CN110493190B - Data information processing method and device, computer equipment and storage medium - Google Patents
Data information processing method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110493190B CN110493190B CN201910635736.9A CN201910635736A CN110493190B CN 110493190 B CN110493190 B CN 110493190B CN 201910635736 A CN201910635736 A CN 201910635736A CN 110493190 B CN110493190 B CN 110493190B
- Authority
- CN
- China
- Prior art keywords
- service
- risk assessment
- value
- index
- key data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/0807—Network architectures or network communication protocols for network security for authentication of entities using tickets, e.g. Kerberos
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/20—Network architectures or network communication protocols for network security for managing network security; network security policies in general
Abstract
The application relates to a data information processing method, a data information processing device, computer equipment and a storage medium. The method comprises the following steps: acquiring a login request sent by a terminal, and determining a user identifier of a current login user from the login request; acquiring service source data of different services corresponding to user identifications from a plurality of service servers, and calling a service risk assessment model to perform risk assessment on the service source data of each service to obtain a service risk assessment value; when the service risk assessment value is larger than the risk threshold value, triggering an interception instruction to be sent to the service server, wherein the interception instruction is used for indicating the service server to stop service processing; and generating an early warning page according to the service risk assessment value and the service source data, and sending the early warning page to the terminal. By adopting the method, users do not need to log in different service systems to carry out service risk inquiry one by one, and only relevant information of risk service is returned to the users, thereby reducing occupation of service server resources and communication transmission resources.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a method and an apparatus for processing data information, a computer device, and a storage medium.
Background
With the continuous development of internet technology, more and more business transactions provide online transactions of businesses, and meanwhile, online business query, business operation processing and the like are improved, such as business operations of purchasing financial sample business and performing project investment and the like; however, when a user wants to query information related to different services handled by the user, the user often needs to log in different service systems to query one by one, and the service systems often return all the information related to the services to the user, thereby occupying a large amount of service server resources and communication transmission resources.
Disclosure of Invention
In view of the foregoing, it is necessary to provide a method and an apparatus for processing data information, a computer device, and a storage medium.
A method of processing data information, the method comprising:
acquiring a login request sent by a terminal, and determining a user identifier of a current login user from the login request;
acquiring service source data of different services corresponding to the user identification from a plurality of service servers, and calling a service risk assessment model to perform risk assessment on the service source data of each service to obtain a service risk assessment value;
when the service risk assessment value is larger than a risk threshold value, triggering an interception instruction to be sent to the service server, wherein the interception instruction is used for indicating the service server to stop service processing;
and generating an early warning page according to the service risk assessment value and the service source data, and sending the early warning page to the terminal.
In one embodiment, the step of invoking a business risk assessment model to perform risk assessment on the business source data of each business includes:
determining local time, and determining a target time period according to the local time and a preset reference window length;
extracting key data of the service source data, and extracting index key data and service index values corresponding to different service indexes in a target time period from the service source data;
inputting index key data and service index values corresponding to different service indexes in a target time period into a service risk assessment model, and training the service risk assessment model;
and inputting index key data corresponding to different service indexes corresponding to the local time into the trained service risk assessment model to obtain a service risk assessment value.
In one embodiment, the step of extracting, from the service source data, index key data and service index values corresponding to different service indexes in a target time period includes:
analyzing the index key data under the same service index in the target time period, and determining the index key data of which the difference value with the index key data of the adjacent date is larger than a preset threshold value as an abnormal value;
and clearing abnormal values in the index key data.
In one embodiment, before the step of determining the target time period according to the local time and the preset reference window length, the method further includes:
acquiring sample service index values of sample services in a first time period and sample index key data under each service index;
acquiring a plurality of different pre-selection window lengths, determining historical time periods according to the first time period and each pre-selection window length, and acquiring historical service index values of the sample service every day in each historical time period and historical index key data corresponding to different service indexes;
respectively constructing a preselected linear regression model corresponding to each preselected window length according to historical index key data and historical service index values in each historical time period;
respectively inputting the sample index key data into preselected linear regression models corresponding to the preselected window lengths, and estimating a net value estimated value of the sample service in a first time period by using the preselected linear regression models;
and respectively calculating the error value between the net value estimated value of the preselected linear regression model corresponding to each preselected window length and the sample service index value, and taking the preselected window length corresponding to the net value estimated value with the minimum error of the sample service index value as the reference window length.
In one embodiment, the step of determining the user identifier of the current login user from the login request includes:
calling a camera device to acquire face image data according to the login request;
and acquiring image characteristic data from the face image data, and determining the user identification of the current login user according to the image characteristic data.
An apparatus for processing data information, the apparatus comprising:
the user identification acquisition module is used for acquiring a login request sent by a terminal and determining the user identification of the current login user from the login request;
a risk assessment value acquisition module, configured to acquire service source data of different services corresponding to the user identifier from multiple service servers, and call a service risk assessment model to perform risk assessment on the service source data of each service, to obtain a service risk assessment value;
the interception instruction acquisition module is used for triggering an interception instruction to be sent to the service server when the service risk assessment value is larger than a risk threshold value, and the interception instruction is used for indicating the service server to stop service processing;
and the early warning information sending module is used for generating an early warning page according to the service risk assessment value and the service source data and sending the early warning page to the terminal.
