CN-122022902-A - Personalized service recommendation method, device, equipment and storage medium

CN122022902ACN 122022902 ACN122022902 ACN 122022902ACN-122022902-A

Abstract

The application discloses a personalized service recommendation method, a device, equipment and a storage medium, which relate to the technical field of big data, wherein the method comprises the following steps: and uniformly collecting feedback data of the clients in different channels through the platform, determining feedback emotion analysis results, client satisfaction grading values, potential problems, client life cycle stages, point rewards, exclusive offers and comprehensive behavior characteristics according to the client feedback data, and comprehensively generating a personalized service recommendation scheme. The method and the system collect feedback data on different channels through a unified platform, ensure the effectiveness of the feedback data, analyze the feedback data in real time according to the collected feedback data, analyze the feedback emotion, customer satisfaction, potential problem identification, life cycle stage, point rewards, exclusive offers and the like, accurately identify the true emotion and the demand of the customer, ensure the accuracy and the reliability of analysis results, and provide personalized service recommendation through comprehensive analysis of behavior characteristics, thereby improving the customer satisfaction.

Inventors

Yu Duojia
NING XUANCHENG

Assignees

中移动金融科技有限公司
中国移动通信集团有限公司

Dates

Publication Date: 20260512
Application Date: 20241111

Claims (10)

