CN118365119A - Credit data processing method based on credit bureau alliance - Google Patents
Credit data processing method based on credit bureau alliance Download PDFInfo
- Publication number
- CN118365119A CN118365119A CN202410443257.8A CN202410443257A CN118365119A CN 118365119 A CN118365119 A CN 118365119A CN 202410443257 A CN202410443257 A CN 202410443257A CN 118365119 A CN118365119 A CN 118365119A
- Authority
- CN
- China
- Prior art keywords
- credit
- data
- risk
- information
- investigation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 39
- 230000005540 biological transmission Effects 0.000 claims abstract description 30
- 230000008859 change Effects 0.000 claims abstract description 29
- 238000012795 verification Methods 0.000 claims abstract description 18
- 238000004458 analytical method Methods 0.000 claims abstract description 6
- 238000004806 packaging method and process Methods 0.000 claims abstract description 6
- 238000011835 investigation Methods 0.000 claims description 82
- 238000000034 method Methods 0.000 claims description 44
- 230000008569 process Effects 0.000 claims description 36
- 230000002093 peripheral effect Effects 0.000 claims description 15
- 230000008520 organization Effects 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 8
- 238000012797 qualification Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000007619 statistical method Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims 3
- 238000012550 audit Methods 0.000 claims 1
- 238000012958 reprocessing Methods 0.000 claims 1
- 238000012552 review Methods 0.000 description 8
- 230000001105 regulatory effect Effects 0.000 description 7
- 230000002159 abnormal effect Effects 0.000 description 6
- 101001121408 Homo sapiens L-amino-acid oxidase Proteins 0.000 description 2
- 102100026388 L-amino-acid oxidase Human genes 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/104—Peer-to-peer [P2P] networks
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Technology Law (AREA)
- Computer Networks & Wireless Communication (AREA)
- Educational Administration (AREA)
- Signal Processing (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
本发明公开了基于征信机构联盟的征信数据处理方法，本发明涉及数据处理领域，包括以下步骤：设置征信联盟平台，对使用该平台的征信机构进行合法性验证，并设置数据传输通道，将所获得的征信数据通过数据传输通道进行传输；建立征信数据池，对其中的征信数据进行去重处理和完整性分析；预设征信周期，获取征信周期内的征信数据并对其进行处理，获取其第一风险数据，对征信周期内的第一风险数据进行统计，获取其变化趋势以及对应的第二风险数据；对第一风险数据和第二风险数据进行分析处理，获取综合风险数据，并将所获得的数据信息打包为征信数据包，输出风险预测结果；本发明在一定程度上提高了征信数据处理的准确性。
The present invention discloses a credit data processing method based on a credit reporting agency alliance. The present invention relates to the field of data processing and comprises the following steps: setting up a credit reporting alliance platform, conducting legitimacy verification on credit reporting agencies using the platform, and setting up a data transmission channel to transmit the obtained credit data through the data transmission channel; establishing a credit data pool to perform deduplication processing and integrity analysis on the credit data therein; presetting a credit reporting cycle, obtaining and processing the credit data within the credit reporting cycle, obtaining its first risk data, performing statistics on the first risk data within the credit reporting cycle, obtaining its change trend and corresponding second risk data; analyzing and processing the first risk data and the second risk data to obtain comprehensive risk data, and packaging the obtained data information into a credit reporting data packet to output a risk prediction result; the present invention improves the accuracy of credit data processing to a certain extent.
Description
技术领域Technical Field
本发明涉及数据处理领域，具体是基于征信机构联盟的征信数据处理方法。The present invention relates to the field of data processing, and in particular to a credit reporting data processing method based on a credit reporting agency alliance.
背景技术Background technique
征信是指专业化、独立的第三方机构为个人或企业建立信用档案，依法采集、客观记录其信用信息，并依法对外提供信用信息服务的一种活动，从而帮助人员判断对应人员或企业是否可靠；随着社会的发展，越来越多的领域将会应用到个人征信，因此，征信与我们的日常生活息息相关，此外，征信的数据处理方法也尤为重要。Credit reporting refers to an activity in which a professional and independent third-party organization establishes a credit file for an individual or enterprise, collects and objectively records their credit information in accordance with the law, and provides credit information services to the outside world in accordance with the law, thereby helping people to judge whether the corresponding person or enterprise is reliable; with the development of society, more and more fields will be applied to personal credit reporting. Therefore, credit reporting is closely related to our daily life. In addition, the data processing method of credit reporting is also particularly important.
公开号为CN110765484B的一种征信数据处理方法及电子设备公开了一种征信数据处理方法及电子设备，该方法包括：接收征信查询请求后，解析所述征信查询请求生成相应的解析结果，并根据所述解析结果获取相应的业务场景；根据所述业务场景调用相应的决策配置规则，并根据所述决策配置规则获取所述征信查询请求对应的征信数据，其中包括通过预设接口从至少一个预设征信服务端获取所述征信数据；将获取的征信数据按照定制要求生成相应的定制数据，以响应所述征信查询请求。该方法能够根据征信查询请求的实际情况制定查询策略，并能够与预设征信服务端进行相适应的数据交互，提高处理效率的同时保证整个系统的稳定而有序。A credit data processing method and electronic device with publication number CN110765484B discloses a credit data processing method and electronic device, the method comprising: after receiving a credit inquiry request, parsing the credit inquiry request to generate a corresponding parsing result, and obtaining a corresponding business scenario according to the parsing result; calling a corresponding decision configuration rule according to the business scenario, and obtaining the credit data corresponding to the credit inquiry request according to the decision configuration rule, including obtaining the credit data from at least one preset credit service end through a preset interface; generating corresponding customized data according to customized requirements from the obtained credit data to respond to the credit inquiry request. The method can formulate a query strategy according to the actual situation of the credit inquiry request, and can perform appropriate data interaction with the preset credit service end, thereby improving processing efficiency while ensuring the stability and order of the entire system.
