerates the digital transformation of the whole society and accelerates the application of 5G in various scenes. The construction of the intelligent network point becomes the key point of transformation of each line of network point, and also becomes a sign of digital transformation of each line of information technology, so as to support various financial scene types, such as various aspects of operation, acquisition, marketing and the like. However, the construction ideas of many urban shops still stay on the stacking of the machine, and the user satisfaction is improved in modes of manual drainage, manual assessment of behavior norms and the like. However, the traditional offline channel driving and acquisition mode is not well improved, online and offline data are not fused, and the differentiated service of thousands of people and thousands of sides is not well landed. Currently, the network points are also manually guided to different service areas to wait for the number calling service, or guided to operate intelligent self-service machines to transact related services, and the off-line process is closed loop. The whole process and various labels of the online user portrait are cut, and the effect of channel cooperation and marketing promotion is not achieved. With the development of technologies such as the Internet of things, cloud computing, big data and artificial intelligence, the data islands of all departments are opened, online and offline information is converged in real time and analyzed in a linkage manner, the technology of the Internet of things in the whole website is integrated, the user perception experience is intelligently improved, online and standardization of website operation can be promoted, the operation quality is improved, and the website efficiency is improved.
The application number is CN201610236992.7, and the intelligent control method and system for the Internet of things based on user perception are disclosed, so that all users in a target area can be intelligently identified, and the working state of the appointed Internet of things equipment is controlled according to the control parameter of the target user with the highest priority, thereby changing the current situation that the working conditions of various equipment in a living room are not associated with the activities of the users, and improving the perception experience of people.
The application number is CN201711283640.8, a customer insight method and system suitable for financial scene is disclosed, the obtained financial data of the user is analyzed through a data analysis model, and the analysis result is obtained, so that the personal condition and the current status of the asset of the customer are better known, and the corresponding business purpose is achieved, for example: improving sales performance of financial products, effective financial risk management and control, and the like.
The Chinese patent with the application number of CN205847455U discloses an intelligent financial system based on an intelligent video analysis technology, which is mainly used for site security, and can give an alarm or remind through sound or wireless equipment when abnormal target behaviors are detected, so that the situation that potential safety hazards and losses are caused is truly prevented.
At present, some urban shops improve brands and customer viscosity through the design sense of flagship, humanized area division, multifunctional hardware equipment deployment and more specialized and standardized customer service, but lack of unified management, lack of real-time feedback, evaluation and guiding closed loops, emergency treatment on emergencies is not perfect enough, and service specification examination is mostly carried out through post-hoc video sampling examination, so that a mind-to-mind is easy to get away, the influence caused by bad service attitudes cannot be remedied in time, and the like; on the other hand, as described above, many mature technologies are enough to promote service leaps (internet of things, artificial intelligence and big data), but are often limited to certain specific application scenes or fields, cannot open on-line and off-line multi-channel data barriers, have insufficient channel coordination, and cannot really provide accurate differentiated services.
Through the above analysis, the problems and defects existing in the prior art are as follows: in the application scene of the prior art, data island exists, channel cooperation barriers and website situation lack uniform perception.
The difficulty of solving the problems and the defects is as follows: firstly, the original data quality is low due to the diversity, complexity, semantic inconsistency and the like of the data; secondly, the protocols of the network point terminals are different, and multiple protocol analysis needs to be adapted to provide a flexible configuration function; in addition, the website data belong to different departments, and information barriers and security access problems exist; finally, how to increase service awareness and user perception through a digital operation means, and enabling a financial scene through technology is a process of continuous exploration and excavation.
The meaning of solving the problems and the defects is as follows: the business full-chain data are integrated through financial and scientific means, the user perception experience is intelligently improved, the online and standardization of website operation are promoted, the digital operation quality is improved, and the website efficiency is improved.
Disclosure of Invention
Aiming at the problems existing in the prior art, the invention provides a financial scene user perception information processing method, a system, equipment and application.
The invention is realized in such a way that the method for processing the perceived information of the users in the financial scene comprises the following steps:
acquisition of sensor data of various Internet of things terminals of off-line network points, on-line open bank buried point data, information push of a third party system, and other platforms or business flow data in a line; and the business universe data acquisition is completed, and the full perception of the production data of the digital operation data is provided.
ETL, offline calculation, real-time calculation, AI algorithm analysis and the like of the data; and finishing data processing, processing and value mining, carrying out multi-dimensional and multi-level exploration on structural and non-structural data, and driving service value through the data.
Hierarchical data fusion is carried out through data modeling, so that data asset construction is realized; numerous financial scenes are solidified through modeling, high-value data of industry are precipitated, and more direct data support is provided for upper business application.
The construction of a data service system is realized through unified service opening, unified authority management, unified operation and maintenance management and a unified alarm center; through systematic construction, the safety of data and the continuous healthy operation capability of the data are ensured.
