WO2021135842A1 - 群体不满意用户识别方法、装置、设备及存储介质 - Google Patents

群体不满意用户识别方法、装置、设备及存储介质 Download PDF

Info

Publication number
WO2021135842A1
WO2021135842A1 PCT/CN2020/134359 CN2020134359W WO2021135842A1 WO 2021135842 A1 WO2021135842 A1 WO 2021135842A1 CN 2020134359 W CN2020134359 W CN 2020134359W WO 2021135842 A1 WO2021135842 A1 WO 2021135842A1
Authority
WO
WIPO (PCT)
Prior art keywords
group
data
satisfaction
individual
dissatisfied
Prior art date
Application number
PCT/CN2020/134359
Other languages
English (en)
French (fr)
Inventor
程印超
刘宁
刘晓宇
谢奇芳
Original Assignee
***通信有限公司研究院
***通信集团有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by ***通信有限公司研究院, ***通信集团有限公司 filed Critical ***通信有限公司研究院
Publication of WO2021135842A1 publication Critical patent/WO2021135842A1/zh

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
    • G06Q30/0202—Market predictions or forecasting for commercial 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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • 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
    • G06Q10/067—Enterprise or organisation modelling
    • 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

Definitions

  • This application relates to the field of business evaluation, and in particular to a method, device, equipment and storage medium for identifying group dissatisfied users.
  • the embodiments of the present application provide a method, device, equipment, and storage medium for identifying group dissatisfied users, aiming to realize the prediction of the satisfaction of group users.
  • the embodiment of the present application provides a method for identifying group dissatisfied users, including:
  • attribute characteristic data of the group to be predicted under the group service is used to characterize the group user attributes of the group to be predicted
  • the group dissatisfied user identification model is generated based on the attribute feature data of multiple group samples of the group business and the group satisfaction degree.
  • the method further includes:
  • the user data of the group service includes historical data of individual users in the corresponding group of the group service;
  • the group dissatisfied user identification model is determined.
  • the determining the group satisfaction measurement model according to the user data of the group service includes:
  • the group satisfaction measurement model is determined based on the individual satisfaction measurement data and individual member relationship data in the historical data of individual users in the effective group.
  • the determination of the effective group based on the individual satisfaction evaluation data in the historical data of individual users in the corresponding group includes:
  • the determination of the group satisfaction measurement model based on the individual satisfaction measurement data and individual member relationship data in the historical data of individual users in the effective group includes:
  • the group satisfaction measurement model is determined based on the influence value of the individual users in the effective group and the individual satisfaction measurement data.
  • the determining the group dissatisfied user identification model according to the group satisfaction of the group sample in the training set and the attribute characteristic data of the group sample includes:
  • the group satisfaction and attribute characteristic data of the group samples in the training set are trained based on a regression algorithm or a deep learning algorithm to obtain the group dissatisfied user identification model.
  • the embodiment of the present application also provides a device for identifying group dissatisfied users, including:
  • the obtaining module is configured to obtain the attribute characteristic data of the group to be predicted under the group service; the attribute characteristic data is used to characterize the group user attributes of the group to be predicted;
  • An identification module configured to classify the group to be predicted based on the group dissatisfied user identification model and the attribute characteristic data of the group to be predicted, and identify the group dissatisfied users in the group business;
  • the group dissatisfied user identification model is generated based on the attribute feature data of multiple group samples of the group business and the group satisfaction degree.
  • the device further includes a training module, and the training module is configured to:
  • the user data of the group service includes historical data of individual users in the corresponding group of the group service;
  • the group dissatisfied user identification model is determined.
  • the embodiment of the present application further provides a group dissatisfied user identification device, including: a processor and a memory configured to store a computer program that can run on the processor, wherein, when the processor is configured to run the computer program, Perform the steps of the method described in any embodiment of the present application.
  • the embodiments of the present application also provide a storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in any of the embodiments of the present application are implemented.
  • the technical solution provided by the embodiments of the application obtains the attribute characteristic data of the group to be predicted under the group business; based on the attribute characteristic data of the group to be predicted and the group dissatisfied user identification model, the group to be predicted is classified and identified Group dissatisfied users in the group service; wherein, the group dissatisfied user identification model is generated based on the attribute feature data of multiple group samples of the group service and group satisfaction, and can be realized based on the group dissatisfaction
  • the user identification model classifies the groups that have not participated in the satisfaction evaluation in the group business, and then identifies potential group dissatisfied users, which can eliminate the process of satisfaction evaluation of individual users of a large number of group users, which greatly improves This improves the efficiency of the evaluation and reduces the cost and expense of the evaluation.
  • FIG. 1 is a schematic flowchart of a method for identifying group dissatisfied users according to an embodiment of this application;
  • FIG. 2 is a schematic diagram of a process of training a group dissatisfied user identification model according to an embodiment of the application
  • FIG. 3 is a schematic structural diagram of a group dissatisfied user identification device according to an embodiment of the application.
  • Fig. 4 is a schematic structural diagram of a group dissatisfied user identification device according to an embodiment of the application.
  • the group to be predicted is classified based on the attribute feature data of the group to be predicted and the group dissatisfied user identification model, and then Identifying potential group dissatisfied users can save the process of evaluating individual users of a large number of group users in satisfaction, greatly improving the efficiency of evaluation execution, and reducing evaluation costs and costs.
  • the embodiment of the present application provides a method for identifying group dissatisfied users. As shown in FIG. 1, the method includes:
  • Step 101 Obtain attribute feature data of the group to be predicted under the group service; the attribute feature data is used to characterize the group user attributes of the group to be predicted;
  • Step 102 Classify the group to be predicted based on the attribute feature data of the group to be predicted and the group dissatisfied user identification model, and identify the group of dissatisfied users in the group service;
  • the group dissatisfied user identification model is generated based on the attribute feature data of multiple group samples of the group business and the group satisfaction degree.
  • the group to be predicted may be household or enterprise group users
  • the attribute characteristic data may include at least one of the following: number of members, group nature, service order status, network preference, consumption preference, and credit status.
  • the number of members is the number of individual users in the group
