WO2017107794A1 - 风险识别方法及装置 - Google Patents
风险识别方法及装置 Download PDFInfo
- Publication number
- WO2017107794A1 WO2017107794A1 PCT/CN2016/109421 CN2016109421W WO2017107794A1 WO 2017107794 A1 WO2017107794 A1 WO 2017107794A1 CN 2016109421 W CN2016109421 W CN 2016109421W WO 2017107794 A1 WO2017107794 A1 WO 2017107794A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- risk
- user
- probability
- behavior data
- network behavior
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
- G06Q40/08—Insurance
Definitions
- the present invention relates to the field of data processing technologies, and in particular, to a risk identification method and apparatus.
- the prior art generally captures users who are less experienced according to the user's complaints, and performs manual appeasement or work order differentiation treatment for these users, and more focuses on the identification and remediation after the occurrence of problems, and cannot find the existing risk users in time. Affect the promotion efficiency of products or services.
- the invention provides a risk identification method and device, which are used for solving the problem that the user is unable to find the risk user in time and affect the promotion efficiency of the product or the service by manually searching for the user to improve the satisfaction.
- the present invention provides a risk identification method, including:
- the present invention provides a risk identification device comprising:
- the obtaining module is configured to acquire network behavior data when the user uses the target object in real time;
- the risk identification module is configured to perform risk identification on the network behavior data according to a pre-established risk model to obtain a risk probability of the user.
- the risk identification method and device of the present invention obtains the risk probability of the user by performing risk identification on the network behavior data according to a pre-established risk model by acquiring network behavior data when the user uses the target object in real time.
- the risk user can be automatically identified through data modeling, and the objectivity and accuracy of the user risk identification can be greatly improved.
- the potential risk user can be predicted in advance, which is beneficial to improving the promotion efficiency of the product or service.
- 1 is a schematic flow chart of an existing manual periodic search method
- FIG. 2 is a schematic flowchart of a risk identification method according to Embodiment 1 of the present invention.
- FIG. 3 is a schematic flowchart of a method for constructing a risk model according to Embodiment 1 of the present invention
- FIG. 4 is a schematic flowchart of a risk identification method according to Embodiment 2 of the present invention.
- FIG. 5 is a schematic flowchart diagram of a risk rating method according to Embodiment 2 of the present invention.
- FIG. 6 is a schematic diagram of application of a risk identification method according to Embodiment 2 of the present invention.
- FIG. 7 is a second schematic diagram of application of a risk identification method according to Embodiment 2 of the present invention.
- FIG. 8 is a schematic structural diagram of a risk identification apparatus according to Embodiment 3 of the present invention.
- FIG. 9 is a schematic structural diagram of a risk identification apparatus according to Embodiment 4 of the present invention.
- FIG. 10 is a schematic structural diagram of a rating module according to Embodiment 4 of the present invention.
- FIG. 2 it is a schematic flowchart of a risk identification method according to Embodiment 1 of the present invention, and the risk identification method includes:
- Step 101 Obtain real-time network behavior data when the user uses the target object.
- the network behavior data of the user using the target object can be captured in real time from the online application.
- the user can be captured in real time from the online application based on the specific communication interface.
- Network behavioral data in the process of products or services provided by the enterprise.
- the online behavior data of the user includes: user level, user fault information, user product release information, user product retention, user work order information, user complaint information, and user browsing information.
- Step 102 Perform risk identification on the network behavior data according to a pre-established risk model to obtain a risk probability of the user.
- a risk model is pre-established. After the online behavior data of the user is obtained, the online behavior data of the user can be directly used as the input of the risk model, and the risk model identifies the risk of the input network behavior data. The output of the risk model is the probability of the user's risk.
- the pre-established risk model may be a mathematical model established based on a machine learning method in a specific implementation; wherein the machine learning method may include one or more of the following methods: Correlation learning method, boosting learning method Bayesian learning method, Eigen learning method, Vector learning method and Meta-Heuristics learning method.
- the machine learning method may include one or more of the following methods: Correlation learning method, boosting learning method Bayesian learning method, Eigen learning method, Vector learning method and Meta-Heuristics learning method.
- those skilled in the art may adopt other machine learning methods according to actual needs, or may also adopt other mathematical modeling methods, such as various linear or nonlinear modeling methods, etc., which are specific to the risk model of this embodiment. Mathematical modeling methods are not limited.
- the risk identification method provided by the embodiment obtains the user when the target object is used in real time.
- the network behavior data is used to perform risk identification on the network behavior data according to a pre-established risk model to obtain a risk probability of the user.
- the risk user can be automatically identified through data modeling, which can greatly improve the objectivity and accuracy of the user risk identification, and further, the real-time network behavior of the user through data modeling. Data monitoring can predict potential risk users in advance and help improve the efficiency of product or service promotion.
- a risk model needs to be established in advance through the historical network behavior data of the user.
- FIG. 3 it is a schematic flowchart of a risk model construction method in Embodiment 1 of the present invention, and the risk model construction method includes:
- Step 201 Determine an algorithm corresponding to the risk model according to the historical network behavior data of the user.
- the connection to the Open Data Processing Service is established periodically or periodically through an Application Programming Interface (API), and the ODPS is based on the API call, and the corresponding user is
- the network behavior data is pushed to the API, where the network behavior data from the user at the ODPS is monitored and the network behavior data of the user acquired periodically or periodically is taken as the historical network behavior data of the user.
- API Application Programming Interface
- a regression analysis algorithm is preferably employed as the algorithm corresponding to the risk model.
- the algorithm corresponding to the risk model is:
- P denotes the probability of risk
- x i denotes the i-th influence factor
- ⁇ i denotes the coefficient of the i-th influence factor
- the historical network behavior data of the user is input into the algorithm as an impact factor of the algorithm, for example, user level, user fault information, user product release information, user product retention, user work order information, user complaint information, and
- the user's browsing information can be used as an influence factor of the algorithm.
- Step 202 Perform risk identification training on the historical network behavior data according to the algorithm. Obtaining a risk identification result of the historical network behavior data.
- the stored user's historical network behavior data is taken as input, input into the initially established risk model for risk identification training, and the risk identification result of historical network behavior data is obtained.
