CN103886501B - Post-loan risk early warning system based on semantic emotion analysis - Google Patents
Post-loan risk early warning system based on semantic emotion analysis Download PDFInfo
- Publication number
- CN103886501B CN103886501B CN201410138443.7A CN201410138443A CN103886501B CN 103886501 B CN103886501 B CN 103886501B CN 201410138443 A CN201410138443 A CN 201410138443A CN 103886501 B CN103886501 B CN 103886501B
- Authority
- CN
- China
- Prior art keywords
- relevant information
- post
- emotional
- sentiment analysis
- system based
- 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.)
- Expired - Fee Related
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 71
- 230000008451 emotion Effects 0.000 title description 2
- 230000002996 emotional effect Effects 0.000 claims abstract description 39
- 238000007418 data mining Methods 0.000 claims abstract description 19
- 230000003993 interaction Effects 0.000 claims abstract description 12
- 238000000034 method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 241000239290 Araneae Species 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Machine Translation (AREA)
Abstract
一种基于语义情感分析的贷后风险预警系统，其特征在于，包括：网络数据挖掘模块，用于从网络上搜集客户企业的相关信息，所述相关信息包括以下的一种或者几种：与客户企业相关的新闻、评论、微博、举报、投诉；语义情感分析模块，用于接收所述相关信息并进行情感成分分析，生成情感极性K和情感强度M；分析总模块，用于获取所述情感极性K和所述情感强度M，并且根据所述相关信息的来源生成情感极性K值和情感强度M值，之后根据预定公式依次计算得出可靠系数P和总体可靠系数W；用户交互模块，用于在所述总体可靠系数W低于警戒值时发出警告。本发明能够及时的对客户企业的重大变动做出预警，帮助银行更好的管理客户企业，有效的降低贷后风险。
A post-loan risk early warning system based on semantic sentiment analysis, characterized in that it includes: a network data mining module, which is used to collect relevant information of customer enterprises from the Internet, and the relevant information includes one or more of the following: News, comments, microblogs, reports, and complaints related to the client enterprise; the semantic sentiment analysis module is used to receive the relevant information and perform emotional component analysis to generate emotional polarity K and emotional intensity M; the general analysis module is used to obtain The emotional polarity K and the emotional intensity M, and the emotional polarity K value and the emotional intensity M value are generated according to the source of the relevant information, and then the reliability coefficient P and the overall reliability coefficient W are sequentially calculated according to a predetermined formula; A user interaction module, configured to issue a warning when the overall reliability coefficient W is lower than a warning value. The invention can timely give early warning to major changes of client enterprises, help banks better manage client enterprises, and effectively reduce post-loan risks.
Description
技术领域technical field
本发明涉及一种基于语义情感分析的贷后风险预警系统，属于计算机领域。The invention relates to a post-loan risk early warning system based on semantic emotion analysis, which belongs to the field of computers.
背景技术Background technique
随着社会经济的高速发展，企业和个人都有可能向银行或金融机构申请贷款。例如，企业为了扩大生产经营规模，需要引进先进技术及设备，然而这些技术及设备通常需要花费大量款项，动辄数百万、上千万元。个人用户为了创办公司或购买住房，也需要花费几十万甚至上百万。对于这些企业及个人，一次性支付如此巨大的款项是非常困难的，解决的办法就包括向银行贷款。企业或个人用户通过向银行申请贷款，在银行对企业或个人的身份进行验证后，签订贷款合同，然后发放贷款。With the rapid development of social economy, both enterprises and individuals may apply for loans from banks or financial institutions. For example, in order to expand the scale of production and operation, enterprises need to introduce advanced technology and equipment. However, these technologies and equipment usually need to spend a lot of money, often tens of millions or tens of millions of yuan. Individual users also need to spend hundreds of thousands or even millions to start a company or buy a house. For these enterprises and individuals, it is very difficult to pay such a huge amount at one time, and the solution includes borrowing from the bank. Enterprises or individual users apply for a loan from the bank, sign a loan contract after the bank verifies the identity of the enterprise or individual, and then issue the loan.
