WO2019232964A1 - 风险管理数据处理方法、装置、计算机设备和存储介质 - Google Patents

风险管理数据处理方法、装置、计算机设备和存储介质 Download PDF

Info

Publication number
WO2019232964A1
WO2019232964A1 PCT/CN2018/104759 CN2018104759W WO2019232964A1 WO 2019232964 A1 WO2019232964 A1 WO 2019232964A1 CN 2018104759 W CN2018104759 W CN 2018104759W WO 2019232964 A1 WO2019232964 A1 WO 2019232964A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
risk
event
task
party
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.)
Ceased
Application number
PCT/CN2018/104759
Other languages
English (en)
French (fr)
Inventor
霍丽
梁荣才
刘芸
杜号权
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Publication of WO2019232964A1 publication Critical patent/WO2019232964A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • 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

Definitions

  • the present application relates to a risk management data processing method, device, computer equipment, and storage medium.
  • IT risk is also known as information technology risk.
  • IT risk refers to any adverse situation caused by the use of computer hardware, software, networks and other systems, including program errors, system downtime, software defects, operational errors, hardware failures, insufficient capacity, Network loopholes and failure recovery.
  • program errors system downtime
  • software defects software defects
  • operational errors hardware failures
  • insufficient capacity Network loopholes and failure recovery.
  • network loopholes Network loopholes and failure recovery.
  • a risk management data processing method is provided.
  • a risk management data processing method includes:
  • the report data includes cause data and influence data of each risk event, and a preset classification model is used to obtain a risk corresponding to each risk event according to the cause data and influence data Types of;
  • a risk management data processing device includes:
  • a risk event set acquisition module configured to acquire a risk event set, where each risk event in the risk event set carries a user identifier
  • An event reporting task creation module configured to create corresponding event reporting tasks for each of the risk events, and obtain an event reporting task set
  • the target interface party selection module is configured to select a target interface party corresponding to each event reporting task from a set of interface parties corresponding to each risk event according to the user identifier, and send each event reporting task to a terminal corresponding to its target interface party.
  • a risk type acquisition module is configured to receive report data sent by a terminal corresponding to the target interface party, the report data includes cause data and influence data of each risk event, and a preset classification model is adopted according to the cause data and influence data. Get the risk type corresponding to each risk event;
  • a reporting data sending module configured to select a reviewer corresponding to each risk event according to the risk type, and send the reported data to a terminal corresponding to each reviewer;
  • a report file generating module is configured to receive the review data sent by the terminal corresponding to each reviewer. When it is determined that the review data corresponding to any risk event passes the review based on the review data, a report file is generated based on the report data passed by the review.
  • a computer device includes a memory and one or more processors.
  • the memory stores computer-readable instructions.
  • the one or more processors are executed. The following steps:
  • the report data includes cause data and influence data of each risk event, and a preset classification model is used to obtain a risk corresponding to each risk event according to the cause data and influence data Types of;
  • One or more non-volatile storage media storing computer-readable instructions.
  • the computer-readable instructions When executed by one or more processors, the one or more processors execute the following steps:
  • the report data includes cause data and influence data of each risk event, and a preset classification model is used to obtain a risk corresponding to each risk event according to the cause data and influence data Types of;
  • FIG. 1 is an application scenario diagram of a risk management data processing method according to one or more embodiments
  • FIG. 2 is a schematic flowchart of a risk management data processing method according to one or more embodiments
  • FIG. 3 is a schematic flowchart of step S206 according to one or more embodiments.
  • FIG. 4 is a block diagram of a risk management data processing apparatus according to one or more embodiments.
  • FIG. 5 is a block diagram of a computer device according to one or more embodiments.
  • the risk management data processing method provided in this application can be applied to the application environment shown in FIG. 1.
  • the terminal 104 corresponding to the target interface party, the terminal 106 corresponding to the reviewer, and the terminal 108 corresponding to the event investigator communicate with the risk management server 102 through the network, respectively.
  • the risk management server 102 obtains the risk event set, it creates an event reporting task for each risk event, and assigns the event reporting task to the target interface party, and the target interface party can report and enter the event reporting task through its corresponding terminal 104, and then The reported data is returned to the risk management server 102 through the terminal 104.
  • the risk management server 102 classifies risk events based on the reported data, then selects the reviewer based on the classification results, sends the reported data to the corresponding terminal of the reviewer 106, and finally according to the reviewer
  • the review data returned by the corresponding terminal determines whether the risk event passes the review, generates a report file for the risk event that passed the review, and sends it to the terminal 108 corresponding to the event investigator.
  • the terminal 104 corresponding to the target interface party, the terminal 106 corresponding to the reviewer, and the terminal 108 corresponding to the event investigator may be, but are not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices, and the server 102 It can be implemented by an independent server or a server cluster composed of multiple servers.
  • a risk management data processing method is provided.
  • the method is applied to the risk management server 102 in FIG. 1 as an example, and includes the following steps:
  • step S202 a risk event set is acquired, and each risk event in the risk event set carries a user identifier.
  • a risk event set refers to a set of at least one risk event, and a risk event refers to any event that may cause an adverse situation due to the use of computer hardware, software, or network.
  • the user ID is used to uniquely identify the user who caused the risk event, and is composed of a preset number of digits, letters, or other special symbols.
  • the risk management server acquires risk events in real time from a third-party system server, such as an operation and maintenance system server, in a real-time and synchronous manner.
  • a third-party system server such as an operation and maintenance system server
  • the user corresponding to the user identification may be an individual, or may be a company, a team, or the like.
  • the same industry often contains multiple professional subsidiaries, and each professional subsidiary corresponds to a user.
  • an insurance company group a professional company responsible for property insurance and a professional responsible for life insurance Each company corresponds to a user.
  • Step S204 Create corresponding event reporting tasks for each risk event, and obtain event reporting task sets.
  • the risk management server may store a task template in advance, and the task template includes entries such as a risk event name, a risk event cause, a risk event history, and a possible impact of the risk event.
  • each risk event in the risk event set uses a task template to create a corresponding event reporting task.
  • the task name of the event reporting task may be named after the risk event name, or The numbering rules set in advance are numbered. For example, the names can be named according to 001, 002, 003, etc.
  • the event reporting task set corresponding to the risk event set is obtained.
  • step S206 the target interface party corresponding to each event reporting task is selected from the set of interface parties corresponding to each risk event according to the user identification, and each event reporting task is sent to the terminal corresponding to its target interface party.
  • all user IDs have one or more interface parties associated with them stored in the risk management server.
  • the interface party can be identified by name, mobile phone number, and mailbox in the risk management server.
  • One user ID corresponds to All the interface parties in the group constitute the interface party set. Therefore, the corresponding interface party can be found according to the user ID carried in the risk event, and the event reporting task corresponding to the risk event is assigned to the interface party corresponding to the user ID carried in the risk event.
  • the risk management server selects the target interface party from the set of interface parties corresponding to the user identification.
  • the target interface party may be randomly selected as the target interface party.
  • the risk management server selects the target interface party from the set of interface parties corresponding to the user identification.
  • the target interface party may be selected according to the long-term connection status and priority of each interface party in the interface party set.
  • the long connection state corresponding to each interface party in the interface party set, and the interface party whose long connection state is maintained as the candidate interface party to obtain the candidate interface party set, and obtain the correspondence of each candidate interface party in the candidate interface party set.
  • Task priority select the candidate interface party with the highest task priority from the set of candidate interface parties as the target interface party.
  • step S208 the report data sent by the terminal corresponding to the target interface party is received.
  • the report data includes cause data and influence data of each risk event, and a preset classification model is used to obtain a risk type corresponding to each risk event according to the cause data and influence data.
  • the reported data is data entered by the target interface party at its corresponding terminal according to the corresponding task, including the name of the risk event, the cause data corresponding to the risk event, the process data, and the impact data.
  • the types of risks include system risk, network risk, data risk, and operational risk.
  • the preset classification model is obtained through machine learning training.
  • a supervised model training method such as a logistic regression model, SVM (Support Vector Machine, Support Vector Machine), Bayesian models, convolutional neural networks, etc.
  • the risk management server after receiving the report data sent by the terminal corresponding to the target interface party, the risk management server inputs the cause data and influence data in the report data into the trained classification model to obtain the risk type corresponding to the risk event.
  • step S210 the reviewer corresponding to each risk event is selected according to the risk type, and the reported data is sent to the terminal corresponding to each reviewer.
  • each reviewer corresponds to a user ID in the risk management server.
  • the user ID is used to uniquely identify the identity of the reviewer. It can be a name, social account number, ID number, mobile phone number, etc.
  • the mapping relationship between the user ID and the risk type corresponding to the reviewer can be established.
  • the risk management server obtains the risk type of the risk event, it can find its corresponding The user identification, and then report the risk event data to the terminal corresponding to the user identification.
  • the reviewer corresponding to the user ID may review the reported data corresponding to the risk event through the terminal.
  • the review may directly give an overall conclusion to the reported data, and the conclusion may be that the review is passed or the review fails.
  • improvement suggestions can be given; each item of the reported data can be reviewed separately, such as the cause of the event, the course of the event, and the impact of the event, and the review conclusions can be given.
  • Step S212 Receive the review data sent by the terminal corresponding to each reviewer, determine whether each risk event passes the review based on the review data, and when any risk event is judged to pass the review based on the review data, a report file is generated based on the reported data passed the review.
  • the risk management server parses the review data, obtains the review conclusions in the review data, and determines whether the risk event has passed the review based on the review conclusions.
  • the review of the risk event can be directly determined based on the review conclusion.