- the accuracy of the risk model it is necessary to perform data training on the model based on the historical network behavior data of the user, and the accuracy of the data model trained by the data can be more accurate.
- Step 203 Construct the risk model by using the risk identification result as a model parameter.
- the risk identification result is used as the model parameter of the risk model, and the model parameter is used to complete the construction of the risk model.
- the real-time network behavior data of the user is monitored by means of data modeling, and potential risk users can be predicted in advance.
- early processing of users can not only improve user experience, but also avoid negative impact on corporate image, facilitate product or service promotion, and thus reduce business operations. cost.
- FIG. 4 it is a schematic flowchart of a risk identification method according to Embodiment 2 of the present invention, and the risk identification method includes:
- Step 301 Determine an algorithm corresponding to the risk model according to historical network behavior data of the user.
- Step 302 Perform risk identification training on the historical network behavior data according to the algorithm, and obtain a risk identification result of the historical network behavior data.
- Step 303 Construct the risk model by using the risk identification result as a model parameter.
- Steps 301 to 303 are the procedures for establishing the risk model in advance. For details, refer to the description of related content in steps 201 to 203 of the foregoing embodiment, and details are not described herein again.
- Step 304 Obtain real-time network behavior data when the user uses the target object.
- the user's online network behavior data can be captured in real time from the online application.
- the online application can be used to capture the product or service provided by the user in the real-time application.
- Network behavior data includes: user level, user fault information, user product release information, user product retention, user work order information, user complaint information, and user browsing information.
- Step 305 Enter the network behavior data of the user into the risk model for risk identification, and obtain a risk probability of the user.
- the online behavior data of the user can be directly used as the input of the risk model constructed in the above step 303, and the risk model identifies the risk of the input network behavior data, and the output of the risk model is The probability of the user's risk.
- Step 306 Output the risk probability of the user, so that the administrator performs corresponding processing on the user according to the risk probability.
- the risk probability of the user may be notified to the administrator of the product or service by SMS, email or short message (Imessage). After obtaining the risk probability of the user, the relevant administrator can communicate with the user to help the user solve the current problem.
- Step 307 Receive a processing result of the administrator for the user, where the processing result includes a correction parameter that corrects a risk probability of the user.
- the user's risk will be reduced.
- the user's dissatisfaction will be caused.
- the problem accumulates, the user's emotion will be accumulated. It will become more and more violent, making the user's risk higher.
- Users may complain or complain about products or services. For example, complaints are made to enterprises through public methods such as Weibo and forums, which will have a very negative impact on the corporate image and increase the operating costs of the enterprise.
- the processing result includes a correction parameter that corrects the risk probability of the user.
- Step 308 Correct the risk probability by using the modified parameter to obtain a final risk probability of the user.
- Step 309 Rate the risk of the user by using the final risk probability.
- the rate is corrected to get the final risk probability of the user. Further, the risk degree of the user is rated by using the risk probability of the corrected user.
- a mapping relationship table between the risk probability and the risk level is set in advance, and after obtaining the final risk probability of the user, the mapping relationship table is queried, and the risk corresponding to the final risk probability is obtained therefrom.
- the target level is set in advance, and after obtaining the final risk probability of the user.
- the risk level includes: high risk, danger, sub-health and health, wherein the high-risk corresponding risk probability range [70%, 100%]; the risk corresponding probability probability range [40%, 70 %]; The range of risk probabilities corresponding to sub-health [10%, 40%]; the range of health-related risk probabilities [0%, 10%]. For example, when the final risk probability of the acquired user is 38%, the target level of the user risk is the sub-health level.
- the method provided in this embodiment may be implemented by the risk identification system shown in FIG. 6.
- the data modeling center in FIG. 6 is used to implement the process of constructing the risk model, and specifically, the related content in steps 301 to 303 may be performed.
- the risk identification center is configured to implement a risk identification process for the network behavior data when the user uses the target object, and specifically, the related content in steps 304 to 309 may be performed.
- the risk identification center After obtaining the risk probability of the user, the risk identification center sends the risk probability of the user to the administrator of the product or service through the notification channel, for example, the administrator can be notified by SMS, email or IM.
- the data modeling center in the risk identification system establishes a connection with the ODPS through the API, and the ODPS pushes the network behavior data of the corresponding user to the API periodically or periodically based on the API call, and listens to the user from the ODPS at the API.
- the network behavior data, and the user's network behavior data obtained periodically or periodically as the user's historical network behavior data.
- the risk identification center can be in real time
- the trend of the user's risk probability is monitored, and the trend of the user's risk probability can be displayed on the information display platform based on the API.
- FIG. 7 it is an application example diagram of the risk identification method of the second embodiment.
- the risk degree of the user is monitored. After the user is set to the sub-health level, the user's risk probability will be linearly attenuated within a period of time after the user uses the product, thereby affecting the user's risk degree to different degrees. .
- the risk identification method provided by the embodiment obtains the risk behavior of the network behavior data according to the pre-established risk model by obtaining the network behavior data when the user uses the target object in real time, and obtains the risk probability of the user according to the risk. The probability ranks the user's risk.
- the risk user can be automatically identified through data modeling, which can greatly improve the objectivity and accuracy of the user risk identification.
- the user's real-time network behavior data is monitored by means of data modeling, and potential risk users can be predicted in advance. Before users complain or complain about products or services, early processing of users can not only improve user experience, but also avoid negative impact on corporate image, facilitate product or service promotion, and thus reduce business operations. cost.
- FIG. 8 is a schematic structural diagram of a risk identification apparatus according to Embodiment 3 of the present invention.
- the risk identification apparatus includes: an acquisition module 11 and a risk identification module 12.
- the obtaining module 11 is configured to acquire network behavior data when the user uses the target object in real time.
- the obtaining module 11 can capture the online network behavior data of the user in real time from the online application. Specifically, in this embodiment, the obtaining module 11 can capture the user in real time from the online application through the communication interface.
- the user's network behavior data includes: user level, user fault information, user product release information, user product retention, user work order information, user complaint information, and user browsing information.
- the risk identification module 12 is configured to perform risk identification on the network behavior data according to a pre-established risk model to obtain a risk probability of the user.
- a risk model is pre-established. After the network behavior data of the user is obtained in real time, the risk identification module 12 can directly input the user's network behavior data as a risk model, and the risk model performs the input network behavior data. Risk identification, the output of the risk model is the risk probability of the user.
