CN113450028A - Behavior fund analysis method and system - Google Patents
Behavior fund analysis method and system Download PDFInfo
- Publication number
- CN113450028A CN113450028A CN202111006839.2A CN202111006839A CN113450028A CN 113450028 A CN113450028 A CN 113450028A CN 202111006839 A CN202111006839 A CN 202111006839A CN 113450028 A CN113450028 A CN 113450028A
- Authority
- CN
- China
- Prior art keywords
- transaction
- account information
- evaluation
- abnormal data
- database
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Technology Law (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention relates to the technical field of fund analysis, and particularly discloses a behavior fund analysis method and system, wherein the method comprises the steps of receiving transaction data of account information, sequencing the transaction data based on time items of the transaction data, and generating a transaction database; traversing the transaction database, determining account information of a frequently-used party, sending a verification request to the account information of the frequently-used party, and determining first abnormal data based on a verification result; identifying second abnormal data existing in the transaction data based on the trained abnormal data identification model; and finally, obtaining the risk probability of the transaction data through a trained risk assessment model, and sending early warning information to account information when the risk probability is higher than a threshold value. According to the method, the interactive evaluation module is used for evaluating the interactivity of the user before abnormal data analysis is carried out through the model, so that the authenticity is high, the cost is low, and the traditional behavior fund analysis process is optimized.
Description
Technical Field
The invention relates to the technical field of fund analysis, in particular to a behavior fund analysis method and system.
Background
Most of the existing behavior fund analysis systems identify abnormal data of behavior fund through extremely large and complex analysis models, and then judge the risk probability of the abnormal data; in fact, some abnormal data are very easy to identify, and if model analysis is performed on each transaction data, the system load is heavy, so that the existing behavior fund analysis system needs to be optimized.
Disclosure of Invention
The present invention is directed to a behavior fund analysis method and system, which solve the problems set forth in the background art.
In order to achieve the purpose, the invention provides the following technical scheme:
a behavioral fund analysis method, the method comprising:
receiving transaction data of account information, reading time items of the transaction data, sequencing the transaction data based on the time items, and generating a transaction database;
traversing the transaction database, determining account information of a frequently-used party, sending a verification request to the account information of the frequently-used party, and determining first abnormal data based on a verification result;
if the first abnormal data does not exist, generating a transaction feature vector library based on the transaction database, calling a trained abnormal data identification model, inputting the transaction feature vector into the abnormal data identification model, and identifying second abnormal data existing in the transaction data;
and calling a trained risk evaluation model, inputting the abnormal data into the risk evaluation model to obtain the risk probability of the transaction data, and sending early warning information to account information when the risk probability is higher than a threshold value.
As a further limitation of the technical scheme of the invention: the step of traversing the transaction database, determining account information of a frequently-used party, sending a verification request to the account information of the frequently-used party, and determining first abnormal data based on a verification result comprises the following steps:
traversing the transaction database, and extracting the account information of the transaction counterpart in the transaction data;
calculating the number of repetition times of the account information of the transaction counter side, and sequencing the account information of the transaction counter side according to the number of repetition times;
intercepting a preset amount of the account information of the transaction counterpart to obtain account information of a common party;
sequentially sending evaluation requests containing evaluation tables to account information of different common parties, receiving evaluation results, and confirming first abnormal data based on the evaluation results;
wherein the evaluation table comprises evaluation items and rating options.
As a further limitation of the technical scheme of the invention: the step of sequentially sending evaluation requests containing evaluation tables to account information of different common parties, receiving evaluation results and confirming first abnormal data based on the evaluation results comprises the following steps:
establishing a connection channel with a problem database, wherein the problem database comprises problem items and difficulty items corresponding to the problem items;
randomly reading the problems with different difficulties, and inserting the problems into an evaluation table based on the difficulty sequence;
and sequentially sending evaluation requests containing evaluation tables to account information of different common parties, and acquiring evaluation results in real time.