Supporting online and offline website digital operation for data application; through the micro front-end technical architecture, the integration of a plurality of web applications after the rapid development and fission of the service is supported, so that independent lectures of each application are ensured, and the complete flow experience capability of the whole product is ensured.
The application scene of the user is mined, more intelligent personalized service is provided, and the perception of the user is improved. This part is the forefront of the business, where the actual value is most generated.
Further, for each collected device data, other system data of the line side or third party data, supporting interface visual editing of ETL flow and rules; according to the configuration rule, incomplete data, erroneous data, repeated data and the like are filtered and cleaned; converting inconsistent data or normalizing different expressions of unified semantics according to the construction of a data dictionary; for the data of preliminary processing, the data processing module supports offline/real-time processing based on a Hadoop, spark, flink framework, including index aggregation, statistics and alarming with different granularity.
Further, the data acquisition specifically includes:
1) The terminal directly adopts or edge gateway to butt up each Internet of things sensing equipment in the line, and the butt up protocol comprises MQTT (S) and LwM2M, coAP, TCP/IP; the communication mode supports 4G/5G, wifi, bluetooth, NB-IoT and Ethernet;
2) Management and control command issuing of each physical device are realized through the object model;
3) And (3) interfacing with an open interface of a third-party system in a mode of timing task scheduling, application registration and the like, or periodically scanning the third-party system by ftp(s) to push files.
Further, the data calculation and analysis specifically includes:
1) Filtering the collected data, performing primary processing according to the rule design, and writing the data into Kafka;
2) For data with low real-time requirements, offline calculation is carried out through Spark or MapReduce, and the data is written into HDFS or HIVE;
3) For a service scene with high real-time requirement, performing real-time calculation in a flink mode, and supporting jar packet calling or performing service calculation description execution in a fink sql mode;
4) The AI algorithm analysis supports offline algorithm sdk invocation, algorithm model management, model online training functions, user data mining and algorithm exploration capabilities.
Further, the data asset construction specifically includes:
1) The data of the preliminary cleaning is stored in the source pasting layer and used for storing the original data;
2) Dividing topics according to different applications of the industry, and writing the results of the calculation analysis of 2 into different topic libraries;
3) Carrying out abstract aggregation on the results, fusing according to different application dimensions to form a new table, and storing the new table in an application layer; dimension partitioning includes enterprise applications, personal applications, internal management applications, and intelligent network points.
Further, the data application comprises a mobile end open bank, online and offline website business transaction reservation, unified mobile operation and maintenance, an intelligent park and digital twin.
Further, the data application specifically includes:
1) The online bank provides low-risk personal business handling, and content navigation is provided through a voice recognition technology; and carrying out identity card and online signature authentication by OCR technology; meanwhile, constructing user portraits based on buried point data, wherein the user portraits comprise age, engaged industry, fund strength, investment preference and risk bearing capacity;
2) The method comprises the steps of carrying out unified management on sensing equipment in each website through the construction of an internet of things platform, including cameras, temperature and humidity sensors, temperature control panels and various intelligent screens, and carrying out unified management on equipment assets in a row based on RFID and other technologies; a plurality of AI algorithms are embedded, so that face recognition, chest card recognition, video behavior analysis, psychological detection and vehicle recognition are supported, and algorithm customization development is supported;
3) Through digital twin construction, high-precision three-dimensional model construction is carried out on equipment, positions and environments inside and outside a line, and on-line and off-line data are unified and fused for real-time display; constructing a pilot cockpit, and carrying out real-time situation awareness and unified warning; and various professions such as security protection, fire protection, logistics energy, pipeline network and risk management and control are presented in a unified way, so that the digital operation capability of banks is improved.
Further, the enhancing the user perception specifically includes:
1) Through the mobile terminal website APP application, off-line website position inquiry, number calling reservation and parking reservation are provided, related business handling queuing conditions of nearby websites are checked in real time, and more convenient business travel handling planning is provided for clients;
2) Through in-site video behavior analysis, on-site normalization inspection is performed, so that the service quality of personnel in a line is improved, and the most direct perception experience is brought to a customer; normative checks include dressing norms, appearance norms, behavior norms, and service norms; through real-time thermal analysis, the personnel conditions in each area are counted, related persons are timely notified to conduct guiding and distribution, and each customer brings better space feeling and order feeling;
3) Performing face recognition through a multi-camera, performing comparison and analysis with an in-line face library, associating user portraits, and performing large-screen display and broadcasting according to an on-line reservation service; the on-site intelligent interactive display screen is used for scoring target clients through a face recognition technology and intelligently pushing product information in a row; for VIP personnel, the first time message informs the client manager to guide, and the indoor temperature and humidity and illumination conditions of the VIP are set in advance according to daily preferences of the VIP client, so that intelligent and careful environment sensing experience is provided.
It is a further object of the present invention to provide a computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of the financial scene-like user awareness information processing method.
Another object of the present invention is to provide a financial scene type user-perceived information processing system implementing the financial scene type user-perceived information processing method, the financial scene type user-perceived information processing system comprising:
the data acquisition module is used for acquiring sensor data of each Internet of things terminal of an off-line website, buried point data of an on-line open bank, push information of a third party system and data of other platforms or business processes in a line;
the computing and analyzing module is used for computing and analyzing ETL, off-line computing, real-time computing and AI algorithm analysis of the data;
the data asset construction module is used for carrying out layered data fusion through data modeling to realize data asset construction;
the data service system construction module is used for realizing the data service system construction through unified service opening, unified authority management, unified operation and maintenance management and unified alarm center;
the data application module is used for supporting online and offline website digital operation to apply data;
and the user perception promotion module is used for mining the application scene of the user, providing more intelligent personalized service and promoting the perception of the user.
The invention further aims to provide an application of the financial scene type user perception information processing method in digital transformation of urban businesses and construction of intelligent network points.
By combining all the technical schemes, initial test point verification is carried out in a Guiyang bank, so that a business hall is helped to analyze visitor constitution, hot spot areas and passenger flow tracks, and off-line business marketing popularization is promoted in a targeted manner; and meanwhile, the video behavior analysis capability is utilized to support real-time unmanned business hall service standard inspection of the headquarters. Meanwhile, based on the scheme and the cooperation of the optical large bank, a standard Internet of things service system is built, an intra-line Internet of things platform is built, and the digital transformation of the system is promoted. The invention has the advantages and positive effects that: the invention collects global related data through the unified access gateway, including but not limited to: terminal data of the internet of things sensing equipment, buried point data of bank application, data pushed by a third party system and the like. In a data fusion center, carrying out layered construction on acquired data, wherein the data comprises a source pasting layer, a detail layer, a theme layer, an application layer and the like; and supporting custom data model and batch and stream unified processing. To ensure consistency, integrity, etc. of data, the data fusion center supports intelligent data management. And in an application enabling center, a unified open interface is provided, data and algorithm exploration are supported, and common AI algorithm model packaging capability is provided. In the asset operation and maintenance center, the Internet of things technology is adopted to provide full life cycle management of equipment inside and outside a row, and real-time position detection is provided based on indoor and outdoor positioning technology. The mobile terminal unified operation and maintenance APP can be adopted to carry out full-flow visual management of equipment repair, work order circulation, fault assessment, intelligent dispatch, acceptance and evaluation and the like. Based on global data fusion, a bank digital operation center is constructed, wherein the bank digital operation center comprises a leading cockpit, branch network point distribution, visitor hotness, post\VIP personnel track, service standardization video analysis, a unified alarm center, digital twinning and the like. Network point online, low risk business and business that customer can operate by himself can be directly signed or video authenticated online; the off-line fixed point mechanism is required to perform fixed point operation (supervision requirement), and services such as on-line reservation number taking, nearby website recommendation, parking space reservation and the like are provided. According to the self-built app of the bank mobile terminal, client resource information and the like pushed by other third party traffic platforms are used for constructing user portraits, and main dimensions include but are not limited to: age, financial strength, investment experience, risk preferences, revenue targets, personality traits, investment terms, and the like, to provide personalized financial service recommendations.
According to the invention, for off-line website access clients, the multi-camera carries out multi-screen prompt and voice broadcasting guidance through face recognition, and relevant personnel are informed to guide and shunt according to different services and regional people flow thermal analysis. And combining with AI video behavior analysis, carrying out on-site normative checking on service personnel in the hall, notifying related persons and the like in time when complaints or emergency events occur, providing a plan auxiliary decision, and reducing or eliminating negative effects. After automatic identification of the VIP client, the client manager is notified at a first time, and the types of business that may need to be transacted, as well as the financial products that may be accepted, are listed. According to the preference of the clients, the VIP room temperature humidity and illumination are regulated, and even music with higher frequency recently played by the clients and the like are played.
The system is constructed through the integrated Internet of things management system, equipment and environmental facilities in the network are all connected into the Internet of things system, and the comprehensive intelligent management of equipment, environment, energy and security is realized. Compared with the traditional independent operation of each specialty, the method can solve the problems of information isolation, response lag, lack of unified upper layer design and the like, and realize full perception of the operation situation of the in-line network.
The invention can carry out real-time on-site normative checking of staff in a row through AI video behavior analysis, and mainly comprises dressing norms, appearance norms, behavior norms and the like. Compared with manual post-sampling inspection, the inspection is more transparent, the evidence is more complete, the improvement is more timely, and better perception experience can be brought to the user. Giving full play to off-line network points, and transmitting the trust and the sense of expertise of people to people face to face and heart.
The method tracks the behavior track of the client at the network point and accurately records the client line-moving rule and the stay area; and drawing a thermodynamic diagram of the residence time of the client in each area, and analyzing the precisely recommended optimal contact point.