- the risk identification device obtains the risk behavior of the network behavior data according to the pre-established risk model by acquiring the network behavior data when the user uses the target in real time, and obtaining the risk probability of the user.
- the risk user can be automatically identified through data modeling, which can greatly improve the objectivity and accuracy of the user risk identification.
- the user's real-time network behavior data is monitored by means of data modeling, and potential risk users can be predicted in advance.
- FIG. 9 is a schematic structural diagram of a risk identification apparatus according to Embodiment 4 of the present invention.
- the risk identification apparatus includes: an acquisition module 11 and a risk identification module 12 in the foregoing Embodiment 3, and a rating module 13
- the rating module 13 is configured to rate the user's risk according to the risk probability after the risk identification module 12 obtains the risk probability of the user.
- the determining module 14 is configured to determine an algorithm corresponding to the risk model according to the historical network behavior data of the user.
- the obtaining module 11 is configured to periodically or periodically acquire the network behavior data of the user before acquiring the network behavior data of the user in real time, and store the network behavior data as historical network behavior data.
- the training module 15 is configured to perform risk identification training on the historical network behavior data according to the algorithm, and obtain a risk identification result of the historical network behavior data.
- the model building module 16 is configured to construct the risk model using the risk identification result as a model parameter.
- P denotes the risk probability
- x i denotes the i-th influence factor
- ⁇ i denotes the coefficient of the i-th influence factor
- the historical network behavior data serves as an influence factor in the algorithm.
- FIG. 10 is a schematic structural diagram of a rating module in the fourth embodiment.
- An optional structure of the rating module 13 includes an output unit 131, a receiving unit 132, and a rating unit 133.
- the output unit 131 is configured to output the risk probability of the user, so that the administrator performs corresponding processing on the user according to the risk probability.
- the receiving unit 132 is configured to receive a processing result of the administrator for the user.
- the rating unit 133 is configured to rate the risk level of the user according to the processing result.
- the processing result includes a correction parameter that corrects the risk probability.
- the rating unit 133 is specifically configured to modify the risk probability by using the modified parameter to obtain a final risk probability of the user, and use the final risk probability to rate the risk of the user.
- the correction parameter includes: a first weight value corresponding to the risk probability, and an estimated risk probability and a probability obtained by the administrator performing related processing on the user and evaluating the risk of the user.
- a rating unit 133 specifically configured to acquire a first product of the risk probability and the first weight value, and a second product of the estimated risk probability and the second weight value, and calculate the first product sum The sum value of the second product is taken as the final risk probability.
