CN113516302A - Business risk analysis method, device, equipment and storage medium - Google Patents
Business risk analysis method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113516302A CN113516302A CN202110696697.0A CN202110696697A CN113516302A CN 113516302 A CN113516302 A CN 113516302A CN 202110696697 A CN202110696697 A CN 202110696697A CN 113516302 A CN113516302 A CN 113516302A
- Authority
- CN
- China
- Prior art keywords
- data
- risk
- business
- service
- parcel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Abstract
The invention relates to the technical field of artificial intelligence, and provides a business risk analysis method, a device, equipment and a storage medium, which are used for improving the accuracy of business risk prediction based on user behavior analysis. The business risk analysis method comprises the following steps: carrying out parcel trip data analysis on the parcel data of the grid map and the mobile position data of the user to obtain target parcel trip data; performing business index regression analysis based on a preset time period on the trip data of the target area to obtain target business index prediction data; classifying target service index prediction data based on real-time risk types to obtain dynamic service risk data; classifying the user information based on risk types to obtain static business risk data; and determining target business risk data according to the dynamic business risk data and the static business risk data. In addition, the invention also relates to a block chain technology, and the grid map region data and the user mobile position data can be stored in the block chain.
Description
Technical Field
The invention relates to the field of intelligent decision making of artificial intelligence, in particular to a business risk analysis method, a business risk analysis device, business risk analysis equipment and a storage medium.
Background
In the big data era, analysis of user travel tracks is often used for data mining, such as: through the analysis of the user travel track, the information of the user such as hobbies, consumption level, working environment, travel rules, interpersonal network and the like can be found, and rich user portrait can be established through the information. Analysis of the user travel track is also applied to data prediction, and at present, a monomorphic business risk prediction is usually performed according to user behavior information and a single prediction model to realize the business risk prediction based on the user travel track analysis.
However, the prediction data (i.e., user behavior information) adopted has hysteresis, and the single prediction model has poor prediction flexibility and applicability, so that the prediction timeliness and stability are poor, and the business risk prediction accuracy based on the user behavior analysis is low.
Disclosure of Invention
The invention provides a business risk analysis method, a business risk analysis device, business risk analysis equipment and a storage medium, which are used for improving the accuracy of business risk prediction based on user behavior analysis.
The first aspect of the present invention provides a business risk analysis method, including:
acquiring grid map zone data and user mobile position data, and performing zone trip data analysis on the grid map zone data and the user mobile position data to obtain target zone trip data;
calling a preset business index prediction model, and performing business index regression analysis based on a preset time period on the trip data of the target area to obtain target business index prediction data;
calling a preset dynamic business risk prediction model, and classifying the target business index prediction data based on real-time risk types to obtain dynamic business risk data;
acquiring user information, calling a preset static business risk prediction model, and classifying the user information based on risk types to obtain static business risk data;
and performing service risk grade identification on the dynamic service risk data and the static service risk data to obtain target service risk data.
Optionally, in a first implementation manner of the first aspect of the present invention, the obtaining grid map parcel data and user mobile position data, and performing parcel travel data analysis on the grid map parcel data and the user mobile position data to obtain target parcel travel data includes:
acquiring initial gridding map data and grid point similarity measurement of the initial gridding map data, and carrying out fragment clustering on the initial gridding map data based on the grid point similarity measurement to obtain grid map fragment data;
and acquiring user moving position data, and performing area analysis, area travel data supplement and record statistics on the grid map area data through the user moving position data to obtain target area travel data.
Optionally, in a second implementation manner of the first aspect of the present invention, the obtaining of the user moving position data, and performing parcel analysis, parcel travel data supplement, and record statistics on the grid map parcel data according to the user moving position data to obtain target parcel travel data includes:
acquiring user moving position data, and extracting the block track sequence characteristics of the block data of the grid map based on the user moving position data to obtain initial travel sequence data corresponding to each block;
predicting the initial trip sequence data corresponding to each parcel based on a trip track to obtain predicted trip sequence data corresponding to each parcel;
merging the initial trip sequence data corresponding to each parcel with the predicted trip sequence data corresponding to each parcel to obtain target trip sequence data corresponding to each parcel;
and according to preset statistical indexes, counting the target trip sequence data corresponding to each block to obtain the target block trip data.
Optionally, in a third implementation manner of the first aspect of the present invention, the invoking a preset service index prediction model, and performing service index regression analysis based on a preset time period on the target parcel travel data to obtain target service index prediction data includes:
acquiring service index data to be processed, calling a preset service index prediction model, and performing multi-linear variable operation on the trip data of the target area and the service index data to be processed for a preset time period to obtain initial service index prediction data;
respectively carrying out data statistical analysis based on a preset historical time period, data extraction based on a current time period and data extraction based on a prediction time period on the initial service index prediction data to obtain historical time period service index change trend data, current time period service index data and prediction time period service index data;
and determining the historical period service index change trend data, the current period service index data and the forecast period service index data as target service index forecast data.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the performing, on the initial service index prediction data, data statistical analysis based on a preset historical period, data extraction based on a current period, and data extraction based on a prediction period, respectively, to obtain historical period service index change trend data, current period service index data, and prediction period service index data includes:
performing sliding reading on the initial service index prediction data based on a preset historical time period, a current time period and a prediction time period to obtain historical window sequence data, current window sequence data and prediction time period service index data;
carrying out mean value calculation or maximum value statistics on the historical window sequence data to obtain historical time period service index variation trend data;
and intercepting the current window sequence data according to a preset intercepting interval to obtain the current time interval service index data.
Optionally, in a fifth implementation manner of the first aspect of the present invention, the performing service risk level identification on the dynamic service risk data and the static service risk data to obtain target service risk data includes:
performing two-dimensional matrix conversion and weighted summation on the dynamic business risk data and the static business risk data to obtain a risk score value;
comparing and analyzing the risk score value with a preset grade threshold value to obtain a comparison and analysis result;
and determining the service risk information corresponding to the preset grade threshold value as target service risk data according to the comparison and analysis result.
Optionally, in a sixth implementation manner of the first aspect of the present invention, after performing service risk level identification on the dynamic service risk data and the static service risk data to obtain target service risk data, the method further includes:
and acquiring historical service risk data corresponding to the user information, acquiring a corresponding adjustment strategy according to the target service risk data and the historical service risk data, and executing the adjustment strategy.