然而，现有技术中，用户在获得贷款后的使用期间，银行仅能依靠其工作人员人工的去收集跟用户相关的各种各样的信息，然后对信息进行处理分析，最后根据分析结果评判用户的还款能力，以确保发放的贷款和利息能够及时有效的收回。但是，长期实践中发现，在庞大的信息源中完全依靠人工去收集、处理分析跟用户相关的信息会存在：工作量巨大、信息处理效率较低的缺陷与问题；以至于无法及时通知相关人员和机构触发风险处理流程，导致银行不能及时作出判断并规避风险。However, in the existing technology, the bank can only rely on its staff to manually collect various information related to the user during the period of use after the user obtains the loan, then process and analyze the information, and finally judge according to the analysis results The user's repayment ability to ensure that the loan and interest issued can be recovered in a timely and effective manner. However, in long-term practice, it has been found that completely relying on manual collection, processing and analysis of user-related information in huge information sources will have defects and problems such as huge workload and low information processing efficiency; so that relevant personnel cannot be notified in time And institutions trigger the risk treatment process, which makes the bank unable to make timely judgments and avoid risks.
发明内容Contents of the invention
本发明就是鉴于上述问题而提出，其目的在于，提供一种基于语义情感分析的贷后风险预警系统，以解决工作量巨大、信息处理效率较低、而无法及时触发风险处理流程的问题。The present invention is proposed in view of the above problems, and its purpose is to provide a post-loan risk early warning system based on semantic sentiment analysis to solve the problems of huge workload, low information processing efficiency, and failure to trigger the risk processing process in time.
本发明提供一种基于语义情感分析的贷后风险预警系统，其特征在于，该系统包括：The present invention provides a post-loan risk early warning system based on semantic sentiment analysis, characterized in that the system includes:
网络数据挖掘模块，用于从网络上搜集客户企业的相关信息，所述相关信息包括以下的一种或者几种：与客户企业相关的新闻、评论、微博、举报、投诉；The network data mining module is used to collect relevant information of the client company from the Internet, and the relevant information includes one or more of the following: news, comments, Weibo, reports, and complaints related to the client company;
语义情感分析模块，用于接收所述相关信息并进行情感成分分析，生成情感极性K和情感强度M；A semantic sentiment analysis module, configured to receive the relevant information and perform sentiment component analysis to generate sentiment polarity K and sentiment intensity M;
分析总模块，用于获取所述情感极性K和所述情感强度M，并且根据所述相关信息的来源生成情感极性K值和情感强度M值，之后根据预定公式依次计算得出可靠系数P和总体可靠系数W；The overall analysis module is used to obtain the emotional polarity K and the emotional intensity M, and generate the emotional polarity K value and the emotional intensity M value according to the source of the relevant information, and then calculate the reliability coefficient sequentially according to a predetermined formula P and overall reliability coefficient W;
用户交互模块，用于在所述总体可靠系数W低于警戒值时发出警告。A user interaction module, configured to issue a warning when the overall reliability coefficient W is lower than a warning value.
计算所述可靠系数P的预定公式为：P＝K*M。A predetermined formula for calculating the reliability factor P is: P=K*M.
计算所述总体可靠系数W的预定公式为：W＝P1+P2+P3+P4+P5+……+Pn，其中P1、P2、P3、P4、P5、……Pn分别对应不同所述相关信息的可靠系数。The predetermined formula for calculating the overall reliability coefficient W is: W=P 1 +P 2 +P 3 +P 4 +P 5 +...+P n , where P 1 , P 2 , P 3 , P 4 , P 5 , ... P n respectively correspond to reliability coefficients of different related information.
所述网络数据挖掘模块采用网络爬虫从网络上搜集客户企业的相关信息。The network data mining module uses web crawlers to collect relevant information of customer enterprises from the Internet.
所述网络数据挖掘模块采用聚焦爬虫从网络上搜集客户企业的相关信息。The network data mining module uses focused crawlers to collect relevant information of customer enterprises from the Internet.
所述语义情感分析模块采用句级情感分析对所述相关信息进行情感成分分析。The semantic sentiment analysis module uses sentence-level sentiment analysis to analyze the sentiment components of the relevant information.
所述用户交互模块包括：管理单元，用于客户企业信息录入、信息搜集范围设置、预警范围设置和查看客户企业状态。The user interaction module includes: a management unit, which is used for customer enterprise information entry, information collection range setting, early warning range setting and checking the customer enterprise status.