- the rating unit 133 is specifically configured to query a mapping relationship between the preset risk probability and the risk level according to the final risk probability, and obtain a target level of the risk corresponding to the final risk probability.
- the functional modules of the risk identification device provided in this embodiment can be used to execute the process of the risk identification method shown in FIG. 2 to FIG. 4, and the specific working principle is not described again. Description of the example.
- the risk identification device obtains the risk behavior of the network behavior data according to the pre-established risk model by obtaining the network behavior data when the user uses the target object in real time, and obtains the risk probability of the user according to the risk. The probability ranks the user's risk.
- the risk user can be automatically identified through data modeling, which can greatly improve the objectivity and accuracy of the user risk identification.
- the user's real-time network behavior data is monitored by means of data modeling, and potential risk users can be predicted in advance. Before users complain or complain about products or services, early processing of users can not only improve user experience, but also avoid negative impact on corporate image, facilitate product or service promotion, and thus reduce business operations. cost.
- the aforementioned program can be stored in a computer readable storage medium.
- the program when executed, performs the steps including the foregoing method embodiments; and the foregoing storage medium includes various media that can store program codes, such as a ROM, a RAM, a magnetic disk, or an optical disk.
Landscapes
- Business, Economics & Management (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
一种风险识别方法及装置,该方法包括下述步骤:实时获取用户使用目标对象时的网络行为数据(101),依据预先建立的风险模型对所述网络行为数据进行风险识别,得到所述用户的风险识别概率(102)。根据用户的网络行为数据,通过数据建模可以自动识别出风险用户,能够提高用户风险识别的客观性和准确性。进一步地,通过数据建模的方式对用户实时的网络行为数据进行监测,能够提前预测出潜在的风险用户,有利于提高产品或者服务。
Description
本发明涉及数据处理技术领域,尤其涉及一种风险识别方法及装置。
在使用企业所提供的产品或者服务的过程中,用户往往会遇到产品故障、服务器响应用时长、工单提交失败等各种问题。随着这些问题的累积,用户对该产品或者服务的体验越来越差,企业收到的投诉意见也会越来越多,对于产品或者服务的推广会造成影响,为了将产品或者服务进一步推广势必需要企业加大成本。
目前,为了提高用户对产品或者服务的体验,降低用户的投诉率,提升用户的满意度,企业可以通过人工定期查找的方式,捕获感受较差的用户,然后通过主动关怀或者工单区别处理的方法,来提升体验较差的用户的满意度。人工对用户进行定期查找的方法整个流程图如图1所示。该方法整个流程都需要人工干预,增加了人工成本。
而且现有技术一般根据用户的投诉意见,来捕获感受较差的用户,并针对这些用户进行人工安抚或工单区别处理,更偏重出现问题后的识别及补救,无法及时发现存在的风险用户,影响产品或者服务的推广效率。
发明内容
本发明提供一种风险识别方法及装置,用于解决通过人工对用户进行定期查找来提升满意度的方法存在无法及时发现风险用户,影响产品或者服务的推广效率的问题。
为了实现上述目的,本发明提供了一种风险识别方法,包括:
实时获取用户使用目标对象时的网络行为数据;
依据预先建立的风险模型对所述网络行为数据进行风险识别,得到所
述用户的风险概率。
为了实现上述目的,本发明提供了一种风险识别装置,包括:
获取模块,用于实时获取用户使用目标对象时的网络行为数据;
风险识别模块,用于依据预先建立的风险模型对所述网络行为数据进行风险识别,得到所述用户的风险概率。
本发明的风险识别方法及装置,通过实时获取用户使用目标对象时的网络行为数据,依据预先建立的风险模型对所述网络行为数据进行风险识别,得到所述用户的风险概率。本发明中根据用户的网络行为数据,通过数据建模可以自动识别出风险用户,能够大大提高用户风险识别的客观性和准确性。进一步地,通过数据建模的方式对用户实时的网络行为数据进行监测,能够提前预测出潜在的风险用户,有利于提高产品或者服务的推广效率。
图1为现有人工定期查找方法的流程示意图;
图2为本发明实施例一的风险识别方法的流程示意图;
图3为本发明实施例一中风险模型构建方法的流程示意图;
图4为本发明实施例二的风险识别方法的流程示意图;
图5为本发明实施例二中风险度评级方法的流程示意图;
图6为本发明实施例二的风险识别方法的应用示意图之一;
图7为本发明实施例二的风险识别方法的应用示意图之二;
图8为本发明实施例三的风险识别装置的结构示意图;
图9为本发明实施例四的风险识别装置的结构示意图;
图10为本发明实施例四中的评级模块的结构示意图。
下面结合附图对本发明实施例提供的风险识别方法及装置进行详细描述。
实施例一
如图2所示,其为本发明实施例一的风险识别方法的流程示意图,该风险识别方法包括:
步骤101、实时获取用户使用目标对象时的网络行为数据。
在实际中,可以从在线应用程序中实时抓取用户的使用目标对象的网络行为数据,具体而言,本实施例中,基于特定通信接口可以从在线应用程序中,实时抓取该用户在使用企业所提供的产品或服务的过程中的网络行为数据。其中,用户的在线网络行为数据包括:用户级别、用户故障信息、用户产品释放信息、用户产品保有、用户工单信息、用户投诉信息以及用户的浏览信息等。
步骤102、依据预先建立的风险模型对所述网络行为数据进行风险识别,得到所述用户的风险概率。
本实施例中,预先建立有一个风险模型,在获取到用户在线的网络行为数据后,可直接以用户在线的网络行为数据作为风险模型的输入,风险模型对输入的网络行为数据进行风险识别,风险模型的输出就是用户的风险概率。