A second aspect of the present invention provides a business risk analysis device, including:
the system comprises a parcel analysis module, a target parcel travel module and a storage module, wherein the parcel analysis module is used for acquiring parcel data of a grid map and user mobile position data, and carrying out parcel travel data analysis on the parcel data of the grid map and the user mobile position data to obtain target parcel travel data;
the regression analysis module is used for calling a preset business index prediction model and carrying out business index regression analysis based on a preset time period on the trip data of the target area to obtain target business index prediction data;
the first classification module is used for calling a preset dynamic business risk prediction model and classifying the target business index prediction data based on real-time risk types to obtain dynamic business risk data;
the second classification module is used for acquiring user information, calling a preset static business risk prediction model, and classifying the user information based on risk types to obtain static business risk data;
and the identification module is used for carrying out service risk grade identification on the dynamic service risk data and the static service risk data to obtain target service risk data.
Optionally, in a first implementation manner of the second aspect of the present invention, the tile region analyzing module includes:
a clustering unit, configured to obtain initial grid map data and grid point similarity measurement of the initial grid map data, and perform parcel clustering on the initial grid map data based on the grid point similarity measurement to obtain grid map parcel data;
and the analysis and statistics unit is used for acquiring the mobile position data of the user, and performing area analysis, area trip data supplement and record statistics on the grid map area data through the mobile position data of the user to obtain target area trip data.
Optionally, in a second implementation manner of the second aspect of the present invention, the analysis statistic unit is specifically configured to:
acquiring user moving position data, and extracting the block track sequence characteristics of the block data of the grid map based on the user moving position data to obtain initial travel sequence data corresponding to each block;
predicting the initial trip sequence data corresponding to each parcel based on a trip track to obtain predicted trip sequence data corresponding to each parcel;
merging the initial trip sequence data corresponding to each parcel with the predicted trip sequence data corresponding to each parcel to obtain target trip sequence data corresponding to each parcel;
and according to preset statistical indexes, counting the target trip sequence data corresponding to each block to obtain the target block trip data.
Optionally, in a third implementation manner of the second aspect of the present invention, the regression analysis module includes:
the prediction unit is used for acquiring service index data to be processed, calling a preset service index prediction model, and performing multi-linear variable operation on the trip data of the target area and the service index data to be processed for a preset time period to obtain initial service index prediction data;
the time interval analysis unit is used for respectively carrying out data statistical analysis based on a preset historical time interval, data extraction based on the current time interval and data extraction based on the prediction time interval on the initial service index prediction data to obtain historical time interval service index change trend data, current time interval service index data and prediction time interval service index data;
and the determining unit is used for determining the historical period service index change trend data, the current period service index data and the prediction period service index data as target service index prediction data.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the time period analysis unit is specifically configured to:
performing sliding reading on the initial service index prediction data based on a preset historical time period, a current time period and a prediction time period to obtain historical window sequence data, current window sequence data and prediction time period service index data;
carrying out mean value calculation or maximum value statistics on the historical window sequence data to obtain historical time period service index variation trend data;
and intercepting the current window sequence data according to a preset intercepting interval to obtain the current time interval service index data.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the identification module is specifically configured to:
performing two-dimensional matrix conversion and weighted summation on the dynamic business risk data and the static business risk data to obtain a risk score value;
comparing and analyzing the risk score value with a preset grade threshold value to obtain a comparison and analysis result;
and determining the service risk information corresponding to the preset grade threshold value as target service risk data according to the comparison and analysis result.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the business risk analyzing apparatus further includes:
and the strategy execution module is used for acquiring historical business risk data corresponding to the user information, acquiring a corresponding adjustment strategy according to the target business risk data and the historical business risk data, and executing the adjustment strategy.
A third aspect of the present invention provides a business risk analysis device, including: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the business risk analysis device to perform the business risk analysis method described above.
A fourth aspect of the present invention provides a computer-readable storage medium having stored therein instructions, which, when run on a computer, cause the computer to perform the business risk analysis method described above.
In the technical scheme provided by the invention, grid map zone data and user mobile position data are obtained, and zone trip data analysis is carried out on the grid map zone data and the user mobile position data to obtain target zone trip data; calling a preset business index prediction model, and performing business index regression analysis based on a preset time period on the trip data of the target area to obtain target business index prediction data; calling a preset dynamic business risk prediction model, and classifying target business index prediction data based on real-time risk types to obtain dynamic business risk data; acquiring user information, calling a preset static business risk prediction model, and classifying the user information based on risk types to obtain static business risk data; and performing service risk grade identification on the dynamic service risk data and the static service risk data to obtain target service risk data. In the embodiment of the invention, the problem of hysteresis of target business index prediction data is solved, the flexibility and the applicability of prediction of target business risk data are improved, the timeliness and the stability of prediction are further improved, the accuracy of trip data of a target district is improved, the data richness and the data quality of the business index prediction data are improved, the efficiency and the accuracy of business risk grade identification are improved, and the business risk prediction accuracy based on user behavior analysis is improved.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a business risk analysis method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of another embodiment of a business risk analysis method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an embodiment of a business risk analysis device according to an embodiment of the present invention;
fig. 4 is a schematic diagram of another embodiment of a business risk analysis device in the embodiment of the present invention;
fig. 5 is a schematic diagram of an embodiment of a business risk analysis device in the embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a business risk analysis method, a business risk analysis device, business risk analysis equipment and a storage medium, and improves the accuracy of business risk prediction based on user behavior analysis.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For convenience of understanding, a specific flow of the embodiment of the present invention is described below, and referring to fig. 1, an embodiment of the business risk analysis method in the embodiment of the present invention includes:
101. acquiring grid map zone data and user mobile position data, and performing zone trip data analysis on the grid map zone data and the user mobile position data to obtain target zone trip data.
It is to be understood that the execution subject of the present invention may be a business risk analysis device, and may also be a terminal or a server, which is not limited herein. The embodiment of the present invention is described by taking a server as an execution subject.