所述管理单元为B/S架构的管理系统。The management unit is a management system of B/S structure.
所述用户交互模块包括：预警单元，用于在所述总体可靠系数W低于警戒值时发出警告。The user interaction module includes: a warning unit, configured to issue a warning when the overall reliability coefficient W is lower than a warning value.
与现有技术相比，本发明的有益效果为：由于本发明的基于语义情感分析的贷后风险预警系统，能够自动的依次通过网络数据挖掘模块、语义情感分析模块、分析总模块完成客户企业相关信息的搜集、情感分析、并得出客户企业的总体可靠系数，并在总体可靠系数低于警戒值时由用户交互模块自动的发出警告，因此减少人工操作成本，提高工作效率，所以能够及时的对客户企业的重大变动做出预警，帮助银行更好的管理客户企业，有效的降低贷后风险。Compared with the prior art, the beneficial effects of the present invention are: due to the post-loan risk warning system based on semantic sentiment analysis of the present invention, the customer enterprise can be automatically and sequentially completed through the network data mining module, the semantic sentiment analysis module, and the total analysis module. The collection of relevant information, sentiment analysis, and the overall reliability coefficient of the customer enterprise are obtained, and when the overall reliability coefficient is lower than the warning value, the user interaction module automatically issues a warning, thus reducing manual operation costs and improving work efficiency, so it can be timely Provide early warning of major changes in client companies, help banks better manage client companies, and effectively reduce post-loan risks.
附图说明Description of drawings
图1为本发明的基于语义情感分析的贷后风险预警系统的结构框图。Fig. 1 is a structural block diagram of the post-loan risk early warning system based on semantic sentiment analysis of the present invention.
图2为图1所示语义情感分析模块情感分析的的流程图。FIG. 2 is a flow chart of sentiment analysis of the semantic sentiment analysis module shown in FIG. 1 .
图3为图1所示语义情感分析模块句级情感分析的流程图。Fig. 3 is a flowchart of sentence-level sentiment analysis of the semantic sentiment analysis module shown in Fig. 1 .
图4为图1所示总分析模块工作的流程图。Fig. 4 is a flow chart of the work of the total analysis module shown in Fig. 1 .
具体实施方式detailed description
为使本发明的目的、技术方案和优点更加清楚明白，下面结合实施方式和附图，对本发明做进一步详细说明。在此，本发明的示意性实施方式及说明用于解释本发明，但并不作为对本发明的限定。In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in further detail below in conjunction with the embodiments and accompanying drawings. Here, the exemplary embodiments and descriptions of the present invention are used to explain the present invention, but not to limit the present invention.
图1所示是本发明的基于语义情感分析的贷后风险预警系统的结构框图，如图1所示，本发明的基于语义情感分析的贷后风险预警系统包括：网络数据挖掘模块101、语义情感分析模块102、分析总模块103和用户交互模块104。网络数据挖掘模块101和语义情感分析模块102之间相互连接；语义情感分析模块102和分析总模块103之间相互连接；分析总模块103和用户交互模块104之间相互连接。Shown in Fig. 1 is the structural block diagram of the post-loan risk early warning system based on semantic sentiment analysis of the present invention, as shown in Figure 1, the post-loan risk early warning system based on semantic sentiment analysis of the present invention comprises: network data mining module 101, semantic Sentiment analysis module 102 , general analysis module 103 and user interaction module 104 . The network data mining module 101 and the semantic sentiment analysis module 102 are connected to each other; the semantic sentiment analysis module 102 is connected to the general analysis module 103; the general analysis module 103 and the user interaction module 104 are connected to each other.