  • the obtained review conclusions include Multiple review conclusions, that is, when the review conclusions are directed to a single item in the reported data, it is determined whether these review conclusions include unsuccessful review conclusions. If so, it is judged that the risk event review has failed.
  • a report file corresponding to the risk event is generated based on the reported data that passes the review.
  • the report file contains at least the data such as the name of the risk event, reported data, and review conclusions.
  • the risk management server sends the report file to a terminal corresponding to the event investigator. Specifically, when the report file acquisition request sent by the terminal corresponding to the event investigator is received, the report file corresponding to the report file acquisition request is separately sent to the terminal corresponding to the event investigator; or when the number of report files exceeds Set a threshold, such as five, to send all the report files that have been generated to the terminal corresponding to the event investigator; you can also query the report files that are not currently sent at regular intervals, such as 2 days, and then Send all unsent report files found to the terminal corresponding to the incident investigator.
  • Set a threshold such as five
  • a risk event is obtained through a risk management server, a report task is generated for the risk event, and then it is assigned to the corresponding target interface party, and receives the report data sent by the target interface party through its corresponding terminal, and sends the report data To the corresponding reviewer, judge whether the risk event review has passed based on the review data returned by the corresponding terminal of the reviewer, and when it passes, generate a report file to realize the automated management of risk events and improve the efficiency of risk management.
  • the step of obtaining a set of risk events includes: obtaining source data corresponding to the risk event; creating an ETL (Extract-Transform-Load, extraction / transformation / load) task according to the source data, and triggering the ETL tool to run the ETL task;
  • the result of the ETL task corresponds to the set of risk events.
  • the risk management server obtains source data corresponding to a risk event from a third-party system server such as an operation and maintenance system server, and the source data includes, but is not limited to, a user identifier corresponding to the risk event, a type of the risk event, and a brief description of the risk event, such as The causes and effects of risk events, and the estimated loss of risk events.
  • the format of the source data may be, for example, one or more of a variety of data sources such as a data source MySQL, a data source Oracle, a data source PostgreSQL, a data source DB2, and a data source SQL Server.
  • the corresponding ETL tool is selected to run the ETL task according to the data type of the source data, and a risk event set is obtained according to the operation result.
  • the risk management server may first perform a uniform format conversion on the source data, such as uniformly converting the source data into a comma-separated value CSV format, and then create an ETL task based on the converted source data, and select the corresponding CSV format.
  • the ETL tool runs the ETL task and obtains a set of risk events based on the results of the operation.
  • the ETL tool can be used to better integrate the acquired source data and quickly obtain a set of risk events.
  • the step of selecting the target interface party corresponding to each event reporting task from the set of interface parties corresponding to each risk event according to the user identification includes:
  • step S206A the long-connected state corresponding to each interface party in the set of interface parties is obtained, and the interface party whose long-connected state is maintained is used as the candidate interface party to obtain the set of candidate interface parties.
  • the terminal corresponding to the interface party and the risk management server adopt a long connection for communication. Therefore, when selecting the target interface party, it can first determine whether the long connection corresponding to each interface party in the interface party set is a long connection state, and the interface party whose long connection state is maintained as an alternative interface party, and finally obtain the target interface party. set.
  • a heartbeat detection packet can be sent to the terminal corresponding to the interface party.
  • the heartbeat response packet is judged to be in a long connection state, otherwise, it can be determined that the corresponding long connection of the interface party has been disconnected, or the heartbeat detection packet can be sent again when no heartbeat response packet is received within a preset time, and It is judged again whether the heartbeat response packet is received within a preset time, so that an error judgment may occur when the terminal corresponding to the interface party has a short-term failure, so as to select as many alternative interface parties as to have the long connection online.
  • Step S206B Obtain a task priority corresponding to each candidate interface party in the candidate interface party set.
  • step S206C the candidate interface party with the highest task priority is selected from the set of candidate interface parties as the target interface party.
  • a task priority is set for each interface party in the interface party set.
  • the task priority can be set according to the experience and position of the interface party.
  • the The task priority sorts each candidate interface party, and the candidate interface party with the highest priority is selected as the target interface party according to the sorting result.
  • selecting the target interface party based on the long-term connection status and task priority of the interface party can ensure that the reporting task is allocated to the most appropriate interface party in a timely manner, thereby improving task processing efficiency and processing quality.
  • the preset classification model can be trained by: obtaining the reporting data and corresponding risk categories corresponding to the historical reporting task; obtaining the training set according to the cause data, impact data, and risk categories corresponding to the reporting data; according to The training set is modeled to obtain a classification model.
  • the cause data includes one or more of data such as program errors, software defects, operational errors, hardware failures, insufficient capacity, network vulnerabilities, etc.
  • the affected data include network delays, communication interruptions, system paralysis, and data loss.
  • data loss One or more.
  • these data are mapped to the feature vector space to obtain the input feature vector and the expected output feature vector corresponding to each historical reporting task.
  • Input feature vectors and expected output feature vectors are used to construct training samples for model training.
  • supervised model training methods such as logistic regression models, SVM (Support Vector Machine), and Bayesian Models, etc.
  • the stochastic gradient algorithm can be used for model training.
  • the cost function J ( ⁇ ) needs to be minimized.
  • the cost function can be expressed by the following formula:
  • m represents the number of sample features in the training set
  • x (i) is the input feature vector
  • y (i) is the expected output feature vector
  • h ⁇ (x (i) ) is the actual output feature vector for each training
  • ⁇ T x is equal to the sum of the product of features and parameters, where x (i) is the input feature vector.
  • the method further includes: when it is determined that there is report data that fails the review according to the review data, generating a revision task according to the report data that fails the review and its corresponding review data, and sending the revision task to the target interface Party corresponding terminal.
  • the revision task includes the reporting data and review data corresponding to the risk event to be revised, and is used to instruct the target interface party to revise the reported data according to the review data. Further, after the target interface party completes the revision task, it sends the revised corresponding reporting data to the risk management server through its corresponding terminal again, and the risk management server sends the revised reporting data to the corresponding terminal of the reviewer again and accepts it. After the review data returned from the terminal corresponding to the reviewer, judge again whether the risk event passes the review, and if it passes, proceed to the above step S214, otherwise repeat the steps in this embodiment until the risk event passes the review.
  • the above method further includes: generating a tracking task for each risk event in the risk event set to obtain a tracking task set; allocating each tracking task in the tracking task set to a terminal corresponding to the target interface party; and receiving a target interface party corresponding
  • the feedback data sent by the terminal is sent to the terminal corresponding to the event investigator.
  • feedback data refers to data related to improvement measures for risk events, including the implementation status, progress description, and output description of each improvement measure.
  • the implementation status includes unimplemented, ongoing, and completed implementation.
  • the progress description refers to the current progress corresponding to the implementation status
  • the output description refers to the result description corresponding to the current progress.
  • the risk management server may mark the status of each event reporting task, mark the event reporting task as incomplete for the event that has not received the reported data, and mark the event reporting task that has received the reported data and has not passed the review as In the process of completion, the event reporting task that has passed the review is marked as completed.
  • the risk management server can query the current completion status corresponding to each event reporting task from the database every preset time, such as every other day, filter out all the event reporting tasks whose current status is incomplete, and calculate each outstanding task separately.
  • the time difference between the time when the event reporting task was created and the current time determines whether the time difference is greater than a preset threshold, where the preset threshold can be set and changed according to business needs. For example, if the creation time of a report task at a certain time is "April 3, 2018", the current time is "April 7, 2018", and the preset threshold is 2, it can be determined that the time difference 4 is greater than the preset Threshold 2.
  • a reminder message is generated for the event reporting task, and the reminder information is sent to the terminal corresponding to the target interface party corresponding to the event reporting task.
  • an automatic reminder for the target interface party can be implemented, thereby improving the completion failure of the task.
  • steps in the flowchart of Fig. 2-3 are displayed in sequence as indicated by the arrows, these steps are not necessarily performed sequentially in the order indicated by the arrows. Unless explicitly stated in this document, the execution of these steps is not strictly limited, and these steps can be performed in other orders. Moreover, at least part of the steps in Figure 2-3 may include multiple sub-steps or stages. These sub-steps or stages are not necessarily performed at the same time, but may be performed at different times. These sub-steps or stages The execution order of is not necessarily performed sequentially, but may be performed in turn or alternately with at least a part of another step or a sub-step or stage of another step.
  • a risk management data processing device 400 is provided, and the device includes:
  • the risk event set acquisition module 402 is configured to acquire a risk event set, where each risk event in the risk event set carries a user identifier;
  • An event reporting task creation module 404 is configured to create corresponding event reporting tasks for each risk event and obtain a set of event reporting tasks;
  • the target interface party selection module 406 is configured to select the target interface party corresponding to each event reporting task from the set of interface parties corresponding to each risk event according to the user identifier, and send each event reporting task to the terminal corresponding to its target interface party;
  • the risk type acquisition module 408 is configured to receive the report data sent by the terminal corresponding to the target interface party.
  • the report data includes the cause data and influence data of each risk event. Based on the cause data and influence data, a preset classification model is used to obtain the corresponding risk event correspondence. Risk type
  • a reporting data sending module 410 configured to select a reviewer corresponding to each risk event according to the type of risk, and send the report data to a terminal corresponding to each reviewer;
  • a report file generating module 412 is configured to receive the review data sent by the terminal corresponding to each reviewer. When it is determined that the review data corresponding to any risk event passes the review based on the review data, a report file is generated based on the report data passed by the review.