其中预先建立风险模型在具体实现中可以为基于机器学习方法建立的数学模型;其中,机器学习方法可以包括如下方法中的一种或多种:相关(Correlation)学习方法、增强(boosting)学习方法、贝叶斯(Bayes)学习方法、特征空间(Eigen)学习方法、特征向量(Vector)学习方法和元启发式(Meta-Heuristics)学习方法。当然,本领域技术人员可以根据实际需要,采用其它机器学习方法,或者,还可以采用其它数学建模方法,如各种线性或者非线性建模方法等等,本实施例对具体的风险模型的数学建模方法不加以限制。
本实施例提供的风险识别方法,通过实时获取用户使用目标对象时的
网络行为数据,依据预先建立的风险模型对所述网络行为数据进行风险识别,得到所述用户的风险概率。本实施例中根据用户的网络行为数据,通过数据建模可以自动识别出风险用户,能够大大提高用户风险识别的客观性和准确性,进一步地,通过数据建模的方式对用户实时的网络行为数据进行监测,能够提前预测出潜在的风险用户,有利于提高产品或者服务的推广效率。
进一步地,在步骤101实时获取用户在线的网络行为数据之前,还需要通过用户的历史网络行为数据来预先建立一个风险模型。
如图3所示,其为本发明实施例一中的风险模型构建方法的流程示意图,该风险模型构建方法包括:
步骤201、依据所述用户的历史网络行为数据,确定所述风险模型对应的算法。
具体地,定期或定时地通过应用程序编程接口(Application Programming Interface,简称API)建立到开放数据处理服务(Open Data Processing Service,简称ODPS)的连接,由ODPS基于API调用的方式,将相应用户的网络行为数据推送至该API,在该API处监听获取来自在ODPS的用户的网络行为数据,并将该定期或定时获取的用户的网络行为数据作为用户的历史网络行为数据。
本实施例中,优选地采用回归分析算法作为风险模型对应的算法。其中,该风险模型对应的算法为:
其中,P,表示风险概率;xi,表示第i个影响因子;βi,表示第i个影响因子的系数。
本实施例中用户的历史网络行为数据用于作为算法的影响因子输入到该算法中,例如,用户级别、用户故障信息、用户产品释放信息、用户产品保有、用户工单信息、用户投诉信息以及用户的浏览信息可以分别作为算法的影响因子。
步骤202、按照所述算法对所述历史网络行为数据进行风险识别训练,
得到所述历史网络行为数据的风险识别结果。
基于回归分析算法建立初步的风险模型后,将存储的用户的历史网络行为数据作为输入,输入到初步建立的风险模型中进行风险识别训练,得到历史网络行为数据的风险识别结果。本实施例中,为了提高风险模型的精确度,需要基于用户的历史网络行为数据对模型进行数据训练,经过数据训练的风险模型的精准度能够更为精确。
步骤203、使用所述风险识别结果作为模型参数构建所述风险模型。
在获取到历史网络行为数据的风险识别结果后,将该风险识别结果作为风险模型的模型参数,使用该模型参数来完成风险模型的构建。
本实施例中,通过数据建模的方式对用户实时的网络行为数据进行监测,能够提前预测出潜在的风险用户。在用户对产品或者服务提出投诉或者抱怨之前,提早对用户进行相关处理,不仅可以提高用户感受,而且可以避免对企业形象造成的负面影响,有利于产品或者服务的推广,进而能降低企业的运营成本。
实施例二
如图4所示,其为本发明实施例二的风险识别方法的流程示意图,该风险识别方法包括:
步骤301、依据用户的历史网络行为数据,确定所述风险模型对应的算法。
步骤302、按照所述算法对所述历史网络行为数据进行风险识别训练,得到所述历史网络行为数据的风险识别结果。
步骤303、使用所述风险识别结果作为模型参数构建所述风险模型。
步骤301~步骤303为预先建立风险模型的过程,可参见上述实施例步骤201~步骤203中相关内容的记载,此处不再赘述。
步骤304、实时获取用户使用目标对象时的网络行为数据。
在实际中,可以从在线应用程序中实时抓取用户的在线网络行为数据,具体而言,本实施例中,可以从在线应用程序实时抓取处于该用户在使用企业所提供的产品或服务过程中的网络行为数据。其中,用户的在线网络
行为数据包括:用户级别、用户故障信息、用户产品释放信息、用户产品保有、用户工单信息、用户投诉信息以及用户的浏览信息等。
步骤305、将用户的所述网络行为数据输入到所述风险模型中进行风险识别,得到所述用户的风险概率。
在获取到用户在线的网络行为数据后,可直接以用户在线的网络行为数据作为上述步骤303中所构建的风险模型的输入,风险模型对输入的网络行为数据进行风险识别,风险模型的输出就是用户的风险概率。
步骤306、输出用户的所述风险概率,以使管理员按照所述风险概率对所述用户进行相应处理。
在获取到用户的风险概率后,可以将该用户的风险概率通过短信、邮件或者短消息(Imessage)通知给产品或者服务的管理员。相关管理员获取到该用户的风险概率后,可以与用户进行沟通,帮助用户解决当前遇到的问题。
步骤307、接收所述管理员针对所述用户的处理结果,其中,所述处理结果中包括对用户的风险概率进行修正的修正参数。
在相关的管理员对用户的问题进行处理后,用户的风险就会降低,实际应用中,当用户的问题长时间得不到处理会引起用户的不满,随着这些问题的累积,用户的情绪将会越来越暴躁,使得用户的风险变高。用户可能就会对产品或者服务提出投诉或者抱怨,例如,通过微博、论坛等公开方式对企业进行投诉,从而给企业形象带来极度负面的影响,提高了企业的运营成本。
为了更准确地为用户最终的危险性别进行评级,管理员需要将处理结果进行反馈。其中,该处理结果中包括对用户的风险概率进行修正的修正参数。
步骤308、使用所述修正参数对所述风险概率进行修正,得到所述用户的最终风险概率。
步骤309、采用所述最终风险概率对所述用户的风险度进行评级。
在获取到反馈的处理结果后,就可以根据该修正参数对用户的风险概
率进行修正,得到该用户的最终风险概率。进一步地,采用修正后的用户的风险概率,对用户的风险度进行评级。
如图5所示,其为本实施例二中对用户的风险度进行评级的示意图。其中,反馈的处理结果中的所述修正参数包括:通过风险模型计算出的风险概率对应的第一权重值,以及在管理员对用户进行相关处理,对用户的风险重新进行评估得到的评估风险概率和与该评估风险概率对应的第二权重值,其中,第一权重值+第二权重值=1。
使用修正参数对风险概率进行修正,得到用户的最终风险概率,具体为获取风险概率与第一权重值的第一乘积,以及评估风险概率与第二权重值的第二乘积,计算第一乘积和第二乘积的和值作为最终风险概率。
进一步地,本实施例中预先设置有风险概率与风险度级别之间的映射关系表,在获取到用户的最终风险概率后,查询该映射关系表,从中得到与该最终风险概率对应的风险度的目标级别。
本实施例中,风险度级别包括:高危、危险、亚健康和健康,其中,高危对应风险概率的取值范围[70%,100%];危险对应风险概率的取值范围[40%,70%];亚健康对应风险概率的取值范围[10%,40%];健康对应风险概率的取值范围[0%,10%]。例如,当获取到的用户的最终风险概率为38%时,则用户风险度的目标级别就是亚健康级别。
本实施例提供的方法可以由图6所示的风险识别系统来完成,图6中的数据建模中心用于实现风险模型的构建流程,具体可以执行步骤301~步骤303中的相关内容。风险识别中心用于实现对用户使用目标对象时的网络行为数据的风险识别流程,具体可以执行步骤304~步骤309中的相关内容。在获取到用户的风险概率后,风险识别中心通过通知通道向产品或者服务的管理员发送用户的风险概率,例如可以通过短信、邮件或者IM等方式通知管理员。风险识别系统中数据建模中心通过API与ODPS建立连接,由ODPS基于API调用的方式,定期或定时地将相应用户的网络行为数据推送至该API,在该API处监听获取来自在ODPS的用户的网络行为数据,并将该定期或定时获取的用户的网络行为数据作为用户的历史网络行为数据。在获取到用户的最终风险概率后,风险识别中心可以实时地
监控用户的风险概率的变化趋势,并且可以基于API将用户的风险概率的变化趋势在信息展示平台进行显示。
如图7所示,其为本实施例二的风险识别方法的应用示例图。基于上述风险识别系统对用户的风险度进行监控,在将用户设置为亚健康级别后,在用户使用产品的后面一段时间内,用户的风险概率将线性衰减,进而不同程度的影响用户的风险度。