Wherein the user mobile location data is used to indicate Location Based Services (LBS) of the user mobile terminal. The grid map zone data is used for indicating grid map data for zone clustering based on the index data of each grid point, and the grid map zone data comprises longitude and latitude, boundaries, distances in the longitude and latitude, place names of locations, interest point information, average interest point service index data and the like of each grid corresponding to each zone.
After obtaining the user authorization, the server extracts the global positioning data of the user mobile terminal in real time, thereby obtaining the user mobile position data; and extracting the gridding map data which is subjected to the partition from the preset service system so as to obtain the gridding map partition data.
Calling a preset Geographic Information System (GIS), carrying out data extraction and data fusion on the overlapped region of the grid map parcel data and the user mobile position data to obtain initial parcel travel data, wherein the initial parcel travel data is used for indicating travel track data of each parcel in the grid map parcel data of a user; and performing basic statistics on the initial parcel travel data based on preset statistical indexes to realize parcel travel data analysis on the grid map parcel data and the user mobile position data so as to obtain target parcel travel data, wherein the statistical indexes include but are not limited to occurrence times, residence time, occurrence frequency and the like.
102. And calling a preset business index prediction model, and performing business index regression analysis based on a preset time period on the trip data of the target area to obtain target business index prediction data.
For example, taking a service index as a consumption level and a service index prediction model as a consumption level prediction model as an example, the server may extract data of travel data of a target parcel based on a preset historical time period to obtain travel data of the parcel to be predicted, where the preset time period includes the preset historical time period, a current time period and a prediction time period, and it is assumed that the preset historical time period is 2021.01.01-2021.03.31, the current time period is 2021.04.01-2021.05.31, and the prediction time period is 2021.06.01-2021.08.31; the method comprises the steps that a server obtains user information, and corresponding (same or similar) to-be-processed consumption level data, namely to-be-processed business index data, are obtained on the basis of the user information and to-be-predicted parcel travel data; calling a preset consumption level prediction model, namely a business index prediction model, respectively carrying out multiple linear regression processing and variation trend statistical analysis with the independent variable of 2021.01.01-2021.03.31, multiple linear regression processing with the independent variable of 2021.04.01-2021.05.31 and multiple linear regression processing with the independent variable of 2021.06.01-2021.08.31 on trip data of a to-be-predicted zone to realize calling the preset business index prediction model, and carrying out business index regression analysis based on a preset time period on trip data of a target zone so as to obtain historical period consumption level variation trend data (namely historical period business index variation trend data), current period consumption level data (namely current period business index data) and predicted period consumption level data (namely predicted period business index data); and determining the consumption level variation trend data of the historical period, the consumption level data of the current period and the consumption level data of the prediction period as service index prediction data.
Optionally, the server may obtain the user information, obtain corresponding to-be-processed service index data based on the user information and the target parcel travel data, call a preset service index prediction model, and perform prediction, sliding reading, and statistical analysis based on a prediction time period on the target parcel travel data and the to-be-processed service index data to obtain target service index prediction data including historical period service index variation trend data, current period service index data, and prediction period service index data.
103. And calling a preset dynamic business risk prediction model, and classifying target business index prediction data based on real-time risk types to obtain dynamic business risk data.
The preset dynamic business risk prediction model is obtained by extracting business index prediction data of a part of users (a part of users who are overdue once and a part of users who are never overdue) from data of a user group as a preset classification model for training of a training set, and the dynamic business risk prediction model is a dynamic classification model, and as the business index prediction data comprise user mobile location data LBS which are updated in real time, the result generated by the dynamic business risk prediction model can also be dynamically updated. Business risks may be as follows: risk of debt repayment.
The server calls a preset dynamic business risk prediction model, carries out probability value calculation and probability value discrimination based on real-time risk types on target business index prediction data to realize calling the preset dynamic business risk prediction model, and carries out classification based on the real-time risk types on the target business index prediction data to obtain dynamic business risk data, wherein the dynamic business risk data can be used for indicating high risk or low risk, or the dynamic business risk data can also be used for indicating risk or no risk.
Optionally, the dynamic business risk prediction model may be obtained by connecting and combining a plurality of classification networks (classifiers) according to a preset logical connection relationship, the server performs probability value calculation based on a real-time risk type on target business index prediction data through the dynamic business risk prediction model to obtain a plurality of initial classification values, performs weighted summation on the plurality of initial classification values to obtain a target classification value, performs comparative analysis on the target classification value and a preset threshold value to obtain an analysis result, and generates data represented by a dynamic business risk according to the analysis result, that is, dynamic business risk data, so as to call the preset dynamic business risk prediction model and classify the target business index prediction data based on the real-time risk type.
104. And acquiring user information, calling a preset static business risk prediction model, and classifying the user information based on risk types to obtain static business risk data.
The preset static business risk prediction model is obtained by training a preset classification model through personal information of part of users extracted from data of a user group and is used for business risk prediction. The server acquires a user identity identification number, and acquires user information corresponding to the user identity identification number through a pre-established corresponding relationship between the user identity identification number and the user information, wherein the user information comprises but is not limited to age, academic calendar, personal income, work field, work age, asset information and the like; calling a multi-level feature extraction network in a preset static business risk prediction model, performing multi-level feature extraction on user information to obtain static feature information, performing probability value calculation and threshold value discrimination on the static feature information based on risk types to realize calling the preset static business risk prediction model, and performing risk type-based classification on the user information to obtain static business risk data, wherein the multi-level feature extraction network is a feature extraction network formed by connecting a plurality of feature extraction models in series, and the feature extraction models in the plurality of feature extraction models are different.
105. And performing service risk grade identification on the dynamic service risk data and the static service risk data to obtain target service risk data.
The server calls a preset conversion function, two-dimensional matrix conversion is carried out on the dynamic business risk data and the static business risk data respectively to obtain a dynamic risk two-dimensional matrix and a static risk two-dimensional matrix, and the dynamic risk two-dimensional matrix and the static risk two-dimensional matrix are summed according to a preset weight to obtain a risk score value; comparing and analyzing the risk score value with a preset grade condition, and determining the service risk information meeting the preset grade condition as target service risk data so as to realize service risk grade identification of the dynamic service risk data and the static service risk data, wherein the preset grade condition is used for indicating an identification strategy of each service risk grade, and the preset grade condition can comprise a preset grade threshold value and a judgment condition corresponding to the preset grade threshold value; the business risk levels may include high business risk, medium business risk, and low business risk, and the business risk levels may also include business risk and no business risk.