  • the group nature refers to the classification attribute of the group (for example, family users or corporate group users)
  • the service order situation can be the service order time period corresponding to the group.
  • the feature data of multiple dimensions corresponding to the attribute feature data can be standardized and normalized to obtain the attribute feature data.
  • the method for identifying group dissatisfied users in the embodiments of this application does not require large-scale sampling and invitations.
  • the attribute feature data of the group the overall satisfaction of the group with the group business is predicted, and the potential group dissatisfied users are identified, which not only greatly improves
  • the efficiency of evaluation execution reduces evaluation costs and costs, and also reduces harassment to users; at the same time, according to the identified groups of dissatisfied users, personalized services and customized marketing can be used to ease the relationship, which can greatly improve the overall service quality and marketing Effect, avoid business loss.
  • the method further includes: generating group dissatisfied users based on attribute feature data and group satisfaction of multiple group samples of the group business Identify the model.
  • a trained group dissatisfied user identification model is obtained.
  • the methods for training the group's dissatisfied user recognition model include:
  • Step 201 Obtain user data of a group service; the user data of the group service includes historical data of individual users in the corresponding group of the group service;
  • the family or enterprise as a unit can be used to obtain the information of the stock group users, that is, to obtain each individual in the same family or the same enterprise group for each type of business.
  • Historical data of members in a certain historical time period may include: individual user satisfaction evaluation data, individual business information data related to individual historical evaluation users, and individual user member relationship data, and the data is standardized and normalized.
  • the household, government and enterprise services include household broadband services, household V-network services, enterprise private line services, enterprise broadband services, 400 short number services, and so on.
  • the individual user satisfaction evaluation data includes one or more of: user ID, evaluation time, satisfaction value of group business, etc.; among them, the individuals of the same family or the same enterprise group include two types, and the satisfaction evaluation has been conducted. Of users and users who have not conducted a satisfaction assessment.
  • the satisfaction value of the group business can be a corresponding value, for example, any value from 1 to 10 selected by the user during the satisfaction evaluation.
  • the satisfaction value of the group business is a null value.
  • the individual business information data related to the individual historical evaluation user includes one or more of basic user information, historical network behavior data, historical communication behavior data, historical complaint data, historical business system data, and the like.
  • the basic user information data includes one or more of cell phone number, name, region, age, income level, education background, and industry.
  • the historical network behavior data includes one or more of game preferences, video preferences, shopping preferences, live broadcast preferences, VR (virtual reality) preferences, network dependence, and duration of stay on different networks (4G/3G/wifi).
  • the historical communication behavior data includes one or more of ARPU (average income per user), DOU (average monthly online traffic per household), account balance, business default information, communication duration, package, network access duration, and so on.
  • the historical complaint data includes one or more of the number of monthly complaints, the frequency of monthly complaints, the complaint level, the complaint resolution rate, and the number of complaints escalation.
  • the historical business system data includes one or more of service subscription activation time, package change activation time, service unsubscription processing time, business consultation answer rate, and the like.
  • the individual member relationship data includes one or more of member positions, superior-subordinate relationships, positions, business IDs, working years, and the like.
  • Step 202 Determine a group satisfaction measurement model according to the user data of the group service
  • the determining the group satisfaction measurement model according to the user data of the group service includes:
  • the group satisfaction measurement model is determined based on the individual satisfaction measurement data and individual member relationship data in the historical data of individual users in the effective group.
  • the determining the effective group based on the individual satisfaction evaluation data in the historical data of individual users in the corresponding group includes:
  • the effective group can be selected according to the following formula:
  • k for the group P e in the number of individuals involved in the evaluation of user satisfaction, w is the total amount of all individual users in the group P e.
  • the determining the group satisfaction measurement model based on individual satisfaction measurement data and individual member relationship data in the historical data of individual users in the effective group includes:
  • the group satisfaction measurement model is determined based on the influence value of the individual users in the effective group and the individual satisfaction measurement data.
  • satisfaction (t i ) is the satisfaction value of the i-th individual user.
  • the satisfaction (t j ) of these individual users is a null value, j ⁇ [k+1, w].
  • the influence value or ranking value of each individual user who participated in the satisfaction evaluation in the above time period in P e is calculated. Because group users aggregate the influence of each individual differently, the influence in the group is calculated separately for the individual, namely:
  • u i f(t i ), which is the influence value u i corresponding to the t i user in P e .
  • the satisfaction measurement model of the group users P e is determined as follows:
  • Step 203 Determine the group satisfaction of the group samples in the training set according to the group satisfaction measurement model
  • the group satisfaction of the group samples in the training set is calculated according to the group satisfaction measurement model determined in step 202.
  • Step 204 Determine the group dissatisfied user identification model according to the group satisfaction of the group samples in the training set and the attribute characteristic data of the group samples.
  • the determining the group dissatisfied user identification model according to the group satisfaction of the group samples in the training set and the attribute characteristic data of the group samples includes:
  • the group satisfaction and attribute characteristic data of the group samples in the training set are trained based on a regression algorithm or a deep learning algorithm to obtain the group dissatisfied user identification model.
  • attribute characteristic data of the population sample can be expressed as:
  • the regression algorithm may be a machine learning algorithm such as linear regression, logistic regression, and decision tree.
  • the logistic regression algorithm is used as an example to illustrate, the corresponding group dissatisfied user identification model is as follows:
  • a 0 is the reference parameter
  • ⁇ a 1 , a 2 , a 3 ,..., a m ⁇ are the parameters obtained by training.
  • the influence factor of each characteristic variable can be calculated by random forest or other algorithms, and the above regression algorithm is used Weighted calculation, calculate the corresponding ⁇ a 1 ,a 2 ,a 3 ,..., am ⁇ parameters again.
  • the method for identifying unsatisfied users in the embodiments of this application can be used not only in fields such as communications, banking, insurance, etc., but also in traditional fields such as retail and hospitals, providing technical support for different industries and fields.
  • the embodiment of the present application also provides a device for identifying group dissatisfied users.