In one embodiment, the risk assessment value obtaining module is further configured to determine a local time, and determine a target time period according to the local time and a preset reference window length; extracting key data of the service source data, and extracting index key data and service index values corresponding to different service indexes in a target time period from the service source data; inputting index key data and service index values corresponding to different service indexes in a target time period into a service risk assessment model, and training the service risk assessment model; and inputting the index key data corresponding to different service indexes corresponding to the local time into the trained service risk assessment model to obtain a service risk assessment value.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring a login request sent by a terminal, and determining a user identifier of a current login user from the login request;
acquiring service source data of different services corresponding to the user identification from a plurality of service servers, and calling a service risk assessment model to perform risk assessment on the service source data of each service to obtain a service risk assessment value;
when the service risk assessment value is larger than a risk threshold value, triggering an interception instruction to be sent to the service server, wherein the interception instruction is used for indicating the service server to stop service processing;
and generating an early warning page according to the service risk assessment value and the service source data, and sending the early warning page to the terminal.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring a login request sent by a terminal, and determining a user identifier of a current login user from the login request;
acquiring service source data of different services corresponding to the user identification from a plurality of service servers, and calling a service risk assessment model to perform risk assessment on the service source data of each service to obtain a service risk assessment value;
when the service risk assessment value is larger than a risk threshold value, triggering an interception instruction to be sent to the service server, wherein the interception instruction is used for indicating the service server to stop service processing;
and generating an early warning page according to the service risk assessment value and the service source data, and sending the early warning page to the terminal.
The processing method, the device, the computer equipment and the storage medium of the data information acquire a login request sent by a terminal, determine a user identifier of a current login user from the login request, thereby acquiring service source data of different services corresponding to the user identifiers from a plurality of service servers, calling a service risk assessment model to carry out risk assessment on the service source data of each service to obtain a service risk assessment value, realizing the service risk assessment on the service of the current login user, triggering an interception instruction to send to the service server when the service risk assessment value is greater than a risk threshold value, wherein the interception instruction is used for instructing the service server to stop service processing, generating an early warning page according to the service risk assessment value and the service source data to send to the terminal, intercepting the service processing with risk in time, and sending related information of the risk service to the terminal, the user does not need to log in different service systems to carry out service risk inquiry one by one, and only relevant information of the risk service is returned to the user, so that occupation of service server resources and communication transmission resources is reduced
Drawings
FIG. 1 is a diagram illustrating an exemplary implementation of a method for processing data information;
FIG. 2 is a flow diagram illustrating a method for processing data information according to one embodiment;
FIG. 3 is a schematic flow chart illustrating a process of invoking a business risk assessment model to perform risk assessment on business source data of each business in one embodiment;
FIG. 4 is a block diagram of an apparatus for processing data information according to an embodiment;
FIG. 5 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further 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 present application and are not intended to limit the present application.
The data information processing method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the service query application server 104 via a network. A user logs in through the terminal 102, after the terminal 102 detects the login operation of the user, a login request is generated and sent to the business query application server 104, the business query application server 104 determines a user identifier of the current login user from the login request, so that business source data of different businesses corresponding to the user identifier are obtained from the business servers 106, a business risk assessment model is called to carry out risk assessment on the business source data of each business, a business risk assessment value is obtained, and when the business risk assessment value is larger than a risk threshold value, the business query application server 104 triggers an interception instruction to send to the business servers 106, so that the business servers 106 stop business processing; the service query application server 104 further generates an early warning page according to the service risk assessment value and the service source data, and sends the early warning page to the terminal 102, so that the user can obtain the relevant information of the risk service. By adopting the method, users do not need to log in different service systems to carry out service risk inquiry one by one, and only relevant information of risk service is returned to the users, thereby reducing occupation of service server resources and communication transmission resources. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the service query application server 104 and the service server 106 may be implemented by independent servers or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, a data information processing method is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
step S210: and acquiring a login request sent by the terminal, and determining the user identification of the current login user from the login request.
In this step, the user identifier refers to a character string for uniquely identifying the current login user, and may be identity information of the login user, such as a resident identification card.
Specifically, the terminal is provided with a service query application, a user can log in the application through an account password, the terminal detects the login operation of the user, generates a login request and sends the login request to a server corresponding to the service query application, and the server obtains a user identifier corresponding to the user account from the login request.
Step S220: and acquiring service source data of different services corresponding to the user identification from the plurality of service servers, and calling a service risk assessment model to perform risk assessment on the service source data of each service to obtain a service risk assessment value.
The service inquiry application server is in butt joint with a plurality of service servers to realize data transmission with a plurality of license source servers; the service server comprises servers corresponding to various different types of services, such as fund service, stock service, project investment service and the like; the service source data includes data for assessing the risk of the service, for example, the service source data of the fund service includes data of different indexes of each day of the fund sample service, such as mecury duration of market index, numerical gain rate of the current day, net value of fund unit, and the like.
Specifically, the server obtains service source data corresponding to the user identifier from a plurality of service servers according to the user identifier, for example, search fund sample service data purchased by the user from a fund purchasing service server, search project information invested by the user from a project investment service server, and the like.
After the server obtains the service source data, a service risk assessment model corresponding to the service type is called, and risk assessment is carried out on each service source data. The server can pre-configure index key data of the business indexes influencing the risk assessment and generate processing rules of the index key data, after the business source data are obtained, the index key data corresponding to the business indexes can be generated by utilizing the business source data according to the processing rules, and then the business risk assessment value is calculated according to the index key data through the enterprise risk assessment model.
Step S230: and when the service risk assessment value is larger than the risk threshold value, triggering an interception instruction to be sent to the service server, wherein the interception instruction is used for indicating the service server to stop service processing.
In the step, after acquiring a service risk assessment value corresponding to each service, a server judges whether the service has a risk according to the service risk assessment value; when the service risk assessment value reaches a risk threshold value, determining that the service reaching the risk threshold value has risk, and sending an interception instruction to a service server corresponding to the service by the server, so that the corresponding service server responds to the interception instruction, and timely and effectively intercepts the service processing with risk.
Step S240: and generating an early warning page according to the service risk assessment value and the service source data, and sending the early warning page to the terminal.
After the server intercepts the service processing of the service with risk, an early warning page is generated according to the service risk assessment value and the service source data, and the early warning page is sent to the terminal to be displayed, so that a user can know the service with risk and the service source data related to the service through the terminal, and a corresponding risk management and control strategy is analyzed in a targeted manner. By evaluating the user risks and the enterprise risks corresponding to the service requests, the risk loopholes can be effectively found, the service requests with risks can be intercepted in time, and the service requests can be effectively monitored so as to improve the safety of the service requests.