As a further limitation of the technical scheme of the invention: the steps of sequentially sending evaluation requests containing evaluation tables to account information of different common parties and acquiring evaluation results in real time comprise:
sequentially sending evaluation requests containing evaluation tables to account information of different common parties, and determining scores according to states of rating options in the evaluation tables;
obtaining feedback information of a user according to problems in an evaluation table, comparing the feedback information with prestored reference information, and generating a correction score according to a comparison result; the feedback information comprises question answers and corresponding answer duration;
generating a safety score based on the score and the correction score, comparing the safety score with a preset score threshold value, and marking corresponding account information of the common party when the safety score is lower than the preset score threshold value;
and counting the marked common party account information and determining first abnormal data.
As a further limitation of the technical scheme of the invention: the step of generating a transaction feature vector library based on the transaction database comprises:
performing feature extraction on the transaction data in the transaction database to obtain transaction attributes;
preprocessing the transaction attribute;
and constructing a transaction characteristic vector of the target account arranged in time sequence in the target time period according to the preprocessed transaction attributes.
As a further limitation of the technical scheme of the invention: the method further comprises the following steps:
determining a position to be detected in a transaction database according to a preset offset;
determining a separator according to the position to be detected, and extracting target data according to the separator;
extracting time information in the target data based on a regular expression;
and generating an index library according to the time information and the corresponding offset.
As a further limitation of the technical scheme of the invention: the step of determining a separator according to the position to be detected and extracting target data according to the separator comprises the following steps:
reading bytes at the position to be detected in a transaction database, and judging whether the bytes are separators or not;
when the bytes are separators, values are taken one by one from the current offset until the next separator or file sentence end identifier is encountered;
when the bytes are not separators, traversing byte by byte until separators are encountered, recording corresponding offsets, and then taking values byte by byte from the current offset until the next separator or file sentence end identifier is encountered;
and extracting bytes between the separators according to the separators to obtain target data.
The technical scheme of the invention also provides a behavior fund analysis system, which comprises:
the database generation module is used for receiving transaction data of account information, reading time items of the transaction data, sequencing the transaction data based on the time items and generating a transaction database;
the interactive evaluation module is used for traversing the transaction database, determining account information of a frequently-used party, sending a verification request to the account information of the frequently-used party, and determining first abnormal data based on a verification result;
the abnormal data identification module is used for generating a transaction characteristic vector library based on the transaction database if the first abnormal data does not exist, calling a trained abnormal data identification model, inputting the transaction characteristic vector into the abnormal data identification model and identifying second abnormal data existing in the transaction data;
and the risk evaluation module is used for calling a trained risk evaluation model, inputting the abnormal data into the risk evaluation model to obtain the risk probability of the transaction data, and sending early warning information to account information when the risk probability is higher than a threshold value.
As a further limitation of the technical scheme of the invention: the interactive rating module comprises:
the information extraction unit is used for traversing the transaction database and extracting the account information of the transaction counter party in the transaction data;
the repeated frequency calculating unit is used for calculating the repeated frequency of the account information of the transaction counter side and sequencing the account information of the transaction counter side according to the repeated frequency;
the intercepting unit is used for intercepting the preset intercepting amount of the account information of the transaction counterpart to obtain the account information of the common party;
the processing execution unit is used for sequentially sending evaluation requests containing evaluation tables to account information of different common parties, receiving evaluation results and confirming first abnormal data based on the evaluation results;
wherein the evaluation table comprises evaluation items and rating options.
As a further limitation of the technical scheme of the invention: the process execution unit includes:
the system comprises a connection subunit, a problem database and a data processing unit, wherein the connection subunit is used for establishing a connection channel with the problem database, and the problem database comprises problem items and difficulty items corresponding to the problem items;
the random reading subunit is used for randomly reading the problems with different difficulties and inserting the problems into an evaluation table based on the difficulty sequence;
and the feedback subunit is used for sequentially sending the evaluation requests containing the evaluation tables to the account information of different common parties and acquiring the evaluation results in real time.
Compared with the prior art, the invention has the beneficial effects that: according to the method, before abnormal data analysis is carried out through the model, interactive evaluation is carried out on the user through the interactive evaluation module, authenticity is high, cost is low, and a traditional behavior fund analysis process is optimized.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention.
FIG. 1 shows a flow diagram of a behavioral fund analysis method.
FIG. 2 illustrates a first sub-flow block diagram of a behavioral fund analysis method.