  • the device includes: an acquisition module 301 and an identification module 302, wherein:
  • the obtaining module 301 is configured to obtain the attribute characteristic data of the group to be predicted under the group service; the attribute characteristic data is used to characterize the group user attributes of the group to be predicted;
  • the recognition module 302 is configured to classify the group to be predicted based on the group dissatisfied user identification model and the attribute characteristic data of the group to be predicted, and identify the group dissatisfied users in the group business; wherein, the The group dissatisfied user identification model is generated based on the attribute feature data of multiple group samples of the group business and the group satisfaction degree.
  • the device further includes: a training module 303, and the training module 303 is configured to:
  • the user data of the group service includes historical data of individual users in the corresponding group of the group service;
  • the group dissatisfied user identification model is determined.
  • the training module 303 is further configured to:
  • the group satisfaction measurement model is determined based on the individual satisfaction measurement data and individual member relationship data in the historical data of individual users in the effective group.
  • the training module 303 is further configured to:
  • the training module 303 is further configured to:
  • the group satisfaction measurement model is determined based on the influence value of the individual users in the effective group and the individual satisfaction measurement data.
  • the training module 303 is further configured to:
  • the group satisfaction and attribute characteristic data of the group samples in the training set are trained based on a regression algorithm or a deep learning algorithm to obtain the group dissatisfied user identification model.
  • the acquisition module 301, the recognition module 302, and the training module 303 can be implemented by a processor in a device for identifying users who are dissatisfied with the group.
  • the processor needs to run a computer program in the memory to realize its functions.
  • the group dissatisfied user identification device provided in the above embodiment performs group dissatisfied user identification
  • only the division of the above-mentioned program modules is used as an example for illustration.
  • the above-mentioned processing can be allocated according to needs. Different program modules are completed, that is, the internal structure of the device is divided into different program modules to complete all or part of the processing described above.
  • the device for identifying group dissatisfied users provided in the foregoing embodiments belong to the same concept as the embodiment of the method for identifying group dissatisfied users. For the specific implementation process, please refer to the method embodiment, which will not be repeated here.
  • the embodiment of the present application also provides a device for identifying users who are dissatisfied with the group.
  • FIG. 4 only shows an exemplary structure of the user identification device for dissatisfied users of the group, but not the entire structure, and part of the structure or all of the structure shown in FIG. 4 can be implemented as required.
  • the group dissatisfied user identification device 400 includes: at least one processor 401, a memory 402, and at least one network interface 403.
  • the group is dissatisfied that the various components in the user identification device 400 are coupled together through the bus system 404.
  • the bus system 404 is used to implement connection and communication between these components.
  • the bus system 404 also includes a power bus, a control bus, and a status signal bus.
  • various buses are marked as the bus system 404 in FIG. 4.
  • the memory 402 in the embodiment of the present application is configured to store various types of data to support the operation of the identification device for dissatisfied users. Examples of such data include: any computer program used to identify devices for unsatisfied users of the group.
  • the method for identifying group dissatisfied users disclosed in the embodiments of the present application may be applied to the processor 401 or implemented by the processor 401.
  • the processor 401 may be an integrated circuit chip with signal processing capabilities. In the implementation process, the steps of the method for identifying group dissatisfied users can be completed by hardware integrated logic circuits in the processor 401 or instructions in the form of software.
  • the aforementioned processor 401 may be a general-purpose processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, and the like.
  • the processor 401 may implement or execute the methods, steps, and logical block diagrams disclosed in the embodiments of the present application.
  • the general-purpose processor may be a microprocessor or any conventional processor or the like. Combining the steps of the method disclosed in the embodiments of the present application, it may be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of hardware and software modules in the decoding processor.
  • the software module may be located in a storage medium, and the storage medium is located in the memory 402.
  • the processor 401 reads the information in the memory 402 and completes the steps of the method for identifying group dissatisfied users provided by the embodiment of the present application in combination with its hardware.
  • the group dissatisfied user identification device can be used by one or more application specific integrated circuits (ASIC, Application Specific Integrated Circuit), DSP, programmable logic device (PLD, Programmable Logic Device), and complex programmable logic.
  • a device CPLD, Complex Programmable Logic Device
  • FPGA general-purpose processor
  • controller microcontroller
  • MCU Micro Controller Unit
  • microprocessor Microprocessor
  • the memory 402 may be a volatile memory or a non-volatile memory, and may also include both volatile and non-volatile memory.
  • the non-volatile memory can be a read-only memory (ROM, Read Only Memory), a programmable read-only memory (PROM, Programmable Read-Only Memory), an erasable programmable read-only memory (EPROM, Erasable Programmable Read- Only Memory, Electrically Erasable Programmable Read-Only Memory (EEPROM), Ferromagnetic Random Access Memory (FRAM), Flash Memory, Magnetic Surface Memory , CD-ROM, or CD-ROM (Compact Disc Read-Only Memory); magnetic surface memory can be magnetic disk storage or tape storage.
  • the volatile memory may be a random access memory (RAM, Random Access Memory), which is used as an external cache.
  • RAM random access memory
  • SRAM static random access memory
  • SSRAM synchronous static random access memory
  • Synchronous Static Random Access Memory Synchronous Static Random Access Memory
  • DRAM Dynamic Random Access Memory
  • SDRAM Synchronous Dynamic Random Access Memory
  • DDRSDRAM Double Data Rate Synchronous Dynamic Random Access Memory
  • ESDRAM Enhanced Synchronous Dynamic Random Access Memory
  • SLDRAM synchronous connection dynamic random access memory
  • DRRAM Direct Rambus Random Access Memory
  • the memories described in the embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memories.
  • the embodiment of the present application also provides a storage medium, that is, a computer storage medium, which may specifically be a computer-readable storage medium, such as a memory 402 storing a computer program, which can be used by a group of dissatisfied users.
  • the processor 401 of the identification device executes to complete the steps described in the method in the embodiment of the present application.
  • the computer-readable storage medium may be a memory such as ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disk, or CD-ROM.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Educational Administration (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Data Mining & Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种群体不满意用户识别方法、装置、设备及存储介质。其中，该方法包括：获取群体业务下待预测群体的属性特征数据；所述属性特征数据用于表征所述待预测群体的群体用户属性（101）；基于所述待预测群体的属性特征数据和群体不满意用户识别模型，对所述待预测群体进行分类，识别出所述群体业务中的群体不满意用户（102）；其中，所述群体不满意用户识别模型为基于所述群体业务的多个群体样本的属性特征数据和群体满意度生成的。可以实现基于该群体不满意用户识别模型对群体业务中未参与过满意度测评的群体进行分类，进而识别出潜在的群体不满意用户。