The invention constructs the website portrait information and the client portrait information and provides more accurate personalized service. The website portraits comprise, but are not limited to, the conditions of the number of clients to visit, the number of historical visitors, the number of VIP (very important person), the reservation condition, the queuing number and the like, so that clients can intuitively know specific information of the website, and the time for transacting business is reasonably planned. Customer portraits include, but are not limited to, age, engaging in industry, fund strength, investment preference, risk bearing capacity and the like, target customers are scored through a website customer information interaction screen, a face recognition technology, a voice recognition technology and the like, product information in the row is intelligently pushed, voice recognition interaction capacity is provided, and more convenient, rapid and customized services are provided.
The method solves the problems of data island, channel cooperation barrier, lack of unified perception of network situation and the like; the interaction and interconnection modes of banks and users are changed, and the limitations in the fields of time, space, perception, emotion and the like are broken through. The invention provides more accurate personalized service, thereby improving user perception experience, assisting digital transformation of the city business and construction of intelligent network points.
Drawings
Fig. 1 is a flowchart of a method for processing financial scene user perception information according to an embodiment of the present invention.
FIG. 2 is a schematic diagram of a financial scene-based user-aware information handling system according to an embodiment of the present invention;
in fig. 2: 1. a data acquisition module; 2. a calculation and analysis module; 3. a data asset construction module; 4. a data service system construction module; 5. a data application module; 6. and a user perception lifting module.
Fig. 3 is a flowchart of an implementation of a method for processing financial scene-type user-aware information according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the following examples in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Aiming at the problems existing in the prior art, the invention provides a financial scene user perception information processing method, a system, equipment and application, and the invention is described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the method for processing the financial scene user perception information provided by the invention comprises the following steps:
s101: acquisition of sensor data of various Internet of things terminals of off-line network points, on-line open bank buried point data, information push of a third party system, and other platforms or business flow data in a line;
s102: calculating and analyzing ETL, off-line calculation, real-time calculation and AI algorithm analysis of the data;
s103: hierarchical data fusion is carried out through data modeling, so that data asset construction is realized;
s104: the construction of a data service system is realized through unified service opening, unified authority management, unified operation and maintenance management, unified alarm center and the like;
s105: supporting online and offline website digital operation for data application;
s106: the application scene of the user is mined, more intelligent personalized service is provided, and the perception of the user is improved.
As an optimization scheme of the embodiment of the invention, all the intelligent terminals of the internet of things comprise, but are not limited to, an ATM, a temperature and humidity sensor, an air quality monitor, an armor cash carrier, key equipment, a high-definition camera, an entrance guard, a fire-fighting facility, a waterfall screen and the like; the acquisition of device data and status is performed through a direct connection or edge gateway, and support protocols include, but are not limited to, MQTT (S), lwM2M, coAP, TCP/IP, modBus, RS232, RS485, 3/4/5G, wifi and the like; meanwhile, the acquisition module supports two modes of pushing and pulling, and provides interface docking with a third-party system API based on the distributed scheduling system. For application scenarios with high real-time requirements, the acquisition module also supports topic subscription and publishing based on message middleware, including but not limited to Kafka, rabbitMQ, activeMQ and the like.
And supporting interface visual editing of ETL flow and rules for the collected equipment data, other system data of the line side or third party data. According to the configuration rule, incomplete data, erroneous data, repeated data and the like are filtered and cleaned; converting inconsistent data or normalizing different expressions of unified semantics according to the construction of a data dictionary; for the data of preliminary processing, the data processing module supports offline/real-time processing based on Hadoop, spark, flink and other frames, including index aggregation, statistics, alarming and the like with different granularity, and also supports big data calculation of specific business logic. The AI capability mainly comprises two parts, namely AI processing capability provided by a hardware manufacturer, and development and integration are carried out in a SDK (software development kit) mode; on the other hand, based on the self-grinding AI algorithm module, an open interface call is provided for analysis processing, and the AI algorithm is currently supported to include, but not limited to, specific object recognition (work clothes, work cards, key objects and the like), OCR recognition (universal scene character recognition, card character recognition, financial bill recognition and the like), human body and behavior recognition (human body attribute detection, tumbling, sleeping sentry, smoking, video behaviors like mobile phone playing and the like), track recognition, thermal recognition and the like.
The data asset construction mainly realizes global digital operation through the data processing, and supports the rapid development of business more intelligently, more simply, more widely. The data layering is understood according to different services, is not limited to the source pasting layer, the theme layer and the application layer provided by the embodiment of the invention, and has no absolute specification; the method aims at improving the data quality through layering construction, unifying the same index semantics of different scenes, reducing the data use difficulty, enabling the data to be assets, and fully mining the data value of the industry.
Construction of a unified layer including, but not limited to, unified service opening, unified rights management, unified operation and maintenance management, unified alarm center, and the like. And through modularized construction, abstracting and stripping the public service and the irrelevant service of each micro service to form a data service support system.
With the above capability integration, data base support is accomplished, on which is the most valuable data application. Including, but not limited to, site operation situational awareness, "thousand people thousand face" service recommendation, key equipment full life cycle management, site service specification inspection, and the like. Meanwhile, the application scene of the user is mined, more intelligent personalized service is provided, and the perception of the user is improved.