In the embodiment of the invention, the problem of hysteresis of target business index prediction data is solved, the flexibility and the applicability of prediction of target business risk data are improved, the timeliness and the stability of prediction are further improved, the accuracy of trip data of a target district is improved, the data richness and the data quality of the business index prediction data are improved, the efficiency and the accuracy of business risk grade identification are improved, and the business risk prediction accuracy based on user behavior analysis is improved.
Referring to fig. 2, another embodiment of the business risk analysis method according to the embodiment of the present invention includes:
201. and acquiring the initial gridding map data and grid point similarity measurement of the initial gridding map data, and carrying out region clustering on the initial gridding map data based on the grid point similarity measurement to obtain grid map region data.
The grid point similarity measurement comprises distance data of longitude and latitude of each grid point in the initial grid map data and average interest point service index data of each grid point, wherein the average interest point service index data is used for indicating the average service index data of all interest points in each grid point in the initial grid map data.
The execution process is as follows: taking average interest point service index data of grid point similarity measurement as per-human consumption data as an example for explanation, a server acquires original map data, and performs gridding processing based on geographic positions on the original map data to obtain preprocessed map data, wherein the preprocessed map data comprise, but are not limited to, longitude and latitude, boundaries, distances in the longitude and latitude, place names of locations and the like of grids; acquiring interest point information corresponding to each grid in the preprocessed map data, acquiring per-person consumption price data, namely per-person consumption price data, from a comment website or other channels based on the interest point information, and performing weighted summation on the per-person consumption price data to obtain average interest point consumption level data, namely average interest point service index data; performing data fusion on the preprocessed map data, the interest point information and the average interest point consumption level data to obtain initial gridding map data; acquiring grid point similarity measurement in initial gridding map data, calling a preset density-based spatial clustering algorithm (DBSCAN) to calculate Manhattan distance of each grid point in the initial gridding map data based on the grid point similarity measurement, and determining and connecting core points of each grid point according to the Manhattan distance so as to obtain grid map fragment data.
And carrying out fragment clustering on the initial gridding map data based on the grid point similarity measurement, so that the accuracy and the richness of the fragment data of the gridding map are improved.
202. And acquiring the mobile position data of the user, and performing area analysis, area trip data supplement and record statistics on the grid map area data through the mobile position data of the user to obtain target area trip data.
Specifically, the server acquires user mobile position data, and performs area track sequence feature extraction based on the user mobile position data on grid map area data to obtain initial travel sequence data corresponding to each area; predicting initial trip sequence data corresponding to each parcel based on a trip track to obtain predicted trip sequence data corresponding to each parcel; merging the initial trip sequence data corresponding to each parcel with the predicted trip sequence data corresponding to each parcel to obtain target trip sequence data corresponding to each parcel; and according to preset statistical indexes, counting the target trip sequence data corresponding to each block to obtain the target block trip data.
After obtaining the user authorization, the server captures the global positioning data of the user mobile terminal in real time, thereby obtaining the user mobile position data, calls a preset track simplification algorithm, and carries out track simplification processing on the user mobile position data to obtain preprocessed mobile position data; mapping the pre-processing mobile position data to grid map area data, or performing space-time-based data fusion on the pre-processing mobile position data and the grid map area data to obtain processed area data, performing trajectory feature extraction on the processed area data based on time sequences to obtain initial travel sequence data corresponding to each area, wherein the travel sequence data corresponding to each area are sequence numbers related to space and time.
The server calls an input gate, an output gate and a memory gate in the preset long-short term memory model LSTM, performs forward propagation processing and backward propagation processing based on the trip track on the initial trip sequence data corresponding to each segment to obtain predicted trip sequence data corresponding to each segment so as to realize the trip track-based prediction on the initial trip sequence data corresponding to each segment; or, the server calls a preset differential integrated moving average autoregressive model (ARIMA), and performs smooth differential processing and parameter estimation on the initial travel sequence data corresponding to each segment to obtain predicted travel sequence data corresponding to each segment, so as to realize the travel track-based prediction of the initial travel sequence data corresponding to each segment.
The server combines the initial trip sequence data corresponding to each parcel with the predicted trip sequence data corresponding to each parcel to obtain target trip sequence data corresponding to each parcel; and according to preset statistical indexes, counting the target trip sequence data corresponding to each block to obtain trip statistical data corresponding to each block, namely the trip data of the target block, wherein the statistical indexes comprise the occurrence times, residence time, occurrence frequency and the like corresponding to a historical time period, a current time period or a future time period respectively. Through the operation, the accuracy of the trip data of the target area is improved.
203. And calling a preset business index prediction model, and performing business index regression analysis based on a preset time period on the trip data of the target area to obtain target business index prediction data.
Specifically, the server acquires service index data to be processed, calls a preset service index prediction model, and performs multivariate linear variable operation on the trip data of the target area and the service index data to be processed for a preset time period to obtain initial service index prediction data; respectively carrying out data statistical analysis based on a preset historical time period, data extraction based on a current time period and data extraction based on a prediction time period on the initial service index prediction data to obtain historical time period service index change trend data, current time period service index data and prediction time period service index data; and determining the historical period service index change trend data, the current period service index data and the prediction period service index data as target service index prediction data.
The execution process for acquiring the service index data to be processed comprises the following steps: the method comprises the steps that a server acquires user information and acquires corresponding to-be-processed business index data based on the user information and target parcel travel data, specifically, the server acquires the user information, searches the business index data in a preset database through the user information and returns search information, if the search information is a non-empty set, the business index data in the search information is extracted, so that to-be-processed business index data is acquired, the to-be-processed business index data is the business index data of a user, if the search information is an empty set, the user information and the target parcel travel data are determined as target data, the similarity is sorted in a descending order by calculating the similarity between the to-be-analyzed data (including personal information and parcel travel data of all users) in the preset database and the target data, and the to-be-analyzed data corresponding to the first arranged similarity is obtained according to the first arranged data, and extracting corresponding to-be-processed service index data from a preset database, wherein the to-be-processed service index data is similar to the service index data of the user.