1. A personalized service recommendation method, the method comprising: Collecting client feedback data of clients in various channels uniformly through a preset platform; carrying out feedback emotion analysis according to the client feedback data to obtain a feedback emotion analysis result; carrying out customer satisfaction scoring according to the customer feedback data to obtain a customer satisfaction scoring value; carrying out potential problem identification according to the feedback emotion analysis result and the customer satisfaction degree score value to obtain a potential problem identification result; Determining a life cycle stage of the client according to the feedback emotion analysis result; determining a point reward based on the customer lifecycle stage and the customer satisfaction score value; Determining a proprietary offer according to the customer lifecycle stage and the point rewards; comprehensively analyzing according to the feedback emotion analysis result, the customer satisfaction degree grading value, the potential problem, the customer life cycle stage and the point rewards to obtain comprehensive behavior characteristics; And determining a personalized service recommendation scheme according to the client feedback data, the feedback emotion analysis result, the client satisfaction degree score value, the potential problem, the client life cycle stage, the point rewards, the exclusive offers and the comprehensive behavior characteristics, and pushing the personalized service recommendation scheme to a user.
2. The method of claim 1, wherein the step of collecting customer feedback data of customers in a plurality of different channels in a unified manner through a preset platform comprises: The feedback data of the clients in a plurality of different channels are collected uniformly through a preset platform; determining channel weights corresponding to the plurality of different channels according to the client coverage rate, the feedback quality, the client preference and the response speed; carrying out weighted summation on feedback data in the plurality of different channels according to the channel weights to obtain channel weight summation results; Determining feedback influence factors according to feedback timeliness, customer life cycle stages, market environment changes and historical feedback data; Determining a feedback influence value according to the feedback influence factor and a life cycle stage corresponding to the last time of the preset time; and summing the channel weight summation result and the feedback influence value to obtain the customer feedback data.
3. The method of claim 1, wherein the step of performing feedback emotion analysis based on the client feedback data to obtain feedback emotion analysis results comprises: Determining the feedback weight of each piece of feedback data of each client in the client feedback data according to the feedback importance weight, the time-related weight and the feedback source weight; carrying out weighted summation on emotion scores of each piece of feedback data of each client in the client feedback data according to the feedback weights to obtain feedback weight summation results; Determining a client point rewards value of each client according to the client emotion influence factors and the client point rewards; and determining a feedback emotion analysis result of each client in the client feedback data according to the feedback weight summation result and the client point rewarding value.
4. The method of claim 1, wherein said step of scoring customer satisfaction based on said customer feedback data to obtain a customer satisfaction score value comprises: weighting and summing the satisfaction score of each customer in the customer feedback data according to the satisfaction score weight to obtain a satisfaction summation result; Determining a satisfaction influence value of each client according to the satisfaction influence factor and the feedback emotion analysis result of each client; and determining the customer satisfaction grading value of each customer in the customer feedback data according to the satisfaction summation result and the satisfaction influence value.
5. The method of claim 1 wherein said step of performing a potential problem identification based on said feedback emotion analysis result and said customer satisfaction score value, obtaining a potential problem identification result comprises: according to the adjustment coefficient, adjusting historical feedback emotion score and historical customer satisfaction score data to obtain a dynamic adjustment factor; or setting an adjustment coefficient according to the business target, and determining a dynamic adjustment factor according to the adjustment coefficient; or, predicting historical feedback emotion score and historical customer satisfaction score data based on a machine learning mode, and determining a dynamic adjustment factor according to a prediction result; Determining a difference between the feedback emotion analysis result and the customer satisfaction score value; And determining a potential problem identification result according to the difference value, a preset difference threshold value and the dynamic adjustment factor.
6. The method of claim 1, wherein the step of determining a client lifecycle stage based on the feedback emotion analysis result comprises: Determining linear correlation between the historical feedback emotion score and the historical lifecycle stage data according to the Pearson correlation coefficient, and adjusting the linear correlation according to the adjustment coefficient to obtain a lifecycle adjustment factor; determining the client activity of each client according to the online behavior data analysis mode, the transaction data analysis mode and the interaction data analysis mode; And determining a client life cycle stage according to the client liveness, the feedback emotion analysis result, a first liveness threshold value, a second liveness threshold value, a first feedback emotion score threshold value, a second feedback emotion score threshold value and the life cycle adjusting factor, wherein the client life cycle stage comprises an introduction period, a growth period, a maturation period and a decay period, and the first feedback emotion score threshold value is larger than or equal to the second feedback emotion score threshold value.
7. The method of claim 1, wherein after the step of determining a personalized service recommendation based on the customer feedback data, the feedback emotion analysis result, the customer satisfaction score value, the potential problem, the customer lifecycle stage, the point reward, the proprietary offer, and the integrated behavioral characteristics, further comprising: Evaluating the personalized service recommendation scheme to obtain an evaluation result; Judging whether the personalized service recommendation scheme is effective according to the evaluation result; if the personalized service recommendation scheme is invalid, adjusting the potential problems of the clients according to the scheme adjustment coefficient and the evaluation result, and determining the adjusted personalized service recommendation scheme according to the adjusted potential problems of the clients; Adjusting the point rewards according to the adjustment weight coefficient to obtain adjusted point rewards; Optimizing the adjusted personalized service recommendation scheme according to the point rewards after adjustment, obtaining an optimized personalized service recommendation scheme, and pushing the optimized personalized service recommendation scheme to a user.
8. A personalized service recommendation device, characterized in that the personalized service recommendation device comprises: The client feedback data collection module is used for uniformly collecting client feedback data of clients in a plurality of different channels through a preset platform; the feedback emotion analysis module is used for carrying out feedback emotion analysis according to the client feedback data to obtain a feedback emotion analysis result; The customer satisfaction scoring module is used for scoring the customer satisfaction according to the customer feedback data to obtain a customer satisfaction scoring value; The potential problem identification module is used for carrying out potential problem identification according to the feedback emotion analysis result and the customer satisfaction degree score value to obtain a potential problem identification result; the client life cycle determining module is used for determining a client life cycle stage according to the feedback emotion analysis result; the point rewards determining module is used for determining point rewards according to the client life cycle stage and the client satisfaction degree scoring value; the exclusive offer determining module is used for determining exclusive offers according to the life cycle stage of the client and the point rewards; The behavior characteristic comprehensive analysis module is used for comprehensively analyzing according to the feedback emotion analysis result, the customer satisfaction degree score value, the potential problem, the customer life cycle stage and the point rewards to obtain comprehensive behavior characteristics; and the personalized service recommendation module is used for determining a personalized service recommendation scheme according to the client feedback data, the feedback emotion analysis result, the client satisfaction degree grading value, the potential problem, the client life cycle stage, the point rewards, the exclusive offers and the comprehensive behavior characteristics and pushing the personalized service recommendation scheme to a user.
9. A personalized service recommendation device, characterized in that the device comprises a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the personalized service recommendation method according to any one of claims 1 to 7.
10. A storage medium, characterized in that the storage medium is a computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the personalized service recommendation method according to any one of claims 1 to 7.