Other steps may be performed by those skilled in the art of the method for processing financial scene type user-awareness information provided by the present invention, and the method for processing financial scene type user-awareness information provided by the present invention in fig. 1 is merely a specific embodiment.
As shown in fig. 2, the financial scene type user perception information processing system provided by the embodiment of the invention includes:
the data acquisition module 1 is used for acquiring sensor data of each Internet of things terminal of an off-line website, buried point data of an on-line open bank, push information of a third party system and other in-line platform or business process data;
the computing and analyzing module 2 is used for computing and analyzing ETL, off-line computing, real-time computing and AI algorithm analysis of the data;
the data asset construction module 3 is used for carrying out layered data fusion through data modeling to realize data asset construction;
the data service system construction module 4 is used for realizing data service system construction through unified service opening, unified authority management, unified operation and maintenance management, unified alarm center and the like;
the data application module 5 is used for supporting online and offline website digital operation to apply data;
the user perception enhancement module 6 is used for mining application scenes of users, providing more intelligent personalized services and enhancing user perception.
The specific working principle of the financial scene user perception information processing system provided by the embodiment of the invention is as follows:
the service is the root of improving the perception of users, and only the satisfaction degree of the users is continuously improved, the viscosity of the clients can be maintained and enhanced. The specific service promotion is actually to fall to different financial scenes, and the data is taken as important production data, so that the decision is made on the full-link quantitative analysis of each financial scene. The scheme firstly obtains the global data through the data acquisition module 1 and grasps the elements generated in the service scene in an omnibearing way. But these elements are complex, unstructured and not easily understood. Through the calculation and analysis module 2, the data are explored, association relations among the data are mined, and business understanding of industries is gradually precipitated by combining with the layered construction thought of the data asset construction module 3, so that self-industry competitive advantages are formed. But how better these data are to be applied, this introduces a data service architecture construction module 4, which opens up the data capability through architecture construction, making the data application simpler and safer. Based on the capability construction, different data application modules 5 can be quickly constructed, the application becomes lighter, and the market response is more timely and efficient. Through the flexible combination of multiple applications, the comprehensive personalized centroid service of the user is provided, so that the perception of the user is improved. Under the interaction of the continuously adjusted modes, new data elements are generated, other data values can be possibly mined, application service construction is guided, the whole data values form a closed loop, and the business transformation development is driven in a spiral mode.
The technical scheme of the invention is further described below with reference to the accompanying drawings.
As shown in fig. 3, the method for processing the financial scene user perception information provided by the invention specifically comprises the following steps:
1) Collecting data;
2) Calculating and analyzing data;
3) Constructing data assets;
4) A data service system;
5) Data application;
6) And the user perception is improved.
In the embodiment of the invention, the step 1) of data acquisition comprises off-line network node each Internet of things terminal sensor data, on-line open bank buried point data, third party system push information, other in-line platform or business flow data and the like, and the detailed steps comprise:
1.1 The terminal directly adopts or edge gateway to butt up each Internet of things sensing equipment in the line, and the butt up protocol comprises but is not limited to MQTT (S), lwM2M, coAP, TCP/IP and the like; the communication mode supports 4G/5G, wifi, bluetooth, NB-IoT, ethernet and the like;
1.2 The management and control command issuing of each physical device are realized through the object model;
1.3 The method is characterized by comprising the steps of) abutting an open interface of a third-party system in a mode of timing task scheduling, application registration and the like, or scanning a third-party system push file in a mode of ftp(s) timing, wherein other data pulling or pushing modes are not described in detail herein;
in the embodiment of the invention, the step 2) of data calculation and analysis comprises ETL of data, off-line calculation, real-time calculation, AI algorithm analysis and the like; the detailed steps include:
2.1 Data filtering the data collected in 1), performing primary processing according to the rule design, and writing into Kafka
2.2 For data with low real-time requirements, offline calculation is carried out through Spark or MapReduce, and the data is written into HDFS or HIVE;
2.3 For a service scene with high real-time requirement, performing real-time calculation in a flink mode, and supporting jar packet calling or performing service calculation description execution in a fink sql mode;
2.4 AI algorithm analysis supports offline algorithm sdk invocation, algorithm model management, model online training and other functions, and supports user data mining and algorithm exploration capabilities;
in the embodiment of the invention, the step 3) of data asset construction mainly carries out layered data fusion through data modeling and mainly comprises a source pasting layer, a theme layer, an application layer and the like; the detailed steps include:
3.1 2.1) the primarily cleaned data are stored in a source pasting layer and used for storing original data, so that the subsequent other analysis and use are convenient;
3.2 Providing data model design capability in the example, dividing topics according to different applications of industry, and writing the results of the calculation analysis in 2.2) and 2.3) into different topic libraries;
3.3 Further abstract aggregation is carried out on the results, and new tables can be formed by fusion according to different application dimensions and stored in an application layer; dimension partitioning includes, but is not limited to, enterprise applications, personal applications, internal management applications, smart points, etc.;
in the embodiment of the invention, the step 4) of data service system construction mainly comprises unified service opening, unified authority management, unified operation and maintenance management, unified alarm center and the like;