The data information processing method comprises the steps of obtaining a login request sent by a terminal, determining a user identifier of a current login user from the login request, obtaining service source data of different services corresponding to the user identifier from a plurality of service servers, calling a service risk assessment model to carry out risk assessment on the service source data of each service to obtain a service risk assessment value, realizing service risk assessment on the service of the current login user, triggering an interception instruction to send to the service servers when the service risk assessment value is larger than a risk threshold value, wherein the interception instruction is used for indicating the service servers to stop service processing, generating an early warning page according to the service risk assessment value and the service source data to send to the terminal, intercepting the service processing with risks in time, sending related information of the risk service to the terminal, and inquiring the user does not need to log in different service systems one by one, and only the relevant information of the risk service is completely returned to the user, so that the occupation of the service server resource and the communication transmission resource is reduced, and the service can be effectively monitored so as to improve the safety of service processing.
In one embodiment, the step of determining the user identification of the current login user from the login request comprises: calling a camera device to acquire face image data according to the login request; and acquiring image characteristic data from the face image data, and determining the user identification of the current login user according to the image characteristic data.
In the embodiment, a user can log in service query application through a face; the method comprises the steps that after a terminal receives login operation of a user test, a camera device is called to obtain face image data of the user, the face image data of the user are sent to a server, the face image data of the user are analyzed by the server to obtain image feature data of the face image data, the server compares the image feature data with image feature data stored in a database, and if the comparison similarity rate is larger than a preset threshold value, a user identification corresponding to the image feature data in the database is determined to be the user identification of the current login user.
Referring to fig. 3, fig. 3 is a schematic flowchart illustrating a process of invoking a business risk assessment model to perform risk assessment on business source data of each business in an embodiment, where in this embodiment, invoking the business risk assessment model to perform risk assessment on the business source data of each business includes:
step S310: determining local time, and determining a target time period according to the local time and a preset reference window length;
step S320: extracting key data from the business source data, and extracting index key data and business index values corresponding to different business indexes in a target time period from the business source data;
step S330: inputting index key data and service index values corresponding to different service indexes in a target time period into a service risk assessment model, and training the service risk assessment model;
step S340: and inputting index key data corresponding to different service indexes corresponding to the local time into the trained service risk assessment model to obtain a service risk assessment value.
In this embodiment, the business risk assessment model may be a linear regression model
Wherein y is a service risk assessment value, x is index key data of each service index, and theta is a corresponding coefficient of the index key data of each service index; the local time refers to the time when the user initiates a login request; base ofThe quasi-regression window length refers to the value length of index key data of a linear regression model, and the target time period is a historical time period which is pushed forward by taking the receiving time as the starting time and takes the duration as the length of a standard window; specifically, after acquiring index key data and a service index value corresponding to a service index in a target time period, the server trains coefficients of a linear regression model by using the index key data and the service index value corresponding to the service index in the target time period, and after the training is completed, the server inputs the index key data of each service index at a time corresponding to local time into the linear regression model, and acquires a value output by the linear regression model as a service risk assessment value.
Still taking the bond unit net value of the service as the bond service and the service risk assessment value as the bond sample service as an example, the server determines the historical time period with the duration as the reference regression window length as the target time period according to the local time and the reference regression window length, wherein the local time is taken as the starting time, for example, the reference regression window length can be set to 35 days, when the numerical attribute of a certain bond in 9-29 months needs to be estimated, the target time period is determined to be thirty-five transaction days from 8-25-9-28 days, and when the numerical attribute of the bond in 9-28 months needs to be estimated, the target time period is determined to be thirty-five transaction days from 8-24-9-27 days. The method comprises the steps that a server obtains index key data corresponding to each business index in business source data and historical unit net values corresponding to bond net values, the index key data corresponding to each business index on each day in a target time period and the historical unit net values serve as training data and are substituted into a linear regression model one by one, the mean square error in the target time period is minimized to serve as an optimization target, the weight coefficient of each index key data is calculated to obtain the trained linear regression model, the index key data corresponding to each business index of bond sample business at local time are obtained, and the predicted value of the bond unit net values of the bond sample business at local time is calculated to serve as a business risk assessment value.
In one embodiment, the step of extracting index key data and service index values corresponding to different service indexes in a target time period from service source data includes: analyzing index key data under the same service index in a target time period, and determining the index key data of which the difference value with the index key data of adjacent dates is greater than a preset threshold value as an abnormal value; and clearing abnormal values in the index key data.
Specifically, the server analyzes the index key data under the service index A, when the difference value between the index key data of the service index A on a certain day and the index key data of the two days before and after the certain day in the target time period is larger than a preset threshold value, the index key data of the service index A on the certain day is considered to be an abnormal value, the abnormal value of the service index A is set to be a zero value, the abnormal value of the service index A is eliminated, the influence of the abnormal value on the subsequent line service risk assessment is reduced, and the accuracy of the service risk assessment is improved.
The linear regression model usually predicts the business index value according to the index key data of the business index so as to determine the business risk assessment of the business, the regression window length has a great influence on the accuracy of the business risk assessment, the proper window length can obviously improve the business predicted value, namely the accuracy of the business risk assessment, and the improper window length can cause the accuracy of the business risk assessment to be greatly reduced. Therefore, in an embodiment, before the step of determining the target time period according to the local time and the preset reference window length, the method further includes: acquiring sample service index values of sample services in a first time period and sample index key data under each service index; acquiring a plurality of different preselection window lengths, determining a historical time period according to the first time period and each preselection window length, and acquiring a daily historical service index value of a sample service in each historical time period and historical index key data corresponding to different service indexes; respectively constructing a preselected linear regression model corresponding to each preselected window length according to historical index key data and historical service index values in each historical time period; respectively inputting the key data of the sample indexes into preselected linear regression models corresponding to the lengths of preselected windows, and estimating a net value estimated value of the sample service in a first time period by using the preselected linear regression models; and respectively calculating error values between the net value estimated value of the preselected linear regression model corresponding to each preselected window length and the sample service index value, and taking the preselected window length corresponding to the net value estimated value with the minimum error of the sample service index value as the reference window length.