FIG. 3 illustrates a second sub-flow block diagram of a behavioral fund analysis method.
FIG. 4 illustrates a third sub-flow block diagram of a behavioral fund analysis method.
FIG. 5 illustrates a fourth sub-flow block diagram of a behavioral fund analysis method.
FIG. 6 illustrates a fifth sub-flow block diagram of a behavioral fund analysis method.
FIG. 7 shows a sixth sub-flow block diagram of a behavioral fund analysis method.
Fig. 8 shows a block diagram of the component structure of the action fund analysis system.
Fig. 9 is a block diagram showing a constitutional structure of an interactive evaluation module in the action fund analysis system.
Fig. 10 is a block diagram showing a constitutional structure of a processing execution unit in the interactive rating module.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Example 1
Fig. 1 shows a flow chart of a behavior fund analysis method, and in an embodiment of the present invention, a behavior fund analysis method is provided, where the method includes:
step S100: receiving transaction data of account information, reading time items of the transaction data, sequencing the transaction data based on the time items, and generating a transaction database;
firstly, the sample to be analyzed is analyzed for the behavior fund, the sample is the transaction data of the account information, the transaction data generally has time items, and the transaction data is sequenced according to the time items, so that the subsequent operation is facilitated.
Step S200: traversing the transaction database, determining account information of a frequently-used party, sending a verification request to the account information of the frequently-used party, and determining first abnormal data based on a verification result;
before the abnormity analysis is carried out, the account can be preliminarily judged through some simple interaction processes, the authenticity of the interaction judgment process is high, the cost is low, and the judgment is not needed by means of a complex model.
Step S300: if the first abnormal data does not exist, generating a transaction feature vector library based on the transaction database, calling a trained abnormal data identification model, inputting the transaction feature vector into the abnormal data identification model, and identifying second abnormal data existing in the transaction data;
the purpose of step S300 is to perform anomaly identification on the transaction data through a preset anomaly data identification model, and this process is completed by a computer, where the anomaly data identification model may be in the prior art, or may be obtained by reading some known transaction data with anomaly data through a big data technology and performing feature extraction on these data to obtain an anomaly data identification model.
Step S400: calling a trained risk evaluation model, inputting the abnormal data into the risk evaluation model to obtain the risk probability of the transaction data, and sending early warning information to account information when the risk probability is higher than a threshold value;
when transaction data is abnormal, whether the transaction data is the first abnormal data or the second abnormal data, the risk probability of the transaction data needs to be calculated, for example, the abnormal reason of some abnormal data is caused by a program, the abnormal data and the early warning information are obviously not in one-to-one correspondence, and the early warning information can be generated only when the abnormal data are dangerous enough.
Fig. 2 shows a first sub-flow diagram of a behavioral fund analysis method, wherein the steps of traversing the transaction database, determining common party account information, sending a verification request to the common party account information, and determining first abnormal data based on a verification result comprise:
step S201: traversing the transaction database, and extracting the account information of the transaction counterpart in the transaction data;
step S202: calculating the number of repetition times of the account information of the transaction counter side, and sequencing the account information of the transaction counter side according to the number of repetition times;
step S203: intercepting a preset amount of the account information of the transaction counterpart to obtain account information of a common party;
step S204: sequentially sending evaluation requests containing evaluation tables to account information of different common parties, receiving evaluation results, and confirming first abnormal data based on the evaluation results;
wherein the evaluation table comprises evaluation items and rating options.
Steps S201 to S204 are specific steps of the evaluation process, the transaction is performed by two parties, which are divided into the own party and the opposite party, the account information of the opposite party of the transaction is obtained, and then the account information is sorted according to the number of times of repetition of the account information of the opposite party, that is, the account information of the opposite party is sorted according to the transaction frequency.
Fig. 3 shows a second sub-flow diagram of the behavior fund analysis method, the step of sequentially sending evaluation requests containing evaluation tables to account information of different common parties, receiving evaluation results, and confirming first abnormal data based on the evaluation results includes:
step S2041: establishing a connection channel with a problem database, wherein the problem database comprises problem items and difficulty items corresponding to the problem items;
step S2042: randomly reading the problems with different difficulties, and inserting the problems into an evaluation table based on the difficulty sequence;
step S2043: and sequentially sending evaluation requests containing evaluation tables to account information of different common parties, and acquiring evaluation results in real time.