in the embodiment of the invention, the step 5) data application is mainly used for supporting online and offline website digitalized operation, including but not limited to mobile end open bank, offline website business transaction reservation, unified mobile operation and maintenance, intelligent park, digital twin and the like, and the detailed construction steps comprise:
5.1 On-line banking provides low risk personal business handling (meeting within regulatory requirements), and provides fast and convenient content navigation through voice recognition technology; the identity card, the online signature authentication and the like are carried out through the OCR technology, so that the business handling speed is improved; meanwhile, constructing user portraits based on buried point data, including but not limited to age, engaged industry, capital effort, investment preference, risk bearing capacity and the like;
5.2 The sensing equipment in each website is managed in a unified way through the platform construction of the Internet of things, including but not limited to cameras, temperature and humidity sensors, temperature control panels, various intelligent screens and the like, and the equipment assets in the row are managed in a unified way based on the technology of RFID and the like; a plurality of AI algorithms are embedded, so that face recognition, chest card recognition, video behavior analysis, psychological detection, vehicle recognition and the like are supported, and algorithm customization development is supported;
5.3 Digital twin construction is adopted to carry out high-precision three-dimensional model construction on equipment, positions and environments inside and outside the line, and unified fusion and real-time display are carried out on-line and off-line data; and constructing a pilot cockpit, and carrying out real-time situation awareness and unified warning. And various professions such as security protection, fire protection, logistics energy, pipeline network, risk management and control and the like are presented uniformly, so that the digital operation capability of banks is improved.
In the embodiment of the present invention, step 6) promotes user perception mainly through various application construction in step 5), digs user application scenes, and provides more intelligent personalized services, and detailed construction steps include, but are not limited to:
6.1 Through the mobile terminal website APP application, off-line website position inquiry, number calling reservation, parking reservation and the like are provided, related business handling queuing conditions of nearby websites are checked in real time, and more convenient business travel handling planning is provided for clients, so that user perception is improved;
6.2 Through in-site video behavior analysis, on-site normative checking is carried out, so that the service quality of personnel in a line is improved, and the most direct perception experience is brought to a customer; normative checks include, but are not limited to, dressing norms, appearance norms, behavior norms, service norms, and the like; through real-time thermal analysis, statistics each regional personnel condition in time notifies relevant people to guide and shunt, and each customer brings better space sense and order sense.
6.3 Face recognition is carried out through the multi-camera, comparison and analysis are carried out on the face recognition and the in-line face library, user portraits are associated, and large-screen display, broadcasting and the like are carried out according to online reservation service; and the on-site intelligent interactive display screen is used for scoring the target clients through a face recognition technology and intelligently pushing the product information in the line. For VIP personnel, the first time message informs the client manager to guide, and the indoor temperature and humidity and illumination conditions of the VIP are set in advance according to daily preferences of the VIP client, so that intelligent and careful environment sensing experience is provided.
In summary, through technical applications such as the internet of things, big data, artificial intelligence, etc., user perception experience is improved, interaction and interconnection modes of banks and users are improved, limitations in the fields of time, space, perception, emotion, etc. are broken through, more accurate personalized services are provided, user perception experience is improved, and digital transformation of power-assisted city business and intelligent network construction are improved.
The invention realizes the full-internet-of-things sensing access of the direct connection equipment, the gateway equipment, the internet-of-things system, the third party system and the edge node, the plug-in design of the equipment access protocol is plug-in, plug-and-play, the new protocol equipment is quickly accessed, and the new service is quickly constructed. And constructing a layered data model, and carrying out data batch and stream integrated processing by adopting a renter resource isolation mode to quickly form in-line data assets. AI enabling, integrating various algorithm capabilities such as face recognition, normalization inspection, intelligent recommendation, OCR recognition, psychological detection and the like, providing an algorithm self-defining function, and supporting rapid landing of business application based on an AI technology. The full-perception full-linkage of the Internet of things sensing equipment is based on a data twin system, the intelligent application of the full scene is built based on 'artificial cost'.
The universal capability of the invention realizes the global sensing of underground and overground areas and the coordination of the things of people, vehicles, things and things in Beijing auxiliary center project, and realizes the real-time sensing of the large-screen city situation based on the digital twin technology.
It should be noted that the embodiments of the present invention can be realized in hardware, software, or a combination of software and hardware. The hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or special purpose design hardware. Those of ordinary skill in the art will appreciate that the apparatus and methods described above may be implemented using computer executable instructions and/or embodied in processor control code, such as provided on a carrier medium such as a magnetic disk, CD or DVD-ROM, a programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The device of the present invention and its modules may be implemented by hardware circuitry, such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., as well as software executed by various types of processors, or by a combination of the above hardware circuitry and software, such as firmware.
The foregoing is merely illustrative of specific embodiments of the present invention, and the scope of the invention is not limited thereto, but any modifications, equivalents, improvements and alternatives falling within the spirit and principles of the present invention will be apparent to those skilled in the art within the scope of the present invention.