In this embodiment, the first time period may be selected as the first 5 days of the local time, for example, the local time is 12 months and 20 days, the first time period is 12 months and 15 days to 12 months and 19 days, and the server obtains numerical resource data of the sample service every day from 12 months and 15 days to 12 months and 19 days as the sample value.
The length of the preselected window refers to the value length of index key data of the linear regression model; after obtaining a first time period and a plurality of preselected window lengths, the server obtains historical time periods with the date of the first time period as the starting time and the duration as different preselected window lengths, and obtains historical index key data and business index values of all business indexes of the sample business every day in the historical time periods.
For example, the server may set the preselected window lengths with the lengths of 10 days, 20 days, 30 days, … days and 100 days respectively by taking 10 days as a step length, after obtaining the first time period within 12 months and 15 days to 12 months and 19 days, the server determines the second time period with the time length of 10 days as 12 months and 5 days to 12 months and 14 days, and obtains the historical index key data and the business index values of different business indexes corresponding to the sample business within the second time period; similarly, the second time period with the time length of 20 days is determined to be from 11 months 25 days to 12 months 14 days, and by analogy, the server respectively acquires historical index key data and service index values of different service indexes corresponding to the sample services in the second time periods with the time lengths of other different preselected window lengths, such as 20 days and 30 days.
When the time window length is 10 days, training a linear regression model through index key data and service index values of different service indexes of the sample service in a historical time period with the time length of 10 days; when the length of the time window is 20 days, a linear regression model is trained through the service index value of the service index of the sample service in the historical time period with the time length of 20 days and key data of different historical indexes, and so on, the server obtains a preselected linear regression model corresponding to the lengths of a plurality of preselected windows.
The server respectively inputs the index key data of each day in the first time period to the pre-selection linear regression model to obtain service predicted values of different service indexes corresponding to the sample service corresponding to each day, so that the service predicted values of the sample service predicted by the pre-selection linear regression model corresponding to different pre-selection window lengths in each day can be obtained; and the server determines the length of the reference window according to the error value between the service index value of the sample service of each day in the first time period and the service predicted value of the sample service predicted by different preselected linear regression models in the same day. In this embodiment, the error of the service predicted value of a single sample service in the first time period is minimized to form an optimization target, and the initial value of the optimal regression window length is selected, so that the accuracy of the service predicted value is improved.
Further, in one embodiment, the step of using the preselected window length corresponding to the net worth estimate with the minimum error of the sample traffic indicator value as the reference window length comprises: acquiring an adjusting coefficient of the length of a reference window; adjusting the length of the reference regression window according to the adjustment coefficient to obtain the optimal regression window length; and determining the optimal regression window length as the reference window length.
When the prediction model is a linear regression model, the accuracy of the linear regression model for predicting the service risk assessment is often related to the length of a regression window; the adjustment coefficient of the length of the reference regression window can be set by a user and sent to the server through the terminal, or can be set by the server after analyzing the service source data. Specifically, after obtaining the adjustment coefficient of the reference window, the server adjusts the length of the reference regression window according to the adjustment coefficient to obtain the optimal regression window length, and then obtains the service predicted values of different service indexes by using the optimal regression window length as the regression window length, thereby further improving the accuracy of obtaining the service predicted values.
Taking the bond business as an example, when the server obtains a business risk evaluation value of the bond business, such as a prediction value of bond net value, the adjustment coefficients include a public opinion adjustment coefficient, a popularity adjustment coefficient and an economic cycle adjustment coefficient of the bond business.
For the public opinion adjustment coefficient, because the linear regression model usually predicts the business risk assessment value of bond business according to the index key data affecting the unit net value, the public opinion condition affecting the size of the business risk assessment value generally occurs suddenly and has a large influence on the business risk assessment value, when the length of the regression window is too long, the linear regression model is difficult to quickly react to the public opinion condition, and the accuracy of the net value estimation of the linear regression model is reduced. Therefore, the server can acquire the name of the enterprise to which the bond business belongs and the name of the industry to which the bond business belongs; acquiring news corpus data of the bond business in a preset time period according to the enterprise name and the industry name; extracting event keywords from the news corpus data, and matching the event keywords with event tags in a preset event tag library; and determining a public opinion adjustment coefficient according to the matching result of the event keyword and the event label.
The preset time period is a time period before the preset receiving time, and may be one month, half month, and the like. The server acquires keywords related to the bond business, crawls news corpus data related to the keywords from the internet by a web crawler technology, analyzes the news corpus data by using a TF-IDF (term frequency-inverse document frequency) algorithm, extracts event keywords capable of summarizing the news corpus data from each piece of news corpus data, matches the event keywords with a preset event label library, determines that major public opinion accidents occur in enterprises or industries related to the bond business to be shared when matching results of the event keywords and the event labels are successful, can set public opinion adjustment coefficients to be less than 1 at the moment, achieves reduction of the length of a reference regression window, and reduces influence of index key data of historical unit net values of a target time period and different business indexes affecting the unit net values on predicted values of the bond net values, namely business risk assessment values, the accuracy of business risk assessment is improved; when the matching result of the event keyword and the event label fails to be matched, determining that no major public opinion accident occurs in the enterprises or industries related to the bond service to be shared, and at the moment, the server does not set the public opinion adjustment coefficient or sets the public opinion adjustment coefficient to 1. By acquiring news corpus data related to bond services, setting a public opinion adjustment coefficient when a matching result of an event keyword of the news corpus data and an event label in a preset event label library, subsequently adjusting the length of a regression window through the adjustment coefficient, and adjusting the length of the regression window of a linear regression model according to the public opinion condition of a sample service, the accuracy of the model on the service risk assessment value of a single bond service is improved.