Description

Personalized service recommendation method, device, equipment and storage medium Technical Field The present application relates to the field of big data technologies, and in particular, to a personalized service recommendation method, device, equipment, and storage medium. Background Customer feedback and satisfaction management have become a critical loop in modern enterprises. To remain competitive and meet customer needs, many businesses employ various methods to collect and analyze customer feedback to better understand customer needs and improve quality of service. Existing methods of customer feedback and satisfaction management suffer from the disadvantage that businesses typically collect customer feedback through independent channels (e.g., telephone, mail, social media). The feedback data of each channel is relatively independent, lacks unified comprehensive analysis, and is difficult to comprehensively reflect the overall experience of clients, so that the representativeness and the effectiveness of the feedback data are insufficient. The existing customer feedback analysis is mostly dependent on static data, lacks of real-time performance and dynamic adjustment capability, and is difficult to accurately identify the true emotion and the requirement of a customer, so that customer satisfaction degree of service recommendation is low. Disclosure of Invention The application mainly aims to provide a personalized service recommendation method, device, equipment and storage medium, and aims to solve the technical problems that the effectiveness of feedback data is insufficient, and the customer satisfaction degree of service recommendation is low due to the lack of real-time dynamic adjustment capability in the existing method. In order to achieve the above object, the present application provides a personalized service recommendation method, which includes: Collecting client feedback data of clients in various channels uniformly through a preset platform; carrying out feedback emotion analysis according to the client feedback data to obtain a feedback emotion analysis result; carrying out customer satisfaction scoring according to the customer feedback data to obtain a customer satisfaction scoring value; carrying out potential problem identification according to the feedback emotion analysis result and the customer satisfaction degree score value to obtain a potential problem identification result; Determining a life cycle stage of the client according to the feedback emotion analysis result; determining a point reward based on the customer lifecycle stage and the customer satisfaction score value; Determining a proprietary offer according to the customer lifecycle stage and the point rewards; comprehensively analyzing according to the feedback emotion analysis result, the customer satisfaction degree grading value, the potential problem, the customer life cycle stage and the point rewards to obtain comprehensive behavior characteristics; And determining a personalized service recommendation scheme according to the client feedback data, the feedback emotion analysis result, the client satisfaction degree score value, the potential problem, the client life cycle stage, the point rewards, the exclusive offers and the comprehensive behavior characteristics, and pushing the personalized service recommendation scheme to a user. In one embodiment, the step of collecting, by the preset platform, the feedback data of the clients in the plurality of different channels includes: The feedback data of the clients in a plurality of different channels are collected uniformly through a preset platform; determining channel weights corresponding to the plurality of different channels according to the client coverage rate, the feedback quality, the client preference and the response speed; carrying out weighted summation on feedback data in the plurality of different channels according to the channel weights to obtain channel weight summation results; Determining feedback influence factors according to feedback timeliness, customer life cycle stages, market environment changes and historical feedback data; Determining a feedback influence value according to the feedback influence factor and a life cycle stage corresponding to the last time of the preset time; and summing the channel weight summation result and the feedback influence value to obtain the customer feedback data. In an embodiment, the step of performing feedback emotion analysis according to the client feedback data to obtain a feedback emotion analysis result includes: Determining the feedback weight of each piece of feedback data of each client in the client feedback data according to the feedback importance weight, the time-related weight and the feedback source weight; carrying out weighted summation on emotion scores of each piece of feedback data of each client in the client feedback data according to the feedback weights to obtain feedback weigh