Claims (8)

1. The financial scene type user perception information processing method is characterized by comprising the following steps of:
acquisition of sensor data of various Internet of things terminals of off-line network points, on-line open bank buried point data, information push of a third party system, and other platforms or business flow data in a line;
calculating and analyzing ETL, off-line calculation, real-time calculation and AI algorithm analysis of the data;
hierarchical data fusion is carried out through data modeling, so that data asset construction is realized;
constructing a data service system through unified service opening, unified authority management, unified operation and maintenance management and a unified alarm center;
supporting online and offline website digital operation for data application;
excavating a user application scene;
for collected equipment data, other system data of a line side or third party data, supporting interface visual editing ETL flow and rules; according to the configuration rule, incomplete data, erroneous data and repeated data are filtered and cleaned; converting inconsistent data or normalizing different expressions of unified semantics according to the construction of a data dictionary; for the data of preliminary processing, the data processing module supports offline/real-time processing based on a Hadoop, spark, flink framework, and comprises index aggregation, statistics and alarming of different granularities;
the data acquisition specifically comprises:
1) The terminal directly adopts or edge gateway to butt up each Internet of things sensing device in the line, and the butt up protocol comprises MQTT and LwM2M, coAP, TCP/IP; the communication mode supports 4G/5G, wifi, bluetooth, NB-IoT and Ethernet;
2) Management and control command issuing of each physical device are realized through the object model;
3) And interfacing an open interface of the third party system by a timing task scheduling and application registration mode, or pushing files by the third party system by ftp timing scanning.
2. The method for processing financial scene-type user-aware information according to claim 1, wherein said data calculation and analysis specifically comprises:
1) The collected data is subjected to data filtering, primary processing treatment is carried out according to rule design, and the data is written into Kafka or other message middleware;
2) For data with low real-time requirements, offline calculation is carried out through Spark or MapReduce, and the data is written into HDFS or HIVE;
3) For a service scene with high real-time requirement, performing real-time calculation in a flink mode, and supporting jar packet calling or performing service calculation description execution in a fink sql mode;
4) The AI algorithm analysis supports offline algorithm sdk invocation, algorithm model management, model online training functions, user data mining and algorithm exploration capabilities.
3. The method for processing financial scene-type user-aware information according to claim 1, wherein said data asset construction specifically comprises:
1) The data of the preliminary cleaning is stored in the source pasting layer and used for storing the original data;
2) Dividing topics according to different applications of the industry, and writing the results of calculation and analysis into different topic libraries;
3) Carrying out abstract aggregation on the results, fusing according to different application dimensions to form a new table, and storing the new table in an application layer; dimension partitioning includes enterprise applications, personal applications, internal management applications, and intelligent network points.
4. The method for processing financial scene type user perception information as claimed in claim 1, wherein the data application comprises mobile end open bank, off-line network business transaction reservation, unified mobile operation and maintenance, smart park, digital twin;
the data application specifically comprises:
1) The online bank provides low-risk personal business handling, and content navigation is provided through a voice recognition technology; and carrying out identity card and online signature authentication by OCR technology; meanwhile, constructing user portraits based on buried point data, wherein the user portraits comprise age, engaged industry, fund strength, investment preference and risk bearing capacity;
2) The method comprises the steps of carrying out unified management on sensing equipment in each website through Internet of things platform construction, including cameras, temperature and humidity sensors, temperature control panels and various intelligent screens, and carrying out unified management on equipment assets in a row based on RFID technology; a plurality of AI algorithms are embedded, so that face recognition, chest card recognition, video behavior analysis, psychological detection and vehicle recognition are supported, and algorithm customization development is supported;
3) Through digital twin construction, high-precision three-dimensional model construction is carried out on equipment, positions and environments inside and outside a line, and on-line and off-line data are unified and fused for real-time display; constructing a pilot cockpit, and carrying out real-time situation awareness and unified warning; and the security, fire protection, logistic energy, pipeline network and risk management and control are presented in a unified way, so that the digital operation capability of the bank is improved.
5. The method for processing financial scene type user perception information as claimed in claim 1, comprising the following steps:
1) Through the mobile terminal website APP application, off-line website position inquiry, number calling reservation and parking reservation are provided, related business handling queuing conditions of nearby websites are checked in real time, and more convenient business travel handling planning is provided for clients;
2) Through in-site video behavior analysis, on-site normalization inspection is performed, so that the service quality of personnel in a line is improved, and the most direct perception experience is brought to a customer; normative checks include dressing norms, appearance norms, behavior norms, and service norms; through real-time thermal analysis, the personnel conditions in each area are counted, related persons are timely notified to conduct guiding and distribution, and each customer brings better space feeling and order feeling;
3) Performing face recognition through a multi-camera, performing comparison and analysis with an in-line face library, associating user portraits, and performing large-screen display and broadcasting according to an on-line reservation service; the on-site intelligent interactive display screen is used for scoring target clients through a face recognition technology and intelligently pushing product information in a row; for VIP personnel, the first time message informs the client manager to guide, and the indoor temperature and humidity and illumination conditions of the VIP are set in advance according to daily preferences of the VIP client, so that intelligent and careful environment sensing experience is provided.
6. A computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the financial scene-type user-awareness information processing method of claim 1.
7. A financial scene type user-perceived information processing system that implements the financial scene type user-perceived information processing method of any one of claims 1 to 5, characterized in that the financial scene type user-perceived information processing system comprises:
the data acquisition module is used for acquiring sensor data of each Internet of things terminal of an off-line website, buried point data of an on-line open bank, push information of a third party system and data of other platforms or business processes in a line;
the computing and analyzing module is used for computing and analyzing ETL, off-line computing, real-time computing and AI algorithm analysis of the data;
the data asset construction module is used for carrying out layered data fusion through data modeling to realize data asset construction;
the data service system construction module is used for realizing the data service system construction through unified service opening, unified authority management, unified operation and maintenance management and unified alarm center;
the data application module is used for supporting online and offline website digital operation to apply data;
and the user perception promotion module is used for mining the application scene of the user, providing more intelligent personalized service and promoting the perception of the user.
8. A method for applying the financial scene type user perception information processing method according to any one of claims 1-5 in digital transformation of urban businesses and construction of intelligent network points.
CN202111317763.5A 2021-11-09 2021-11-09 Financial scene user perception information processing method, system, equipment and application Active CN113836215B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111317763.5A CN113836215B (en) 2021-11-09 2021-11-09 Financial scene user perception information processing method, system, equipment and application