For the popularity adjustment coefficient, the server can acquire the historical financial index of the bond service to be shared from the object source data and acquire the tripartite number of the historical financial index; acquiring financial indexes of the bond business to be shared at the receiving time; comparing the financial index with the tertile number to determine the industry scene degree type; and determining a scene type adjustment coefficient according to the industry scene degree type. Specifically, the server obtains historical financial indexes of bond businesses to be shared, and obtains a first quantile Q1 and a second quantile Q2 of the historical financial indexes, wherein the first quantile Q1 and the second quantile Q2 divide all the historical financial indexes into three equal parts which are respectively a high value, a medium value and a low value. The server compares the financial index of the receiving time with the three-quantile after obtaining the financial index of the receiving time, when the financial index of the receiving time is larger than a first three-quantile Q1 and smaller than a second three-quantile Q2, the business scene degree type of the receiving time is considered to be a stable type, when the financial index of the receiving time is smaller than a first three-quantile Q1, the current business scene degree type is considered to be a declining type, and when the financial index of the receiving time is larger than a second three-quantile Q2, the current business scene degree type is considered to be a scene type. The financial index can be selected as the rolling market profit rate of the bond business, and the current constant business scene degree type can be accurately estimated by utilizing the rolling market profit rate of the bond business.
When the current industry popularity type is the popularity type or the decline type, the server can set the popularity type adjustment coefficient to a value smaller than 1, so as to reduce the length of the reference regression window, reduce the influence of historical unit net value of a target time period and historical index key data of different business indexes influencing the unit net value on a predicted value of the bond net value, namely a business risk assessment value, and improve the accuracy of business risk assessment; when the current industry popularity type is a stable type, the server does not set the popularity type adjustment coefficient or set the popularity type adjustment coefficient to 1, and does not adjust the length of the reference regression window. The method comprises the steps of determining the current industry popularity by obtaining financial indexes of receiving time, shortening the length of a reference regression window when the industry popularity is in the popularity or is declined so as to reduce the influence of historical unit net value of a target time period and historical index key data of different business indexes influencing the unit net value on the predicted value of the bond net value, improve the accuracy of business risk assessment, adjust the length of the regression window of a linear regression model according to the market environment corresponding to the bond business and improve the accuracy of the business risk assessment value of the bond business.
For the economic cycle adjustment coefficient, the server acquires a stock market index in a preset time period and generates an index curve according to the stock market index; the exponential curve is put into a pre-trained neural network model, and the economic cycle type is obtained through the neural network model; and determining an economic cycle adjusting coefficient according to the economic cycle type.
The economic cycle types can include mild rising, mild falling, sudden rising, sudden falling and the like; the server establishes a neural network model in advance, and the neural network model can be trained through a plurality of exponential curves with economic cycle type labels in advance. The server obtains a stock market index, such as a Lu-Shen-300 index, in a preset time period, generates an index curve according to the stock market index, and obtains the economic cycle type by using the neural network model by inputting the index curve into the neural network model. When the current economic cycle adjustment coefficient is of a swell or a fall type, the server can set the economic cycle adjustment coefficient to be a value smaller than 1, so that the length of a reference regression window is reduced, the influence of historical unit net worth of a target time period and historical index key data of different business indexes influencing the unit net worth on a predicted value of bond net worth, namely a business risk assessment value is reduced, and the accuracy of business risk assessment is improved; when the current economic period is of a mild rising or mild falling type, the server does not set an economic period adjustment coefficient or sets the economic period adjustment coefficient to 1, and does not adjust the length of the reference regression window. By obtaining the type of the economic cycle in which the receiving time is located, when the economic cycle is in a relatively fluctuating cycle, the length of the reference regression window is shortened, the length of the regression window of the linear regression model is adjusted according to the current macroscopic economic environment, and the accuracy of the model in service risk assessment of a single bond sample service is improved.
It should be understood that although the steps in the flowcharts of fig. 2 or 3 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 2 or 3 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 4, there is provided a data information processing apparatus including: a user identifier obtaining module 410, a risk assessment value obtaining module 420, an interception instruction obtaining module 430, and an early warning information sending module 440, wherein:
a user identifier obtaining module 410, configured to obtain a login request sent by a terminal, and determine a user identifier of a current login user from the login request;
a risk assessment value obtaining module 420, configured to obtain service source data of different services corresponding to the user identifier from the multiple service servers, and invoke a service risk assessment model to perform risk assessment on the service source data of each service, so as to obtain a service risk assessment value;
an interception instruction obtaining module 430, configured to trigger an interception instruction to be sent to the service server when the service risk assessment value is greater than the risk threshold, where the interception instruction is used to instruct the service server to stop service processing;
and the early warning information sending module 440 is configured to generate an early warning page according to the service risk assessment value and the service source data, and send the early warning page to the terminal.
In one embodiment, the risk assessment value acquisition module is specifically configured to determine local time, and determine a target time period according to the local time and a preset reference window length; extracting key data from the service source data, and extracting index key data and service index values corresponding to different service indexes in a target time period from the service source data; inputting index key data and service index values corresponding to different service indexes in a target time period into a service risk assessment model, and training the service risk assessment model; and inputting index key data corresponding to different service indexes corresponding to the local time into the trained service risk assessment model to obtain a service risk assessment value.
In one embodiment, the risk assessment value acquisition module is specifically configured to analyze index key data of the same service index in a target time period, and determine, as an abnormal value, index key data whose difference from index key data of adjacent dates is greater than a preset threshold; and clearing abnormal values in the index key data.
In one embodiment, the risk assessment value acquisition module is configured to acquire a sample service index value of a sample service in a first time period and sample index key data under each service index; acquiring a plurality of different preselection window lengths, determining historical time periods according to the first time period and each preselection window length, and acquiring historical service index values of sample services in each historical time period every day and historical index key data corresponding to different service indexes; respectively constructing a preselected linear regression model corresponding to each preselected window length according to historical index key data and historical service index values in each historical time period; respectively inputting the key data of the sample indexes into preselected linear regression models corresponding to the lengths of preselected windows, and estimating a net value estimated value of the sample service in a first time period by using the preselected linear regression models; and respectively calculating error values between the net value estimated value of the preselected linear regression model corresponding to each preselected window length and the sample service index value, and taking the preselected window length corresponding to the net value estimated value with the minimum error of the sample service index value as the reference window length.