  • the risk event set acquisition module 402 is configured to acquire source data corresponding to the risk event, create an ETL task based on the source data, trigger an ETL tool to run the ETL task, and obtain a risk event set according to a running result corresponding to the ETL task.
  • the target interface party selection module 406 is configured to obtain the long-connected state corresponding to each interface party in the set of interface parties, and use the interface party whose long-connected state is maintained as the candidate interface party to obtain the set of candidate interface parties. To obtain the task priority corresponding to each candidate interface party in the candidate interface party set, and select the candidate interface party with the highest task priority from the candidate interface party set as the target interface party.
  • the above-mentioned device further includes: a classification model training module for obtaining reporting data corresponding to the historical reporting task and corresponding risk categories; obtaining a training set according to the cause data, impact data, and risk categories corresponding to the reporting data; according to The training set is modeled to obtain a classification model.
  • the above-mentioned device further includes: a revision task generating and sending module, configured to generate a revision based on the report data that fails the review and the corresponding review data when it is determined that there is report data that fails the review. Task, sending the revision task to the terminal corresponding to the target interface party.
  • a revision task generating and sending module configured to generate a revision based on the report data that fails the review and the corresponding review data when it is determined that there is report data that fails the review. Task, sending the revision task to the terminal corresponding to the target interface party.
  • the above device further includes: a risk event tracking module, configured to generate a tracking task for each risk event in the risk event set, to obtain a tracking task set; and assign each tracking task in the tracking task set to a target interface party.
  • Terminal receiving feedback data sent by the terminal corresponding to the target interface party, and sending the feedback data to the terminal corresponding to the event investigation party.
  • the above device further includes: a task reminder module, configured to obtain the current status corresponding to each event reporting task, filter out all event reporting tasks whose current status is incomplete, and calculate each current status as uncompleted respectively The time difference between the creation time of the event reporting task and the current time. When the time difference is greater than a preset threshold, a reminder message is generated and sent to the terminal corresponding to the target interface party.
  • a task reminder module configured to obtain the current status corresponding to each event reporting task, filter out all event reporting tasks whose current status is incomplete, and calculate each current status as uncompleted respectively The time difference between the creation time of the event reporting task and the current time. When the time difference is greater than a preset threshold, a reminder message is generated and sent to the terminal corresponding to the target interface party.
  • Each module in the above-mentioned risk management data processing device may be implemented in whole or in part by software, hardware, and a combination thereof.
  • the above-mentioned modules may be embedded in the hardware in or independent of the processor in the computer device, or may be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
  • a computer device is provided.
  • the computer device may be a server, and its internal structure diagram may be as shown in FIG. 5.
  • the computer device includes a processor, a memory, a network interface, and a database connected through a system bus.
  • the processor of the computer device is used to provide computing and control capabilities.
  • the memory of the computer device includes a non-volatile storage medium and an internal memory.
  • the non-volatile storage medium stores an operating system, computer-readable instructions, and a database.
  • the internal memory provides an environment for the operation of the operating system and computer-readable instructions in a non-volatile storage medium.
  • the database of the computer equipment is used to store various data in the process of risk management data processing, such as the current status data of the event reporting task, the information of each interface party in the interface party set, and the status of the persistent connection.
  • the network interface of the computer device is used to communicate with an external terminal through a network connection.
  • the computer-readable instructions are executed by a processor to implement a risk management data processing method.
  • FIG. 5 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied.
  • the specific computer equipment may be Include more or fewer parts than shown in the figure, or combine certain parts, or have a different arrangement of parts.
  • a computer device including a memory and a processor.
  • the memory stores computer-readable instructions.
  • the processor executes the computer-readable instructions, the processor implements the following steps: obtaining a risk event set, and obtaining the risk event set.
  • Each risk event carries a user identification; a corresponding event reporting task is created for each risk event to obtain an event reporting task set; and a target interface party corresponding to each event reporting task is selected from the set of interface parties corresponding to each risk event according to the user identification, Send each event reporting task to the terminal corresponding to its target interface party; receive the reporting data sent by the terminal corresponding to the target interface party, the reporting data includes the cause data and impact data of each risk event, and presets are adopted based on the cause data and impact data Based on the classification model to obtain the risk type corresponding to each risk event; select the reviewer corresponding to each risk event according to the risk type, and send the reported data to the terminal corresponding to each reviewer; receive the review data sent by the terminal corresponding to each reviewer When it is determined that the reported data corresponding to any risk event passes the review based on the review data, a report file is generated based on the reported data passed the review.
  • the step of obtaining a set of risk events includes: obtaining source data corresponding to the risk event; creating an ETL task based on the source data, triggering an ETL tool to run the ETL task; and obtaining a set of risk events according to a running result corresponding to the ETL task.
  • the step of selecting the target interface party corresponding to each event reporting task from the interface party set corresponding to each risk event according to the user identification includes: obtaining the long connection status corresponding to each interface party in the interface party set, and The interface party whose connection status is maintained is used as the candidate interface party to obtain the candidate interface party set; obtain the task priority corresponding to each candidate interface party in the candidate interface party set; and select the task priority from the candidate interface party set.
  • the highest candidate interface party is the target interface party.
  • the preset classification model can be trained by: obtaining the reporting data corresponding to the historical reporting task and the corresponding risk category; according to the reporting data, Cause data, impact data, and risk categories are obtained from the training set; the model is obtained from the training set to obtain the classification model.
  • the processor when the processor executes the computer-readable instructions, the processor further implements the following steps: when it is determined that there is report data that fails the review according to the review data, generating a revision task according to the report data that fails the review and its corresponding review data To send the revision task to the terminal corresponding to the target interface party.
  • the processor executes the computer-readable instructions, the following steps are further implemented: generating a tracking task for each risk event in the risk event set to obtain a tracking task set; assigning each tracking task in the tracking task set to a target interface party correspondingly
  • the terminal receives feedback data sent by the terminal corresponding to the target interface party, and sends the feedback data to the terminal corresponding to the event investigation party.
  • the processor executes the computer-readable instructions, the following steps are further implemented: acquiring the current status corresponding to each event reporting task, filtering out all event reporting tasks whose current status is incomplete, and calculating each current status as uncompleted separately The time difference between the creation time of the completed event reporting task and the current time. When the time difference is greater than a preset threshold, a reminder message is generated and sent to the terminal corresponding to the target interface party.
  • a computer-readable storage medium on which computer-readable instructions are stored.
  • the following steps are implemented: acquiring a risk event set, and each risk event in the risk event set. Carry the user ID; create corresponding event reporting tasks for each risk event to obtain the event reporting task set; select the target interface party corresponding to each event reporting task from the set of interface parties corresponding to each risk event according to the user ID, and report each event
  • the reporting task is sent to the terminal corresponding to its target interface party; receiving the reporting data sent by the terminal corresponding to the target interface party, the reporting data includes the cause data and impact data of each risk event, and a preset classification model is adopted according to the cause data and impact data
  • the step of obtaining a set of risk events includes: obtaining source data corresponding to the risk event; creating an ETL task based on the source data, triggering an ETL tool to run the ETL task; and obtaining a set of risk events according to a running result corresponding to the ETL task.
  • the step of selecting the target interface party corresponding to each event reporting task from the interface party set corresponding to each risk event according to the user identification includes: obtaining the long connection status corresponding to each interface party in the interface party set, and The interface party whose connection status is maintained is used as the candidate interface party to obtain the candidate interface party set; obtain the task priority corresponding to each candidate interface party in the candidate interface party set; and select the task priority from the candidate interface party set.
  • the highest candidate interface party is the target interface party.
  • the preset classification model can be trained by: obtaining the reporting data corresponding to the historical reporting task and the corresponding risk category; corresponding to the reporting data The cause data, impact data, and risk category of the training set are obtained; the model is obtained based on the training set to obtain the classification model.
  • the following steps are further implemented: when it is determined from the review data that there is report data that fails the review, generating a revision based on the report data that fails the review and its corresponding review data Task, sending the revision task to the terminal corresponding to the target interface party.
  • the following steps are further implemented: generating a tracking task for each risk event in the risk event set to obtain a tracking task set; and allocating each tracking task in the tracking task set to a target interface party Corresponding terminal; receiving feedback data sent by the terminal corresponding to the target interface party, and sending the feedback data to the terminal corresponding to the event investigation party.
  • the following steps are also implemented: obtaining the current status corresponding to each event reporting task, filtering out all event reporting tasks whose current status is incomplete, and calculating each current status as The time difference between the creation time of the unfinished event and the current time is reported. When the time difference is greater than a preset threshold, a reminder message is generated and sent to the terminal corresponding to the target interface party.
  • Non-volatile memory may 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.
  • RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Synchlink DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
  • SRAM static RAM
  • DRAM dynamic RAM
  • SDRAM synchronous DRAM
  • DDRSDRAM dual data rate SDRAM
  • ESDRAM enhanced SDRAM
  • SLDRAM synchronous chain Synchlink DRAM
  • Rambus direct RAM
  • DRAM direct memory bus dynamic RAM
  • RDRAM memory bus dynamic RAM