本实施例提供的风险识别方法,通过实时获取用户使用目标对象时的网络行为数据,依据预先建立的风险模型对所述网络行为数据进行风险识别,得到所述用户的风险概率,根据所述风险概率对所述用户的风险度进行评级。本实施例中根据用户的网络行为数据,通过数据建模可以自动识别出风险用户,能够大大提高用户风险识别的客观性和准确性。
进一步地,通过数据建模的方式对用户实时的网络行为数据进行监测,能够提前预测出潜在的风险用户。在用户对产品或者服务提出投诉或者抱怨之前,提早对用户进行相关处理,不仅可以提高用户感受,而且可以避免对企业形象造成的负面影响,有利于产品或者服务的推广,进而能降低企业的运营成本。
实施例三
如图8所示,其为本发明实施例三的风险识别装置的结构示意图,该风险识别装置包括:获取模块11和风险识别模块12。
获取模块11,用于实时获取用户使用目标对象时的网络行为数据。
在实际中,获取模块11可以从在线应用程序中实时抓取用户的在线网络行为数据,具体而言,本实施例中,获取模块11通过通信接口可以从在线应用程序实时抓取该用户在使用企业所提供的产品或服务过程中的网络行为数据。其中,用户的网络行为数据包括:用户级别、用户故障信息、用户产品释放信息、用户产品保有、用户工单信息、用户投诉信息以及用户的浏览信息等。
风险识别模块12,用于依据预先建立的风险模型对所述网络行为数据进行风险识别,得到所述用户的风险概率。
本实施例中,预先建立有一个风险模型,在实时获取到用户的网络行为数据后,风险识别模块12可直接以用户的网络行为数据作为风险模型的输入,风险模型对输入的网络行为数据进行风险识别,风险模型的输出就是用户的风险概率。
其中预先建立风险模型在具体实现可参见上述实施例中相关内容的记载,此处不再赘述。
本实施例提供的风险识别装置,通过实时获取用户使用目标时的网络行为数据,依据预先建立的风险模型对所述网络行为数据进行风险识别,得到所述用户的风险概率。本实施例中根据用户的网络行为数据,通过数据建模可以自动识别出风险用户,能够大大提高用户风险识别的客观性和准确性。进一步地,通过数据建模的方式对用户实时的网络行为数据进行监测,能够提前预测出潜在的风险用户。
实施例四
如图9所示,其为本发明实施例四的风险识别装置的结构示意图,该风险识别装置除了包括上述实施例三中的获取模块11和风险识别模块12之外,还包括:评级模块13、确定模块14、训练模块15和模型构建模块16。
其中,评级模块13,用于在风险识别模块12得到用户的风险概率之后,根据风险概率对用户的风险度进行评级
确定模块14,用于依据用户的历史网络行为数据,确定所述风险模型对应的算法。
具体地,获取模块11,用于在实时获取用户的网络行为数据之前,定期或定时获取用户的网络行为数据,并将所述网络行为数据作为历史网络行为数据进行存储。
训练模块15,用于按照所述算法对所述历史网络行为数据进行风险识别训练,得到所述历史网络行为数据的风险识别结果。
模型构建模块16,用于使用所述风险识别结果作为模型参数构建所述风险模型。
进一步地,所述风险模型对应的算法为:
其中,P,表示风险概率;xi,表示第i个影响因子;βi,表示第i个影响因子的系数;所述历史网络行为数据作为所述算法中的影响因子。
图10所示,其为本实施例四中评级模块的结构示意图。其中,评级模块13的一种可选地结构方式包括:输出单元131、接收单元132和评级单元133。
具体地,输出单元131,用于输出所述用户的所述风险概率,以使管理员按照所述风险概率对所述用户进行相应处理。
接收单元132,用于接收所述管理员针对所述用户的处理结果。
评级单元133,用于根据所述处理结果对所述用户的风险度进行评级。
进一步地,所述处理结果包括对所述风险概率进行修正的修正参数。
评级单元133,具体用于使用所述修正参数对所述风险概率进行修正,得到所述用户的最终风险概率,采用所述最终风险概率对所述用户的风险度进行评级。
可选地,所述修正参数包括:所述风险概率对应的第一权重值,以及在所述管理员对所述用户进行相关处理,对所述用户的风险进行评估得到的评估风险概率和与所述评估风险概率对应的第二权重值;所述第一权重值+所述第二权重值=1。
评级单元133,具体用于获取所述风险概率与所述第一权重值的第一乘积,以及所述评估风险概率与所述第二权重值的第二乘积,以及计算所述第一乘积和所述第二乘积的和值作为所述最终风险概率。
进一步地,评级单元133,具体用于依据所述最终风险概率查询预设的风险概率与风险度级别之间的映射关系表,获取与所述最终风险概率对应的风险度的目标级别。
本实施例提供的风险识别装置的各功能模块可用于执行图2~4中所示的风险识别方法的流程,其具体工作原理不再赘述,详见方法实
施例的描述。
本实施例提供的风险识别装置,通过实时获取用户使用目标对象时的网络行为数据,依据预先建立的风险模型对所述网络行为数据进行风险识别,得到所述用户的风险概率,根据所述风险概率对所述用户的风险度进行评级。本实施例中根据用户的网络行为数据,通过数据建模可以自动识别出风险用户,能够大大提高用户风险识别的客观性和准确性。
进一步地,通过数据建模的方式对用户实时的网络行为数据进行监测,能够提前预测出潜在的风险用户。在用户对产品或者服务提出投诉或者抱怨之前,提早对用户进行相关处理,不仅可以提高用户感受,而且可以避免对企业形象造成的负面影响,有利于产品或者服务的推广,进而能降低企业的运营成本。
本领域普通技术人员可以理解:实现上述各方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成。前述的程序可以存储于一计算机可读取存储介质中。该程序在执行时,执行包括上述各方法实施例的步骤;而前述的存储介质包括:ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是:以上各实施例仅用以说明本发明的技术方案,而非对其限制;尽管参照前述各实施例对本发明进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分或者全部技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本发明各实施例技术方案的范围。
Claims (16)
- 一种风险识别方法,其特征在于,包括:实时获取用户使用目标对象时的网络行为数据;依据预先建立的风险模型对所述网络行为数据进行风险识别,得到所述用户的风险概率。
- 根据权利要求1所述的风险识别方法,其特征在于,所述实时获取用户的在线网络行为数据之前,还包括:依据用户的历史网络行为数据,确定所述风险模型对应的算法;按照所述算法对所述历史网络行为数据进行风险识别训练,得到所述历史网络行为数据的风险识别结果;使用所述风险识别结果作为模型参数构建所述风险模型。
- 根据权利要求1-3任一项所述的风险识别方法,其特征在于,所述依据预先建立的风险模型对所述网络行为数据进行风险识别,得到所述用户的风险概率之后,还包括:根据所述风险概率对所述用户的风险度进行评级。
- 根据权利要求4所述的风险识别方法,其特征在于,所述根据所述风险概率对所述用户的风险度进行评级,包括:输出用户的所述风险概率,以使管理员按照所述风险概率对所述用户进行相应处理;接收所述管理员针对所述用户的处理结果;根据所述处理结果对所述用户的风险度进行评级。
- 根据权利要求5所述的风险识别方法,其特征在于,所述处理结果包括对所述风险概率进行修正的修正参数;所述根据所述处理结果对所述用户的风险度进行评级,包括:使用所述修正参数对所述风险概率进行修正,得到所述用户的最终风险概率;采用所述最终风险概率对所述用户的风险度进行评级。
- 根据权利要求6所述的风险识别方法,其特征在于,所述修正参数包括:所述风险概率对应的第一权重值,以及在所述管理员对所述用户进行相关处理,对所述用户的风险进行评估得到的评估风险概率和与所述评估风险概率对应的第二权重值;所述第一权重值+所述第二权重值=1;所述使用所述修正参数对所述风险概率进行修正,得到所述用户的最终风险概率,包括:获取所述风险概率与所述第一权重值的第一乘积,以及所述评估风险概率与所述第二权重值的第二乘积;计算所述第一乘积和所述第二乘积的和值作为所述最终风险概率。