The preset business index prediction model is a model obtained by extracting a part of users with abundant business index data from a user group, grading the business index data, and then taking the part of the graded business index data as a training set to train and optimize a preset regression model based on travel record statistical data. The server takes the trip data of the target area and a preset time period as independent variables, takes the service index data to be processed as dependent variables, calls a preset service index prediction model, and carries out digital variable prediction operation on the independent variables and the dependent variables to obtain initial service index prediction data; and performing data reading and data statistical analysis on the initial service index prediction data in a preset historical time period, a current time period and a prediction time period to obtain target service index prediction data comprising historical time period service index change trend data, current time period service index data and prediction time period service index data. The data richness and the data quality of the service index prediction data are improved.
Specifically, the server performs sliding reading on the initial service index prediction data based on a preset historical time period, a current time period and a prediction time period to obtain historical window sequence data, current window sequence data and prediction time period service index data; carrying out mean value calculation or maximum value statistics on the historical window sequence data to obtain historical time period service index variation trend data; and intercepting the current window sequence data according to a preset interception interval to obtain the current time period service index data.
The method comprises the steps that a server creates a history sliding window of a preset history period, the history sliding window is a window corresponding to a preset reading period in the preset history period, initial service index prediction data are read in a sliding mode through the history sliding window to obtain history window sequence data, mean value calculation or maximum value statistics are conducted on the history window sequence data to obtain a plurality of statistical sequence data, and the statistical sequence data are determined to be service index variation trend data of the history period, for example: the preset historical time period corresponds to 2021.01.01-2021.03.31, the length of a historical sliding window corresponds to the length of one month in 2021.01.01-2021.03.31, initial service index prediction data are read in a sliding mode through the historical sliding window, obtained historical window sequence data are service index prediction data respectively corresponding to 1 month in 2021, 2 months in 2021 and 3 months in 2021, and mean value calculation or maximum value statistics are respectively carried out on the service index prediction data of 1 month in 2021, 2 months in 2021 and 3 months in 2021, so that service index change trend data in the historical time period are obtained.
And the server creates a current sliding window of the current time period and a prediction sliding window of the prediction time period, and respectively carries out sliding reading on the initial service index prediction data through the current sliding window and the prediction sliding window to obtain current window sequence data and prediction time period service index data. The preset interception interval may be an interception proportion corresponding to the service index level, for example: intercepting proportions corresponding to the service index grades are all 90%, current window sequence data are divided according to preset service index grade interval values to obtain high service index time sequence data, medium service index time sequence data and low service index time sequence data, and 90% of sequence data are extracted from the high service index time sequence data, the medium service index time sequence data and the low service index time sequence data respectively to obtain current time period service index data; the preset clipping interval may also be a preset interval corresponding to the prediction time period, for example: if the duration of the prediction period is 30 days, the preset interception interval is 27 consecutive days in the 30 days. The data richness and the data quality of the service index prediction data are improved.
204. And calling a preset dynamic business risk prediction model, and classifying target business index prediction data based on real-time risk types to obtain dynamic business risk data.
205. And acquiring user information, calling a preset static business risk prediction model, and classifying the user information based on risk types to obtain static business risk data.
The execution process of step 204-205 is similar to the execution process of step 103-104 described above, and will not be described herein again.
206. And performing service risk grade identification on the dynamic service risk data and the static service risk data to obtain target service risk data.
Specifically, the server performs two-dimensional matrix conversion and weighted summation on the dynamic business risk data and the static business risk data to obtain a risk score value; comparing and analyzing the risk score value with a preset grade threshold value to obtain a comparison and analysis result; and determining the service risk information corresponding to the preset grade threshold as target service risk data according to the comparison and analysis result.
The server calls a preset conversion function reshape, and one-dimensional arrays of the dynamic business risk data and the static business risk data are created respectively to obtain a dynamic one-dimensional array and a static two-dimensional array; respectively carrying out two-dimensional matrix conversion on the dynamic one-dimensional array and the static two-dimensional array to obtain a dynamic business risk two-dimensional matrix and a static business risk two-dimensional matrix; weighting and summing the dynamic service risk two-dimensional matrix and the static service risk two-dimensional matrix according to a preset weight proportion to obtain a risk score value, wherein the weight value of the static service risk two-dimensional matrix is larger than that of the dynamic service risk two-dimensional matrix; and judging whether the risk score value is greater than a preset grade threshold value, comparing the analysis result, if the comparison analysis result is represented by positive data, acquiring service risk information corresponding to the preset grade threshold value, determining the service risk information corresponding to the preset grade threshold value as target service risk data, and if the comparison analysis result is represented by negative data, judging the preset grade threshold value of the next grade. The efficiency and the accuracy of business risk level identification are improved.
Specifically, the server identifies the business risk level of the dynamic business risk data and the static business risk data, acquires historical business risk data corresponding to the user information after obtaining target business risk data, acquires a corresponding adjustment strategy according to the target business risk data and the historical business risk data, and executes the adjustment strategy.
The server retrieves the preset database according to the user information to obtain corresponding historical business risk data, wherein the analysis time corresponding to the historical business risk data is similar to the analysis time corresponding to the target business risk data, and the analysis time is as follows: the analysis time corresponding to the target business risk data is 2021.01.01-2021.07.31, and the analysis time corresponding to the historical business risk data is 2020.07.31-2020.12.30; judging whether the target business risk data is the same as the historical business risk data or not to obtain a result to be analyzed; if the result to be analyzed is yes, stopping execution and not processing; if not, obtaining an adjustment strategy corresponding to the result to be analyzed, and executing the adjustment strategy to obtain new target business risk data, wherein the adjustment strategy comprises at least one of an optimization strategy of a business index prediction model, a dynamic business risk prediction model and a static business risk prediction model, an adjustment scheme of an execution process of the target business risk data, and a test strategy, and the test strategy is as follows: obtaining script execution logs of data processing (such as data processing of grid map area data, user mobile position data and the like) in the execution process of the target business risk data, analyzing the script execution logs according to conditions of scripts to be tested to obtain scripts to be tested, testing and optimizing the scripts to be tested, and running the scripts subjected to testing and optimization to obtain new target business risk data. By acquiring the corresponding adjustment strategy according to the target business risk data and the historical business risk data and executing the adjustment strategy, the business prediction accuracy based on the user behavior analysis is improved.