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Operations Research (AREA)
  • Physics & Mathematics (AREA)
  • Educational Administration (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Game Theory and Decision Science (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Debugging And Monitoring (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种风险管理数据处理方法，包括：获取风险事件集合，分别对各个风险事件创建事件上报任务，从各个风险事件对应的接口方集合中选取各个事件上报任务对应的目标接口方，将各个事件上报任务分别发送至其目标接口方对应的终端，接收目标接口方对应的终端发送的上报数据，采用预设的分类模型得到各个风险事件对应的风险类型；根据风险类型选取各个风险事件对应的评审方，将上报数据发送至各个评审方对应的终端；接收各个评审方对应的终端发送的评审数据，当根据评审数据判断出任意一个风险事件对应的上报数据通过评审时，根据评审通过的上报数据生成报告文件。

Description

风险管理数据处理方法、装置、计算机设备和存储介质
相关申请的交叉引用
本申请要求于2018年06月07日提交中国专利局，申请号为2018105822439，申请名称为“风险管理数据处理方法、装置、计算机设备和存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及一种风险管理数据处理方法、装置、计算机设备和存储介质。
背景技术
IT风险也称为信息科技风险，IT风险是指任何由于使用计算机硬件、软件、网络等系统所引发的不利情况，包括程序错误、系统宕机、软件缺陷、操作失误、硬件故障、容量不足、网络漏洞及故障恢复等。在大型的集团中，为减少IT风险事件造成的损失，需要对风险事件进行有效的管理。
传统技术中，对各个专业公司的风险事件进行管理，通常是由专门的事件调查方，通过发邮件等线下沟通的方式对风险事件进行管理和监督，然而，发明人意识到，这种方式下需要时间调查员花费大量的时间来进行沟通，导致风险管理的效率低下。
发明内容
根据本申请公开的各种实施例，提供一种风险管理数据处理方法、装置、计算机设备和存储介质。
一种风险管理数据处理方法，包括：
获取风险事件集合，所述风险事件集合中各个风险事件携带用户标识；
分别对所述各个风险事件创建对应的事件上报任务，得到事件上报任务集合；
根据所述用户标识分别从各个风险事件对应的接口方集合中选取各个事件上报任务对应的目标接口方，将各个事件上报任务分别发送至其目标接口方对应的终端；
接收所述目标接口方对应的终端发送的上报数据，所述上报数据包括各个风险事件的起因数据及影响数据，根据所述起因数据及影响数据采用预设的分类模型得到各个风险事件对应的风险类型；
根据所述风险类型选取各个风险事件对应的评审方，将所述上报数据发送至各个评审方对应的终端；及
接收各个评审方对应的终端发送的评审数据，当根据所述评审数据判断出任意一个风险事件对应的上报数据通过评审时，根据评审通过的上报数据生成报告文件。
一种风险管理数据处理装置，包括：
风险事件集合获取模块，用于获取风险事件集合，所述风险事件集合中各个风险事件携带用户标识；
事件上报任务创建模块，用于分别对所述各个风险事件创建对应的事件上报任务，得到事件上报任务集合；
目标接口方选取模块，用于根据所述用户标识分别从各个风险事件对应的接口方集合中选取各个事件上报任务对应的目标接口方，将各个事件上报任务分别发送至其目标接口方对应的终端；
风险类型获取模块，用于接收所述目标接口方对应的终端发送的上报数据，所述上报数据包括各个风险事件的起因数据及影响数据，根据所述起因数据及影响数据采用预设的分类模型得到各个风险事件对应的风险类型；
上报数据发送模块，用于根据所述风险类型选取各个风险事件对应的评审方，将所述上报数据发送至各个评审方对应的终端；及
报告文件生成模块，用于接收各个评审方对应的终端发送的评审数据，当根据所述评审数据判断出任意一个风险事件对应的评审数据通过评审时，根据评审通过的上报数据生成报告文件。
一种计算机设备，包括存储器和一个或多个处理器，所述存储器中储存有计算机可读指令，所述计算机可读指令被所述处理器执行时，使得所述一个或多个处理器执行以下步骤：
获取风险事件集合，所述风险事件集合中各个风险事件携带用户标识；
分别对所述各个风险事件创建对应的事件上报任务，得到事件上报任务集合；
根据所述用户标识分别从各个风险事件对应的接口方集合中选取各个事件上报任务对应的目标接口方，将各个事件上报任务分别发送至其目标接口方对应的终端；
接收所述目标接口方对应的终端发送的上报数据，所述上报数据包括各个风险事件的起因数据及影响数据，根据所述起因数据及影响数据采用预设的分类模型得到各个风险事件对应的风险类型；
根据所述风险类型选取各个风险事件对应的评审方，将所述上报数据发送至各个评审方对应的终端；及
接收各个评审方对应的终端发送的评审数据，当根据所述评审数据判断出任意一个风险事件对应的上报数据通过评审时，根据评审通过的上报数据生成报告文件。
一个或多个存储有计算机可读指令的非易失性存储介质，计算机可读指令被一个或多个处理器执行时，使得一个或多个处理器执行以下步骤：
获取风险事件集合，所述风险事件集合中各个风险事件携带用户标识；
分别对所述各个风险事件创建对应的事件上报任务，得到事件上报任务集合；
根据所述用户标识分别从各个风险事件对应的接口方集合中选取各个事件上报任务对应的目标接口方，将各个事件上报任务分别发送至其目标接口方对应的终端；
接收所述目标接口方对应的终端发送的上报数据，所述上报数据包括各个风险事件的起因数据及影响数据，根据所述起因数据及影响数据采用预设的分类模型得到各个风险事件对应的风险类型；
根据所述风险类型选取各个风险事件对应的评审方，将所述上报数据发送至各个评审方对应的终端；及
接收各个评审方对应的终端发送的评审数据，当根据所述评审数据判断出任意一个风险事件对应的上报数据通过评审时，根据评审通过的上报数据生成报告文件。
本申请的一个或多个实施例的细节在下面的附图和描述中提出。本申请的其它特征和优点将从说明书、附图以及权利要求书变得明显。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其它的附图。
图1为根据一个或多个实施例中风险管理数据处理方法的应用场景图；
图2为根据一个或多个实施例中风险管理数据处理方法的流程示意图；
图3为根据一个或多个实施例中步骤S206的流程示意图；
图4为根据一个或多个实施例中风险管理数据处理装置的框图；
图5为根据一个或多个实施例中计算机设备的框图。
具体实施方式
为了使本申请的技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
本申请提供的风险管理数据处理方法，可以应用于如图1所示的应用环境中。其中，目标接口方对应的终端104、评审方对应的终端106以及事件调查方对应的终端108分别通过网络与风险管理服务器102通过网络进行通信。风险管理服务器102获取到风险事件集合后，分别对各个风险事件创建事件上报任务，将事件上报任务分配至目标接口方，目标接口方可通过其对应的终端104对事件上报任务进行上报录入，然后通过终端104将上报数据返回至风险管理服务器102，风险管理服务器102根据上报数据对风险事件进行分类，然后根据分类结果选择评审方，将上报数据发送至评审方106对应的终端，最后根据 评审方对应的终端返回的评审数据判断风险事件是否通过评审，对通过评审的风险事件生成报告文件，发送至事件调查方对应的终端108。其中，目标接口方对应的终端104、评审方对应的终端106以及事件调查方对应的终端108可以但不限于是各种个人计算机、笔记本电脑、智能手机、平板电脑和便携式可穿戴设备，服务器102可以用独立的服务器或者是多个服务器组成的服务器集群来实现。
在一些实施例中，如图2所示，提供了一种风险管理数据处理方法，以该方法应用于图1中的风险管理服务器102为例进行说明，包括以下步骤：
步骤S202，获取风险事件集合，风险事件集合中各个风险事件携带用户标识。
风险事件集合指的是至少一个风险事件所组成的集合，风险事件指的是指任何由于使用计算机硬件、软件、网络等可能会引发不利情况的事件。用户标识用于唯一标识引发风险事件的用户的身份，由预设位数的数字、字母或其它特殊符号等组成。
在一些实施例中，风险管理服务器通过实时同步地方式从第三方系统服务器例如运维系统服务器实时获取风险事件。进一步地，用户标识对应的用户可以为个人，也可以为公司、团队等。如，在大型的集团公司中，同一个行业往往包含多家专业子公司，其中，每一专业子公司对应一个用户，如，在保险公司集团中，负责产险的专业公司、负责寿险的专业公司分别对应一个用户。
步骤S204，分别对各个风险事件创建对应的事件上报任务，得到事件上报任务集合。
具体地，风险管理服务器中可预先存储有任务模板，任务模板中包括风险事件名称、风险事件起因、风险事件经过、风险事件可能造成的影响等条目。当风险管理服务器获取到风险事件集合后，对风险事件集合中各个风险事件分别采用任务模板创建对应的事件上报任务，其中，事件上报任务的任务名称可以以风险事件的名称进行命名，也可以按照事先设定好的编号规律进行编号，如可将名称按照001、002、003……进行命名，对各个风险事件创建好了事件上报任务后，得到风险事件集合对应的事件上报任务集合。
步骤S206，根据用户标识分别从各个风险事件对应的接口方集合中选取各个事件上报任务对应的目标接口方，将各个事件上报任务分别发送至其目标接口方对应的终端。
具体地，所有的用户标识在风险管理服务器中都保存有一个或多个与之相关联的接口方，接口方在风险管理服务器中可以用姓名、手机号、邮箱等进行标识，一个用户标识对应的所有接口方即组成接口方集合，因此，可根据风险事件中携带的用户标识查找对应的接口方，将风险事件对应的事件上报任务分配至风险事件中携带的用户标识所对应的接口方。
在一些实施例中，风险管理服务器从用户标识对应的接口方集合中选取目标接口方可以是随机选取任意一个接口方作为目标接口方。在另一个实施例中，风险管理服务器从用户标识对应的接口方集合中选取目标接口方可以是根据接口方集合中各个接口方对应的长连接状态和优先级进行选取，具体地，可以首先获取接口方集合中各个接口方对应的长连接状态，将所长连接状态为保持状态的接口方作为备选接口方，得到备选接口方集合， 获取备选接口方集合中各个备选接口方对应的任务优先级；从备选接口方集合中选取任务优先级最高的备选接口方作为目标接口方。
步骤S208，接收目标接口方对应的终端发送的上报数据，上报数据包括各个风险事件的起因数据及影响数据，根据起因数据及影响数据采用预设的分类模型得到各个风险事件对应的风险类型。