Step S2041 to step S2043 provide a specific evaluation method, first, taking a traditional evaluation form as an example, generally, the evaluation of the user account by the opposite account can be obtained through the evaluation form, but these are regular, such as a full score, and so on, and therefore, their actual evaluation effect is very low; however, if the order of the options is disturbed, the scorers need to carefully read and do questions, which obviously causes aversion, and most of the scorers directly disregard the evaluation request, so the actual evaluation effect is lower; the method provides a compromise mode, namely, a plurality of questions, such as the questions like the verification codes, are inserted in advance, the user is not difficult to answer the questions, the concentration degree of the user is improved to a certain degree, and in addition, the problem of automatic evaluation of the machine can be effectively prevented.
Fig. 4 shows a third sub-flow diagram of the behavior fund analysis method, where the step of sending evaluation requests including evaluation tables to account information of different common parties in sequence and obtaining evaluation results in real time includes:
step S20431: sequentially sending evaluation requests containing evaluation tables to account information of different common parties, and determining scores according to states of rating options in the evaluation tables;
step S20432: obtaining feedback information of a user according to problems in an evaluation table, comparing the feedback information with prestored reference information, and generating a correction score according to a comparison result; the feedback information comprises question answers and corresponding answer duration;
step S20433: generating a safety score based on the score and the correction score, comparing the safety score with a preset score threshold value, and marking corresponding account information of the common party when the safety score is lower than the preset score threshold value;
step S20434: and counting the marked common party account information and determining first abnormal data.
In steps S20431 to S20434, a score and a revised score are generated, the score is related to the evaluation table, and the revised score is related to the question, wherein in the revised score, there is a special case that the user directly stops at a certain question, and the evaluation process is directly ignored, but the answer before this is still valid, so that stopping answering the question has a certain influence, but the emphasis should be placed on the answered question; as for the influence of stopping answering, the influence is distinguished by answering time length, and the longer the answering time length is, the more importance the evaluation party pays to the user, and the corresponding correction score should be higher.
FIG. 5 shows a fourth sub-flow block diagram of a behavioral fund analysis method, the step of generating a transaction feature vector library based on the transaction database comprising:
step S301: performing feature extraction on the transaction data in the transaction database to obtain transaction attributes;
step S302: preprocessing the transaction attribute;
step S303: and constructing a transaction characteristic vector of the target account arranged in time sequence in the target time period according to the preprocessed transaction attributes.
Step S301 to step S303 are feature extraction processes, and a transaction feature vector is finally generated, which is used as an input of the abnormal data recognition model.
FIG. 6 shows a fifth sub-flow block diagram of a behavioral fund analysis method, the method further comprising:
step S501: determining a position to be detected in a transaction database according to a preset offset;
step S502: determining a separator according to the position to be detected, and extracting target data according to the separator;
step S503: extracting time information in the target data based on a regular expression;
step S504: and generating an index library according to the time information and the corresponding offset.
Step S501 to step S504 provide an index database generation method, which corresponds to a query function in software, and first, the transaction database is already a sorted transaction database, the offset is a preset value, for example, 1kb, and based on the offset of 1kb, each node is determined, and the node positions are respectively 1kb, 2kb, 3kb, and so on; extracting some target data according to the positions, then extracting time items in the target data, and finally generating an index database, wherein the index database has two items, namely the time items and the corresponding offsets; when a user wants to inquire some transaction data, the corresponding offset can be read in the index database directly through the time item, then the corresponding position is positioned in the transaction database, and at this time, the desired data can be found only by traversing the content of 1 kb; it can be seen that in this process, only the index database and a certain piece of data with the size of 1kb are processed, which can greatly relieve the operation pressure. Of course, in the transaction database with time items, it seems simpler to locate a position directly, but in terms of practical operation, it is also a process of traversing comparison, and in the case of a very large transaction database, the speed of this approach is slow because the reading process becomes slow.