In the embodiment of the invention, the problem of hysteresis of target business index prediction data is solved, the flexibility and the applicability of prediction of target business risk data are improved, the timeliness and the stability of prediction are further improved, the accuracy of trip data of a target district is improved, the data richness and the data quality of the business index prediction data are improved, the efficiency and the accuracy of business risk grade identification are improved, and the business risk prediction accuracy based on user behavior analysis is improved.
In the above description of the business risk analysis method in the embodiment of the present invention, referring to fig. 3, a business risk analysis device in the embodiment of the present invention is described below, and an embodiment of the business risk analysis device in the embodiment of the present invention includes:
a parcel analysis module 301, configured to obtain parcel data of the grid map and user mobile position data, and perform parcel travel data analysis on the parcel data of the grid map and the user mobile position data to obtain target parcel travel data;
the regression analysis module 302 is configured to invoke a preset business index prediction model, perform business index regression analysis based on a preset time period on the travel data of the target parcel, and obtain target business index prediction data;
the first classification module 303 is configured to invoke a preset dynamic business risk prediction model, and classify target business index prediction data based on real-time risk types to obtain dynamic business risk data;
the second classification module 304 is configured to obtain user information, call a preset static business risk prediction model, and perform risk type-based classification on the user information to obtain static business risk data;
and the identifying module 305 is configured to perform service risk level identification on the dynamic service risk data and the static service risk data to obtain target service risk data.
The functional implementation of each module in the business risk analysis device corresponds to each step in the business risk analysis method embodiment, and the functions and implementation processes are not described in detail herein.
In the embodiment of the invention, the problem of hysteresis of target business index prediction data is solved, the flexibility and the applicability of prediction of target business risk data are improved, the timeliness and the stability of prediction are further improved, the accuracy of trip data of a target district is improved, the data richness and the data quality of the business index prediction data are improved, the efficiency and the accuracy of business risk grade identification are improved, and the business risk prediction accuracy based on user behavior analysis is improved.
Referring to fig. 4, another embodiment of the business risk analysis device according to the embodiment of the present invention includes:
a parcel analysis module 301, configured to obtain parcel data of the grid map and user mobile position data, and perform parcel travel data analysis on the parcel data of the grid map and the user mobile position data to obtain target parcel travel data;
the parcel analysis module 301 specifically includes:
a clustering unit 3011, configured to obtain grid point similarity measurement of the initial grid map data and the initial grid map data, and perform parcel clustering on the initial grid map data based on the grid point similarity measurement to obtain grid map parcel data;
the analyzing and counting unit 3012 is configured to obtain user moving position data, and perform parcel analysis, parcel travel data supplement, and record counting on the grid map parcel data according to the user moving position data to obtain target parcel travel data;
the regression analysis module 302 is configured to invoke a preset business index prediction model, perform business index regression analysis based on a preset time period on the travel data of the target parcel, and obtain target business index prediction data;
the first classification module 303 is configured to invoke a preset dynamic business risk prediction model, and classify target business index prediction data based on real-time risk types to obtain dynamic business risk data;
the second classification module 304 is configured to obtain user information, call a preset static business risk prediction model, and perform risk type-based classification on the user information to obtain static business risk data;
and the identifying module 305 is configured to perform service risk level identification on the dynamic service risk data and the static service risk data to obtain target service risk data.
Optionally, the analysis statistics unit 3012 may be further specifically configured to:
acquiring user moving position data, and performing fragment track sequence feature extraction based on the user moving position data on the grid map fragment data to obtain initial travel sequence data corresponding to each fragment;
predicting initial trip sequence data corresponding to each parcel based on a trip track to obtain predicted trip sequence data corresponding to each parcel;
merging the initial trip sequence data corresponding to each parcel with the predicted trip sequence data corresponding to each parcel to obtain target trip sequence data corresponding to each parcel;
and according to preset statistical indexes, counting the target trip sequence data corresponding to each block to obtain the target block trip data.
Optionally, the regression analysis module 302 includes:
the prediction unit 3021 is configured to obtain service index data to be processed, call a preset service index prediction model, and perform multivariate linear variable operation on the trip data of the target area and the service index data to be processed for a preset time period to obtain initial service index prediction data;
a time period analysis unit 3022, configured to perform data statistical analysis based on a preset historical time period, data extraction based on a current time period, and data extraction based on a predicted time period on the initial service index prediction data, respectively, to obtain historical time period service index change trend data, current time period service index data, and predicted time period service index data;
a determining unit 3023, configured to determine, as target service index prediction data, service index change trend data in a historical period, service index data in a current period, and service index data in a prediction period.
Optionally, the period analysis unit 3022 may be further specifically configured to:
performing sliding reading on the initial service index prediction data based on a preset historical time period, a current time period and a prediction time period to obtain historical window sequence data, current window sequence data and prediction time period service index data;
carrying out mean value calculation or maximum value statistics on the historical window sequence data to obtain historical time period service index variation trend data;
and intercepting the current window sequence data according to a preset interception interval to obtain the current time period service index data.
Optionally, the identification module 305 may be further specifically configured to:
performing two-dimensional matrix conversion and weighted summation on the dynamic business risk data and the static business risk data to obtain a risk score value;
comparing and analyzing the risk score value with a preset grade threshold value to obtain a comparison and analysis result;
and determining the service risk information corresponding to the preset grade threshold as target service risk data according to the comparison and analysis result.
Optionally, the business risk analysis device further includes:
and the policy executing module 306 is configured to acquire historical business risk data corresponding to the user information, acquire a corresponding adjustment policy according to the target business risk data and the historical business risk data, and execute the adjustment policy.
The functional implementation of each module and each unit in the business risk analysis device corresponds to each step in the business risk analysis method embodiment, and the functions and implementation processes are not described in detail herein.
In the embodiment of the invention, the problem of hysteresis of target business index prediction data is solved, the flexibility and the applicability of prediction of target business risk data are improved, the timeliness and the stability of prediction are further improved, the accuracy of trip data of a target district is improved, the data richness and the data quality of the business index prediction data are improved, the efficiency and the accuracy of business risk grade identification are improved, and the business risk prediction accuracy based on user behavior analysis is improved.
Fig. 3 and fig. 4 describe the business risk analysis device in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the business risk analysis device in the embodiment of the present invention is described in detail from the perspective of hardware processing.
Fig. 5 is a schematic structural diagram of a business risk analysis device according to an embodiment of the present invention, where the business risk analysis device 500 may generate relatively large differences due to different configurations or performances, and may include one or more processors (CPUs) 510 (e.g., one or more processors) and a memory 520, and one or more storage media 530 (e.g., one or more mass storage devices) storing applications 533 or data 532. Memory 520 and storage media 530 may be, among other things, transient or persistent storage. The program stored in the storage medium 530 may include one or more modules (not shown), each of which may include a series of instructions operating on the business risk analysis device 500. Still further, processor 510 may be configured to communicate with storage medium 530 to execute a series of instruction operations in storage medium 530 on business risk analysis device 500.
Business risk analysis device 500 may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input-output interfaces 560, and/or one or more operating systems 531, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, and the like. Those skilled in the art will appreciate that the business risk analysis device configuration shown in FIG. 5 does not constitute a limitation of business risk analysis devices, and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.
The present application further provides a business risk analysis device, including: a memory having instructions stored therein and at least one processor, the memory and the at least one processor interconnected by a line; the at least one processor invokes the instructions in the memory to cause the business risk analysis device to perform the steps in the business risk analysis method described above. The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, and which may also be a volatile computer-readable storage medium, having stored therein instructions, which, when run on a computer, cause the computer to perform the steps of the business risk analysis method.
Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A business risk analysis method is characterized by comprising the following steps:
acquiring grid map zone data and user mobile position data, and performing zone trip data analysis on the grid map zone data and the user mobile position data to obtain target zone trip data;
calling a preset business index prediction model, and performing business index regression analysis based on a preset time period on the trip data of the target area to obtain target business index prediction data;
calling a preset dynamic business risk prediction model, and classifying the target business index prediction data based on real-time risk types to obtain dynamic business risk data;
acquiring user information, calling a preset static business risk prediction model, and classifying the user information based on risk types to obtain static business risk data;
and performing service risk grade identification on the dynamic service risk data and the static service risk data to obtain target service risk data.
2. The business risk analysis method according to claim 1, wherein the obtaining grid map parcel data and user mobile position data, and carrying out parcel travel data analysis on the grid map parcel data and the user mobile position data to obtain target parcel travel data comprises:
acquiring initial gridding map data and grid point similarity measurement of the initial gridding map data, and carrying out fragment clustering on the initial gridding map data based on the grid point similarity measurement to obtain grid map fragment data;
and acquiring user moving position data, and performing area analysis, area travel data supplement and record statistics on the grid map area data through the user moving position data to obtain target area travel data.
3. The business risk analysis method according to claim 2, wherein the obtaining of the user mobile position data, and performing parcel analysis, parcel travel data supplement, and record statistics on the grid map parcel data through the user mobile position data to obtain target parcel travel data comprises:
acquiring user moving position data, and extracting the block track sequence characteristics of the block data of the grid map based on the user moving position data to obtain initial travel sequence data corresponding to each block;
predicting the initial trip sequence data corresponding to each parcel based on a trip track to obtain predicted trip sequence data corresponding to each parcel;
merging the initial trip sequence data corresponding to each parcel with the predicted trip sequence data corresponding to each parcel to obtain target trip sequence data corresponding to each parcel;
and according to preset statistical indexes, counting the target trip sequence data corresponding to each block to obtain the target block trip data.
4. The business risk analysis method according to claim 1, wherein the calling a preset business index prediction model to perform business index regression analysis based on a preset time period on the target parcel travel data to obtain target business index prediction data comprises:
acquiring service index data to be processed, calling a preset service index prediction model, and performing multi-linear variable operation on the trip data of the target area and the service index data to be processed for a preset time period to obtain initial service index prediction data;
respectively carrying out data statistical analysis based on a preset historical time period, data extraction based on a current time period and data extraction based on a prediction time period on the initial service index prediction data to obtain historical time period service index change trend data, current time period service index data and prediction time period service index data;
and determining the historical period service index change trend data, the current period service index data and the forecast period service index data as target service index forecast data.
5. The business risk analysis method according to claim 4, wherein the performing data statistics analysis based on a preset historical period, data extraction based on a current period, and data extraction based on a predicted period on the initial business index prediction data to obtain historical period business index change trend data, current period business index data, and predicted period business index data respectively comprises:
performing sliding reading on the initial service index prediction data based on a preset historical time period, a current time period and a prediction time period to obtain historical window sequence data, current window sequence data and prediction time period service index data;
carrying out mean value calculation or maximum value statistics on the historical window sequence data to obtain historical time period service index variation trend data;
and intercepting the current window sequence data according to a preset intercepting interval to obtain the current time interval service index data.
6. The business risk analysis method according to claim 1, wherein the performing business risk level identification on the dynamic business risk data and the static business risk data to obtain target business risk data comprises:
performing two-dimensional matrix conversion and weighted summation on the dynamic business risk data and the static business risk data to obtain a risk score value;
comparing and analyzing the risk score value with a preset grade threshold value to obtain a comparison and analysis result;
and determining the service risk information corresponding to the preset grade threshold value as target service risk data according to the comparison and analysis result.
7. The business risk analysis method according to any one of claims 1 to 6, wherein the performing business risk level identification on the dynamic business risk data and the static business risk data to obtain target business risk data further comprises:
and acquiring historical service risk data corresponding to the user information, acquiring a corresponding adjustment strategy according to the target service risk data and the historical service risk data, and executing the adjustment strategy.