Description

群体不满意用户识别方法、装置、设备及存储介质
相关申请的交叉引用
本申请基于申请号为202010000892.0、申请日为2020年01月02日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本申请涉及业务评估领域，尤其涉及一种群体不满意用户识别方法、装置、设备及存储介质。
背景技术
随着网络技术和科技的迅速发展，通信运营商推出了很多针对家庭、企业等群体的群体业务，比如家庭宽带、家庭V网业务、企业专线业务、400短号业务等，这些群体业务中的个体用户既是独立个体又是群体的一份子，不同于个人业务，这些群体业务需要考虑群体的感受和意见反馈，需对整个群体进行满意度的预测和评估，识别群体不满意用户，以降低家庭及政企业务的退订、不续约风险。
发明内容
有鉴于此，本申请实施例提供了一种群体不满意用户识别方法、装置、设备及存储介质，旨在实现对群体用户的满意度的预测。
本申请实施例的技术方案是这样实现的：
本申请实施例提供了一种群体不满意用户识别方法，包括：
获取群体业务下待预测群体的属性特征数据；所述属性特征数据用于 表征所述待预测群体的群体用户属性；
基于所述待预测群体的属性特征数据和群体不满意用户识别模型，对所述待预测群体进行分类，识别出所述群体业务中的群体不满意用户；
其中，所述群体不满意用户识别模型为基于所述群体业务的多个群体样本的属性特征数据和群体满意度生成的。
上述方案中，所述方法还包括：
获取群体业务的用户数据；所述群体业务的用户数据包含所述群体业务相应群体下个体用户的历史数据；
根据所述群体业务的用户数据确定群体满意度测算模型；
根据所述群体满意度测算模型确定训练集中群体样本的群体满意度；
根据所述训练集中群体样本的群体满意度和群体样本的属性特征数据，确定所述群体不满意用户识别模型。
上述方案中，所述根据所述群体业务的用户数据确定群体满意度测算模型，包括：
基于相应群体下个体用户的历史数据中的个体满意度测评数据确定有效的群体；
基于所述有效的群体下个体用户的历史数据中的个体满意度测评数据和个体成员关系数据确定所述群体满意度测算模型。
上述方案中，所述基于相应群体下个体用户的历史数据中的个体满意度测评数据确定有效的群体，包括：
根据相应群体下个体用户的历史数据中的个体满意度测评数据确定相应群体中参与过满意度测评的个体用户数量；
基于同一群体中参与过满意度测评的个体用户的数量与总的个体用户的数量的比值确定所述群体是否为有效的群体。
上述方案中，所述基于所述有效的群体下个体用户的历史数据中的个 体满意度测评数据和个体成员关系数据确定所述群体满意度测算模型，包括：
基于个体用户的个体成员关系数据确定个体用户的影响力值；
基于所述有效的群体下个体用户的影响力值和所述个体满意度测评数据确定所述群体满意度测算模型。
上述方案中，所述根据所述训练集中群体样本的群体满意度和群体样本的属性特征数据，确定所述群体不满意用户识别模型，包括：
对所述训练集中群体样本的群体满意度和属性特征数据基于回归算法或者深度学习算法进行训练，得到所述群体不满意用户识别模型。
本申请实施例还提供了一种群体不满意用户识别装置，包括：
获取模块，配置为获取群体业务下待预测群体的属性特征数据；所述属性特征数据用于表征所述待预测群体的群体用户属性；
识别模块，配置为基于群体不满意用户识别模型和所述待预测群体的属性特征数据，对所述待预测群体进行分类，识别出所述群体业务中的群体不满意用户；
其中，所述群体不满意用户识别模型为基于所述群体业务的多个群体样本的属性特征数据和群体满意度生成的。
上述方案中，所述装置还包括训练模块，所述训练模块配置为：
获取群体业务的用户数据；所述群体业务的用户数据包含所述群体业务相应群体下个体用户的历史数据；
根据所述群体业务的用户数据确定群体满意度测算模型；
根据所述群体满意度测算模型确定训练集中群体样本的群体满意度；
根据所述训练集中群体样本的群体满意度和群体样本的属性特征数据，确定所述群体不满意用户识别模型。
本申请实施例又提供了一种群体不满意用户识别设备，包括：处理器 和配置为存储能够在处理器上运行的计算机程序的存储器，其中，所述处理器，配置为运行计算机程序时，执行本申请任一实施例所述方法的步骤。
本申请实施例还提供了一种存储介质，所述存储介质上存储有计算机程序，所述计算机程序被处理器执行时，实现本申请任一实施例所述方法的步骤。
本申请实施例提供的技术方案，获取群体业务下待预测群体的属性特征数据；基于所述待预测群体的属性特征数据和群体不满意用户识别模型，对所述待预测群体进行分类，识别出所述群体业务中的群体不满意用户；其中，所述群体不满意用户识别模型为基于所述群体业务的多个群体样本的属性特征数据和群体满意度生成的，可以实现基于该群体不满意用户识别模型对群体业务中未参与过满意度测评的群体进行分类，进而识别出潜在的群体不满意用户，可以省去对较多数量的群体用户的个体用户进行满意度测评的过程，大大提升了测评执行效率，减少了测评成本和代价。
附图说明
图1为本申请实施例群体不满意用户识别方法的流程示意图；
图2为本申请实施例训练群体不满意用户识别模型的流程示意图；
图3为本申请实施例群体不满意用户识别装置的结构示意图；
图4为本申请实施例群体不满意用户识别设备的结构示意图。
具体实施方式
下面结合附图及实施例对本申请再作进一步详细的描述。
除非另有定义，本文所使用的所有的技术和科学术语与属于本申请的技术领域的技术人员通常理解的含义相同。本文中在本申请的说明书中所使用的术语只是为了描述具体的实施例的目的，不是旨在于限制本申请。
相关技术中，为了对群体业务下不同群体进行满意度调查，往往需要 进行大规模的抽样和邀约，不仅耗费精力，且往往会影响群体业务的用户体验。
基于此，在本申请的各种实施例中，通过构建群体不满意用户识别模型，基于待预测群体的属性特征数据和所述群体不满意用户识别模型，对所述待预测群体进行分类，进而识别出潜在的群体不满意用户，可以省去对较多数量的群体用户的个体用户进行满意度测评的过程，大大提升了测评执行效率，减少了测评成本和代价。
本申请实施例提供了一种群体不满意用户识别方法，如图1所示，该方法包括：
步骤101，获取群体业务下待预测群体的属性特征数据；所述属性特征数据用于表征所述待预测群体的群体用户属性；
步骤102，基于所述待预测群体的属性特征数据和群体不满意用户识别模型，对所述待预测群体进行分类，识别出所述群体业务中的群体不满意用户；
其中，所述群体不满意用户识别模型为基于所述群体业务的多个群体样本的属性特征数据和群体满意度生成的。
这里，待预测群体可以为家庭或者企业群体用户，属性特征数据可以包括以下至少之一：成员数量、群体性质、业务订购情况、网络偏好、消费偏好、信用情况。其中，成员数量为群体的个体用户的数量，群体性质是指群体的分类属性(比如，家庭用户或者企业群体用户)，业务订购情况可以为群体对应的业务订购时长。
实际应用时，可以将属性特征数据对应的多个维度的特征数据进行标准化和归一化处理，得到属性特征数据。
本申请实施例群体不满意用户识别方法，不需要大规模的抽样和邀约等，根据群体的属性特征数据，预测群体对群体业务的整体满意度，识别 潜在的群体不满意用户，不仅大大提升了测评执行效率，减少了测评成本和代价，也减少了对用户的骚扰；同时，根据识别出的群体不满意用户，可以通过个性化服务以及定制营销来缓解关系，可以大提升整体服务质量和营销效果，避免业务流失。
由于需要使用群体不满意用户识别模型进行预测，基于此，在一实施例中，所述方法还包括：基于所述群体业务的多个群体样本的属性特征数据和群体满意度生成群体不满意用户识别模型。
在一实施例中，基于所述群体业务的多个群体样本的属性特征数据和群体满意度训练群体不满意用户识别模型的参数，得到训练后的群体不满意用户识别模型。如图2所示，训练群体不满意用户识别模型的方法包括：
步骤201，获取群体业务的用户数据；所述群体业务的用户数据包含所述群体业务相应群体下个体用户的历史数据；