It is worth mentioning that a regular expression (regular expression) describes a pattern (pattern) for matching a character string, which can be used to check whether a string contains a certain substring, replace the matched substring, or take out a substring that meets a certain condition from a certain string, etc. This is an open source algorithm and it is easy to query various routines, which can be done by those skilled in the art in the actual programming.
FIG. 7 shows a sixth sub-flow block diagram of a behavioral fund analysis method, wherein the step of determining a separator according to the to-be-detected position and extracting target data according to the separator comprises the following steps:
step S5021: reading bytes at the position to be detected in a transaction database, and judging whether the bytes are separators or not;
step S5022: when the bytes are separators, values are taken one by one from the current offset until the next separator or file sentence end identifier is encountered;
step S5023: when the bytes are not separators, traversing byte by byte until separators are encountered, recording corresponding offsets, and then taking values byte by byte from the current offset until the next separator or file sentence end identifier is encountered;
step S5024: and extracting bytes between the separators according to the separators to obtain target data.
Steps S5021 to S5024 provide a specific target data extraction method, in which the predetermined value of the offset is 1kb, but how to obtain a piece of target data from the position of 1kb needs to be further determined, and this provides a determination method for obtaining target data by delimiters.
Example 2
Fig. 8 is a block diagram illustrating a configuration of a behavior fund analysis system, and in an embodiment of the present invention, a behavior fund analysis system is provided, where the system 10 includes:
the database generation module 11 is configured to receive transaction data of account information, read a time item of the transaction data, sort the transaction data based on the time item, and generate a transaction database;
the interaction evaluation module 12 is configured to traverse the transaction database, determine common party account information, send a verification request to the common party account information, and determine first abnormal data based on a verification result;
an abnormal data identification module 13, configured to generate a transaction feature vector library based on the transaction database if the first abnormal data does not exist, invoke a trained abnormal data identification model, input the transaction feature vector into the abnormal data identification model, and identify second abnormal data existing in the transaction data;
and the risk evaluation module 14 is used for calling the trained risk evaluation model, inputting the abnormal data into the risk evaluation model to obtain the risk probability of the transaction data, and sending early warning information to account information when the risk probability is higher than a threshold value.
Fig. 9 is a block diagram showing a constitutional structure of an interactive evaluation module in the behavior fund analysis system, wherein the interactive evaluation module 12 comprises:
the information extraction unit 121 is configured to traverse the transaction database and extract the transaction counter account information in the transaction data;
a repetition number calculating unit 122, configured to calculate a repetition number of the transaction counterpart account information, and sort the transaction counterpart account information according to the repetition number;
the intercepting unit 123 is configured to intercept a preset intercepting amount of the transaction counterpart account information to obtain common party account information;
the processing execution unit 124 is used for sequentially sending evaluation requests containing evaluation tables to account information of different common parties, receiving evaluation results and confirming first abnormal data based on the evaluation results;
wherein the evaluation table comprises evaluation items and rating options.
Fig. 10 is a block diagram illustrating a structure of a process execution unit in the interactive evaluation module, where the process execution unit 124 includes:
a connection subunit 1241, configured to establish a connection channel with a problem database, where the problem database includes problem items and difficulty items corresponding to the problem items;
a random reading subunit 1242, configured to randomly read problems with different difficulties, and insert the problems into the evaluation table based on the difficulty order;
and the feedback subunit 1243 is configured to send evaluation requests including evaluation tables to different common party account information in sequence, and obtain evaluation results in real time.
The functions that can be implemented by the behavioral fund analysis method are all completed by a computer device, and the computer device comprises one or more processors and one or more memories, wherein at least one program code is stored in the one or more memories, and is loaded and executed by the one or more processors to implement the functions of the behavioral fund analysis method.
The processor fetches instructions and analyzes the instructions one by one from the memory, then completes corresponding operations according to the instruction requirements, generates a series of control commands, enables all parts of the computer to automatically, continuously and coordinately act to form an organic whole, realizes the input of programs, the input of data, the operation and the output of results, and the arithmetic operation or the logic operation generated in the process is completed by the arithmetic unit; the Memory comprises a Read-Only Memory (ROM) for storing a computer program, and a protection device is arranged outside the Memory.
Illustratively, a computer program can be partitioned into one or more modules, which are stored in memory and executed by a processor to implement the present invention. One or more of the modules may be a series of computer program instruction segments capable of performing certain functions, which are used to describe the execution of the computer program in the terminal device.
Those skilled in the art will appreciate that the above description of the service device is merely exemplary and not limiting of the terminal device, and may include more or less components than those described, or combine certain components, or different components, such as may include input output devices, network access devices, buses, etc.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is the control center of the terminal equipment and connects the various parts of the entire user terminal using various interfaces and lines.
The memory may be used to store computer programs and/or modules, and the processor may implement various functions of the terminal device by operating or executing the computer programs and/or modules stored in the memory and calling data stored in the memory. The memory mainly comprises a storage program area and a storage data area, wherein the storage program area can store an operating system, application programs (such as an information acquisition template display function, a product information publishing function and the like) required by at least one function and the like; the storage data area may store data created according to the use of the berth-state display system (e.g., product information acquisition templates corresponding to different product types, product information that needs to be issued by different product providers, etc.), and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The terminal device integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the modules/units in the system according to the above embodiment may be implemented by a computer program, which may be stored in a computer-readable storage medium and used by a processor to implement the functions of the embodiments of the system. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution media, and the like.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A behavioral fund analysis method, the method comprising:
receiving transaction data of account information, reading time items of the transaction data, sequencing the transaction data based on the time items, and generating a transaction database;
traversing the transaction database, determining account information of a frequently-used party, sending a verification request to the account information of the frequently-used party, and determining first abnormal data based on a verification result;
if the first abnormal data does not exist, generating a transaction feature vector library based on the transaction database, calling a trained abnormal data identification model, inputting the transaction feature vector into the abnormal data identification model, and identifying second abnormal data existing in the transaction data;
and calling a trained risk evaluation model, inputting the abnormal data into the risk evaluation model to obtain the risk probability of the transaction data, and sending early warning information to account information when the risk probability is higher than a threshold value.
2. A behavioral funds analysis method according to claim 1, wherein the step of traversing the transaction database, determining frequent party account information, sending a validation request to the frequent party account information, determining first anomaly data based on the validation result comprises:
traversing the transaction database, and extracting the account information of the transaction counterpart in the transaction data;
calculating the number of repetition times of the account information of the transaction counter side, and sequencing the account information of the transaction counter side according to the number of repetition times;
intercepting a preset amount of the account information of the transaction counterpart to obtain account information of a common party;
sequentially sending evaluation requests containing evaluation tables to account information of different common parties, receiving evaluation results, and confirming first abnormal data based on the evaluation results;
wherein the evaluation table comprises evaluation items and rating options.
3. A behavioral fund analysis method according to claim 2, wherein the steps of sequentially sending evaluation requests containing evaluation forms to different common party account information, receiving evaluation results, and confirming the first abnormal data based on the evaluation results comprise:
establishing a connection channel with a problem database, wherein the problem database comprises problem items and difficulty items corresponding to the problem items;
randomly reading the problems with different difficulties, and inserting the problems into an evaluation table based on the difficulty sequence;
and sequentially sending evaluation requests containing evaluation tables to account information of different common parties, and acquiring evaluation results in real time.
4. A behavioral fund analysis method according to claim 3, wherein the step of sending evaluation requests containing evaluation forms to account information of different common parties in sequence and obtaining evaluation results in real time comprises:
sequentially sending evaluation requests containing evaluation tables to account information of different common parties, and determining scores according to states of rating options in the evaluation tables;
obtaining feedback information of a user according to problems in an evaluation table, comparing the feedback information with prestored reference information, and generating a correction score according to a comparison result; the feedback information comprises question answers and corresponding answer duration;
generating a safety score based on the score and the correction score, comparing the safety score with a preset score threshold value, and marking corresponding account information of the common party when the safety score is lower than the preset score threshold value;
and counting the marked common party account information and determining first abnormal data.
5. A behavioral fund analysis method according to claim 1, wherein the step of generating a transaction feature vector library based on the transaction database comprises:
performing feature extraction on the transaction data in the transaction database to obtain transaction attributes;
preprocessing the transaction attribute;
and constructing a transaction characteristic vector of the target account arranged in time sequence in the target time period according to the preprocessed transaction attributes.
6. A behavioral fund analysis method according to claim 1, further comprising:
determining a position to be detected in a transaction database according to a preset offset;
determining a separator according to the position to be detected, and extracting target data according to the separator;
extracting time information in the target data based on a regular expression;
and generating an index library according to the time information and the corresponding offset.
7. A behavioral fund analysis method according to claim 6, wherein the step of determining a separator based on the to-be-detected position and extracting target data based on the separator comprises:
reading bytes at the position to be detected in a transaction database, and judging whether the bytes are separators or not;
when the bytes are separators, values are taken one by one from the current offset until the next separator or file sentence end identifier is encountered;
when the bytes are not separators, traversing byte by byte until separators are encountered, recording corresponding offsets, and then taking values byte by byte from the current offset until the next separator or file sentence end identifier is encountered;
and extracting bytes between the separators according to the separators to obtain target data.
8. A behavioral fund analysis system, the system comprising:
the database generation module is used for receiving transaction data of account information, reading time items of the transaction data, sequencing the transaction data based on the time items and generating a transaction database;
the interactive evaluation module is used for traversing the transaction database, determining account information of a frequently-used party, sending a verification request to the account information of the frequently-used party, and determining first abnormal data based on a verification result;
the abnormal data identification module is used for generating a transaction characteristic vector library based on the transaction database if the first abnormal data does not exist, calling a trained abnormal data identification model, inputting the transaction characteristic vector into the abnormal data identification model and identifying second abnormal data existing in the transaction data;
and the risk evaluation module is used for calling a trained risk evaluation model, inputting the abnormal data into the risk evaluation model to obtain the risk probability of the transaction data, and sending early warning information to account information when the risk probability is higher than a threshold value.
9. The behavioral funds analysis system according to claim 8, wherein the interactive rating module comprises:
the information extraction unit is used for traversing the transaction database and extracting the account information of the transaction counter party in the transaction data;
the repeated frequency calculating unit is used for calculating the repeated frequency of the account information of the transaction counter side and sequencing the account information of the transaction counter side according to the repeated frequency;
the intercepting unit is used for intercepting the preset intercepting amount of the account information of the transaction counterpart to obtain the account information of the common party;
the processing execution unit is used for sequentially sending evaluation requests containing evaluation tables to account information of different common parties, receiving evaluation results and confirming first abnormal data based on the evaluation results;
wherein the evaluation table comprises evaluation items and rating options.
10. The behavioral fund analysis system according to claim 9, wherein the processing execution unit comprises:
the system comprises a connection subunit, a problem database and a data processing unit, wherein the connection subunit is used for establishing a connection channel with the problem database, and the problem database comprises problem items and difficulty items corresponding to the problem items;
the random reading subunit is used for randomly reading the problems with different difficulties and inserting the problems into an evaluation table based on the difficulty sequence;
and the feedback subunit is used for sequentially sending the evaluation requests containing the evaluation tables to the account information of different common parties and acquiring the evaluation results in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111006839.2A CN113450028A (en) | 2021-08-31 | 2021-08-31 | Behavior fund analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111006839.2A CN113450028A (en) | 2021-08-31 | 2021-08-31 | Behavior fund analysis method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113450028A true CN113450028A (en) | 2021-09-28 |
Family
ID=77819036