8. A business risk analysis device, comprising:
the system comprises a parcel analysis module, a target parcel travel module and a storage module, wherein the parcel analysis module is used for acquiring parcel data of a grid map and user mobile position data, and carrying out parcel travel data analysis on the parcel data of the grid map and the user mobile position data to obtain target parcel travel data;
the regression analysis module is used for calling a preset business index prediction model and carrying out business index regression analysis based on a preset time period on the trip data of the target area to obtain target business index prediction data;
the first classification module is used for calling a preset dynamic business risk prediction model and classifying the target business index prediction data based on real-time risk types to obtain dynamic business risk data;
the second classification module is used for acquiring user information, calling a preset static business risk prediction model, and classifying the user information based on risk types to obtain static business risk data;
and the identification module is used for carrying out service risk grade identification on the dynamic service risk data and the static service risk data to obtain target service risk data.
9. A business risk analysis device, characterized by comprising: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invokes the instructions in the memory to cause the business risk analysis device to perform the business risk analysis method of any one of claims 1-7.
10. A computer-readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, implement the business risk analysis method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110696697.0A CN113516302B (en) | 2021-06-23 | 2021-06-23 | Business risk analysis method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110696697.0A CN113516302B (en) | 2021-06-23 | 2021-06-23 | Business risk analysis method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113516302A true CN113516302A (en) | 2021-10-19 |
| CN113516302B CN113516302B (en) | 2022-01-04 |
Family
ID=78066004
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110696697.0A Active CN113516302B (en) | 2021-06-23 | 2021-06-23 | Business risk analysis method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113516302B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116227961A (en) * | 2022-12-05 | 2023-06-06 | 贝壳找房(北京)科技有限公司 | Resource allocation method, device, equipment and computer readable storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110153368A1 (en) * | 2009-12-17 | 2011-06-23 | XtremeGIS, Inc. | User Interactive Reinsurance Risk Analysis Application |
| CN106651603A (en) * | 2016-12-29 | 2017-05-10 | 平安科技（深圳）有限公司 | Risk evaluation method and apparatus based on position service |
| US20170140312A1 (en) * | 2015-10-23 | 2017-05-18 | Kpmg Llp | System and method for performing signal processing and dynamic analysis and forecasting of risk of third parties |
| CN107633680A (en) * | 2016-07-12 | 2018-01-26 | 阿里巴巴集团控股有限公司 | Acquisition methods, device, equipment and the system of trip data |
| CN110490608A (en) * | 2019-07-12 | 2019-11-22 | 招联消费金融有限公司 | Methods of risk assessment, device, computer equipment and storage medium |
| CN111127062A (en) * | 2018-11-01 | 2020-05-08 | 中国移动通信集团广东有限公司 | Group fraud identification method and device based on space search algorithm |
| CN111950937A (en) * | 2020-09-01 | 2020-11-17 | 上海海事大学 | Key personnel risk assessment method based on fusion space-time trajectory |
-
2021
- 2021-06-23 CN CN202110696697.0A patent/CN113516302B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110153368A1 (en) * | 2009-12-17 | 2011-06-23 | XtremeGIS, Inc. | User Interactive Reinsurance Risk Analysis Application |
| US20170140312A1 (en) * | 2015-10-23 | 2017-05-18 | Kpmg Llp | System and method for performing signal processing and dynamic analysis and forecasting of risk of third parties |
| CN107633680A (en) * | 2016-07-12 | 2018-01-26 | 阿里巴巴集团控股有限公司 | Acquisition methods, device, equipment and the system of trip data |
| CN106651603A (en) * | 2016-12-29 | 2017-05-10 | 平安科技（深圳）有限公司 | Risk evaluation method and apparatus based on position service |
| CN111127062A (en) * | 2018-11-01 | 2020-05-08 | 中国移动通信集团广东有限公司 | Group fraud identification method and device based on space search algorithm |
| CN110490608A (en) * | 2019-07-12 | 2019-11-22 | 招联消费金融有限公司 | Methods of risk assessment, device, computer equipment and storage medium |
| CN111950937A (en) * | 2020-09-01 | 2020-11-17 | 上海海事大学 | Key personnel risk assessment method based on fusion space-time trajectory |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116227961A (en) * | 2022-12-05 | 2023-06-06 | 贝壳找房(北京)科技有限公司 | Resource allocation method, device, equipment and computer readable storage medium |
| CN116227961B (en) * | 2022-12-05 | 2024-04-09 | 贝壳找房(北京)科技有限公司 | Resource allocation method, device, equipment and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113516302B (en) | 2022-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110245981B (en) | Crowd type identification method based on mobile phone signaling data | |
| CN111614690B (en) | Abnormal behavior detection method and device | |
| Jahani et al. | Improving official statistics in emerging markets using machine learning and mobile phone data | |
| CN110674636B (en) | Power consumption behavior analysis method | |
| US20210073669A1 (en) | Generating training data for machine-learning models | |
| CN113190599B (en) | Processing method, device and equipment for application user behavior data and storage medium | |
| CN110399268A (en) | A kind of method, device and equipment of anomaly data detection | |
| CN111510368A (en) | Family group identification method, device, equipment and computer readable storage medium | |
| CN107274066B (en) | LRFMD model-based shared traffic customer value analysis method | |
| CN113516302B (en) | Business risk analysis method, device, equipment and storage medium | |
| CN113486983A (en) | Big data office information analysis method and system for anti-fraud processing | |
| CN106897743B (en) | Mobile attendance anti-cheating big data detection method based on Bayesian model | |
| CN113256405B (en) | Method, device, equipment and storage medium for predicting cheating user concentrated area | |
| CN113487241A (en) | Method, device, equipment and storage medium for classifying enterprise environment-friendly credit grades | |
| CN111581298B (en) | Heterogeneous data integration system and method for large data warehouse | |
| CN113051291A (en) | Work order information processing method, device, equipment and storage medium | |
| CN117291428A (en) | Enterprise management APP-based data background management system | |
| CN112232606A (en) | Service data prediction method, device, equipment and storage medium | |
| Basik et al. | Slim: Scalable linkage of mobility data | |
| CN106372213A (en) | Position analysis method | |
| CN116361974A (en) | Data source importance discriminating method based on highway service and data network | |
| CN114495137B (en) | Bill abnormity detection model generation method and bill abnormity detection method | |
| CN109902129A (en) | Insurance agent's classifying method and relevant device based on big data analysis | |
| CN115392351A (en) | Risk user identification method and device, electronic equipment and storage medium | |
| CN109919811B (en) | Insurance agent culture scheme generation method based on big data and related equipment |
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 |