- 根据权利要求7所述的风险识别方法,其特征在于,所述采用所述最终风险概率对所述用户的风险度进行评级,包括:依据所述最终风险概率查询预设的风险概率与风险度级别之间的映射关系表;获取与所述最终风险概率对应的风险度的目标级别。
- 一种风险识别装置,其特征在于,包括:获取模块,用于实时获取用户使用目标对象时的网络行为数据;风险识别模块,用于依据预先建立的风险模型对所述网络行为数据进行风险识别,得到所述用户的风险概率。
- 根据权利要求9所述的风险识别装置,其特征在于,还包括:确定模块,用于依据用户的历史网络行为数据,确定所述风险模型对应的算法;训练模块,用于按照所述算法对存储的所述历史网络行为数据进行风险识别训练,得到所述历史网络行为数据的风险识别结果;模型构建模块,用于使用所述风险识别结果作为模型参数构建所述风险模型。
- 根据权利要求9-11任一项所述的风险识别装置,其特征在于,还包括:评级模块,用于根据所述风险概率对所述用户的风险度进行评级。
- 根据权利要求12所述的风险识别装置,其特征在于,所述评级模块,包括:输出单元,用于输出所述用户的所述风险概率,以使管理员按照所述风险概率对所述用户进行相应处理;接收单元,用于接收所述管理员针对所述用户的处理结果;评级单元,用于根据所述处理结果对所述用户的风险度进行评级。
- 根据权利要求13所述的风险识别装置,其特征在于,所述处理结果包括对所述风险概率进行修正的修正参数;所述评级单元,具体用于使用所述修正参数对所述风险概率进行修正,得到所述用户的最终风险概率,采用所述最终风险概率对所述用户的风险度进行评级。
- 根据权利要求14所述的风险识别装置,其特征在于,所述修正参数包括:所述风险概率对应的第一权重值,以及在所述管理员对所述用户进行相关处理,对所述用户的风险进行评估得到的评估风险概率和与所述评估风险概率对应的第二权重值;所述第一权重值+所述第二权重值=1;所述评级单元,具体用于获取所述风险概率与所述第一权重值的第一乘积,以及所述评估风险概率与所述第二权重值的第二乘积,以及计算所述第一乘积和所述第二乘积的和值作为所述最终风险概率。
- 根据权利要求15所述的风险识别装置,其特征在于,所述评级单元,具体用于依据所述最终风险概率查询预设的风险概率与风险度级别之间的映射关系表,获取与所述最终风险概率对应的风险度的目标级别。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510971534.3A CN106910078A (zh) | 2015-12-22 | 2015-12-22 | 风险识别方法及装置 |
CN201510971534.3 | 2015-12-22 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2017107794A1 true WO2017107794A1 (zh) | 2017-06-29 |
Family
ID=59089028
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2016/109421 WO2017107794A1 (zh) | 2015-12-22 | 2016-12-12 | 风险识别方法及装置 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN106910078A (zh) |
WO (1) | WO2017107794A1 (zh) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109657918A (zh) * | 2018-11-19 | 2019-04-19 | 平安科技(深圳)有限公司 | 关联评估对象的风险预警方法、装置和计算机设备 |
CN110135681A (zh) * | 2019-04-03 | 2019-08-16 | 平安科技(深圳)有限公司 | 风险用户识别方法、装置、可读存储介质及终端设备 |
CN111815187A (zh) * | 2020-07-14 | 2020-10-23 | 北京航空航天大学 | 一种基于方向加权网络的制造过程风险评价方法 |
CN112883347A (zh) * | 2021-01-29 | 2021-06-01 | 深圳市鹰硕技术有限公司 | 一种智慧教育平台的应用安全管控方法及系统 |
CN113592315A (zh) * | 2021-08-04 | 2021-11-02 | 北京沃东天骏信息技术有限公司 | 一种处理纠纷单的方法和装置 |
CN114679335A (zh) * | 2022-03-01 | 2022-06-28 | 国网宁夏电力有限公司 | 电力监控系统网络安全风险评估训练、评估方法及设备 |
CN114885183A (zh) * | 2022-04-21 | 2022-08-09 | 武汉斗鱼鱼乐网络科技有限公司 | 一种识别礼包风险用户的方法、装置、介质及设备 |
CN118296392A (zh) * | 2024-06-06 | 2024-07-05 | 戎行技术有限公司 | 一种基于机器学习ai模型的网络行为数据风险评估方法 |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108846687A (zh) * | 2018-04-02 | 2018-11-20 | 平安科技(深圳)有限公司 | 客户分类方法、装置及存储介质 |
CN111612290B (zh) * | 2020-03-31 | 2023-04-07 | 深圳奇迹智慧网络有限公司 | 安保方案生成方法、装置、计算机设备和存储介质 |
CN111737101B (zh) * | 2020-06-24 | 2022-05-03 | 平安科技(深圳)有限公司 | 基于大数据的用户行为监测方法、装置、设备及介质 |
CN112330475A (zh) * | 2020-11-26 | 2021-02-05 | 重庆趣嗨租科技有限公司 | 一种ai风险识别系统 |
CN112801563B (zh) * | 2021-04-14 | 2021-08-17 | 支付宝(杭州)信息技术有限公司 | 风险评估方法和装置 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101110699A (zh) * | 2007-08-07 | 2008-01-23 | 广州诚予国际市场信息研究有限公司 | 具有网络满意度预测预警功能的系统及其实现方法 |
CN102495942A (zh) * | 2011-10-26 | 2012-06-13 | 深信服网络科技(深圳)有限公司 | 一种组织内部网络风险评估方法及系统 |
CN103123712A (zh) * | 2011-11-17 | 2013-05-29 | 阿里巴巴集团控股有限公司 | 一种网络行为数据的监控方法和系统 |
CN104834983A (zh) * | 2014-12-25 | 2015-08-12 | 平安科技(深圳)有限公司 | 业务数据处理方法及装置 |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101470887A (zh) * | 2007-12-24 | 2009-07-01 | 阿里巴巴集团控股有限公司 | 一种贷中预警系统及方法 |
JP5138621B2 (ja) * | 2009-03-02 | 2013-02-06 | 日本電信電話株式会社 | 情報処理装置及び不満解決商品発見方法及びプログラム |
CN103854065A (zh) * | 2012-11-30 | 2014-06-11 | 西门子公司 | 一种用于客户流失预测的方法和装置 |
CN104331404B (zh) * | 2013-07-22 | 2018-05-01 | 中国科学院深圳先进技术研究院 | 一种基于用户手机上网数据的用户行为预测方法和装置 |
CN104113869B (zh) * | 2014-06-20 | 2017-12-22 | 北京拓明科技有限公司 | 一种基于信令数据的潜在投诉用户预测方法及系统 |