这里，可以按照家庭、政企业务分类，根据业务订购关系，以家庭或者企业为单位(对应群体用户)，获取存量群体用户信息，即获取每类业务同一家庭或者同一企业群体用户中每一个体成员在某一历史时间段内的历史数据。该历史数据可以包括：个体用户满意度测评数据、个体历史测评用户相关的个体业务信息数据以及个体用户成员关系数据，并将数据统一标准化和归一化处理。
所述家庭、政企业务包括家庭宽带业务、家庭V网业务、企业专线业务、企业宽带业务、400短号业务等。
所述个体用户满意度测评数据包括：用户ID、测评时间、群体业务的满意度值等的一种或者多种；其中，同一家庭或者同一企业群体用户的个体包括两类，进行过满意度测评的用户和没有进行过满意度测评的用户。对于进行过满意度测评的用户，群体业务的满意度值可以为对应的数值，比如，为用户在满意度测评时选择的1至10中的任一数值。对于没有进行 过满意度测评的用户，群体业务的满意度值为空值。
所述个体历史测评用户相关的个体业务信息数据包括：用户基本信息、历史网络行为数据、历史通信行为数据、历史投诉数据、历史业务***数据等的一种或者多种。所述用户基本信息数据包括手机号码、姓名、地域、年龄、收入水平、学历、从事行业等的一种或者多种。所述历史网络行为数据包括游戏偏好、视频偏好、购物偏好、直播偏好、VR(虚拟现实)偏好、网络依赖度、不同网络(4G/3G/wifi)驻留时长等的一种或者多种。所述历史通信行为数据包括ARPU(每用户平均收入)、DOU(平均每户每月上网流量)、账户余额、业务违约信息、通信时长、套餐、入网时长等的一种或者多种。所述历史投诉数据包括月投诉次数、月投诉频率、投诉级别、投诉解决率、投诉升级次数等的一种或者多种。所述历史业务***数据包括业务订购开通时长、套餐变更开通时长、业务退订办理时长、业务咨询解答率等的一种或者多种。
所述个体成员关系数据包括：成员岗位、上下级关系、职务、业务ID、工作年限等一种或者多种。
步骤202，根据所述群体业务的用户数据确定群体满意度测算模型；
在一实施例中，所述根据所述群体业务的用户数据确定群体满意度测算模型，包括：
基于相应群体下个体用户的历史数据中的个体满意度测评数据确定有效的群体；
基于所述有效的群体下个体用户的历史数据中的个体满意度测评数据和个体成员关系数据确定所述群体满意度测算模型。
在一实施例中，所述基于相应群体下个体用户的历史数据中的个体满意度测评数据确定有效的群体，包括：
根据相应群体下个体用户的历史数据中的个体满意度测评数据确定相 应群体中参与过满意度测评的个体用户数量；
基于同一群体中参与过满意度测评的个体用户的数量与总的个体用户的数量的比值确定所述群体是否为有效的群体。
实际应用时，可以按照预设规则，选择每个企业或者家庭群体用户中参与过满意度测评的个体用户总量占比达到全体群体客户中个体总量阈值的群体作为有效的群体。比如，可以根据如下公式选择有效的群体：
Figure PCTCN2020134359-appb-000001
其中，k为群体P e中参与过满意度测评的个体用户数量，w为群体P e中所有个体用户的总量。
在一实施例中，所述基于所述有效的群体下个体用户的历史数据中的个体满意度测评数据和个体成员关系数据确定所述群体满意度测算模型，包括：
基于个体用户的个体成员关系数据确定个体用户的影响力值；
基于所述有效的群体下个体用户的影响力值和所述个体满意度测评数据确定所述群体满意度测算模型。
实际应用时，可以根据个体用户在设定时间段内的个体业务信息数据建立宽表，比如，采用t i＝【x i1,x i2,x i3,…,x in】表示，其中，t i为第i个个体用户的个体业务信息数据，n是个体用户相关的业务信息数据维度。
相应地，个体用户的用户满意度采用satisfaction(t i)表示，即satisfaction(t i)为第i个个体用户的满意度值。
如果当前用户在上述时间段内参与过满意度测评，即该用户的满意度值表示为：
satisfaction(t i)∈【1,2,3,4,5,6,7,8,9,10】。
如果当前用户在上述时间段内未参与过满意度测评，即该用户的满意度值表示为：
satisfaction(t i)∈{Ф}，即为空值。
将上述时间段内群体业务同一家庭或者同一企业群体内所有单用户汇聚，用集合表示为：
P e＝{t 1,t 2,t 3,…,t k,t k+1,…,t w}，其中，P e指第e个群体用户(可以为企业或者家庭群体用户)；w为P e中用户的总数量，且w>＝1；k表示前k个该群体用户中参与过满意度测评的个体用户数量；w-k表示该群体用户中未参与过满意度测评的个体用户数量。
因为，{t k+1,…,t w}的用户为未参与过满意度测评的用户，所以，这些个体用户的satisfaction(t j)为空值，j∈【k+1，w】。
实际应用时，根据企业或者家庭群体中个体用户的个体成员关系数据，计算P e中在上述时间段内参与过满意度测评的每个个体用户的影响力值或排序值。因为群体用户汇总每个个体的影响力是有区别的，所以针对个体分别计算在群体中的影响力，即：
u i＝f(t i)，为P e中t i用户对应的影响力值u i。
假设同一家庭或者同一企业业务群体用户P e中有k个用户参与过满意度测评，将这些用户进行汇聚，表示如下：
P e’＝{t 1,t 2,t 3,…,t k}
将上述P e’中每个个体用户对应的影响力进行汇聚，即将参与过满意度测评的每个用户对应的影响力表示为U，即：
U＝{u 1,u 2,u i,...,u k}，其中，w>＝k>＝1。
在一实施例中，考虑了群体用户中个体用户的个体差异后，群体用户P e的满意度测算模型确定如下：
Figure PCTCN2020134359-appb-000002
步骤203，根据所述群体满意度测算模型确定训练集中群体样本的群体 满意度；
根据步骤202确定的群体满意度测算模型计算训练集中的群体样本的群体满意度。
步骤204，根据所述训练集中群体样本的群体满意度和群体样本的属性特征数据，确定所述群体不满意用户识别模型。
在一实施例中，所述根据所述训练集中群体样本的群体满意度和群体样本的属性特征数据，确定所述群体不满意用户识别模型，包括：
对所述训练集中群体样本的群体满意度和属性特征数据基于回归算法或者深度学习算法进行训练，得到所述群体不满意用户识别模型。
这里，群体样本的属性特征数据可以表示为：
{y 1,y 2,y 3,…,y m}，其中，m为P e群体的属性特征变量的维度。
这里，回归算法可以为线性回归、逻辑回归、决策树等机器学习算法等。
在一应用示例中，以采用逻辑回归算法为例进行说明，对应的群体不满意用户识别模型如下：
Figure PCTCN2020134359-appb-000003
其中，a 0为基准参数，{a 1,a 2,a 3,…,a m}为训练得到的参数。
实际应用时，如果群体P e的属性特征数据中每个群体属性特征变量对整体群体满意度的影响不同，可以通过随机森林或者其他算法计算每个特征变量的影响因子，在上述回归算法中进行加权计算，再次计算相应的{a 1,a 2,a 3,…,a m}参数。
本申请实施例群体不满意用户识别方法，不仅可以用于通信、银行、保险等领域，还可以用于零售、医院等传统领域，为不同行业和领域提供技术支撑。
为了实现本申请实施例的方法，本申请实施例还提供一种群体不满意 用户识别装置，如图3所示，该装置包括：获取模块301、识别模块302，其中，
获取模块301，配置为获取群体业务下待预测群体的属性特征数据；所述属性特征数据用于表征所述待预测群体的群体用户属性；
识别模块302，配置为基于群体不满意用户识别模型和所述待预测群体的属性特征数据，对所述待预测群体进行分类，识别出所述群体业务中的群体不满意用户；其中，所述群体不满意用户识别模型为基于所述群体业务的多个群体样本的属性特征数据和群体满意度生成的。
在一实施例中，所述装置还包括：训练模块303，训练模块303配置为：