其中：in:
网络数据挖掘模块101，该网络数据挖掘模块101与互联网相连接，用于从网络上搜集客户企业的相关信息，该相关信息包括以下的一种或者几种：与客户企业相关的新闻、评论、微博、举报、投诉；Network data mining module 101, the network data mining module 101 is connected to the Internet, and is used to collect relevant information of client enterprises from the Internet, and the relevant information includes one or more of the following: news, comments, Weibo, report, complaint;
在搜集客户企业的相关信息时网络数据挖掘模块101主要依靠现有的网络爬虫程序搜集网络上能够查到的所有与客户企业相关的新闻、评论、微博、举报、投诉等相关信息，然后将上述相关信息整理后发送给语义情感分析模块102；When collecting the relevant information of the client enterprise, the network data mining module 101 mainly relies on the existing web crawler program to collect all relevant information related to the client enterprise, such as news, comments, microblogs, reports, complaints, etc. The above-mentioned relevant information is sent to the semantic sentiment analysis module 102 after sorting;
网络数据挖掘模块101所使用的网络爬虫又被成为网页蜘蛛、网络机器人或网页追逐，是一种能够按照设定规则自动抓取网络信息或者程序脚本的计算机程序，另外，根据使用的搜索策略和网页分析算法的不同，网络爬虫可分为通用网络爬虫、聚焦爬虫等多种不同的类型，实际应用中，由于本发明的基于语义情感分析的贷后风险预警系统需要的数据只是和客户企业相关的文本信息，所以数据挖掘的范围可以进行大幅度的缩小以提高搜索的效率和信息实时性。一般来说，新闻，评论等通常都出现在主流的门户网站、行业论坛等网站，举报、投诉信息可以通过政府部门的网站简单高效的获取，新浪微博、人人、腾讯等主流的社交网站也有极高的可能出现与客户企业相关的信息，如果客户在淘宝等电子商务网站上有交易，那么电子商务网站也是关注的焦点。所以，网络数据挖掘模块101的搜索范围有着很强的针对性，所以聚焦爬虫是本发明首选的爬虫程序。The web crawler used by the network data mining module 101 is also called web spider, web robot or web chasing. It is a computer program that can automatically grab web information or program scripts according to set rules. According to different web page analysis algorithms, web crawlers can be divided into various types such as general web crawlers and focused crawlers. text information, so the scope of data mining can be greatly reduced to improve search efficiency and real-time information. Generally speaking, news, comments, etc. usually appear on mainstream portal websites, industry forums and other websites. Information on reports and complaints can be easily and efficiently obtained through websites of government departments. Mainstream social networking sites such as Sina Weibo, Renren, and Tencent There is also a very high possibility that information related to the customer's enterprise will appear. If the customer has transactions on e-commerce websites such as Taobao, then the e-commerce website is also the focus of attention. Therefore, the search range of the network data mining module 101 is highly targeted, so the focused crawler is the preferred crawler program in the present invention.
语义情感分析模块102，用于接收网络数据挖掘模块101搜集的相关信息并进行情感成分分析，生成情感极性K和情感强度M；The semantic sentiment analysis module 102 is used to receive the relevant information collected by the network data mining module 101 and perform sentiment component analysis to generate sentiment polarity K and sentiment intensity M;
语义情感分析是新兴的计算机语言学(computational linguistics)分支，不管在科学研究还是在商业应用都具有重要价值，其涉及计算语言学、数据挖掘以及机器学习等方面的基础研究，并处在不同学科的交叉点，因而情感分析可以促进不同学科的发展，具有重要的价值，其主要用于自然语言中情感成分的分析，也就是情感分析指判定文本所持有情感、观点、态度的极性和强度。通常根据文本粒度的不同，情感性分析主要分为三个方面的内容：词级情感分析(Word-level Sentiment Analysis，WSA)、句级情感分析(Sentence-level Sentiment Analysis，SSA)和篇章级情感分析(Document-levelSentiment Analysis，DSA)。Semantic sentiment analysis is an emerging branch of computational linguistics. It is of great value in both scientific research and commercial applications. It involves basic research in computational linguistics, data mining, and machine learning, and is in different disciplines. Therefore, sentiment analysis can promote the development of different disciplines and is of great value. It is mainly used for the analysis of emotional components in natural language, that is, sentiment analysis refers to the determination of the polarity and strength. Usually according to the text granularity, sentiment analysis is mainly divided into three aspects: word-level sentiment analysis (Word-level Sentiment Analysis, WSA), sentence-level sentiment analysis (Sentence-level Sentiment Analysis, SSA) and chapter-level sentiment analysis. Analysis (Document-level Sentiment Analysis, DSA).