其中，上报数据为目标接口方在其对应的终端根据相应的任务录入的数据，包过风险事件的名称、风险事件对应的起因数据、经过数据和影响数据。风险类型包括系统风险、网络风险、数据风险、运行风险。在本实施例中，预设的分类模型是通过机器学习训练得到的，在进行模型训练时，可以采用有监督的模型训练方式，例如逻辑回归模型、SVM(Support Vector Machine,支持向量机)、贝叶斯模型、卷积神经网络等。
在本实施例中，风险管理服务器接收到目标接口方对应的终端发送的上报数据后，将上报数据中的起因数据及影响数据输入已经训练好的分类模型，得到风险事件对应的风险类型。
步骤S210，根据风险类型选取各个风险事件对应的评审方，将上报数据发送至各个评审方对应的终端。
具体地，对于不同的风险类型预先设置了不同的评审方，因此，在得到了风险事件对应的风险类型后，可根据风险类型选择匹配该风险类型的评审方。在本实施例中，每个评审方在风险管理服务器中都对应一个用户标识，该用户标识用于唯一标识评审方的身份，可以是姓名、社交账号、身份证号、手机号等，当某个风险类型的评审方确定好后，可建立起该评审方对应的用户标识与风险类型之间的映射关系，风险管理服务器在得到风险事件的风险类型后可根据该映射关系查找到其对应的用户标识，然后将该风险事件的上报数据发送至该用户标识对应的终端。
进一步，该用户标识对应的评审方可通过终端对风险事件对应的上报数据进行评审，评审可以是直接对上报数据给出一个整体的结论，结论可以是评审通过或评审不通过，当评审不通过时，可以给出改进意见；也可以是对上报数据的每一项分别进行评审，如分别对事件起因、事件经过、事件影响分别进行评审，并给出评审结论。
步骤S212，接收各个评审方对应的终端发送的评审数据，根据评审数据判断各个风险事件是否通过评审，当根据评审数据判断出任意一个风险事件通过评审时，根据评审通过的上报数据生成报告文件。
具体地，风险管理服务器接收评审方对应的终端发送的评审数据后，解析该评审数据，获取评审数据中的评审结论，根据评审结论判断风险事件是否审核通过。
在一些实施例中，当获取到的评审结论中只有一个整体的评审结论时，可直接根据该评审结论判断风险事件的评审是否通过；在另一个实施例中，当获取到的评审结论中有多个评审结论，即评审结论为分别针对上报数据中单独的一项时，判断这些评审结论中是否包含有未通过的评审结论，若包含，则判定该风险事件评审未通过。
进一步，当风险管理服务器判断出任意一个风险事件对应的上报数据通过评审时，根据该通过评审的上报数据生成风险事件对应的报告文件。报告文件中至少包含风险事件的名称、上报数据及评审结论等数据。
进一步，风险管理服务器将报告文件发送至事件调查方对应的终端。具体地，可以是在接收事件调查方对应的终端所发送的报告文件获取请求时，将报告文件获取请求对应的报告文件单独发送至事件调查方对应的终端；也可以是在报告文件的数量超过设定的阈值，如5个时，将当前已经生成的所有报告文件一起发送事件调查方对应的终端；还可以是每隔一定的时间，例如2天，查询一次当前未发送的报告文件，然后将查找到的所有未发送的报告文件发送至事件调查方对应的终端。
上述风险管理数据处理方法，通过风险管理服务器获取风险事件，对风险事件生成上报任务，然后分配至对应的目标接口方，并接收目标接口方通过其对应的终端发送的上报数据，将上报数据发送至对应的评审方，根据评审方对应的终端返回的评审数据判断风险事件评审是否通过，并在通过时，生成报告文件，实现了风险事件的自动化管理，提高了风险管理效率。
在一些实施例中，获取风险事件集合的步骤包括：获取风险事件对应的源数据；根据源数据创建ETL(Extract-Transform-Load，抽取/转换/加载)任务，触发ETL工具运行ETL任务；根据ETL任务对应的运行结果得到风险事件集合。
具体地，风险管理服务器从第三方系统服务器如运维系统服务器获取风险事件对应的源数据，所述源数据包括但不限于风险事件对应的用户标识、风险事件的类型、风险事件的简要描述如风险事件的起因、影响等，以及风险事件的预估损失等等。源数据的格式例如可以是数据源MySQL、数据源Oracle、数据源PostgreSQL、数据源DB2和数据源SQLServer等多种数据源中的一种或多种。
在一些实施例中，风险管理服务器根据源数据创建ETL任务后，分别根据源数据的数据类型，选择对应的ETL工具运行ETL任务，根据运行结果得到风险事件集合。
在另一些实施例中，风险管理服务器可以首先对源数据进行统一的格式转换，如统一转换为逗号分隔值CSV格式的源数据，然后根据转换后的源数据创建ETL任务，选择CSV格式对应的ETL工具运行ETL任务，根据运行结果得到风险事件集合。
在本实施例中，借助ETL工具可以更好地整合获取到的源数据，快速地获取到风险事件集合。
在一些实施例中，如图3所示，根据用户标识分别从各个风险事件对应的接口方集合中选取各个事件上报任务对应的目标接口方的步骤包括：
步骤S206A，获取接口方集合中各个接口方对应的长连接状态，将长连接状态为保持状态的接口方作为备选接口方，得到备选接口方集合。
具体地，为保证事件上报任务能及时分配至对应的接口方，接口方对应的终端与风险管理服务器之间采用长连接进行通信。因此，在选取目标接口方时，可首先判断接口方集 合中各个接口方对应的长连接是否为长连接状态，将长连接状态为保持状态的接口方作为备选接口方，最终得到目标接口方集合。
具体地，判断接口方集合中各个接口方对应的长连接是否为长连接状态可通过向接口方对应的终端发送心跳检测数据包，当在预设时间内，接收到接口方对应的终端发送的心跳响应包时，判断其为长连接状态，否则，可以判定该接口方对应的长连接已断开，或者，也可以在超过预设时间没有接收到心跳响应包时再次发送心跳检测包，并再次判断是否在预设时间内接收到心跳响应包，从而可以在接口方对应的终端发生短暂故障时出现错误的判断，从而尽可能多的选择到长连接为在线状态的备选接口方。
步骤S206B，获取备选接口方集合中各个备选接口方对应的任务优先级。
步骤S206C，从备选接口方集合中选取任务优先级最高的备选接口方作为目标接口方。
具体地，对于接口方集合中各个接口方均设置有任务优先级，任务优先级可根据接口方的经验、职位等进行设定，获取到各个备选接口方对应的任务优先级后，可按照任务优先级对各个备选接口方进行排序，根据排序结果选择优先级最高的备选接口方作为目标接口方。
在本实例中，通过接口方的长连接状态及任务优先级来选择目标接口方，可以保证上报任务及时地分配至最合适的接口方，从而提高任务的处理效率和处理质量。
在一些实施例中，预设的分类模型可以通过以下方式训练得到：获取历史上报任务对应的上报数据及对应的风险类别；根据上报数据对应的起因数据、影响数据及风险类别得到训练集；根据训练集进行模型得到分类模型。
其中，起因数据包括程序错误、软件缺陷、操作失误、硬件故障、容量不足、网络漏洞等数据中的一种或多种，影响数据包括网络延迟、通讯中断、系统瘫痪、数据丢失等数据中的一种或多种。在本实施例中，获取到历史上报任务对应的上报数据及对应的风险类别后，将这些数据映射到特征向量空间，得到每一个历史上报任务对应的输入特征向量及期望的输出特征向量，根据输入特征向量及期望的输出特征向量构建训练样本进行模型训练，在进行模型训练时，可以采用有监督的模型训练方式，例如逻辑回归模型、SVM(Support Vector Machine,支持向量机)以及贝叶斯模型等。
以SVM为例，可以采用随机梯度算法进行模型训练，在梯度下降过程中需要使得代价函数J(θ)最小，在一些实施例中，代价函数可以采用以下公式表示：
Figure PCTCN2018104759-appb-000001
m表示训练集中样本特征的个数，x (i)为输入特征向量，y (i)表示期望的输出特征向量，h θ(x (i))表示每次训练的实际输出特征向量，其中，
Figure PCTCN2018104759-appb-000002
其中，
Figure PCTCN2018104759-appb-000003
即θ Tx等于特征与参数的乘积的和，其中，x (i)为输入特征向量。
在一些实施例中，上述方法还包括：当根据评审数据判断出存在评审未通过的上报数据时，根据评审未通过的上报数据及其对应的评审数据生成修订任务，将修订任务发送至目标接口方对应的终端。
具体地，修订任务中包含待修订的风险事件对应的上报数据及评审数据，用于指示目标接口方按照评审数据对上报数据进行修订。进一步，目标接口方完成修订任务后，通过其对应的终端将修订后对应的上报数据再次发送至风险管理服务器，风险管理服务器再次将修订后的上报数据发送至评审方对应的终端，并在接受到评审方对应的终端返回的评审数据后，再次判断风险事件是否通过评审，若通过，则进入上述步骤S214，否则重复本实施例中的步骤直至风险事件通过评审。
在一些实施例中，上述方法还包括：对风险事件集合中各个风险事件生成跟踪任务，得到跟踪任务集合；将跟踪任务集合中各个跟踪任务分配至目标接口方对应的终端；接收目标接口方对应的终端发送的反馈数据，将反馈数据发送至事件调查方对应的终端。
其中，反馈数据指的是针对风险事件的改进措施相关数据，包括每个改进措施的实施状态、进展描述以及产出物描述等信息，其中，实施状态包括未实施、正在实施、已完成实施，进展描述指的是实施状态对应的当前进展，产出物描述指的当前进展对应的成果描述。
在本实施例中，风险管理服务器可以对各个事件上报任务进行状态标记，对于未接收到上报数据的事件上报任务标记为未完成，对于已接收到上报数据且未通过评审的事件上报任务标记为完成中，对于已通过评审的事件上报任务标记为已完成。风险管理服务器可以每隔预设的时间，如每隔一天，从数据库中查询各个事件上报任务对应的当前完成状态，筛选出所有当前状态为未完成的事件上报任务，分别计算每个未完成的事件上报任务的创建时间与当前时间的时间差值，判断时间差值是否大于预设阈值，其中，预设阈值可以根据业务需求进行设定和更改。如，某个时间上报任务对应的创建时间为“2018年4月3日”，当前时间为“2018年4月7日”，预设阈值为2，则可判断出时间差值4大于预设阈值2。
进一步，当某个事件上报任务对应的时间差值大于预设阈值时，对该事件上报任务生成提醒信息，将提醒信息发送至所该事件上报任务对应的目标接口方对应的终端。
在本实施例中，通过对时间差值超过预设阈值的事件上报任务生成提醒信息发送至目标接口方对应的终端，可实现对目标接口方的自动提醒，从而提高任务的完成失效。
应该理解的是，虽然图2-3的流程图中的各个步骤按照箭头的指示依次显示，但是这 些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明，这些步骤的执行并没有严格的顺序限制，这些步骤可以以其它的顺序执行。而且，图2-3中的至少一部分步骤可以包括多个子步骤或者多个阶段，这些子步骤或者阶段并不必然是在同一时刻执行完成，而是可以在不同的时刻执行，这些子步骤或者阶段的执行顺序也不必然是依次进行，而是可以与其它步骤或者其它步骤的子步骤或者阶段的至少一部分轮流或者交替地执行。
在一些实施例中，如图4所示，提供了一种风险管理数据处理装置400，该装置包括：