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111317763.5A CN113836215B (en) 2021-11-09 2021-11-09 Financial scene user perception information processing method, system, equipment and application

Publications (2)

Publication Number Publication Date
CN113836215A CN113836215A (en) 2021-12-24
CN113836215B true CN113836215B (en) 2023-11-24

Family

ID=78971303

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111317763.5A Active CN113836215B (en) 2021-11-09 2021-11-09 Financial scene user perception information processing method, system, equipment and application

Country Status (1)

Country Link
CN (1) CN113836215B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114553684B (en) * 2022-02-22 2024-02-09 中国工商银行股份有限公司 Method, device, computer equipment and storage medium for network point operation and maintenance
CN114827210A (en) * 2022-05-12 2022-07-29 国网绿色能源有限公司 Comprehensive energy service platform
CN114819776B (en) * 2022-06-30 2022-10-28 山东捷瑞数字科技股份有限公司 Visitor management system of digital center
CN115834940A (en) * 2022-11-14 2023-03-21 浪潮通信信息***有限公司 IPTV/OTT end-to-end data reverse acquisition analysis method and system

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102044049A (en) * 2011-01-28 2011-05-04 迈普通信技术股份有限公司 Data acquisition system, method and data acquisition server for financial website
CN105913315A (en) * 2016-04-12 2016-08-31 于闻 Bank outlet online marketing and management system and management method thereof
CN107332844A (en) * 2017-07-03 2017-11-07 上海路诚数据服务有限公司 Privacy information application method and personal reference methods of marking
CN207503376U (en) * 2017-12-08 2018-06-15 四川安亮科技有限公司 Financial transaction terminal machine based on NB-IoT
CN108428173A (en) * 2018-01-31 2018-08-21 孙中东 1+1+N Internet banks application architecture and its business model application
CN109872441A (en) * 2019-03-21 2019-06-11 刘静 A kind of bank queuing system based on Internet of Things
CN112585591A (en) * 2018-08-24 2021-03-30 三菱电机株式会社 Data collection server, data utilization server, device, data distribution system, data collection method, and program
CN112651829A (en) * 2021-01-06 2021-04-13 贵州易万与科技有限公司 System for fusing and managing bank data by applying big data technology and middle platform architecture
CN113538036A (en) * 2021-06-04 2021-10-22 深圳市英创艾伦智能科技有限公司 5G, AI edge calculation and Internet of things digital management system, method and device

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102044049A (en) * 2011-01-28 2011-05-04 迈普通信技术股份有限公司 Data acquisition system, method and data acquisition server for financial website
CN105913315A (en) * 2016-04-12 2016-08-31 于闻 Bank outlet online marketing and management system and management method thereof
CN107332844A (en) * 2017-07-03 2017-11-07 上海路诚数据服务有限公司 Privacy information application method and personal reference methods of marking
CN207503376U (en) * 2017-12-08 2018-06-15 四川安亮科技有限公司 Financial transaction terminal machine based on NB-IoT
CN108428173A (en) * 2018-01-31 2018-08-21 孙中东 1+1+N Internet banks application architecture and its business model application
CN112585591A (en) * 2018-08-24 2021-03-30 三菱电机株式会社 Data collection server, data utilization server, device, data distribution system, data collection method, and program
CN109872441A (en) * 2019-03-21 2019-06-11 刘静 A kind of bank queuing system based on Internet of Things
CN112651829A (en) * 2021-01-06 2021-04-13 贵州易万与科技有限公司 System for fusing and managing bank data by applying big data technology and middle platform architecture
CN113538036A (en) * 2021-06-04 2021-10-22 深圳市英创艾伦智能科技有限公司 5G, AI edge calculation and Internet of things digital management system, method and device

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Conceptual analysis of Internet of Things use cases in Banking domain;Hariharan Ramalingam 等;《TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON)》;2034-2039 *
金融+N:构建场景金融新生态;蒋瞳;《中国银行业》(第11期);36-38 *

Also Published As

Publication number Publication date
CN113836215A (en) 2021-12-24

Similar Documents

Publication Publication Date Title
CN113836215B (en) Financial scene user perception information processing method, system, equipment and application
Luque-Ayala et al. Urban operating systems: Producing the computational city
Cheng et al. A digital transformation approach in hospitality and tourism research
CN105608643A (en) Intelligent tourism integrated service management platform
Quasim et al. Fundamentals of smart cities
CN108269331A (en) A kind of intelligent video big data processing system
CN110116414A (en) A kind of shop 4S intelligent comprehensive service robot and its system
Goldsmith et al. A new city O/S: the power of open, collaborative, and distributed governance
Zhong et al. " Robot rooms": how guests use and perceive hotel robots
CN109547436A (en) Relation chain interior joint evaluation method and device, storage medium and electronic equipment
CN113902333A (en) Data operation management system supporting urban operation service and method for constructing same
Zhou Application research of face recognition technology in smart campus
CN109766000A (en) A kind of wisdom education system and method based on virtual reality
Saheb Big data analytics in the context of internet of things and the emergence of real-time systems: a systematic literature review1
Glebova et al. Smart cities’ digital transformation
Taha Osman et al. The Internet of Things in information institutions: Concept, use and challenges
Xiong et al. Cyber–physical–social systems for smart city
Li et al. Design and implementation of smart tourism service platform from the perspective of artificial intelligence
CN116245270A (en) Intelligent school system and intelligent school system application method
Mishra et al. Artificial intelligence for sustainable smart cities
Chen et al. Development of permit-to-work management system based on POP model for petrochemical construction safety
Sun Smart prisons
Neuhüttler et al. Quality based testing of AI-based smart services: the example of Stuttgart airport
Shunhou et al. AIoT on Cloud
Van Till The five technological forces disrupting security: how cloud, social, mobile, big data and IoT are transforming physical security in the digital age

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