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111006839.2A Pending CN113450028A (en) | 2021-08-31 | 2021-08-31 | Behavior fund analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113450028A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116934486A (en) * | 2023-09-15 | 2023-10-24 | 深圳格隆汇信息科技有限公司 | Decision evaluation method and system based on deep learning |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102339445A (en) * | 2010-07-23 | 2012-02-01 | 阿里巴巴集团控股有限公司 | Method and system for evaluating credibility of network trade user |
| CN108711085A (en) * | 2018-05-09 | 2018-10-26 | 平安普惠企业管理有限公司 | A kind of response method and its equipment of transaction request |
| CN108846016A (en) * | 2018-05-05 | 2018-11-20 | 复旦大学 | A kind of searching algorithm towards Chinese word segmentation |
| CN109740838A (en) * | 2018-11-22 | 2019-05-10 | 平安科技（深圳）有限公司 | Provider service evaluation method and relevant device based on big data |
| CN110706090A (en) * | 2019-08-26 | 2020-01-17 | 阿里巴巴集团控股有限公司 | Credit fraud identification method and device, electronic equipment and storage medium |
| CN112801800A (en) * | 2021-04-14 | 2021-05-14 | 深圳格隆汇信息科技有限公司 | Behavior fund analysis system, behavior fund analysis method, computer equipment and storage medium |
-
2021
- 2021-08-31 CN CN202111006839.2A patent/CN113450028A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102339445A (en) * | 2010-07-23 | 2012-02-01 | 阿里巴巴集团控股有限公司 | Method and system for evaluating credibility of network trade user |
| CN108846016A (en) * | 2018-05-05 | 2018-11-20 | 复旦大学 | A kind of searching algorithm towards Chinese word segmentation |
| CN108711085A (en) * | 2018-05-09 | 2018-10-26 | 平安普惠企业管理有限公司 | A kind of response method and its equipment of transaction request |
| CN109740838A (en) * | 2018-11-22 | 2019-05-10 | 平安科技（深圳）有限公司 | Provider service evaluation method and relevant device based on big data |
| CN110706090A (en) * | 2019-08-26 | 2020-01-17 | 阿里巴巴集团控股有限公司 | Credit fraud identification method and device, electronic equipment and storage medium |
| CN112801800A (en) * | 2021-04-14 | 2021-05-14 | 深圳格隆汇信息科技有限公司 | Behavior fund analysis system, behavior fund analysis method, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 许正良: "《管理研究方法》", 30 April 2004 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116934486A (en) * | 2023-09-15 | 2023-10-24 | 深圳格隆汇信息科技有限公司 | Decision evaluation method and system based on deep learning |
| CN116934486B (en) * | 2023-09-15 | 2024-01-12 | 深圳市蓝宇飞扬科技有限公司 | Decision evaluation method and system based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107491536B (en) | Test question checking method, test question checking device and electronic equipment | |
| CN110352425A (en) | The cognition supervision compliance automation of block chain transaction | |
| CN107016132B (en) | Online question bank quality improving method and system and terminal equipment | |
| CN104158828B (en) | The method and system of suspicious fishing webpage are identified based on cloud content rule base | |
| CN108664471B (en) | Character recognition error correction method, device, equipment and computer readable storage medium | |
| CN109933534B (en) | Method and device for determining financial test object | |
| CN112016138A (en) | Method and device for automatic safe modeling of Internet of vehicles and electronic equipment | |
| CN110858353B (en) | Method and system for obtaining case judge result | |
| CN113746758A (en) | Method and terminal for dynamically identifying flow protocol | |
| CN113450028A (en) | Behavior fund analysis method and system | |
| CN109189372B (en) | Development script generation method of insurance product and terminal equipment | |
| CN114579972A (en) | Vulnerability identification method and system for embedded development program | |
| CN112288584B (en) | Insurance report processing method and device, computer readable medium and electronic equipment | |
| CN113821692A (en) | Data processing method, device, server and storage medium | |
| CN114285587A (en) | Domain name identification method and device and domain name classification model acquisition method and device | |
| CN116975284A (en) | Entity relation extraction method and device based on priori knowledge and storage medium | |
| CN115620317A (en) | Method and system for verifying authenticity of electronic engineering document | |
| CN115830598A (en) | Tracing confirmation method, system, equipment and medium for standard equipment | |
| CN114065762A (en) | Text information processing method, device, medium and equipment | |
| CN114792007A (en) | Code detection method, device, equipment, storage medium and computer program product | |
| CN112860892A (en) | Data labeling method, device and equipment in AI model | |
| CN113268977B (en) | Text error correction method and device based on language model, terminal equipment and medium | |
| CN113194106B (en) | Network data security identification system and method | |
| CN114327615B (en) | Interface document generation method and system based on big data | |
| CN114596353B (en) | Question processing method, device, equipment and computer readable storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210928 |
|
| RJ01 | Rejection of invention patent application after publication |