风险事件集合获取模块402，用于获取风险事件集合，风险事件集合中各个风险事件携带用户标识；
事件上报任务创建模块404，用于分别对各个风险事件创建对应的事件上报任务，得到事件上报任务集合；
目标接口方选取模块406，用于根据用户标识分别从各个风险事件对应的接口方集合中选取各个事件上报任务对应的目标接口方，将各个事件上报任务分别发送至其目标接口方对应的终端；
风险类型获取模块408，用于接收目标接口方对应的终端发送的上报数据，上报数据包括各个风险事件的起因数据及影响数据，根据起因数据及影响数据采用预设的分类模型得到各个风险事件对应的风险类型；
上报数据发送模块410，用于根据风险类型选取各个风险事件对应的评审方，将上报数据发送至各个评审方对应的终端；
报告文件生成模块412，用于接收各个评审方对应的终端发送的评审数据，当根据评审数据判断出任意一个风险事件对应的评审数据通过评审时，根据评审通过的上报数据生成报告文件。
在一些实施例中，风险事件集合获取模块402用于获取风险事件对应的源数据，根据源数据创建ETL任务，触发ETL工具运行ETL任务，根据ETL任务对应的运行结果得到风险事件集合。
在一些实施例中，目标接口方选取模块406用于获取接口方集合中各个接口方对应的长连接状态，将长连接状态为保持状态的接口方作为备选接口方，得到备选接口方集合，获取备选接口方集合中各个备选接口方对应的任务优先级，从备选接口方集合中选取任务优先级最高的备选接口方作为目标接口方。
在一些实施例中，上述装置还包括：分类模型训练模块，用于获取历史上报任务对应的上报数据及对应的风险类别；根据上报数据对应的起因数据、影响数据及风险类别得到训练集；根据训练集进行模型得到分类模型。
在一些实施例中，上述装置还包括：修订任务生成及发送模块，用于当根据评审数据判断出存在评审未通过的上报数据时，根据评审未通过的上报数据及其对应的评审数据生 成修订任务，将修订任务发送至目标接口方对应的终端。
在一些实施例中，上述装置还包括：风险事件跟踪模块，用于对风险事件集合中各个风险事件生成跟踪任务，得到跟踪任务集合；将跟踪任务集合中各个跟踪任务分配至目标接口方对应的终端；接收目标接口方对应的终端发送的反馈数据，将反馈数据发送至事件调查方对应的终端。
在一些实施例中，上述装置还包括：任务提醒模块，用于获取各个事件上报任务对应的当前状态，筛选出所有当前状态为未完成的事件上报任务，分别计算每个当前状态为未完成的事件上报任务的创建时间与当前时间的时间差值，当时间差值大于预设阈值时，生成提醒信息，将提醒信息发送至目标接口方对应的终端。
关于风险管理数据处理装置的具体限定可以参见上文中对于风险管理数据处理方法的限定，在此不再赘述。上述风险管理数据处理装置中的各个模块可全部或部分通过软件、硬件及其组合来实现。上述各模块可以硬件形式内嵌于或独立于计算机设备中的处理器中，也可以以软件形式存储于计算机设备中的存储器中，以便于处理器调用执行以上各个模块对应的操作。
在一些实施例中，提供了一种计算机设备，该计算机设备可以是服务器，其内部结构图可以如图5所示。该计算机设备包括通过系统总线连接的处理器、存储器、网络接口和数据库。其中，该计算机设备的处理器用于提供计算和控制能力。该计算机设备的存储器包括非易失性存储介质、内存储器。该非易失性存储介质存储有操作系统、计算机可读指令和数据库。该内存储器为非易失性存储介质中的操作系统和计算机可读指令的运行提供环境。该计算机设备的数据库用于存储风险管理数据处理过程中的各种数据，如事件上报任务的当前状态数据、接口方集合中各个接口方信息、长连接状态信息等。该计算机设备的网络接口用于与外部的终端通过网络连接通信。该计算机可读指令被处理器执行时以实现一种风险管理数据处理方法。
本领域技术人员可以理解，图5中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的计算机设备的限定，具体的计算机设备可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。
在一些实施例中，提供了一种计算机设备，包括存储器和处理器，该存储器存储有计算机可读指令，该处理器执行计算机可读指令时实现以下步骤：获取风险事件集合，风险事件集合中各个风险事件携带用户标识；分别对各个风险事件创建对应的事件上报任务，得到事件上报任务集合；根据用户标识分别从各个风险事件对应的接口方集合中选取各个事件上报任务对应的目标接口方，将各个事件上报任务分别发送至其目标接口方对应的终端；接收目标接口方对应的终端发送的上报数据，上报数据包括各个风险事件的起因数据及影响数据，根据起因数据及影响数据采用预设的分类模型得到各个风险事件对应的风险 类型；根据风险类型选取各个风险事件对应的评审方，将上报数据发送至各个评审方对应的终端；接收各个评审方对应的终端发送的评审数据，当根据评审数据判断出任意一个风险事件对应的上报数据通过评审时，根据评审通过的上报数据生成报告文件。
在一些实施例中，获取风险事件集合的步骤包括：获取风险事件对应的源数据；根据源数据创建ETL任务，触发ETL工具运行ETL任务；根据ETL任务对应的运行结果得到风险事件集合。
在一些实施例中，根据用户标识分别从各个风险事件对应的接口方集合中选取各个事件上报任务对应的目标接口方的步骤包括：获取接口方集合中各个接口方对应的长连接状态，将长连接状态为保持状态的接口方作为备选接口方，得到备选接口方集合；获取备选接口方集合中各个备选接口方对应的任务优先级；从备选接口方集合中选取任务优先级最高的备选接口方作为目标接口方。
在一些实施例中，处理器执行计算机可读指令时还实现以下步骤：预设的分类模型可以通过以下方式训练得到：获取历史上报任务对应的上报数据及对应的风险类别；根据上报数据对应的起因数据、影响数据及风险类别得到训练集；根据训练集进行模型得到分类模型。
在一些实施例中，处理器执行计算机可读指令时还实现以下步骤：当根据评审数据判断出存在评审未通过的上报数据时，根据评审未通过的上报数据及其对应的评审数据生成修订任务，将修订任务发送至目标接口方对应的终端。
在一些实施例中，处理器执行计算机可读指令时还实现以下步骤：对风险事件集合中各个风险事件生成跟踪任务，得到跟踪任务集合；将跟踪任务集合中各个跟踪任务分配至目标接口方对应的终端；接收目标接口方对应的终端发送的反馈数据，将反馈数据发送至事件调查方对应的终端。
在一些实施例中，处理器执行计算机可读指令时还实现以下步骤：获取各个事件上报任务对应的当前状态，筛选出所有当前状态为未完成的事件上报任务；分别计算每个当前状态为未完成的事件上报任务的创建时间与当前时间的时间差值，当时间差值大于预设阈值时，生成提醒信息，将提醒信息发送至目标接口方对应的终端。
在一些实施例中，提供了一种计算机可读存储介质，其上存储有计算机可读指令，计算机可读指令被处理器执行时实现以下步骤：获取风险事件集合，风险事件集合中各个风险事件携带用户标识；分别对各个风险事件创建对应的事件上报任务，得到事件上报任务集合；根据用户标识分别从各个风险事件对应的接口方集合中选取各个事件上报任务对应的目标接口方，将各个事件上报任务分别发送至其目标接口方对应的终端；接收目标接口方对应的终端发送的上报数据，上报数据包括各个风险事件的起因数据及影响数据，根据起因数据及影响数据采用预设的分类模型得到各个风险事件对应的风险类型；根据风险类型选取各个风险事件对应的评审方，将上报数据发送至各个评审方对应的终端；接收各个 评审方对应的终端发送的评审数据，当根据评审数据判断出任意一个风险事件对应的上报数据通过评审时，根据评审通过的上报数据生成报告文件。
在一些实施例中，获取风险事件集合的步骤包括：获取风险事件对应的源数据；根据源数据创建ETL任务，触发ETL工具运行ETL任务；根据ETL任务对应的运行结果得到风险事件集合。
在一些实施例中，根据用户标识分别从各个风险事件对应的接口方集合中选取各个事件上报任务对应的目标接口方的步骤包括：获取接口方集合中各个接口方对应的长连接状态，将长连接状态为保持状态的接口方作为备选接口方，得到备选接口方集合；获取备选接口方集合中各个备选接口方对应的任务优先级；从备选接口方集合中选取任务优先级最高的备选接口方作为目标接口方。
在一些实施例中，计算机可读指令被处理器执行时还实现以下步骤：预设的分类模型可以通过以下方式训练得到：获取历史上报任务对应的上报数据及对应的风险类别；根据上报数据对应的起因数据、影响数据及风险类别得到训练集；根据训练集进行模型得到分类模型。
在一些实施例中，计算机可读指令被处理器执行时还实现以下步骤：当根据评审数据判断出存在评审未通过的上报数据时，根据评审未通过的上报数据及其对应的评审数据生成修订任务，将修订任务发送至目标接口方对应的终端。
在一些实施例中，计算机可读指令被处理器执行时还实现以下步骤：对风险事件集合中各个风险事件生成跟踪任务，得到跟踪任务集合；将跟踪任务集合中各个跟踪任务分配至目标接口方对应的终端；接收目标接口方对应的终端发送的反馈数据，将反馈数据发送至事件调查方对应的终端。
在一些实施例中，计算机可读指令被处理器执行时还实现以下步骤：获取各个事件上报任务对应的当前状态，筛选出所有当前状态为未完成的事件上报任务；分别计算每个当前状态为未完成的事件上报任务的创建时间与当前时间的时间差值，当时间差值大于预设阈值时，生成提醒信息，将提醒信息发送至目标接口方对应的终端。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机可读指令来指令相关的硬件来完成，所述的计算机可读指令可存储于一非易失性计算机可读取存储介质中，该计算机可读指令在执行时，可包括如上述各方法的实施例的流程。其中，本申请所提供的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用，均可包括非易失性和/或易失性存储器。非易失性存储器可包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(EPROM)、电可擦除可编程ROM(EEPROM)或闪存。易失性存储器可包括随机存取存储器(RAM)或者外部高速缓冲存储器。作为说明而非局限，RAM以多种形式可得，诸如静态RAM(SRAM)、动态RAM(DRAM)、同步DRAM(SDRAM)、双数据率SDRAM(DDRSDRAM)、增强型SDRAM(ESDRAM)、同步链路(Synchlink)DRAM(SLDRAM)、存储器总线(Rambus)直接RAM(RDRAM)、直接存储器总线动态RAM(DRDRAM)、 以及存储器总线动态RAM(RDRAM)等。
以上实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。
以上所述实施例仅表达了本申请的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对发明专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本申请构思的前提下，还可以做出若干变形和改进，这些都属于本申请的保护范围。因此，本申请专利的保护范围应以所附权利要求为准。