获取群体业务的用户数据；所述群体业务的用户数据包含所述群体业务相应群体下个体用户的历史数据；
根据所述群体业务的用户数据确定群体满意度测算模型；
根据所述群体满意度测算模型确定训练集中群体样本的群体满意度；
根据所述训练集中群体样本的群体满意度和群体样本的属性特征数据，确定所述群体不满意用户识别模型。
在一实施例中，训练模块303还配置为：
基于相应群体下个体用户的历史数据中的个体满意度测评数据确定有效的群体；
基于所述有效的群体下个体用户的历史数据中的个体满意度测评数据和个体成员关系数据确定所述群体满意度测算模型。
在一实施例中，训练模块303还配置为：
根据相应群体下个体用户的历史数据中的个体满意度测评数据确定相应群体中参与过满意度测评的个体用户数量；
基于同一群体中参与过满意度测评的个体用户的数量与总的个体用户的数量的比值确定所述群体是否为有效的群体。
在一实施例中，训练模块303还配置为：
基于个体用户的个体成员关系数据确定个体用户的影响力值；
基于所述有效的群体下个体用户的影响力值和所述个体满意度测评数据确定所述群体满意度测算模型。
在一实施例中，训练模块303还配置为：
对所述训练集中群体样本的群体满意度和属性特征数据基于回归算法或者深度学习算法进行训练，得到所述群体不满意用户识别模型。
实际应用时，获取模块301、识别模块302及训练模块303，可以由群体不满意用户识别装置中的处理器来实现。当然，处理器需要运行存储器中的计算机程序来实现它的功能。
需要说明的是：上述实施例提供的群体不满意用户识别装置在进行群体不满意用户识别时，仅以上述各程序模块的划分进行举例说明，实际应用中，可以根据需要而将上述处理分配由不同的程序模块完成，即将装置的内部结构划分成不同的程序模块，以完成以上描述的全部或者部分处理。另外，上述实施例提供的群体不满意用户识别装置与群体不满意用户识别方法实施例属于同一构思，其具体实现过程详见方法实施例，这里不再赘述。
基于上述程序模块的硬件实现，且为了实现本申请实施例的方法，本申请实施例还提供一种群体不满意用户识别设备。图4仅仅示出了该群体不满意用户识别设备的示例性结构而非全部结构，根据需要可以实施图4示出的部分结构或全部结构。
如图4所示，本申请实施例提供的群体不满意用户识别设备400包括：至少一个处理器401、存储器402和至少一个网络接口403。群体不满意用户识别设备400中的各个组件通过总线***404耦合在一起。可以理解，总线***404用于实现这些组件之间的连接通信。总线***404除包括数 据总线之外，还包括电源总线、控制总线和状态信号总线。但是为了清楚说明起见，在图4中将各种总线都标为总线***404。
本申请实施例中的存储器402配置为存储各种类型的数据以支持群体不满意用户识别设备的操作。这些数据的示例包括：用于在群体不满意用户识别设备上操作的任何计算机程序。
本申请实施例揭示的群体不满意用户识别方法可以应用于处理器401中，或者由处理器401实现。处理器401可能是一种集成电路芯片，具有信号的处理能力。在实现过程中，群体不满意用户识别方法的各步骤可以通过处理器401中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器401可以是通用处理器、数字信号处理器(DSP，Digital Signal Processor)，或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。处理器401可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者任何常规的处理器等。结合本申请实施例所公开的方法的步骤，可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于存储介质中，该存储介质位于存储器402，处理器401读取存储器402中的信息，结合其硬件完成本申请实施例提供的群体不满意用户识别方法的步骤。
在示例性实施例中，群体不满意用户识别设备可以被一个或多个应用专用集成电路(ASIC，Application Specific Integrated Circuit)、DSP、可编程逻辑器件(PLD，Programmable Logic Device)、复杂可编程逻辑器件(CPLD，Complex Programmable Logic Device)、FPGA、通用处理器、控制器、微控制器(MCU，Micro Controller Unit)、微处理器(Microprocessor)、或者其他电子元件实现，用于执行前述方法。
可以理解，存储器402可以是易失性存储器或非易失性存储器，也可 包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(ROM，Read Only Memory)、可编程只读存储器(PROM，Programmable Read-Only Memory)、可擦除可编程只读存储器(EPROM，Erasable Programmable Read-Only Memory)、电可擦除可编程只读存储器(EEPROM，Electrically Erasable Programmable Read-Only Memory)、磁性随机存取存储器(FRAM，ferromagnetic random access memory)、快闪存储器(Flash Memory)、磁表面存储器、光盘、或只读光盘(CD-ROM，Compact Disc Read-Only Memory)；磁表面存储器可以是磁盘存储器或磁带存储器。易失性存储器可以是随机存取存储器(RAM，Random Access Memory)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的RAM可用，例如静态随机存取存储器(SRAM，Static Random Access Memory)、同步静态随机存取存储器(SSRAM，Synchronous Static Random Access Memory)、动态随机存取存储器(DRAM，Dynamic Random Access Memory)、同步动态随机存取存储器(SDRAM，Synchronous Dynamic Random Access Memory)、双倍数据速率同步动态随机存取存储器(DDRSDRAM，Double Data Rate Synchronous Dynamic Random Access Memory)、增强型同步动态随机存取存储器(ESDRAM，Enhanced Synchronous Dynamic Random Access Memory)、同步连接动态随机存取存储器(SLDRAM，SyncLink Dynamic Random Access Memory)、直接内存总线随机存取存储器(DRRAM，Direct Rambus Random Access Memory)。本申请实施例描述的存储器旨在包括但不限于这些和任意其它适合类型的存储器。
在示例性实施例中，本申请实施例还提供了一种存储介质，即计算机存储介质，具体可以是计算机可读存储介质，例如包括存储计算机程序的存储器402，上述计算机程序可由群体不满意用户识别设备的处理器401执行，以完成本申请实施例方法所述的步骤。计算机可读存储介质可以是 ROM、PROM、EPROM、EEPROM、Flash Memory、磁表面存储器、光盘、或CD-ROM等存储器。
需要说明的是：“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。
另外，本申请实施例所记载的技术方案之间，在不冲突的情况下，可以任意组合。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以权利要求的保护范围为准。

Claims (10)

  1. 一种群体不满意用户识别方法，包括：
    获取群体业务下待预测群体的属性特征数据；所述属性特征数据用于表征所述待预测群体的群体用户属性；
    基于所述待预测群体的属性特征数据和群体不满意用户识别模型，对所述待预测群体进行分类，识别出所述群体业务中的群体不满意用户；
    其中，所述群体不满意用户识别模型为基于所述群体业务的多个群体样本的属性特征数据和群体满意度生成的。
  2. 根据权利要求1所述的方法，其中，所述方法还包括：
    获取群体业务的用户数据；所述群体业务的用户数据包含所述群体业务相应群体下个体用户的历史数据；
    根据所述群体业务的用户数据确定群体满意度测算模型；
    根据所述群体满意度测算模型确定训练集中群体样本的群体满意度；
    根据所述训练集中群体样本的群体满意度和群体样本的属性特征数据，确定所述群体不满意用户识别模型。
  3. 根据权利要求2所述的方法，其中，所述根据所述群体业务的用户数据确定群体满意度测算模型，包括：
    基于相应群体下个体用户的历史数据中的个体满意度测评数据确定有效的群体；
    基于所述有效的群体下个体用户的历史数据中的个体满意度测评数据和个体成员关系数据确定所述群体满意度测算模型。
  4. 根据权利要求3所述的方法，其中，所述基于相应群体下个体用户的历史数据中的个体满意度测评数据确定有效的群体，包括：
    根据相应群体下个体用户的历史数据中的个体满意度测评数据确定相 应群体中参与过满意度测评的个体用户数量；
    基于同一群体中参与过满意度测评的个体用户的数量与总的个体用户的数量的比值确定所述群体是否为有效的群体。
  5. 根据权利要求3所述的方法，其中，所述基于所述有效的群体下个体用户的历史数据中的个体满意度测评数据和个体成员关系数据确定所述群体满意度测算模型，包括：
    基于个体用户的个体成员关系数据确定个体用户的影响力值；
    基于所述有效的群体下个体用户的影响力值和所述个体满意度测评数据确定所述群体满意度测算模型。
  6. 根据权利要求2所述的方法，其中，所述根据所述训练集中群体样本的群体满意度和群体样本的属性特征数据，确定所述群体不满意用户识别模型，包括：
    对所述训练集中群体样本的群体满意度和属性特征数据基于回归算法或者深度学习算法进行训练，得到所述群体不满意用户识别模型。
  7. 一种群体不满意用户识别装置，包括：
    获取模块，配置为获取群体业务下待预测群体的属性特征数据；所述属性特征数据用于表征所述待预测群体的群体用户属性；
    识别模块，配置为基于群体不满意用户识别模型和所述待预测群体的属性特征数据，对所述待预测群体进行分类，识别出所述群体业务中的群体不满意用户；
    其中，所述群体不满意用户识别模型为基于所述群体业务的多个群体样本的属性特征数据和群体满意度生成的。
  8. 根据权利要求7所述的装置，其中，所述装置还包括训练模块，所述训练模块配置为：
    获取群体业务的用户数据；所述群体业务的用户数据包含所述群体业 务相应群体下个体用户的历史数据；
    根据所述群体业务的用户数据确定群体满意度测算模型；
    根据所述群体满意度测算模型确定训练集中群体样本的群体满意度；
    根据所述训练集中群体样本的群体满意度和群体样本的属性特征数据，确定所述群体不满意用户识别模型。
  9. 一种群体不满意用户识别设备，包括：处理器和配置为存储能够在处理器上运行的计算机程序的存储器，其中，
    所述处理器，配置为运行计算机程序时，执行权利要求1至6任一项所述方法的步骤。
  10. 一种存储介质，所述存储介质上存储有计算机程序，所述计算机程序被处理器执行时，实现权利要求1至6任一项所述方法的步骤。
PCT/CN2020/134359 2020-01-02 2020-12-07 群体不满意用户识别方法、装置、设备及存储介质 WO2021135842A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010000892.0A CN113065880A (zh) 2020-01-02 2020-01-02 群体不满意用户识别方法、装置、设备及存储介质
CN202010000892.0 2020-01-02