公开号为CN108230137B的一种实现征信数据处理的方法及装置公开了一种实现征信数据处理方法及系统，包括：获取商户的交易数据，并根据预设的异常判断策略对获取的交易数据进行异常判断；判断出交易数据存在异常时，获取与异常的交易数据关联的交易关联信息；根据获取的交易数据及与交易数据关联的交易关联信息确定是否调整商户征信，并在确定调整商户征信时，对商户征信进行调整。本发明实施例通过交易数据及交易关联信息对商户的交易进行是否异常的判断，通过异常分析作为商户征信调整的一个依据，避免了商户交易数据造假，提高了征信信息的准确性。A method and device for implementing credit data processing with publication number CN108230137B discloses a method and system for implementing credit data processing, including: obtaining transaction data of merchants, and making abnormal judgment on the acquired transaction data according to a preset abnormal judgment strategy; when it is judged that the transaction data is abnormal, obtaining transaction-related information associated with the abnormal transaction data; determining whether to adjust the merchant credit according to the acquired transaction data and the transaction-related information associated with the transaction data, and adjusting the merchant credit when it is determined to adjust the merchant credit. The embodiment of the present invention determines whether the merchant's transaction is abnormal through transaction data and transaction-related information, and uses abnormal analysis as a basis for merchant credit adjustment, thereby avoiding merchant transaction data fraud and improving the accuracy of credit information.
目前对于人们征信数据处理的过程中，仅由类似与银行类的个别机构中有征信数据，然而仅仅拥有银行类的征信数据不足的，与其他征信机构的征信数据并不流通，导致了征信数据孤岛，从而降低了征信数据处理过程中的准确性，因此，如何增大用户征信数据的数据量，提高征信数据处理过程中的准确性是我们需要解决的问题，为此，现提供基于征信机构联盟的征信数据处理方法。At present, in the process of processing people's credit data, only individual institutions such as banks have credit data. However, it is not enough to have only bank-type credit data, and the credit data with other credit agencies are not circulated, resulting in credit data islands, thereby reducing the accuracy of the credit data processing process. Therefore, how to increase the amount of user credit data and improve the accuracy of the credit data processing process is a problem we need to solve. To this end, a credit data processing method based on a credit agency alliance is now provided.
发明内容Summary of the invention
为了解决上述技术问题，本发明的目的在于提供基于征信机构联盟的征信数据处理方法。In order to solve the above technical problems, the purpose of the present invention is to provide a credit data processing method based on a credit reporting agency alliance.
本发明的目的可以通过以下技术方案实现：基于征信机构联盟的征信数据处理方法，包括以下步骤：The purpose of the present invention can be achieved by the following technical solution: a credit reporting data processing method based on a credit reporting agency alliance, comprising the following steps:
步骤S1：设置征信联盟平台，对使用该平台的征信机构进行合法性验证，对验证通过的征信机构设置数据传输通道，征信机构根据平台需求通过数据传输通道上传对应的征信数据，并对所输入的征信数据进行标记；Step S1: Setting up a credit reporting alliance platform, verifying the legitimacy of credit reporting agencies using the platform, setting up data transmission channels for credit reporting agencies that have passed the verification, and credit reporting agencies uploading corresponding credit reporting data through the data transmission channels according to platform requirements, and marking the input credit reporting data;
步骤S2：建立征信数据池，根据数据传输通道所上传的征信数据的标记对征信数据池中的征信数据进行去重处理；Step S2: Establish a credit data pool, and perform deduplication processing on the credit data in the credit data pool according to the tags of the credit data uploaded by the data transmission channel;
步骤S3：对征信数据池中的征信数据进行分析处理，预设征信周期，获取征信周期内各个征信数据对应的第一风险数据，将所获得的第一风险数据进行统计分析，获取其变化趋势，并根据其变化趋势获取其第二风险数据；Step S3: analyzing and processing the credit data in the credit data pool, presetting a credit period, obtaining first risk data corresponding to each credit data in the credit period, statistically analyzing the obtained first risk data, obtaining its change trend, and obtaining its second risk data according to its change trend;
步骤S4：对所获得的第一风险数据和第二风险数据进行分析处理，获取对应征信调查人身份信息对应的综合风险数据，并将所获得的数据信息打包为征信数据包，输出风险预测结果。Step S4: Analyze and process the first risk data and the second risk data obtained, obtain the comprehensive risk data corresponding to the identity information of the credit investigator, package the obtained data information into a credit investigation data package, and output the risk prediction result.
进一步的，所述设置征信联盟平台，对使用该平台的征信机构进行合法性验证，对验证通过的征信机构设置数据传输通道的过程包括：Furthermore, the process of setting up a credit reporting alliance platform, verifying the legitimacy of credit reporting agencies using the platform, and setting up a data transmission channel for credit reporting agencies that have passed the verification includes:
设置征信联盟平台，其中包括征信联盟认证窗口，使用该征信联盟平台的征信机构根据其企业信息通过征信联盟认证窗口上传征信联盟申请；所述征信联盟申请中包括其注册信息、资质认证信息、监管机构备案信息和合规性审查信息；对所获得的征信联盟申请进行审核，若审核通过，则授予该征信机构进入该征信联盟平台的权限，并对其设置数据传输通道，并根据征信机构对该数据传输通道进行标记。A credit reporting alliance platform is set up, which includes a credit reporting alliance authentication window. Credit reporting agencies using the credit reporting alliance platform upload credit reporting alliance applications through the credit reporting alliance authentication window based on their corporate information; the credit reporting alliance application includes its registration information, qualification authentication information, regulatory agency filing information and compliance review information; the obtained credit reporting alliance applications are reviewed, and if the review is passed, the credit reporting agency is granted access to the credit reporting alliance platform, and a data transmission channel is set up for it, and the data transmission channel is marked according to the credit reporting agency.
进一步的，所述征信机构根据平台需求通过数据传输通道上传对应的征信数据，并对所输入的征信数据进行标记的过程包括：Furthermore, the process in which the credit reporting agency uploads corresponding credit reporting data through a data transmission channel according to platform requirements and marks the input credit reporting data includes:
所述征信联盟平台内设置有指令接收窗口，所述指令接收窗口用于接收该平台内工作人员所发送征信采集指令，所述征信采集指令中包括征信调查人身份信息；对所获得的征信采集指令进行验证处理，若验证成功，则将该征信采集指令发送至该征信联盟平台内的所有征信机构内，由各个征信机构采集对应的征信数据，对征信数据进行标记，其中包括获取时间、征信调查人身份信息和征信机构；将所采集到的征信数据通过数据传输通道上传至征信联盟平台内。The credit reporting alliance platform is provided with an instruction receiving window, which is used to receive credit collection instructions sent by the staff of the platform, wherein the credit collection instructions include the identity information of the credit investigator; the obtained credit collection instructions are verified, and if the verification is successful, the credit collection instructions are sent to all credit reporting agencies in the credit reporting alliance platform, and each credit reporting agency collects the corresponding credit data and marks the credit data, including the acquisition time, the identity information of the credit investigator and the credit reporting agency; the collected credit data is uploaded to the credit reporting alliance platform through the data transmission channel.
进一步的，所述建立征信数据池，根据数据传输通道所上传的征信数据的标记对征信数据池中的征信数据进行去重处理的过程包括：Furthermore, the process of establishing a credit data pool and performing deduplication processing on the credit data in the credit data pool according to the tags of the credit data uploaded by the data transmission channel includes:
在征信联盟平台内建立征信数据池，所述征信数据池内设置有中心征信数据池和外围征信数据池，所述中心征信数据池用于储存所采集到的经过去重处理的征信数据；所述外围征信数据池用于临时储存所采集到的未经过去重处理的征信数据；获取征信调查人身份信息，并将其记为关键性采集特征，根据关键性采集特征通过SQL编写查询算法获取中心征信数据池中的该征信调查人身份信息对应的征信数据集；获取外围征信数据池内标记为征信调查人身份信息的征信数据，并将其与中心征信数据池中对应征信数据集内所包含的征信数据进行一一对比，通过哈希算法依次获取对应征信数据的哈希值，若均不一致，则将该征信数据记为不重复数据，并将该征信数据从外围征信数据池中转移至中心征信数据池中，并对该征信调查人身份信息对应的征信数据集进行更新，将该征信数据加入征信数据集中，依次重复对比操作，直至外围征信数据池中无对应征信调查人身份信息对应的征信数据时，完成征信数据的去重处理。A credit investigation data pool is established in the credit investigation alliance platform, wherein the credit investigation data pool is provided with a central credit investigation data pool and a peripheral credit investigation data pool. The central credit investigation data pool is used to store the collected credit investigation data that has been deduplicated; the peripheral credit investigation data pool is used to temporarily store the collected credit investigation data that has not been deduplicated; the identity information of the credit investigator is obtained, and it is recorded as a key collection feature, and a query algorithm is written through SQL according to the key collection feature to obtain the credit investigation data set corresponding to the identity information of the credit investigator in the central credit investigation data pool; the credit investigation data set marked as the identity information of the credit investigator in the peripheral credit investigation data pool is obtained The credit data is collected and compared one by one with the credit data contained in the corresponding credit data set in the central credit data pool. The hash values of the corresponding credit data are obtained in sequence through the hash algorithm. If they are inconsistent, the credit data is recorded as non-duplicate data, and the credit data is transferred from the peripheral credit data pool to the central credit data pool. The credit data set corresponding to the identity information of the credit investigator is updated, and the credit data is added to the credit data set. The comparison operation is repeated in sequence until there is no credit data corresponding to the identity information of the credit investigator in the peripheral credit data pool, and the deduplication of the credit data is completed.
进一步的，所述征信联盟平台内设置有固定的关于征信数据的数据集元素占位，所述数据集元素占位分别与各个征信周期内所包含的不同种类的征信数据一一对应，将征信数据集中的征信数据分别与各个数据集元素占位相互匹配，若该平台内所设置的各个数据集元素占位均匹配成功，则该征信数据集完整；若平台内所设置的各个数据集元素占位存在未匹配成功，则该征信数据集不完整，生成重复采集指令发送至该征信联盟平台内的各个征信机构内，由征信机构重新采集。Furthermore, the credit reporting alliance platform is provided with fixed data set element placeholders for credit data, and the data set element placeholders correspond one-to-one to the different types of credit data contained in each credit reporting cycle, and the credit data in the credit data set is matched with each data set element placeholder. If all data set element placeholders set in the platform are matched successfully, the credit data set is complete; if any of the data set element placeholders set in the platform are not matched successfully, the credit data set is incomplete, and a repeated collection instruction is generated and sent to each credit reporting agency in the credit reporting alliance platform, and the credit reporting agency re-collects the data.
进一步的，所述对征信数据池中的征信数据进行分析处理，预设征信周期，获取征信周期内各个征信数据对应的第一风险数据的过程包括：Furthermore, the process of analyzing and processing the credit data in the credit data pool, presetting a credit cycle, and obtaining the first risk data corresponding to each credit data in the credit cycle includes:
获取该征信联盟平台内不同种类征信数据对应的历史征信数据，生成对应种类征信数据的历史征信数据集，根据历史征信数据集通过自然语言算法对其进行分析训练，构建关键特征提取模型；预设征信周期，获取各个征信周期内对应征信调查人身份信息对应的征信数据；将所获得的征信数据输入至其对应类型的关键特征提取模型中，输出对应类型征信数据的关键特征数据，对所获得的关键特征数据进行分析处理，获取征信周期内的第一风险数据；Obtain historical credit data corresponding to different types of credit data in the credit alliance platform, generate historical credit data sets of corresponding types of credit data, analyze and train the historical credit data sets through natural language algorithms, and build a key feature extraction model; preset credit reporting cycles, obtain credit data corresponding to the identity information of credit investigators in each credit reporting cycle; input the obtained credit data into the key feature extraction model of the corresponding type, output the key feature data of the corresponding type of credit data, analyze and process the obtained key feature data, and obtain the first risk data in the credit reporting cycle;
预设风险等级区间，分别包括低风险区间、中风险区间和高风险区间，将所获得的第一风险数据分别对对应的风险等级区间进行对比分析，根据征信周期内第一风险数据所属风险等级区间获取其风险等级，根据其风险等级设置第一风险系数。The preset risk level intervals include a low risk interval, a medium risk interval and a high risk interval. The obtained first risk data are compared and analyzed with the corresponding risk level intervals respectively. The risk level of the first risk data is obtained according to the risk level interval to which the first risk data belongs within the credit reporting period, and the first risk coefficient is set according to the risk level.
进一步的，所述根据所获得的第一风险数据进行统计分析，获取其变化趋势，并根据其变化趋势获取其第二风险数据的过程包括：Furthermore, the process of performing statistical analysis on the first risk data obtained, obtaining its change trend, and obtaining its second risk data according to its change trend includes:
获取各个征信周期内的第一风险数据，将各个征信周期设置为单位时间，根据征信调查人身份信息对应的征信周期和其中对应的第一风险数据构建第一风险图像，根据第一风险图像内第一风险数据的变化趋势对连续的单位时间进行划分，当第一风险图像内相邻单位时间内的变化趋势一致时，则将所连续的单位时间设置为连续单位集，并将起始单位时间记为该连续单位集的下限，将终止单位时间记为该连续单位集的上限；获取各个连续单位集中各个第一风险数据的变化趋势；所述变化趋势根据连续单位集中下限和上限对应单位时间内的差值所获得；获取各个连续单位集的变化趋势，将其变化趋势记为第二风险数据。Obtain the first risk data in each credit reporting period, set each credit reporting period as a unit time, construct a first risk image according to the credit reporting period corresponding to the identity information of the credit investigator and the corresponding first risk data therein, divide the continuous unit time according to the change trend of the first risk data in the first risk image, and when the change trends in adjacent unit times in the first risk image are consistent, set the continuous unit time as a continuous unit set, and record the starting unit time as the lower limit of the continuous unit set, and record the ending unit time as the upper limit of the continuous unit set; obtain the change trend of each first risk data in each continuous unit set; the change trend is obtained according to the difference between the lower limit and the upper limit of the continuous unit set in the unit time; obtain the change trend of each continuous unit set, and record its change trend as the second risk data.
进一步的，所述对所获得的第一风险数据和第二风险数据进行分析处理，获取对应征信调查人身份信息对应的综合风险数据，并将所获得的数据信息打包为征信数据包，输出风险预测结果的过程包括：Furthermore, the process of analyzing and processing the first risk data and the second risk data obtained, obtaining the comprehensive risk data corresponding to the identity information of the credit investigation person, and packaging the obtained data information into a credit investigation data package, and outputting the risk prediction result includes:
获取第一风险数据、第一风险系数、第二风险数据以及其对应的征信周期和连续单位集，获取征信调查人身份信息对应的连续单位集的个数和连续单位集中征信周期的个数，对所获得的数据信息进行分析处理，获取各个征信周期内的第一风险数据和第一风险系数乘积之和的平均值以及各个连续单位集内第二风险数据的均值，其中预设有第二风险区间，根据其均值所属第二风险区间获取其第二风险系数，获取各个连续单位集中的第二风险数据和第二风险系数的乘积之和；将所获得的乘积之和与第一风险数据和第一风险系数乘积之和的平均值进行分析处理，获取综合风险数据，将该平台内所产生的数据信息打包为征信数据包，输出风险预测结果。Obtain the first risk data, the first risk coefficient, the second risk data and their corresponding credit reporting cycles and continuous unit sets, obtain the number of continuous unit sets corresponding to the credit investigator's identity information and the number of credit reporting cycles in the continuous unit sets, analyze and process the obtained data information, obtain the average value of the sum of the products of the first risk data and the first risk coefficient in each credit reporting cycle and the average value of the second risk data in each continuous unit set, wherein a second risk interval is preset, obtain the second risk coefficient according to the second risk interval to which its average value belongs, obtain the sum of the products of the second risk data and the second risk coefficient in each continuous unit set; analyze and process the obtained sum of products and the average value of the sum of the products of the first risk data and the first risk coefficient, obtain comprehensive risk data, package the data information generated in the platform into a credit reporting data package, and output risk prediction results.
与现有技术相比，本发明的有益效果是：Compared with the prior art, the present invention has the following beneficial effects:
1、通过设置征信数据池，将使用该平台征信机构所获得的各个征信调查人身份信息对应的征信数据进行对比分析，进行去重处理和完整性分析，从而在一定程度上提高了征信数据处理过程中的准确性；1. By setting up a credit data pool, the credit data corresponding to the identity information of each credit investigator obtained by the credit reporting agency using the platform will be compared and analyzed, and duplicate removal and integrity analysis will be performed, thereby improving the accuracy of the credit data processing process to a certain extent;
2、通过对其设置征信周期，对征信周期内的征信数据进行分析处理，获取其第一风险数据，根据所获得的第一风险数据的变化趋势进行分析处理，获取其第二风险数据，从而根据其第一风险数据和第二风险数据获取综合风险数据，根据征信数据本身和其变化趋势对其征信进行分析处理，从而提高了用户征信分析过程中的科学性。2. By setting a credit reporting cycle, analyzing and processing the credit data within the credit reporting cycle, obtaining the first risk data, analyzing and processing the change trend of the first risk data, obtaining the second risk data, thereby obtaining comprehensive risk data based on the first risk data and the second risk data, and analyzing and processing the credit based on the credit data itself and its change trend, thereby improving the scientific nature of the user credit analysis process.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
图1为本申请实施例基于征信机构联盟的征信数据处理方法的原理图。FIG1 is a schematic diagram of a credit data processing method based on a credit reporting agency alliance according to an embodiment of the present application.
具体实施方式Detailed ways
如图1所示，基于征信机构联盟的征信数据处理方法，包括以下步骤：As shown in FIG1 , the credit reporting data processing method based on the credit reporting agency alliance includes the following steps:
步骤S1：设置征信联盟平台，对使用该平台的征信机构进行合法性验证，对验证通过的征信机构设置数据传输通道，征信机构根据平台需求通过数据传输通道上传对应的征信数据，并对所输入的征信数据进行标记；Step S1: Setting up a credit reporting alliance platform, verifying the legitimacy of credit reporting agencies using the platform, setting up data transmission channels for credit reporting agencies that have passed the verification, and credit reporting agencies uploading corresponding credit reporting data through the data transmission channels according to platform requirements, and marking the input credit reporting data;
步骤S2：建立征信数据池，根据数据传输通道所上传的征信数据的标记对征信数据池中的征信数据进行去重处理；Step S2: Establish a credit data pool, and perform deduplication processing on the credit data in the credit data pool according to the tags of the credit data uploaded by the data transmission channel;
步骤S3：对征信数据池中的征信数据进行分析处理，预设征信周期，获取征信周期内各个征信数据对应的第一风险数据，将所获得的第一风险数据进行统计分析，获取其变化趋势，并根据其变化趋势获取其第二风险数据；Step S3: analyzing and processing the credit data in the credit data pool, presetting a credit period, obtaining first risk data corresponding to each credit data in the credit period, statistically analyzing the obtained first risk data, obtaining its change trend, and obtaining its second risk data according to its change trend;
步骤S4：对所获得的第一风险数据和第二风险数据进行分析处理，获取对应征信调查人身份信息对应的综合风险数据，并将所获得的数据信息打包为征信数据包，输出风险预测结果。Step S4: Analyze and process the first risk data and the second risk data obtained, obtain the comprehensive risk data corresponding to the identity information of the credit investigator, package the obtained data information into a credit investigation data package, and output the risk prediction result.
所述设置征信联盟平台，对使用该平台的征信机构进行合法性验证，对验证通过的征信机构设置数据传输通道，征信机构根据平台需求通过数据传输通道上传对应的征信数据，并对所输入的征信数据进行标记的过程包括：The process of setting up a credit reporting alliance platform, verifying the legitimacy of credit reporting agencies using the platform, setting up a data transmission channel for credit reporting agencies that have passed the verification, and credit reporting agencies uploading corresponding credit reporting data through the data transmission channel according to platform requirements, and marking the input credit reporting data includes:
设置征信联盟平台，其中设置有给征信联盟认证窗口，需要使用该征信联盟平台的征信机构根据其企业信息上传征信联盟申请，所述征信联盟申请中包括其注册信息、资质认证信息、监管机构备案信息和合规性审查信息；对所获得的征信联盟申请进行审核，所述征信联盟平台内设置有对应的专业监管团队，将所获得的征信联盟申请发送至专业监管团队中，有专业监管团队进行审核；若审核通过，则授予该征信机构进入该征信联盟平台的权限，并对其设置数据传输通道，并根据征信机构对该数据传输通道进行标记；若审核未通过，则不授予该征信联盟进入该征信联盟平台的权限；A credit alliance platform is set up, in which a credit alliance authentication window is set up. The credit reporting agencies that need to use the credit alliance platform upload credit alliance applications according to their corporate information. The credit alliance applications include their registration information, qualification certification information, regulatory agency filing information and compliance review information; the obtained credit alliance applications are reviewed. The credit alliance platform is equipped with a corresponding professional supervision team. The obtained credit alliance applications are sent to the professional supervision team for review. If the review is passed, the credit reporting agency is granted access to the credit alliance platform, and a data transmission channel is set up for it, and the data transmission channel is marked according to the credit reporting agency; if the review is not passed, the credit alliance is not granted access to the credit alliance platform;
需要进一步说明的是，在具体实施过程中，所述征信联盟申请中所包含信息分别为：所述注册信息为该征信机构的注册名称、法人代表以及联系方式，所述资质认证信息为通过国家金融管理机构或相关主管部门的认证，以确保满足征信机构的法定要求和标准的证明信息；所述监管机构备案信息为监管部门定期对征信机构进行审查和监督所获得的监管报告和年度报告信息；所述合规性审查信息为经过相关监管部门或机构发布的报告，证明其符合合规要求的信息。It should be further explained that, in the specific implementation process, the information contained in the credit reporting alliance application is as follows: the registration information is the registered name, legal representative and contact information of the credit reporting agency; the qualification certification information is the certification information obtained through the national financial management agency or relevant competent authorities to ensure that the statutory requirements and standards of the credit reporting agency are met; the regulatory agency filing information is the regulatory report and annual report information obtained through regular review and supervision of the credit reporting agency by the regulatory authorities; the compliance review information is the report issued by the relevant regulatory authorities or institutions, which proves that it meets the compliance requirements.
所述征信联盟平台内设置有指令接收窗口，所述指令接收窗口用于接收该平台内工作人员所发送征信采集指令，所述征信采集指令中包括征信调查人身份信息、征信调查人身份证明以及征信调查人所授权的申请书；对所获得的征信采集指令进行验证处理，若验证成功，则将该征信采集指令发送至该征信联盟平台内的所有征信机构内，由各个征信机构采集对应的征信数据；The credit union platform is provided with an instruction receiving window, which is used to receive the credit collection instruction sent by the staff of the platform, wherein the credit collection instruction includes the identity information of the credit investigator, the identity certificate of the credit investigator and the application form authorized by the credit investigator; the obtained credit collection instruction is verified, and if the verification is successful, the credit collection instruction is sent to all credit agencies in the credit union platform, and each credit agency collects the corresponding credit data;
所述征信联盟平台内设置有征信数据池，所述数据传输通道通信连接对应标记的征信机构和征信数据池，所述征信机构用于根据征信采集指令采集对应征信调查人的征信数据，并将所采集到的征信数据进行标记，所述标记中包括征信数据获取时间和征信机构名称，并通过数据传输通道传输至征信联盟平台内的征信数据池中；A credit data pool is provided in the credit alliance platform, and the data transmission channel communicates with the corresponding marked credit agency and the credit data pool. The credit agency is used to collect the credit data of the corresponding credit investigator according to the credit collection instruction, and mark the collected credit data. The mark includes the time of obtaining the credit data and the name of the credit agency, and transmits it to the credit data pool in the credit alliance platform through the data transmission channel;
需要进一步说明的是，在具体实施过程中，所述征信联盟平台内的征信机构内设置有与其合作的多元渠道列表，所述多元渠道列表中包括监管部门所认证的各个征信数据来源渠道，通过数据库查询技术依次获取多元渠道列表中对应的征信数据，所述征信数据包括但不限于公共数据、支付数据和金融数据；所述公告数据包括个人或机构的法律诉讼、裁决、破产记录等；所述金融数据包括个人或机构的信用借贷行为和，包括贷款申请、贷款金额、贷款期限、还款记录等，还包括个人的信用卡使用情况，如信用额度、账单还款情况、逾期记录等；所述支付记录包括个人或机构的支付行为，如手机缴费、水电费缴纳情况等。It should be further explained that, in the specific implementation process, the credit reporting agency in the credit reporting alliance platform is provided with a multi-channel list of cooperation with it, and the multi-channel list includes various credit data source channels certified by the regulatory authorities, and the corresponding credit data in the multi-channel list are obtained in sequence through database query technology. The credit data includes but is not limited to public data, payment data and financial data; the announcement data includes legal proceedings, rulings, bankruptcy records, etc. of individuals or institutions; the financial data includes credit borrowing behavior of individuals or institutions, including loan applications, loan amounts, loan terms, repayment records, etc., and also includes personal credit card usage, such as credit limits, bill repayments, overdue records, etc.; the payment records include payment behaviors of individuals or institutions, such as mobile phone payments, water and electricity bill payments, etc.
所述建立征信数据池，根据数据传输通道所上传的征信数据的标记对征信数据池中的征信数据进行去重处理的过程包括：The process of establishing a credit data pool and performing deduplication processing on the credit data in the credit data pool according to the tags of the credit data uploaded by the data transmission channel includes:
所述征信数据池内设置有中心征信数据池和外围征信数据池，所述中心征信数据池用于储存所采集到的经过去重处理的征信数据；所述外围征信数据池用于临时储存所采集到的未经过去重处理的征信数据；获取征信联盟平台内所生成征信采集指令中的征信调查人身份信息，将所获得的征信调查人身份信息记为关键性采集特征，根据关键性采集特征通过SQL编写查询算法获取中心征信数据池中的该征信调查人身份信息对应的征信数据集，将所获得的征信数据集；The credit data pool is provided with a central credit data pool and a peripheral credit data pool, wherein the central credit data pool is used to store the collected credit data that has been deduplicated; the peripheral credit data pool is used to temporarily store the collected credit data that has not been deduplicated; the identity information of the credit investigator in the credit collection instruction generated in the credit alliance platform is obtained, and the obtained identity information of the credit investigator is recorded as a key collection feature. According to the key collection feature, a query algorithm is written through SQL to obtain the credit data set corresponding to the credit investigator identity information in the central credit data pool, and the obtained credit data set is obtained;
所述外围征信数据池中储存有该征信联盟平台中征信机构所采集到的征信数据，获取标记为征信调查人身份信息的征信数据，并将其与中心征信数据池中的对应征信调查人身份信息一致的征信数据集内所包含的征信数据进行一一对比，通过哈希算法依次获取对应征信数据的哈希值，判断是否存在一致，若存在一致，则将该征信数据记为重复数据，将其删除，若均不一致，则将该征信数据记为不重复数据，并将该征信数据从外围征信数据池中转移至中心征信数据池中，并对该征信调查人身份信息对应的征信数据集进行更新，将该征信数据加入征信数据集中；依次重复上述操作，直至外围征信数据池中无对应征信调查人身份信息对应的征信数据时，停止操作；The peripheral credit data pool stores the credit data collected by the credit reporting agencies in the credit reporting alliance platform. The credit data marked as the identity information of the credit investigator is obtained, and the credit data is compared one by one with the credit data set in the central credit data pool that is consistent with the identity information of the corresponding credit investigator. The hash values of the corresponding credit data are obtained in sequence through the hash algorithm to determine whether there is a consistency. If there is a consistency, the credit data is recorded as duplicate data and deleted. If there is no consistency, the credit data is recorded as non-duplicate data, and the credit data is transferred from the peripheral credit data pool to the central credit data pool, and the credit data set corresponding to the identity information of the credit investigator is updated, and the credit data is added to the credit data set; the above operations are repeated in sequence until there is no credit data corresponding to the identity information of the credit investigator in the peripheral credit data pool, and the operation is stopped;
需要进一步说明的是，在具体实施过程中，所述通过哈希算法获取征信数据的哈希值，其步骤为：对所获得的征信数据进行预处理，将征信数据进行数据转化，并填充给长度为512的倍数，并附加数据长度；设定哈希初始值，并将其记为HC；将数据划分为512位的数据块，对所获得的512个数据块进行迭代处理，产生128位输出，将每个数据块的输出结果连接，获取最终的哈希值。It should be further explained that, in the specific implementation process, the hash value of the credit data is obtained through the hash algorithm, and the steps are: pre-processing the obtained credit data, converting the credit data, padding it to a multiple of 512, and appending the data length; setting the initial hash value, and recording it as HC; dividing the data into 512-bit data blocks, iteratively processing the obtained 512 data blocks to generate a 128-bit output, connecting the output results of each data block, and obtaining the final hash value.
获取征信调查人身份信息在中心征信数据池中所对应的征信数据集；所述征信联盟平台内设置有固定的关于征信数据的数据集元素占位，所述数据集元素占位分别与各个征信周期内所包含的不同种类的征信数据一一对应，将征信数据集中的征信数据分别与各个数据集元素占位相互匹配，若匹配成功，且该平台内所设置的各个数据集元素占位均匹配成功，则该征信数据集完整，若匹配未成功，或平台内所设置的各个数据集元素占位存在未匹配成功，则该征信数据集不完整，生成重复采集指令发送至该征信联盟平台内的各个征信机构内，由征信机构重新采集，重复该步骤；Obtain the credit investigation data set corresponding to the credit investigation person's identity information in the central credit investigation data pool; the credit investigation alliance platform is provided with fixed data set element placeholders for credit investigation data, and the data set element placeholders correspond one-to-one to different types of credit investigation data contained in each credit investigation cycle, and the credit investigation data in the credit investigation data set is matched with each data set element placeholder. If the match is successful, and all data set element placeholders set in the platform are matched successfully, then the credit investigation data set is complete; if the match is unsuccessful, or there is an unmatched match among all data set element placeholders set in the platform, then the credit investigation data set is incomplete, and a repeated collection instruction is generated and sent to each credit investigation agency in the credit investigation alliance platform, and the credit investigation agency re-collects and repeats this step;
需要进一步说明的是，在具体实施过程中，通过数据集元素占位将征信数据集中的征信数据进行排查，判断是否存在缺失或重复，从而提高了数据处理过程中的准确性。It should be further explained that, in the specific implementation process, the credit data in the credit data set is checked through the data set element placeholders to determine whether there are any missing or duplicated data, thereby improving the accuracy of the data processing process.
所述对征信数据池中的征信数据进行分析处理，预设征信周期，获取征信周期内各个征信数据对应的第一风险数据，将所获得的第一风险数据进行统计分析，获取其变化趋势，并根据其变化趋势获取其第二风险数据的过程包括：The process of analyzing and processing the credit data in the credit data pool, presetting a credit period, obtaining first risk data corresponding to each credit data in the credit period, statistically analyzing the obtained first risk data, obtaining its change trend, and obtaining its second risk data according to its change trend includes:
获取该征信联盟平台内不同种类征信数据对应的历史征信数据，生成对应种类征信数据的历史征信数据集，将所获得的历史征信数据集划分为训练集和验证集，基于自然语言算法对训练集进行分析处理，构建关键特征提取模型，将所述验证集输入至所构建的关键特征提取模型中，输出结果，将所获得的结果进行验证，获取验证通过率，预设验证通过率阈值，将验证通过率与验证通过率阈值进行对比分析，当验证通过率大于等于验证通过率阈值时，则输出关键特征提取模型；Obtaining historical credit data corresponding to different types of credit data in the credit alliance platform, generating historical credit data sets of corresponding types of credit data, dividing the obtained historical credit data sets into a training set and a verification set, analyzing and processing the training set based on a natural language algorithm, constructing a key feature extraction model, inputting the verification set into the constructed key feature extraction model, outputting the result, verifying the obtained result, obtaining a verification pass rate, presetting a verification pass rate threshold, comparing and analyzing the verification pass rate with the verification pass rate threshold, and outputting the key feature extraction model when the verification pass rate is greater than or equal to the verification pass rate threshold;
预设征信周期，获取各个征信周期内对应征信调查人身份信息对应的征信数据；将所获得的征信数据输入至其对应类型的关键特征提取模型中，输出对应类型征信数据的关键特征数据，对所获得的关键特征数据进行分析处理，获取征信周期内的第一风险数据；Preset a credit investigation cycle, obtain credit investigation data corresponding to the identity information of the credit investigation person in each credit investigation cycle; input the obtained credit investigation data into a key feature extraction model of its corresponding type, output key feature data of the corresponding type of credit investigation data, analyze and process the obtained key feature data, and obtain the first risk data in the credit investigation cycle;
所述对所获得的关键特征数据进行分析处理的过程包括：获取征信数据的类型，将征信数据对应的关键特征数据记为ZXij；其中，i＝1、2……n，分别为不同的征信类型，j＝1、2、3……m，根据其征信周期内对应的单位节点所设置；将第一风险数据记为FYij；预设征信函数和初始系数，分别将其记为Fij和CSij；其中， The process of analyzing and processing the obtained key feature data includes: obtaining the type of credit data, recording the key feature data corresponding to the credit data as ZX ij ; wherein i=1, 2...n, respectively representing different credit types, and j=1, 2, 3...m, set according to the corresponding unit node in its credit cycle; recording the first risk data as FY ij ; presetting the credit function and the initial coefficient, recording them as F ij and CS ij respectively; wherein,
预设风险等级区间，分别包括低风险区间、中风险区间和高风险区间，将所获得的第一风险数据分别对对应的风险等级区间进行对比分析，根据征信周期内第一风险数据所属风险等级区间获取其风险等级，根据其风险等级设置第一风险系数；Preset risk level intervals, including a low risk interval, a medium risk interval and a high risk interval, respectively, compare and analyze the obtained first risk data with the corresponding risk level intervals, obtain the risk level of the first risk data according to the risk level interval to which it belongs within the credit reporting period, and set the first risk coefficient according to the risk level;
获取各个征信周期内的第一风险数据，将各个征信周期设置为单位时间，根据征信调查人身份信息对应的征信周期和征信周期内对应的第一风险数据进行数据可视化分析，构建第一风险图像，根据第一风险图像内第一风险数据的变化趋势对连续的单位时间进行划分，当第一风险图像内相邻单位时间内的变化趋势一致时，则将所连续的单位时间设置为连续单位集，并将起始单位时间记为该连续单位集的下限，将终止单位时间记为该连续单位集的上限；获取各个连续单位集中各个第一风险数据的变化趋势；所述变化趋势根据连续单位集中下限和上限对应单位时间内的差值所获得；对第一风险图像内的第一风险数据进行分析处理，获取各个连续单位集的变化趋势，将其变化趋势记为第二风险数据；Obtain the first risk data in each credit reporting period, set each credit reporting period as a unit time, perform data visualization analysis based on the credit reporting period corresponding to the identity information of the credit investigator and the first risk data corresponding to the credit reporting period, construct a first risk image, divide the continuous unit time according to the change trend of the first risk data in the first risk image, and when the change trends in adjacent unit times in the first risk image are consistent, set the continuous unit time as a continuous unit set, and record the starting unit time as the lower limit of the continuous unit set, and record the ending unit time as the upper limit of the continuous unit set; obtain the change trend of each first risk data in each continuous unit set; the change trend is obtained according to the difference in the unit time corresponding to the lower limit and the upper limit of the continuous unit set; analyze and process the first risk data in the first risk image, obtain the change trend of each continuous unit set, and record its change trend as the second risk data;
需要进一步说明的是，在具体实施过程中，所述第二风险数据可以为正数、负数和0，其根据连续单位集内第一风险数据的变化趋势所获得的，并将所获得的第二风险数据根据其对应的连续单位集进行标记；It should be further explained that, in a specific implementation process, the second risk data may be a positive number, a negative number, or 0, which is obtained according to the change trend of the first risk data in the continuous unit set, and the obtained second risk data is marked according to its corresponding continuous unit set;
所述对所获得的第一风险数据和第二风险数据进行分析处理，获取对应征信调查人身份信息对应的综合风险数据，并将所获得的数据信息打包为征信数据包，输出风险预测结果的过程包括：The process of analyzing and processing the first risk data and the second risk data obtained, obtaining the comprehensive risk data corresponding to the identity information of the credit investigation person, packaging the obtained data information into a credit investigation data package, and outputting the risk prediction result includes:
获取第一风险数据、第二风险数据以及其对应的征信周期和连续单位集，获取连续单位集中征信周期的个数，并将其记为G；根据征信周期内第一风险数据所述风险等级获取其第一风险系数，并将其记为YX；其中，第一风险数据对应为FY；将各个连续单位集中对应的第二风险数据记为FE；将征信调查人身份信息对应的连续单位集的个数设置为L；所述综合风险数据根据所获得的第一风险数据和第二风险数据所获得的；The first risk data, the second risk data and the corresponding credit reporting period and continuous unit set are obtained, the number of credit reporting periods in the continuous unit set is obtained, and it is recorded as G; the first risk coefficient is obtained according to the risk level of the first risk data in the credit reporting period, and it is recorded as YX; wherein, the first risk data corresponds to FY; the second risk data corresponding to each continuous unit set is recorded as FE; the number of continuous unit sets corresponding to the identity information of the credit investigator is set to L; the comprehensive risk data is obtained based on the obtained first risk data and second risk data;
需要进一步说明的是，在具体实施过程中，获取各个连续单位集内的第二风险数据的均值，并将其记为EJ；预设第二风险数据的第二风险区间，分别划分为信用优化区间、信用平稳区间和信用劣化区间，将第二风险数据与第二风险区间进行对比分析，获取第二风险数据所属第二风险区间，根据第二风险区间设置第二风险系数，将第二风险系数记为EX，获取各个连续单位集中的第二风险数据和第二风险系数的乘积之和；将所获得的乘积之和与第一风险数据所设置的均值获取综合风险数据；It should be further explained that, in the specific implementation process, the mean of the second risk data in each continuous unit set is obtained and recorded as EJ; Preset a second risk interval of the second risk data, which is divided into a credit optimization interval, a credit stability interval, and a credit deterioration interval, compare and analyze the second risk data with the second risk interval, obtain the second risk interval to which the second risk data belongs, set a second risk coefficient according to the second risk interval, record the second risk coefficient as EX, obtain the sum of the products of the second risk data and the second risk coefficient in each continuous unit set; obtain comprehensive risk data by adding the sum of the obtained products to the mean value set for the first risk data;
将综合风险数据记为FZ；其中 The comprehensive risk data is denoted as FZ;
将征信调查人身份信息对应的征信数据、第一风险数据、第二风险数据、第二风险系数以及对应的第一风险图像打包为征信数据包，并将征信数据包设置为风险预测结果；Packing the credit investigation data corresponding to the credit investigation person's identity information, the first risk data, the second risk data, the second risk coefficient, and the corresponding first risk image into a credit investigation data package, and setting the credit investigation data package as a risk prediction result;
所述征信联盟平台内设置有征信评估模型，所述征信评估模型根据该平台内的历史征信数据包对其分析训练所获得的，由该征信联盟平台内工作人员随机选取对应的征信数据包输入至征信评估模型内，输出评估结果，对评估结果所获得的综合风险数据与征信数据包内的综合风险数据进行对比分析，若一致，则评估通过，若不一致，则对该征信数据包进行重新处理。The credit alliance platform is provided with a credit assessment model, which is obtained by analyzing and training the historical credit data packets in the platform. The staff of the credit alliance platform randomly selects the corresponding credit data packets and inputs them into the credit assessment model, outputs the assessment results, and compares and analyzes the comprehensive risk data obtained from the assessment results with the comprehensive risk data in the credit data packet. If they are consistent, the assessment is passed; if not, the credit data packet is reprocessed.
以上实施例仅用以说明本发明的技术方法而非限制，尽管参照较佳实施例对本发明进行了详细说明，本领域的普通技术人员应当理解，可以对本发明的技术方法进行修改或等同替换，而不脱离本发明技术方法的精神和范围。The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.
Claims (8)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410443257.8A CN118365119A (en) | 2024-04-12 | 2024-04-12 | Credit data processing method based on credit bureau alliance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410443257.8A CN118365119A (en) | 2024-04-12 | 2024-04-12 | Credit data processing method based on credit bureau alliance |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118365119A true CN118365119A (en) | 2024-07-19 |
Family
ID=91883614
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410443257.8A Pending CN118365119A (en) | 2024-04-12 | 2024-04-12 | Credit data processing method based on credit bureau alliance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118365119A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120278217A1 (en) * | 2011-03-30 | 2012-11-01 | Trans Union Llc | Systems and methods for improving prediction of future credit risk performances |
| CN109615529A (en) * | 2019-02-25 | 2019-04-12 | 中国农业银行股份有限公司 | A kind of credit investigation system based on block chain |
| CN110634068A (en) * | 2018-06-21 | 2019-12-31 | 北京果仁宝软件技术有限责任公司 | Community-chain-based credit investigation data processing method and system |
| US20210166167A1 (en) * | 2019-12-02 | 2021-06-03 | Asia University | Artificial intelligence and blockchain-based inter-enterprise credit rating and risk assessment method and system |
| CN113379530A (en) * | 2021-06-09 | 2021-09-10 | 中国工商银行股份有限公司 | User risk determination method and device and server |
| WO2022062193A1 (en) * | 2020-09-28 | 2022-03-31 | 南京博雅区块链研究院有限公司 | Individual credit assessment and explanation method and apparatus based on time sequence attribution analysis, and device and storage medium |
| CN117237085A (en) * | 2023-08-16 | 2023-12-15 | 中和农信农业集团有限公司 | Information processing method, equipment and computer readable storage medium |
-
2024
- 2024-04-12 CN CN202410443257.8A patent/CN118365119A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120278217A1 (en) * | 2011-03-30 | 2012-11-01 | Trans Union Llc | Systems and methods for improving prediction of future credit risk performances |
| CN110634068A (en) * | 2018-06-21 | 2019-12-31 | 北京果仁宝软件技术有限责任公司 | Community-chain-based credit investigation data processing method and system |
| CN109615529A (en) * | 2019-02-25 | 2019-04-12 | 中国农业银行股份有限公司 | A kind of credit investigation system based on block chain |
| US20210166167A1 (en) * | 2019-12-02 | 2021-06-03 | Asia University | Artificial intelligence and blockchain-based inter-enterprise credit rating and risk assessment method and system |
| WO2022062193A1 (en) * | 2020-09-28 | 2022-03-31 | 南京博雅区块链研究院有限公司 | Individual credit assessment and explanation method and apparatus based on time sequence attribution analysis, and device and storage medium |
| CN113379530A (en) * | 2021-06-09 | 2021-09-10 | 中国工商银行股份有限公司 | User risk determination method and device and server |
| CN117237085A (en) * | 2023-08-16 | 2023-12-15 | 中和农信农业集团有限公司 | Information processing method, equipment and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111667283B (en) | Personal credit investigation system based on block chain | |
| CN113568973B (en) | Financial credit investigation data sharing method and device based on blockchain and federal learning | |
| CN101251913A (en) | Self-service reimbursement management system and method | |
| CN112435112A (en) | Bank internet credit wind control method for small and micro enterprises | |
| CN111709718B (en) | Intelligent factoring asset service platform, method and storage medium based on artificial intelligence | |
| CN107944837A (en) | A kind of authority processing method, device and system | |
| CN110729028A (en) | Health data processing method and device, electronic equipment and storage medium | |
| CN109472678A (en) | A kind of accounting account book management method, electronic device and readable storage medium storing program for executing based on block chain | |
| WO2022121217A1 (en) | Quota prediction method and device, and computer-readable storage medium | |
| CN112116103B (en) | Personal qualification evaluation method, device and system based on federal learning and storage medium | |
| CN110659976A (en) | Enterprise technology service credit investigation system based on block chain and management method thereof | |
| CN112567716A (en) | Secure data transmission system and method | |
| CN117391292A (en) | Carbon emission energy-saving management analysis system and method | |
| CN112287401A (en) | Wisdom medical treatment sharing platform based on block chain | |
| CN107945014A (en) | One kind is based on LAOP platform small amount personal loan systems | |
| CN115115346A (en) | Method and system for distributing old age allowance based on blockchain | |
| CN113919938A (en) | Domestic buyer's warranty financing method, device, equipment and medium based on block chain | |
| CN117633500A (en) | Risk anti-fraud identification method, device, equipment and storage medium | |
| CN113077331A (en) | Personal financial credit evaluation system and method based on big data | |
| CN119088796B (en) | Audit data quality modeling analysis method and equipment | |
| CN114638299B (en) | Intelligent identification method, device and equipment for zombie license and storage medium | |
| CN113378235B (en) | Distributed supply chain financial platform | |
| CN115271913A (en) | Block chain-based high-value financial data uplink storage system and method | |
| CN118365119A (en) | Credit data processing method based on credit bureau alliance | |
| CN116646065B (en) | Internet hospital data security management method and device |
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 |