Claims (20)

  1. 一种风险管理数据处理方法，包括：
    获取风险事件集合，所述风险事件集合中各个风险事件携带用户标识；
    分别对各个所述风险事件创建对应的事件上报任务，得到事件上报任务集合；
    根据所述用户标识分别从各个所述风险事件对应的接口方集合中，确定各个所述事件上报任务对应的目标接口方，将各个所述事件上报任务分别发送至其目标接口方对应的终端；
    接收所述目标接口方对应的终端发送的上报数据，所述上报数据包括各个所述风险事件的起因数据及影响数据，根据所述起因数据及所述影响数据采用预设的分类模型得到各个所述风险事件对应的风险类型；
    根据所述风险类型选取各个所述风险事件对应的评审方，将所述上报数据发送至各个所述评审方对应的终端；及
    接收各个评审方对应的终端发送的评审数据，当根据所述评审数据判断出任意一个所述风险事件对应的上报数据通过评审时，根据评审通过的上报数据生成报告文件。
  2. 根据权利要求1所述的方法，其特征在于，所述获取风险事件集合，包括：
    获取风险事件对应的源数据；
    根据所述源数据创建ETL任务，触发ETL工具运行所述ETL任务；及
    根据所述ETL任务对应的运行结果得到风险事件集合。
  3. 根据权利要求1所述的方法，其特征在于，所述根据所述用户标识分别从各个风险事件对应的接口方集合中选取各个事件上报任务对应的目标接口方，包括：
    获取接口方集合中各个接口方对应的长连接状态，将所述长连接状态为保持状态的接口方作为备选接口方，得到备选接口方集合；
    获取备选接口方集合中各个备选接口方对应的任务优先级；及
    从所述备选接口方集合中选取任务优先级最高的备选接口方作为目标接口方。
  4. 根据权利要求1所述的方法，其特征在于，所述预设的分类模型的生成步骤包括：
    获取历史上报任务对应的上报数据及对应的风险类别；
    根据所述上报数据对应的起因数据、影响数据及风险类别得到训练集；及
    根据所述训练集进行模型得到分类模型。
  5. 根据权利要求1所述的方法，其特征在于，还包括：
    当根据所述评审数据判断出存在评审未通过的上报数据时，根据评审未通过的上报数据及其对应的评审数据生成修订任务，及将所述修订任务发送至所述目标接口方对应的终端。
  6. 根据权利要求1所述的方法，其特征在于，还包括：
    对风险事件集合中各个风险事件生成跟踪任务，得到跟踪任务集合；
    将所述跟踪任务集合中各个跟踪任务分配至所述目标接口方对应的终端；及
    接收所述目标接口方对应的终端发送的反馈数据，将所述反馈数据发送至事件调查方对应的终端。
  7. 根据权利要求1至6任意一项所述的方法，其特征在于，还包括：
    获取各个所述事件上报任务对应的当前状态，筛选出所有当前状态为未完成的事件上报任务；及
    分别计算每个当前状态为未完成的事件上报任务的创建时间与当前时间的时间差值，当所述时间差值大于预设阈值时，生成提醒信息，将所述提醒信息发送至所述目标接口方对应的终端。
  8. 一种风险管理数据处理装置，包括：
    风险事件集合获取模块，用于获取风险事件集合，所述风险事件集合中各个风险事件携带用户标识；
    事件上报任务创建模块，用于分别对所述各个风险事件创建对应的事件上报任务，得到事件上报任务集合；
    目标接口方选取模块，用于根据所述用户标识分别从各个风险事件对应的接口方集合中选取各个事件上报任务对应的目标接口方，将各个事件上报任务分别发送至其目标接口方对应的终端；
    风险类型获取模块，用于接收所述目标接口方对应的终端发送的上报数据，所述上报数据包括各个风险事件的起因数据及影响数据，根据所述起因数据及影响数据采用预设的分类模型得到各个风险事件对应的风险类型；
    上报数据发送模块，用于根据所述风险类型选取各个风险事件对应的评审方，将所述上报数据发送至各个评审方对应的终端；及
    报告文件生成模块，用于接收各个评审方对应的终端发送的评审数据，当根据所述评审数据判断出任意一个风险事件对应的评审数据通过评审时，根据评审通过的上报数据生成报告文件。
  9. 根据权利要求8所述的装置，其特征在于，所述风险事件集合获取模块用于获取风险事件对应的源数据，根据源数据创建ETL任务，触发ETL工具运行ETL任务，及根据ETL任务对应的运行结果得到风险事件集合。
  10. 根据权利要求8所述的装置，其特征在于，目标接口方选取模块用于获取接口方集合中各个接口方对应的长连接状态，将长连接状态为保持状态的接口方作为备选接口方，得到备选接口方集合，获取备选接口方集合中各个备选接口方对应的任务优先级，及从备选接口方集合中选取任务优先级最高的备选接口方作为目标接口方。
  11. 一种计算机设备，包括存储器及一个或多个处理器，所述存储器中储存有计算机可读指令，所述计算机可读指令被所述一个或多个处理器执行时，使得所述一个或多个处理器执行以下步骤：
    获取风险事件集合，所述风险事件集合中各个风险事件携带用户标识；
    分别对各个所述风险事件创建对应的事件上报任务，得到事件上报任务集合；
    根据所述用户标识分别从各个所述风险事件对应的接口方集合中，确定各个所述事件上报任务对应的目标接口方，将各个所述事件上报任务分别发送至其目标接口方对应的终端；
    接收所述目标接口方对应的终端发送的上报数据，所述上报数据包括各个所述风险事件的起因数据及影响数据，根据所述起因数据及所述影响数据采用预设的分类模型得到各个所述风险事件对应的风险类型；
    根据所述风险类型选取各个所述风险事件对应的评审方，将所述上报数据发送至各个所述评审方对应的终端；及
    接收各个评审方对应的终端发送的评审数据，当根据所述评审数据判断出任意一个所述风险事件对应的上报数据通过评审时，根据评审通过的上报数据生成报告文件。
  12. 根据权利要求11所述的计算机设备，其特征在于，所述处理器执行所述计算机可读指令时还执行以下步骤：
    获取风险事件对应的源数据；
    根据所述源数据创建ETL任务，触发ETL工具运行所述ETL任务；及
    根据所述ETL任务对应的运行结果得到风险事件集合。
  13. 根据权利要求11所述的计算机设备，其特征在于，所述处理器执行所述计算机可读指令时还执行以下步骤：
    获取接口方集合中各个接口方对应的长连接状态，将所述长连接状态为保持状态的接口方作为备选接口方，得到备选接口方集合；
    获取备选接口方集合中各个备选接口方对应的任务优先级；及
    从所述备选接口方集合中选取任务优先级最高的备选接口方作为目标接口方。
  14. 根据权利要求11所述的计算机设备，其特征在于，所述处理器执行所述计算机可读指令时还执行以下步骤：
    获取历史上报任务对应的上报数据及对应的风险类别；
    根据所述上报数据对应的起因数据、影响数据及风险类别得到训练集；及
    根据所述训练集进行模型得到分类模型。
  15. 根据权利要求11所述的计算机设备，其特征在于，所述处理器执行所述计算机可读指令时还执行以下步骤：
    当根据所述评审数据判断出存在评审未通过的上报数据时，根据评审未通过的上报数据及其对应的评审数据生成修订任务，及将所述修订任务发送至所述目标接口方对应的终端。
  16. 一个或多个存储有计算机可读指令的非易失性计算机可读存储介质，所述计算机可读指令被一个或多个处理器执行时，使得所述一个或多个处理器执行以下步骤：
    获取风险事件集合，所述风险事件集合中各个风险事件携带用户标识；
    分别对各个所述风险事件创建对应的事件上报任务，得到事件上报任务集合；
    根据所述用户标识分别从各个所述风险事件对应的接口方集合中，确定各个所述事件上报任务对应的目标接口方，将各个所述事件上报任务分别发送至其目标接口方对应的终端；
    接收所述目标接口方对应的终端发送的上报数据，所述上报数据包括各个所述风险事件的起因数据及影响数据，根据所述起因数据及所述影响数据采用预设的分类模型得到各个所述风险事件对应的风险类型；
    根据所述风险类型选取各个所述风险事件对应的评审方，将所述上报数据发送至各个所述评审方对应的终端；及
    接收各个评审方对应的终端发送的评审数据，当根据所述评审数据判断出任意一个所述风险事件对应的上报数据通过评审时，根据评审通过的上报数据生成报告文件。
  17. 根据权利要求16所述的存储介质，其特征在于，所述计算机可读指令被所述处理器执行时还执行以下步骤：
    获取风险事件对应的源数据；
    根据所述源数据创建ETL任务，触发ETL工具运行所述ETL任务；及
    根据所述ETL任务对应的运行结果得到风险事件集合。
  18. 根据权利要求16所述的存储介质，其特征在于，所述计算机可读指令被所述处理器执行时还执行以下步骤：
    获取接口方集合中各个接口方对应的长连接状态，将所述长连接状态为保持状态的接口方作为备选接口方，得到备选接口方集合；
    获取备选接口方集合中各个备选接口方对应的任务优先级；及
    从所述备选接口方集合中选取任务优先级最高的备选接口方作为目标接口方。
  19. 根据权利要求16所述的存储介质，其特征在于，所述计算机可读指令被所述处理器执行时还执行以下步骤：
    获取历史上报任务对应的上报数据及对应的风险类别；
    根据所述上报数据对应的起因数据、影响数据及风险类别得到训练集；及
    根据所述训练集进行模型得到分类模型。
  20. 根据权利要求16所述的存储介质，其特征在于，所述计算机可读指令被所述处理器执行时还执行以下步骤：
    当根据所述评审数据判断出存在评审未通过的上报数据时，根据评审未通过的上报数据及其对应的评审数据生成修订任务，及将所述修订任务发送至所述目标接口方对应的终端。
PCT/CN2018/104759 2018-06-07 2018-09-10 风险管理数据处理方法、装置、计算机设备和存储介质 Ceased WO2019232964A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810582243.9 2018-06-07
CN201810582243.9A CN108874968B (zh) 2018-06-07 2018-06-07 风险管理数据处理方法、装置、计算机设备和存储介质