In one embodiment, the user identification obtaining module is used for calling a camera device to obtain face image data according to a login request; and acquiring image characteristic data from the face image data, and determining the user identification of the current login user according to the image characteristic data.
For specific limitations of the data information processing apparatus, reference may be made to the above limitations of the data information processing method, which are not described herein again. The respective modules in the data information processing apparatus described above may be implemented in whole or in part by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer equipment is used for storing data such as net business values, index key data of business indexes and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a data information processing method.
Those skilled in the art will appreciate that the architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, there is provided a computer device comprising a memory storing a computer program and a processor implementing the following steps when the processor executes the computer program:
acquiring a login request sent by a terminal, and determining a user identifier of a current login user from the login request;
acquiring service source data of different services corresponding to user identifications from a plurality of service servers, and calling a service risk assessment model to perform risk assessment on the service source data of each service to obtain a service risk assessment value;
when the service risk assessment value is larger than the risk threshold value, triggering an interception instruction to be sent to the service server, wherein the interception instruction is used for indicating the service server to stop service processing;
and generating an early warning page according to the service risk assessment value and the service source data, and sending the early warning page to the terminal.
In one embodiment, when the processor executes the computer program to implement the step of calling the service risk assessment model to perform risk assessment on the service source data of each service, the following steps are specifically implemented: determining local time, and determining a target time period according to the local time and a preset reference window length; extracting key data from the service source data, and extracting index key data and service index values corresponding to different service indexes in a target time period from the service source data; inputting index key data and service index values corresponding to different service indexes in a target time period into a service risk assessment model, and training the service risk assessment model; and inputting index key data corresponding to different service indexes corresponding to the local time into the trained service risk assessment model to obtain a service risk assessment value.
In one embodiment, when the processor executes the computer program to realize the step of extracting the index key data and the service index value corresponding to different service indexes in the target time period from the service source data, the following steps are specifically realized: analyzing index key data under the same service index in a target time period, and determining the index key data of which the difference value with the index key data of adjacent dates is greater than a preset threshold value as an abnormal value; and clearing abnormal values in the index key data.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring sample service index values of sample services in a first time period and sample index key data under each service index; acquiring a plurality of different preselection window lengths, determining a historical time period according to the first time period and each preselection window length, and acquiring a daily historical service index value of a sample service in each historical time period and historical index key data corresponding to different service indexes; respectively constructing a preselected linear regression model corresponding to each preselected window length according to historical index key data and historical service index values in each historical time period; respectively inputting the key data of the sample indexes into preselected linear regression models corresponding to the lengths of preselected windows, and estimating a net value estimated value of the sample service in a first time period by using the preselected linear regression models; and respectively calculating error values between the net value estimated value of the preselected linear regression model corresponding to each preselected window length and the sample service index value, and taking the preselected window length corresponding to the net value estimated value with the minimum error of the sample service index value as the reference window length.
In one embodiment, when the processor executes the computer program to implement the step of determining the user identifier of the current login user from the login request, the following steps are specifically implemented: calling a camera device to acquire face image data according to the login request; and acquiring image characteristic data from the face image data, and determining the user identification of the current login user according to the image characteristic data.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring a login request sent by a terminal, and determining a user identifier of a current login user from the login request;
acquiring service source data of different services corresponding to user identifications from a plurality of service servers, and calling a service risk assessment model to perform risk assessment on the service source data of each service to obtain a service risk assessment value;
when the service risk assessment value is larger than the risk threshold value, triggering an interception instruction to be sent to the service server, wherein the interception instruction is used for indicating the service server to stop service processing;
and generating an early warning page according to the service risk assessment value and the service source data, and sending the early warning page to the terminal.
In one embodiment, when the computer program is executed by the processor to implement the step of calling the service risk assessment model to perform risk assessment on the service source data of each service, the following steps are specifically implemented: determining local time, and determining a target time period according to the local time and a preset reference window length; extracting key data from the business source data, and extracting index key data and business index values corresponding to different business indexes in a target time period from the business source data; inputting index key data and service index values corresponding to different service indexes in a target time period into a service risk assessment model, and training the service risk assessment model; and inputting index key data corresponding to different service indexes corresponding to the local time into the trained service risk assessment model to obtain a service risk assessment value.
In one embodiment, when the computer program is executed by the processor to further implement the step of extracting, from the service source data, index key data and service index values corresponding to different service indexes in the target time period, the following steps are specifically implemented: analyzing index key data under the same service index in a target time period, and determining the index key data of which the difference value with the index key data of adjacent dates is greater than a preset threshold value as an abnormal value; and clearing abnormal values in the index key data.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring sample service index values of sample services in a first time period and sample index key data under each service index; acquiring a plurality of different preselection window lengths, determining historical time periods according to the first time period and each preselection window length, and acquiring historical service index values of sample services in each historical time period every day and historical index key data corresponding to different service indexes; respectively constructing a preselected linear regression model corresponding to each preselected window length according to historical index key data and historical service index values in each historical time period; respectively inputting the key data of the sample indexes into preselected linear regression models corresponding to the lengths of preselected windows, and estimating a net value estimated value of the sample service in a first time period by using the preselected linear regression models; and respectively calculating error values between the net value estimated value of the preselected linear regression model corresponding to each preselected window length and the sample service index value, and taking the preselected window length corresponding to the net value estimated value with the minimum error of the sample service index value as the reference window length.
In one embodiment, when the computer program is executed by the processor to perform the step of determining the user identifier of the currently logged-in user from the login request, the following steps are specifically performed: calling a camera device to acquire face image data according to the login request; and acquiring image characteristic data from the face image data, and determining the user identification of the current login user according to the image characteristic data.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method of processing data information, the method comprising:
acquiring a login request sent by a terminal, and determining a user identifier of a current login user from the login request;
acquiring service source data of different services corresponding to the user identification from a plurality of service servers, and calling a service risk assessment model to perform risk assessment on the service source data of each service to obtain a service risk assessment value; wherein the business risk assessment model is a linear regression model;
when the service risk assessment value is larger than a risk threshold value, triggering an interception instruction to be sent to the service server, wherein the interception instruction is used for indicating the service server to stop service processing;
and generating an early warning page according to the service risk assessment value and the service source data, and sending the early warning page to the terminal, so that a user can acquire the service with risk and the service source data related to the service through the terminal, and a corresponding risk management and control strategy can be analyzed in a targeted manner.