情感分析涉及两个重要元素：情感极性和情感强度。情感极性是指文本对应的情感类别，情感极性通常划分为褒义、贬义和客观；而情感强度是对文本表达情感强弱的定量描述。在对某一相关信息进行情感分析后我们会得到一个情感极性和一个情感强度的值，例如，参见图2所示，语义情感分析模块102在接收到待分析文本后开始对待分析文本进行性感的分析，并得出褒义、贬义或客观的情感极性，之后再得出褒义级别或者贬义级别；Sentiment analysis involves two important elements: sentiment polarity and sentiment intensity. Emotional polarity refers to the emotional category corresponding to the text. Emotional polarity is usually divided into commendatory, derogatory, and objective; while emotional intensity is a quantitative description of the emotional strength of the text. After performing sentiment analysis on certain relevant information, we will get a value of sentiment polarity and sentiment strength. For example, referring to FIG. analysis, and obtain commendatory, derogatory or objective emotional polarity, and then obtain the commendatory level or derogatory level;
由于网络数据挖掘模块101从网络上搜集的客户企业相关信息大部分都是几句片段或者简单的句子。所以本发明的基于语义情感分析的贷后风险预警系统主要采用句级情感分析对信息的情感要素进行分析和分级。参见图3所示，使用句级的情感分析首先需要构建情感句分类器，对训练语料进行预处理(分词、词性标注、命名体识别以及分句等)，进而提取情感特征，训练情感分类器，然后预测句子情感极性。Most of the relevant information of the customer enterprise collected by the network data mining module 101 from the Internet is a few fragments or simple sentences. Therefore, the post-loan risk warning system based on semantic sentiment analysis of the present invention mainly uses sentence-level sentiment analysis to analyze and classify the sentiment elements of information. As shown in Figure 3, the use of sentence-level sentiment analysis first needs to build an emotional sentence classifier, preprocess the training corpus (word segmentation, part-of-speech tagging, naming body recognition, and sentence clauses, etc.), and then extract emotional features and train the emotional classifier. , and then predict the sentiment polarity of the sentence.
分析总模块103，用于获取情感极性K和情感强度M，并且根据相关信息的来源生成情感极性K值和情感强度M值，之后根据预定公式依次计算得出可靠系数P和总体可靠系数W；参见图4所示，具体的在分析总模块103中使用者可以预先定义当情感极性为贬义时K为负值，褒义时K为正值。当K为负值时，K的具体值由相关信息的来源确定，例如：当相关信息源于政府部门等比较权威网站上时k的值为-3；当相关信息源于电子商务网站时k的值为-2；当相关信息源于社交平台时k为-1。当K为正值时，K的具体值由客户企业的广告投放情况以及客户企业的性质来决定，例如：当客户企业为电商网站，互联网服务等类型的企业时，K的取值为0.5；当客户企业为餐饮，零售等会进行一定程度的互联网宣传的传统行业时K的取值为1；当客户企业为传统制造业等与互联网关联不大的传统产业时K的取值为2。其中，情感强度M由语义情感分析模块102通过分析词语的情感强度级别、语句的综合情感强度来获得，即不同的情感强度级别、语句的综合情感强度对应一个数字值，这个数字值可以事先进行定义，这样当数据进入分析总模块103时情感强度M已经被确定了。The general analysis module 103 is used to obtain the emotional polarity K and the emotional intensity M, and generate the emotional polarity K value and the emotional intensity M value according to the source of relevant information, and then calculate the reliability coefficient P and the overall reliability coefficient sequentially according to a predetermined formula W; see FIG. 4 , specifically in the general analysis module 103 , the user can predefine that K is a negative value when the emotional polarity is derogatory, and that K is a positive value when the emotional polarity is positive. When K is a negative value, the specific value of K is determined by the source of relevant information, for example: when the relevant information comes from a relatively authoritative website such as a government department, the value of k is -3; when the relevant information comes from an e-commerce website, k The value of k is -2; when the relevant information comes from social platforms, k is -1. When K is a positive value, the specific value of K is determined by the advertisement placement of the client company and the nature of the client company. For example: when the client company is an e-commerce website, Internet service, etc., the value of K is 0.5 ; When the customer enterprise is a traditional industry that conducts a certain degree of Internet publicity, such as catering and retail, the value of K is 1; when the customer enterprise is a traditional industry such as traditional manufacturing that has little connection with the Internet, the value of K is 2 . Wherein, the emotional intensity M is obtained by analyzing the emotional intensity level of the words and the comprehensive emotional intensity of the sentence by the semantic sentiment analysis module 102, that is, different emotional intensity levels and the comprehensive emotional intensity of the sentence correspond to a digital value, and this digital value can be determined in advance. Define, so when the data enters the general analysis module 103, the emotional strength M has been determined.
通过上述方式确定情感极性K值和情感强度M值后就可以根据预定公式计算可靠系数P，预定公式可以是：P＝K*M，使用者也可以根据实际情况设定其它公式，通过可靠系数P就可以定量的衡量当前的相关信息所体现的客户企业的可靠性。之后对所有相关信息计算得出的可靠系数p进行累加，就得到了客户企业的总体可靠系数W，即W＝P1+P2+P3+P4+P5+……+Pn，这里的P1、P2、P3、……Pn分别是不同相关信息对应的可靠系数，当客户企业的总体可靠系数W低于警戒值时，用户交互模块104便会发出警告、并重点监控总体可靠系数W低于警戒值的客户企业，并把企业信息、搜集到的负面信息等信息一并发给相关人员或机构。After determining the emotional polarity K value and the emotional intensity M value through the above method, the reliability coefficient P can be calculated according to the predetermined formula. The predetermined formula can be: P=K*M, and the user can also set other formulas according to the actual situation. The coefficient P can quantitatively measure the reliability of the client enterprise reflected in the current relevant information. Afterwards, the reliability coefficient p calculated by all relevant information is accumulated to obtain the overall reliability coefficient W of the customer enterprise, that is, W=P 1 +P 2 +P 3 +P 4 +P 5 +...+P n , Here, P 1 , P 2 , P 3 , ... P n are the reliability coefficients corresponding to different relevant information. When the overall reliability coefficient W of the client enterprise is lower than the warning value, the user interaction module 104 will issue a warning and focus on Monitor client companies whose overall reliability coefficient W is lower than the warning value, and send corporate information, collected negative information, and other information to relevant personnel or institutions.
用户交互模块104，用于在总体可靠系数W低于警戒值时发出警告，其内包含一个B/S架构的管理模块和一个预警模块。管理模块主要用于客户企业信息录入、信息搜集范围设置、预警范围设置、查看客户企业状态等工作。预警模块可以安装在银行工作人员的电脑中作为一个后台服务，当有客户企业存在异常时，预警模块会发出警告，并提供与该客户企业相关的一些信息供参考，警告在银行工作人员对客户单位做出调查并做出回应之前不会消失，确保问题客户企业得到有效的排查。The user interaction module 104 is used for issuing a warning when the overall reliability coefficient W is lower than the warning value, and includes a B/S structure management module and an early warning module. The management module is mainly used for customer enterprise information entry, information collection range setting, early warning range setting, viewing customer enterprise status, etc. The early warning module can be installed in the computer of the bank staff as a background service. When there is an abnormality in the customer company, the early warning module will issue a warning and provide some information related to the customer company for reference, warning the bank staff to the customer. The unit will not disappear until it makes an investigation and responds, ensuring that problematic customer companies are effectively checked.
Claims (7)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410138443.7A CN103886501B (en) | 2014-04-08 | 2014-04-08 | Post-loan risk early warning system based on semantic emotion analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410138443.7A CN103886501B (en) | 2014-04-08 | 2014-04-08 | Post-loan risk early warning system based on semantic emotion analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103886501A CN103886501A (en) | 2014-06-25 |
| CN103886501B true CN103886501B (en) | 2017-04-26 |
Family
ID=50955379
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410138443.7A Expired - Fee Related CN103886501B (en) | 2014-04-08 | 2014-04-08 | Post-loan risk early warning system based on semantic emotion analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103886501B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104616198B (en) * | 2015-02-12 | 2018-01-26 | 哈尔滨工业大学 | A kind of P2P network loan Risk Forecast Systems based on text analyzing |
| CN106530127B (en) * | 2016-11-09 | 2023-07-14 | 国网江苏省电力公司南京供电公司 | Customer complaint early warning monitoring and analysis system based on text mining technology |
| TWI719246B (en) * | 2017-08-29 | 2021-02-21 | 彰化商業銀行股份有限公司 | Enterprise customer intelligent risk control system |
| CN108197178A (en) * | 2017-12-22 | 2018-06-22 | 国云科技股份有限公司 | A method of enterprise risk assessment |
| CN108229806A (en) * | 2017-12-27 | 2018-06-29 | 中国银行股份有限公司 | A kind of method and system for analyzing business risk |
| CN108062423B (en) * | 2018-01-24 | 2019-04-19 | 北京百度网讯科技有限公司 | Information push method and device |
| CN110443236B (en) * | 2019-08-06 | 2022-04-29 | 中国工商银行股份有限公司 | Method and device for extracting essential information of post-loan documents |
| CN115659995B (en) * | 2022-12-30 | 2023-05-23 | 荣耀终端有限公司 | A text sentiment analysis method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1916956A (en) * | 2006-09-05 | 2007-02-21 | 中国工商银行股份有限公司 | System and method for quantizing risks of financial assets |
| CN1926569A (en) * | 2004-02-23 | 2007-03-07 | 自动金融系统股份有限公司 | Risk management system and method |
| CN102800018A (en) * | 2012-07-09 | 2012-11-28 | 贵州摇钱树软件开发有限公司 | Credit management system and credit processing method thereof |
-
2014
- 2014-04-08 CN CN201410138443.7A patent/CN103886501B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1926569A (en) * | 2004-02-23 | 2007-03-07 | 自动金融系统股份有限公司 | Risk management system and method |
| CN1916956A (en) * | 2006-09-05 | 2007-02-21 | 中国工商银行股份有限公司 | System and method for quantizing risks of financial assets |
| CN102800018A (en) * | 2012-07-09 | 2012-11-28 | 贵州摇钱树软件开发有限公司 | Credit management system and credit processing method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103886501A (en) | 2014-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103886501B (en) | Post-loan risk early warning system based on semantic emotion analysis | |
| Kufile et al. | A framework for integrating social listening data into brand sentiment analytics | |
| US11475414B2 (en) | Method and system for assigning and tracking progress of action items in a review meeting | |
| CN107330613A (en) | A kind of public sentiment monitoring method, equipment and computer-readable recording medium | |
| US9672475B2 (en) | Automated opinion prediction based on indirect information | |
| CN112990973B (en) | Online shop portrait construction method and system | |
| CN118193815A (en) | Network public opinion safety monitoring method based on deep learning neural network algorithm | |
| CN105359181A (en) | Assessing value of brand based on online content | |
| CN105938481A (en) | Anomaly detection method of multi-mode text data in cities | |
| Espina et al. | Infodemiology for syndromic surveillance of dengue and typhoid fever in the Philippines | |
| CN111427880A (en) | Data processing method, device, computing equipment and medium | |
| CN104732425A (en) | E-commerce platform customer behavior analytical method based on big data | |
| CN114417974A (en) | Model training method, information processing method, device, electronic device and medium | |
| Aggrawal et al. | Psychometric analysis and coupling of emotions between state bulletins and Twitter in India during COVID-19 infodemic | |
| CN118747684A (en) | A method, device, equipment and medium for recommending insurance products | |
| US11030228B2 (en) | Contextual interestingness ranking of documents for due diligence in the banking industry with topicality grouping | |
| US20200159738A1 (en) | Contextual interestingness ranking of documents for due diligence in the banking industry with entity grouping | |
| Ibrahim et al. | A multidimensional analysis of media framing in the Russia-Ukraine war | |
| CN108062423B (en) | Information push method and device | |
| Yuan et al. | Research on emotional tendency of earthquake disaster based on E-Trans model: take the topic of “Sichuan Earthquake” on microblog as an example | |
| Cortis et al. | A social opinion gold standard for the Malta government budget 2018 | |
| Chen et al. | The relationship between twitter sentiment and stock performance: A decision tree approach | |
| He et al. | Developing a workflow approach for mining online social media data | |
| Ali et al. | Generative AI in finance: Replicability, methodological contingencies, and future research directions | |
| Regla et al. | An Enhanced Research Productivity Monitoring System for Higher Education Institutions (HEI's) with Natural Language Processing (NLP) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170426 |