Publications (1)

Publication Number Publication Date
WO2021135842A1 true WO2021135842A1 (zh) 2021-07-08

Family

ID=76559561

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/134359 WO2021135842A1 (zh) 2020-01-02 2020-12-07 群体不满意用户识别方法、装置、设备及存储介质

Country Status (2)

Country Link
CN (1) CN113065880A (zh)
WO (1) WO2021135842A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115965137A (zh) * 2022-12-26 2023-04-14 北京码牛科技股份有限公司 特定组织发展对象倾向预测方法、***、终端及存储介质
CN118171196A (zh) * 2024-05-16 2024-06-11 电子科技大学 一种基于光网络大数据的视频业务客户体验质量预测方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120150854A1 (en) * 2010-12-11 2012-06-14 Microsoft Corporation Relevance Estimation using a Search Satisfaction Metric
WO2016196526A1 (en) * 2015-06-01 2016-12-08 Microsoft Technology Licensing, Llc Viewport-based implicit feedback
CN109299265A (zh) * 2018-10-15 2019-02-01 广州虎牙信息科技有限公司 潜在回流用户筛选方法、装置以及电子设备
CN110188796A (zh) * 2019-04-25 2019-08-30 博彦科技股份有限公司 用户识别方法、装置、存储介质和处理器
CN110222272A (zh) * 2019-04-18 2019-09-10 广东工业大学 一种潜在客户挖掘与推荐方法

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101110699B (zh) * 2007-08-07 2010-05-19 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***及其实现方法
US20140122594A1 (en) * 2012-07-03 2014-05-01 Alcatel-Lucent Usa, Inc. Method and apparatus for determining user satisfaction with services provided in a communication network
CN104680428B (zh) * 2015-03-16 2018-03-16 朗新科技股份有限公司 一种电网客户满意度模型的构建方法
CN107018004B (zh) * 2016-01-28 2019-11-12 ***通信集团福建有限公司 用户满意度管理***及方法
CN105933920B (zh) * 2016-03-31 2019-04-09 浪潮天元通信信息***有限公司 一种预测用户满意度的方法及装置
CN109345263A (zh) * 2018-08-02 2019-02-15 北京天元创新科技有限公司 预测客户满意度的方法和***
CN110245787B (zh) * 2019-05-24 2023-11-17 创新先进技术有限公司 一种目标群体预测方法、装置及设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120150854A1 (en) * 2010-12-11 2012-06-14 Microsoft Corporation Relevance Estimation using a Search Satisfaction Metric
WO2016196526A1 (en) * 2015-06-01 2016-12-08 Microsoft Technology Licensing, Llc Viewport-based implicit feedback
CN109299265A (zh) * 2018-10-15 2019-02-01 广州虎牙信息科技有限公司 潜在回流用户筛选方法、装置以及电子设备
CN110222272A (zh) * 2019-04-18 2019-09-10 广东工业大学 一种潜在客户挖掘与推荐方法
CN110188796A (zh) * 2019-04-25 2019-08-30 博彦科技股份有限公司 用户识别方法、装置、存储介质和处理器

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115965137A (zh) * 2022-12-26 2023-04-14 北京码牛科技股份有限公司 特定组织发展对象倾向预测方法、***、终端及存储介质
CN115965137B (zh) * 2022-12-26 2023-11-14 北京码牛科技股份有限公司 特定对象关联性预测方法、***、终端及存储介质
CN118171196A (zh) * 2024-05-16 2024-06-11 电子科技大学 一种基于光网络大数据的视频业务客户体验质量预测方法

Also Published As

Publication number Publication date
CN113065880A (zh) 2021-07-02

Similar Documents

Publication Publication Date Title
WO2020135535A1 (zh) 一种推荐模型训练方法及相关装置
WO2021114974A1 (zh) 用户风险评估方法及装置、电子设备、存储介质
WO2021027317A1 (zh) 基于关系网络的属性信息处理方法、装置、计算机设备和存储介质
CN108280670B (zh) 种子人群扩散方法、装置以及信息投放***
CN108804567A (zh) 提高智能客服应答率的方法、设备、存储介质及装置
WO2017133615A1 (zh) 一种业务参数获取方法及装置
CN109241427A (zh) 信息推送方法、装置、计算机设备和存储介质
US20220114680A1 (en) System and method for evaluating the true reach of social media influencers
US10565525B2 (en) Collaborative filtering method, apparatus, server and storage medium in combination with time factor
WO2020211357A1 (zh) 数据的关联分析方法、装置、计算机设备及存储介质
US20160012479A1 (en) System and method for preference determination
US20210056458A1 (en) Predicting a persona class based on overlap-agnostic machine learning models for distributing persona-based digital content
WO2021135842A1 (zh) 群体不满意用户识别方法、装置、设备及存储介质
WO2021155691A1 (zh) 用户画像生成方法、装置、存储介质及设备
CN112966189B (zh) 一种基金产品推荐***
Chen et al. A context-aware recommendation approach based on feature selection
US11244332B2 (en) Segments of contacts
CN112529665A (zh) 基于组合模型的产品推荐方法、装置及计算机设备
Wang et al. An unsupervised strategy for defending against multifarious reputation attacks
CN109447694B (zh) 一种用户特征分析方法及其***
KR102196167B1 (ko) 사회 지능 평가 방법 및 이를 위한 장치
Wiradinata et al. The analysis of Instagram Technology adoption as marketing tools by small medium enterprise
CN109325781A (zh) 客户品质分析方法、装置、计算机设备和存储介质
CN111291795A (zh) 人群特征分析方法、装置、存储介质和计算机设备
WO2021000411A1 (zh) 基于神经网络的文档分类方法、装置、设备及存储介质

Legal Events

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

Ref document number: 20909951

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: 20909951

Country of ref document: EP

Kind code of ref document: A1