2. The method of claim 1, wherein the step of invoking a business risk assessment model to perform risk assessment on the business source data of each business comprises:
determining local time, and determining a target time period according to the local time and a preset reference window length;
extracting key data of the service source data, and extracting index key data and service index values corresponding to different service indexes in a target time period from the service source data;
inputting index key data and service index values corresponding to different service indexes in a target time period into a service risk assessment model, and training the service risk assessment model;
and inputting index key data corresponding to different service indexes corresponding to the local time into the trained service risk assessment model to obtain a service risk assessment value.
3. The method according to claim 2, wherein the step of extracting index key data and service index values corresponding to different service indexes in a target time period from the service source data comprises:
analyzing index key data under the same service index in the target time period, and determining the index key data of which the difference value with the index key data of adjacent dates is larger than a preset threshold value as an abnormal value;
and clearing abnormal values in the index key data.
4. The method of claim 2, wherein the step of determining the target time period according to the local time and the preset reference window length is preceded by the step of:
acquiring sample service index values of sample services in a first time period and sample index key data under each service index;
acquiring a plurality of different preselected window lengths, determining a historical time period according to the first time period and each preselected window length, and acquiring historical service index values of the sample service every day in each historical time period and historical index key data corresponding to different service indexes;
respectively constructing a preselected linear regression model corresponding to each preselected window length according to historical index key data and historical service index values in each historical time period;
respectively inputting the sample index key data into preselected linear regression models corresponding to the preselected window lengths, and estimating a net value estimated value of the sample service in a first time period by using the preselected linear regression models;
and respectively calculating the error value between the net value estimated value of the preselected linear regression model corresponding to each preselected window length and the sample service index value, and taking the preselected window length corresponding to the net value estimated value with the minimum error of the sample service index value as the reference window length.
5. The method of claim 1, wherein the step of determining the user identification of the currently logged-in user from the login request comprises:
calling a camera device to acquire face image data according to the login request;
and acquiring image characteristic data from the face image data, and determining the user identification of the current login user according to the image characteristic data.
6. An apparatus for processing data information, the apparatus comprising:
the system comprises a user identifier acquisition module, a user identifier acquisition module and a login request sending module, wherein the user identifier acquisition module is used for acquiring a login request sent by a terminal and determining a user identifier of a current login user from the login request;
a risk assessment value acquisition module, configured to acquire service source data of different services corresponding to the user identifier from multiple service servers, and call a service risk assessment model to perform risk assessment on the service source data of each service to obtain a service risk assessment value; wherein the business risk assessment model is a linear regression model;
the interception instruction acquisition module is used for triggering an interception instruction to be sent to the service server when the service risk assessment value is larger than a risk threshold value, and the interception instruction is used for indicating the service server to stop service processing;
and the early warning information sending module is used for generating an early warning page according to the service risk assessment value and the service source data, and sending the early warning page to the terminal, so that a user can acquire the service with risk and the service source data related to the service through the terminal, and a corresponding risk management and control strategy can be analyzed in a targeted manner.
7. The device according to claim 6, wherein the risk assessment value obtaining module is further configured to determine a local time, and determine a target time period according to the local time and a preset reference window length; extracting key data of the service source data, and extracting index key data and service index values corresponding to different service indexes in a target time period from the service source data; inputting index key data and service index values corresponding to different service indexes in a target time period into a service risk assessment model, and training the service risk assessment model; and inputting index key data corresponding to different service indexes corresponding to the local time into the trained service risk assessment model to obtain a service risk assessment value.
8. The apparatus according to claim 7, wherein the risk assessment value acquisition module is further configured to analyze index key data under the same service index in the target time period, and determine index key data with a difference value larger than a preset threshold value from index key data of adjacent dates as an abnormal value; and clearing abnormal values in the index key data.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 5 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910635736.9A CN110493190B (en) | 2019-07-15 | 2019-07-15 | Data information processing method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910635736.9A CN110493190B (en) | 2019-07-15 | 2019-07-15 | Data information processing method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110493190A CN110493190A (en) | 2019-11-22 |
| CN110493190B true CN110493190B (en) | 2022-07-08 |
Family
ID=68547281
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910635736.9A Active CN110493190B (en) | 2019-07-15 | 2019-07-15 | Data information processing method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110493190B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111178386B (en) * | 2019-12-03 | 2022-06-07 | 南京领行科技股份有限公司 | Method and device for processing service of vehicle |
| CN111404721B (en) * | 2020-02-13 | 2023-07-25 | 中国平安人寿保险股份有限公司 | Visual processing method, device and equipment for model training process data based on web |