Publications (1)

Publication Number Publication Date
WO2019232964A1 true WO2019232964A1 (zh) 2019-12-12

Family

ID=64337371

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/104759 Ceased WO2019232964A1 (zh) 2018-06-07 2018-09-10 风险管理数据处理方法、装置、计算机设备和存储介质

Country Status (2)

Country Link
CN (1) CN108874968B (zh)
WO (1) WO2019232964A1 (zh)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112365114A (zh) * 2020-08-24 2021-02-12 南方电网数字电网研究院有限公司 一种基于运维管理平台的电力作业计划管理方法
CN112861496A (zh) * 2021-03-22 2021-05-28 平安商业保理有限公司 报表生成显示方法、装置、计算机设备和可读存储介质
CN113342846A (zh) * 2021-06-29 2021-09-03 福州外语外贸学院 基于大数据的预警把控提醒方法、装置及计算机设备
CN113850520A (zh) * 2021-09-29 2021-12-28 天元大数据信用管理有限公司 一种区域风险防控协同联动方法、装置、设备及介质
CN116506423A (zh) * 2023-04-26 2023-07-28 中国合格评定国家认可中心 一种信息安全数据报送方法及装置
CN117435787A (zh) * 2023-07-10 2024-01-23 中国工商银行股份有限公司 信息展示方法及装置、电子设备和计算机可读存储介质
CN119721719A (zh) * 2025-02-26 2025-03-28 陕西飞天乳业有限公司 一种羊乳制品冷链物流系统风险评价方法

Families Citing this family (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109756363A (zh) * 2018-11-27 2019-05-14 平安科技（深圳）有限公司 数据传输稳定性控制方法、装置、计算机设备及存储介质
CN110033227A (zh) * 2018-11-28 2019-07-19 阿里巴巴集团控股有限公司 数据处理方法、装置、计算设备及存储介质
CN109726987B (zh) * 2018-12-21 2024-05-28 平安科技（深圳）有限公司 事件汇报方法、装置、设备及计算机可读存储介质
CN109657063A (zh) * 2018-12-24 2019-04-19 恒瑞通（福建）信息技术有限公司 一种海量环保人工上报事件数据的处理方法及存储介质
CN109727176A (zh) * 2019-01-03 2019-05-07 深圳壹账通智能科技有限公司 企业监管处理方法、装置、计算机设备和存储介质
CN110084606B (zh) * 2019-03-20 2023-10-10 平安直通咨询有限公司上海分公司 风险控制方法、装置、计算机设备和存储介质
CN112307480B (zh) * 2019-07-24 2023-09-05 中移互联网有限公司 应用软件所在设备的风险分析方法及装置
CN110956445B (zh) * 2019-11-18 2023-03-10 支付宝(杭州)信息技术有限公司 用于生成风险文件的方法和装置
CN111046393B (zh) * 2019-12-14 2022-08-02 深圳市优必选科技股份有限公司 漏洞信息上传方法、装置、终端设备及存储介质
CN112884297A (zh) * 2021-01-29 2021-06-01 绿盟科技集团股份有限公司 基于钓鱼邮件的风险评分确定方法、装置、设备和介质
CN112949262B (zh) * 2021-02-09 2024-05-28 中广核工程有限公司 评审单处理方法、装置、计算机设备和存储介质
CN113705976A (zh) * 2021-08-02 2021-11-26 浪潮天元通信信息系统有限公司 基于业务数据的风险控制方法及系统
CN114240097B (zh) * 2021-12-02 2024-07-12 支付宝(杭州)信息技术有限公司 一种风险评估的方法及装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101833621A (zh) * 2010-04-27 2010-09-15 广州广电运通金融电子股份有限公司 终端安全审计方法及系统
US20130097459A1 (en) * 2011-10-14 2013-04-18 Honeywell International Inc. Methods and systems for distributed diagnostic reasoning
CN105302120A (zh) * 2015-11-19 2016-02-03 广州云湾信息技术有限公司 智能设备的远程服务装置、系统和方法
CN106341248A (zh) * 2015-07-09 2017-01-18 阿里巴巴集团控股有限公司 一种基于云平台的故障处理方法和装置
CN107832429A (zh) * 2017-11-14 2018-03-23 广州供电局有限公司 审计数据处理方法和系统

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140019194A1 (en) * 2012-07-12 2014-01-16 Bank Of America Predictive Key Risk Indicator Identification Process Using Quantitative Methods
CN106156343B (zh) * 2016-07-21 2020-02-18 中国地质大学（武汉） 一种深基坑施工方案安全评审知识库以及自动安全评审方法
CN107644340A (zh) * 2016-07-22 2018-01-30 阿里巴巴集团控股有限公司 风险识别方法、客户端设备及风险识别系统
CN107845033A (zh) * 2017-11-08 2018-03-27 上海壹账通金融科技有限公司 风控报告生成方法、装置、设备及计算机可读存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101833621A (zh) * 2010-04-27 2010-09-15 广州广电运通金融电子股份有限公司 终端安全审计方法及系统
US20130097459A1 (en) * 2011-10-14 2013-04-18 Honeywell International Inc. Methods and systems for distributed diagnostic reasoning
CN106341248A (zh) * 2015-07-09 2017-01-18 阿里巴巴集团控股有限公司 一种基于云平台的故障处理方法和装置
CN105302120A (zh) * 2015-11-19 2016-02-03 广州云湾信息技术有限公司 智能设备的远程服务装置、系统和方法
CN107832429A (zh) * 2017-11-14 2018-03-23 广州供电局有限公司 审计数据处理方法和系统

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112365114A (zh) * 2020-08-24 2021-02-12 南方电网数字电网研究院有限公司 一种基于运维管理平台的电力作业计划管理方法
CN112861496A (zh) * 2021-03-22 2021-05-28 平安商业保理有限公司 报表生成显示方法、装置、计算机设备和可读存储介质
CN113342846A (zh) * 2021-06-29 2021-09-03 福州外语外贸学院 基于大数据的预警把控提醒方法、装置及计算机设备
CN113342846B (zh) * 2021-06-29 2024-03-19 福州外语外贸学院 基于大数据的预警把控提醒方法、装置及计算机设备
CN113850520A (zh) * 2021-09-29 2021-12-28 天元大数据信用管理有限公司 一种区域风险防控协同联动方法、装置、设备及介质
CN116506423A (zh) * 2023-04-26 2023-07-28 中国合格评定国家认可中心 一种信息安全数据报送方法及装置
CN117435787A (zh) * 2023-07-10 2024-01-23 中国工商银行股份有限公司 信息展示方法及装置、电子设备和计算机可读存储介质
CN119721719A (zh) * 2025-02-26 2025-03-28 陕西飞天乳业有限公司 一种羊乳制品冷链物流系统风险评价方法

Also Published As

Publication number Publication date
CN108874968A (zh) 2018-11-23
CN108874968B (zh) 2023-04-18

Similar Documents

Publication Publication Date Title
WO2019232964A1 (zh) 风险管理数据处理方法、装置、计算机设备和存储介质
CN109726983B (zh) 审批任务分配方法、装置、计算机设备和存储介质
WO2021128679A1 (zh) 基于数据决策的测试数据生成方法、装置、计算机设备
WO2021098281A1 (zh) 项目基线数据生成方法、装置、计算机设备和计算机可读存储介质
US10915508B2 (en) Data linking
US11250166B2 (en) Fingerprint-based configuration typing and classification
CN110730101B (zh) 资源分配方法、终端、装置及可读存储介质
CN111027295A (zh) 数据处理方法、装置、计算机设备和存储介质
CN110490594A (zh) 业务数据处理方法、装置、计算机设备和存储介质
WO2020073727A1 (zh) 风险预测方法、装置、计算机设备和存储介质
CN112288400A (zh) 多系统数据交互方法、装置、计算机设备及存储介质
WO2021114613A1 (zh) 基于人工智能的故障节点识别方法、装置、设备和介质
US20240394629A1 (en) Recommendation system and operation method thereof
CN110765169A (zh) 信息推荐方法、装置、计算机设备及存储介质
CN109409780B (zh) 变更处理方法、装置、计算机设备和存储介质
CN113326523A (zh) 一种隐私计算方法、装置及电子设备
CN115185923B (zh) 一种气象观测元数据管理的方法、系统和智能终端
CN105786941B (zh) 一种信息挖掘方法和装置
CN112686010B (zh) 资源数据报表生成方法、装置、计算机设备和存储介质
CN108880884A (zh) 运维告警上报方法、装置、计算机设备和存储介质
CN111784402A (zh) 基于多通路的下单率预测方法、设备及可读存储介质
WO2019085448A1 (zh) 保单问题件处理方法、装置、计算机设备及可读存储介质
CN113779116A (zh) 对象排序方法、相关设备及介质
US20240144198A1 (en) Machine Learning-based Knowledge Management for Incident Response
CN114722025B (zh) 基于预测模型的数据预测方法、装置、设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18921845

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 26/03/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 18921845

Country of ref document: EP

Kind code of ref document: A1