CN105095588B (zh) * | 2015-08-05 | 2018-07-03 | 中国联合网络通信集团有限公司 | 移动互联网用户投诉的预测方法和装置 |
-
2015
- 2015-12-22 CN CN201510971534.3A patent/CN106910078A/zh active Pending
-
2016
- 2016-12-12 WO PCT/CN2016/109421 patent/WO2017107794A1/zh active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101110699A (zh) * | 2007-08-07 | 2008-01-23 | 广州诚予国际市场信息研究有限公司 | 具有网络满意度预测预警功能的系统及其实现方法 |
CN102495942A (zh) * | 2011-10-26 | 2012-06-13 | 深信服网络科技(深圳)有限公司 | 一种组织内部网络风险评估方法及系统 |
CN103123712A (zh) * | 2011-11-17 | 2013-05-29 | 阿里巴巴集团控股有限公司 | 一种网络行为数据的监控方法和系统 |
CN104834983A (zh) * | 2014-12-25 | 2015-08-12 | 平安科技(深圳)有限公司 | 业务数据处理方法及装置 |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109657918A (zh) * | 2018-11-19 | 2019-04-19 | 平安科技(深圳)有限公司 | 关联评估对象的风险预警方法、装置和计算机设备 |
CN109657918B (zh) * | 2018-11-19 | 2023-07-18 | 平安科技(深圳)有限公司 | 关联评估对象的风险预警方法、装置和计算机设备 |
CN110135681A (zh) * | 2019-04-03 | 2019-08-16 | 平安科技(深圳)有限公司 | 风险用户识别方法、装置、可读存储介质及终端设备 |
CN110135681B (zh) * | 2019-04-03 | 2023-08-22 | 平安科技(深圳)有限公司 | 风险用户识别方法、装置、可读存储介质及终端设备 |
CN111815187A (zh) * | 2020-07-14 | 2020-10-23 | 北京航空航天大学 | 一种基于方向加权网络的制造过程风险评价方法 |
CN112883347A (zh) * | 2021-01-29 | 2021-06-01 | 深圳市鹰硕技术有限公司 | 一种智慧教育平台的应用安全管控方法及系统 |
CN112883347B (zh) * | 2021-01-29 | 2023-06-23 | 深圳市鹰硕技术有限公司 | 一种智慧教育平台的应用安全管控方法及系统 |
CN113592315A (zh) * | 2021-08-04 | 2021-11-02 | 北京沃东天骏信息技术有限公司 | 一种处理纠纷单的方法和装置 |
CN114679335A (zh) * | 2022-03-01 | 2022-06-28 | 国网宁夏电力有限公司 | 电力监控系统网络安全风险评估训练、评估方法及设备 |
CN114679335B (zh) * | 2022-03-01 | 2024-03-29 | 国网宁夏电力有限公司 | 电力监控系统网络安全风险评估训练方法、评估方法及设备 |
CN114885183A (zh) * | 2022-04-21 | 2022-08-09 | 武汉斗鱼鱼乐网络科技有限公司 | 一种识别礼包风险用户的方法、装置、介质及设备 |
CN118296392A (zh) * | 2024-06-06 | 2024-07-05 | 戎行技术有限公司 | 一种基于机器学习ai模型的网络行为数据风险评估方法 |
Also Published As
Publication number | Publication date |
---|---|
CN106910078A (zh) | 2017-06-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2017107794A1 (zh) | 风险识别方法及装置 | |
KR102121360B1 (ko) | 사용자 신용 점수를 최적화하기 위한 방법 및 장치 | |
US11276004B2 (en) | Method and apparatus for monitoring system | |
WO2017215403A1 (zh) | 一种用户信用评估方法、装置及存储介质 | |
US11223723B2 (en) | Call center system having reduced communication latency | |
US20150254791A1 (en) | Quality control calculator for document review | |
US8180710B2 (en) | System, method and computer program product for an interactive business services price determination and/or comparison model | |
WO2021057318A1 (zh) | 一种业务进度监控方法、装置、系统及计算机可读存储介质 | |
CN110278121B (zh) | 一种检测网络性能异常的方法、装置、设备及存储介质 | |
US20100217734A1 (en) | Method and system for calculating value of website visitor | |
CN107220845A (zh) | 用户复购概率预测/用户质量确定方法、装置及电子设备 | |
US10657559B2 (en) | Generating and utilizing a conversational index for marketing campaigns | |
CN109711871B (zh) | 一种潜在客户确定方法、装置、服务器及可读存储介质 | |
CN110349039B (zh) | 投诉风险评估方法、系统、计算机设备及可读存储介质 | |
US20120323640A1 (en) | System and method for evaluating assignee performance of an incident ticket | |
CN112785144A (zh) | 基于联邦学习的模型构建方法、设备及存储介质 | |
CN108133390A (zh) | 用于预测用户行为的方法和装置以及计算设备 | |
WO2019080420A1 (zh) | 人机协作的客服方法、电子装置及存储介质 | |
WO2020233021A1 (zh) | 基于智能决策的测试结果分析方法及相关装置 | |
CN105487970A (zh) | 一种界面展示方法及装置 | |
WO2019210585A1 (zh) | 消息推送方法、计算机可读存储介质、终端设备及装置 | |
TWI801334B (zh) | 風險識別方法及裝置 | |
JP2014225177A5 (zh) | ||
CN109615393A (zh) | 断点的跟进处理方法及装置 | |
US11250365B2 (en) | Systems and methods for utilizing compliance drivers to conserve system resources and reduce compliance violations |
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: 16877605 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 16877605 Country of ref document: EP Kind code of ref document: A1 |