| CN113505221B (en) * | 2020-03-24 | 2024-03-12 | 国家计算机网络与信息安全管理中心 | Enterprise false propaganda risk identification method, equipment and storage medium |
| CN111584059B (en) * | 2020-04-21 | 2024-01-23 | 武汉联影医疗科技有限公司 | System monitoring method, device and computer equipment |
| CN111950889A (en) * | 2020-08-10 | 2020-11-17 | 中国平安人寿保险股份有限公司 | Client risk assessment method and device, readable storage medium and terminal equipment |
| CN112348405A (en) * | 2020-11-27 | 2021-02-09 | 中国工商银行股份有限公司 | Method and device for preventing RPA (resilient packet Access) call |
| CN112529321B (en) * | 2020-12-18 | 2023-09-05 | 平安银行股份有限公司 | Risk prediction method and device based on user data and computer equipment |
| CN113965563B (en) * | 2020-12-18 | 2023-09-26 | 深圳平安智汇企业信息管理有限公司 | Service processing method and device based on model and server |
| CN112632381B (en) * | 2020-12-24 | 2021-10-01 | 中电金信软件有限公司 | Information query method and device, computer equipment and storage medium |
| CN113900755B (en) * | 2021-10-11 | 2024-04-16 | 重庆紫光华山智安科技有限公司 | Alarm page processing method and device, computer equipment and readable storage medium |
| CN115086086B (en) * | 2022-08-19 | 2022-11-11 | 湖南三湘银行股份有限公司 | Distributed monitoring method and device for data security |
| CN115759733A (en) * | 2022-10-18 | 2023-03-07 | 广州越秀融资租赁有限公司 | Method, device, medium and equipment for determining user default risk based on business event |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101662773A (en) * | 2008-08-29 | 2010-03-03 | 国际商业机器公司 | Method and equipment for realizing purpose of reducing communication deception risk by using computer |
| CN108876133A (en) * | 2018-06-07 | 2018-11-23 | 中国平安人寿保险股份有限公司 | Risk assessment processing method, device, server and medium based on business information |
| CN109165840A (en) * | 2018-08-20 | 2019-01-08 | 平安科技（深圳）有限公司 | Risk profile processing method, device, computer equipment and medium |
| CN109345374A (en) * | 2018-09-17 | 2019-02-15 | 平安科技（深圳）有限公司 | Risk control method, device, computer equipment and storage medium |
| CN109508994A (en) * | 2018-10-17 | 2019-03-22 | 平安国际融资租赁有限公司 | Business risk control method, device, computer equipment and storage medium |
| CN109636607A (en) * | 2018-12-18 | 2019-04-16 | 平安科技（深圳）有限公司 | Business data processing method, device and computer equipment based on model deployment |
| CN109858737A (en) * | 2018-12-18 | 2019-06-07 | 平安科技（深圳）有限公司 | Rating Model method of adjustment, device and computer equipment based on model deployment |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022657A (en) * | 2016-06-24 | 2016-10-12 | 深圳前海征信中心股份有限公司 | Method and device for monitoring credit risk |
| CN108108973A (en) * | 2017-12-01 | 2018-06-01 | 北京三快在线科技有限公司 | Business risk control method and device |
| CN108462724B (en) * | 2018-05-17 | 2020-07-31 | 京东数字科技控股有限公司 | Data sharing method, device, system, member node and readable storage medium |
| CN109063985B (en) * | 2018-07-18 | 2022-04-29 | 创新先进技术有限公司 | Business risk decision method and device |
-
2019
- 2019-07-15 CN CN201910635736.9A patent/CN110493190B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101662773A (en) * | 2008-08-29 | 2010-03-03 | 国际商业机器公司 | Method and equipment for realizing purpose of reducing communication deception risk by using computer |
| CN108876133A (en) * | 2018-06-07 | 2018-11-23 | 中国平安人寿保险股份有限公司 | Risk assessment processing method, device, server and medium based on business information |
| CN109165840A (en) * | 2018-08-20 | 2019-01-08 | 平安科技（深圳）有限公司 | Risk profile processing method, device, computer equipment and medium |
| CN109345374A (en) * | 2018-09-17 | 2019-02-15 | 平安科技（深圳）有限公司 | Risk control method, device, computer equipment and storage medium |
| CN109508994A (en) * | 2018-10-17 | 2019-03-22 | 平安国际融资租赁有限公司 | Business risk control method, device, computer equipment and storage medium |
| CN109636607A (en) * | 2018-12-18 | 2019-04-16 | 平安科技（深圳）有限公司 | Business data processing method, device and computer equipment based on model deployment |
| CN109858737A (en) * | 2018-12-18 | 2019-06-07 | 平安科技（深圳）有限公司 | Rating Model method of adjustment, device and computer equipment based on model deployment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110493190A (en) | 2019-11-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110493190B (en) | Data information processing method and device, computer equipment and storage medium | |
| CN109345374B (en) | Risk control method and device, computer equipment and storage medium | |
| CN108876133B (en) | Risk assessment processing method, device, server and medium based on business information | |
| CN109858737B (en) | Grading model adjustment method and device based on model deployment and computer equipment | |
| CN109636607B (en) | Service data processing method and device based on model deployment and computer equipment | |
| CN108389121B (en) | Loan data processing method, loan data processing device, loan data processing program, and computer device and storage medium | |
| CN109992601B (en) | To-do information pushing method and device and computer equipment | |
| CN110659800A (en) | Risk monitoring processing method and device, computer equipment and storage medium | |
| CN109543925B (en) | Risk prediction method and device based on machine learning, computer equipment and storage medium | |
| WO2020125463A1 (en) | Report generation method and apparatus, computer device, and computer readable storage medium | |
| CN115526363A (en) | Business data processing method and device, computer equipment and storage medium | |
| CN110490594B (en) | Service data processing method and device, computer equipment and storage medium | |
| CN110489622B (en) | Sharing method and device of object information, computer equipment and storage medium | |
| CN109245996B (en) | Mail pushing method and device, computer equipment and storage medium | |
| CN111414874B (en) | Driving risk prediction method, device and equipment based on human face and storage medium | |
| CN111580874B (en) | System safety control method and system for data application and computer equipment | |
| CN108717426B (en) | Enterprise data updating method and device, computer equipment and storage medium | |
| CN110609954A (en) | Data acquisition method and device, computer equipment and storage medium | |
| CN110135943B (en) | Product recommendation method, device, computer equipment and storage medium | |
| CN111324802A (en) | Data auditing method and device based on identity recognition and computer equipment | |
| CN112766974A (en) | Risk account identification method and device, computer equipment and storage medium | |
| CN112035611A (en) | Target user recommendation method and device, computer equipment and storage medium | |
| CN110750710A (en) | Wind control protocol early warning method and device, computer equipment and storage medium | |
| CN110378811B (en) | Arbitration information processing method, apparatus, computer device and storage medium | |
| CN110765131B (en) | Data compression method and device for goods source data, computer equipment and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |