39 results about "Customer attrition" patented technology

The invention relates to the technical field of artificial intelligence, and discloses a customer loss management method and device, equipment and a storage medium, and the method comprises the steps: obtaining multi-dimensional target data of a target customer; inputting the multi-dimensional target data into a pre-trained customer loss prediction model to obtain a target prediction value output by the customer loss prediction model; constructing a customer portrait of the target customer based on the multi-dimensional target data; determining a loss risk level and a target loss type of the target customer based on the target predicted value; based on the loss risk level, the target loss type and the customer portrait, determining a target retention strategy corresponding to the target loss type; according to the scheme, the customer loss value can be automatically predicted, the loss tendency of the customer can be determined, the accuracy and efficiency of customer loss prediction can be improved, and the customer can be better retained by searching the retention strategy corresponding to the loss type.

The invention belongs to the technical field of big data customer information matching, and discloses an intelligent customer information matching method based on big data, which comprises the following steps of: firstly, establishing a scene customer behavior semantic dictionary according to three groups of new customers, high-value customers and loss early-warning customers, and determining behavior label mapping rules of different customer types; for example, the browsing duration of a new customer exceeds 3 minutes, the consultation frequency exceeds 2, the behavior is defined as a high-intention behavior, the semantic dictionary is dynamically updated every 24 hours based on cross-platform semantic conflict feedback, and the cross-platform data semantic standard is unified; secondly, screening weak association features by adopting a mutual information and customer value double-weight algorithm, setting weights according to customer value differences, and preferentially retaining features with higher association degree with customer demands to generate structured feature vectors; and finally, deploying a preprocessing effect verification module at an edge computing node, performing field secondary labeling, null interpolation complementation and time format unification operation on the data, and improving the data standardization level.

The invention relates to the technical field of data processing, and discloses an insurance policy renewal strategy generation method and device based on dynamic health analysis and a medium, and aims at converting health data of a target user into health factor parameters through a dynamic configuration mapping rule to form a health factor parameter table so as to accurately evaluate the health condition of the user. According to the method, a corresponding insurance premium weighting algorithm is matched for each health factor parameter through an algorithm configuration rule, differential influence of different health factors on insurance premium is fully considered, an insurance premium floating coefficient is obtained through weighting calculation of each health factor parameter, and an insurance policy renewal strategy is generated according to the coefficient and original insurance policy data. The renewal strategy can be accurately matched with the current health condition and risk level of the user, so that the accuracy of the insurance policy renewal strategy is effectively improved, risk mismatching and customer loss risks caused by health changes are reduced, and the method has remarkable beneficial effects on accurate renewal management of insurance services in the financial and medical field.

The invention provides a customer loss early warning method, device and equipment, a medium and a program product, relates to the technical field of artificial intelligence, and can be applied to the field of financial science and technology. The method comprises the following steps: under the condition that authorization of a target customer to use related data thereof is obtained, obtaining data of the target customer in each of W continuous time periods ending the current moment to obtain a target sequence; standardizing the target sequence to obtain an original standard sequence; the original standard sequence is input into a target time sequence behavior anomaly detection model, a reconstruction sequence output by the target time sequence behavior anomaly detection model is obtained, and the target time sequence behavior anomaly detection model is a time sequence behavior anomaly detection model independently constructed for a target customer; comparing the original standard sequence with the reconstructed sequence to obtain a deviation degree; and when the deviation degree meets an abnormal alarm condition, triggering loss early warning of the target customer.

The embodiment of the invention provides a multi-source heterogeneous data processing method and device, equipment, a medium and a product, and relates to the field of artificial intelligence or the field of financial science and technology. A dynamic knowledge graph is constructed by acquiring multi-source heterogeneous data including customer-related data from different data sources and having different formats or structures, and multi-task processing of customer loss prediction, product recommendation and compliance detection is performed on the dynamic knowledge graph through a graph neural network. According to the method, the dynamic knowledge graph which can be updated in real time is constructed, and the graph neural network is combined to realize multi-task processing, so that the problem that an existing service system depends on a static label system and cannot meet dynamic change of customer requirements is solved, dynamic perception of customer states is realized, and customer experience is improved. The processing precision and efficiency of tasks such as customer loss prediction, product recommendation and compliance detection are effectively improved, and reliable data support is provided for business decision making.

The invention discloses a call center information pushing system and method based on big data analysis, and belongs to the field of big data analysis. A transaction information abnormity evaluation model is constructed, customer basic information and customer transaction information are imported into the transaction information abnormity evaluation model for transaction abnormity analysis, and a customer abnormity judgment model is constructed; and substituting the obtained transaction abnormity analysis result, the historical sales data and the score data after each transaction of the customer into a customer abnormity judgment model for customer abnormity analysis, comparing the obtained customer abnormity analysis result with a set customer loss threshold value, and performing customer loss level analysis. And the customer loss grade analysis result obtained through judgment is pushed to the customer service terminal, customer loss early warning is carried out, the customer loss grade is estimated according to the sales characteristics of customer loss, and the accuracy of customer loss early warning is improved.

The invention provides a railway freight customer loss prediction method, and belongs to the field of railway transportation. The method comprises the following steps: constructing a railway freight customer portrait system; constructing a customer freight demand prediction model; constructing a customer loss early warning model based on data in the railway freight customer portrait system; and a demand prediction value output by the customer freight demand prediction model is converted into dynamic input features of the customer loss early warning model, loss risk calculation is executed, and railway freight customer loss prediction is completed. According to the invention, problems of low demand prediction precision, lack of an effective loss early warning mechanism and low data utilization efficiency in existing railway freight customer management are solved.

The present application relates to a kind of railway freight service dynamic matching method and system based on customer characteristics, comprising the following steps: obtaining the customer data of each customer in each customer, customer index and customer traffic data;For each customer, according to customer data, determine customer classification, customer classification includes at least one of customer value, customer loyalty, customer potential value, customer transportation characteristics and customer transfer cost;For each customer, according to customer index, determine customer rating;For each customer, according to customer traffic data, determine customer loss trend;For each customer, according to the customer classification, customer rating and customer loss trend corresponding to customer, match the target freight service corresponding to customer from each freight service, each freight service includes transport capacity guarantee, freight product and value-added service, transport price strategy and transport timeliness.Provide differentiated transport capacity tilt and product service for the needs of different customers and the contribution to railway.

The application discloses a customer loss early warning method and device, a storage medium, a program product and computer equipment. The method comprises the following steps: obtaining behavior data of a target customer, and determining key behavior characteristics corresponding to the behavior data; determining behavior mode change information of the target customer in a target period based on the key behavior characteristics; in the case that the behavior mode change information meets a preset mode deviation condition, determining risk index information of the target customer based on the behavior mode change information, the key behavior characteristics, reference characteristic information associated with the key behavior characteristics; obtaining an early warning strategy based on the key behavior characteristics, the risk index information and a first risk trend direction corresponding to the risk index information, and historical loss-related data of a customer group to which the target customer belongs; and pushing a retention information message corresponding to the early warning strategy to the target customer. Thus, the loss risk early warning accuracy can be improved, and the pushing accuracy of the retention information message pushed to the customer with a high loss risk can be improved.

The application discloses a financial institution asset management scale growth prediction and optimization method and related equipment, first, customer behavior and market data are acquired; then, based on the market data, a time series analysis model is used to predict future asset return rate, and asset allocation strategies of different risk preference customer groups are optimized accordingly; then, expected maximum drawdown of each group is evaluated according to the optimized strategies, and customer churn rate is predicted in combination with the mapping relationship between the expected maximum drawdown and the customer churn rate; meanwhile, based on the predicted asset return rate, customer behavior data and risk attitude, a behavior decision model based on prospect theory is used to predict customer conversion rate; finally, the overall asset management scale growth prediction value of the financial institution is calculated by comprehensively integrating the above results, and an optimization suggestion report containing risk grouping, customer communication and product recommendation strategies is generated. The purpose of the application is to organically integrate market yield prediction, asset allocation optimization, churn rate prediction based on portfolio risk and conversion rate prediction based on customer behavior and preference, and realize result linkage and comprehensive optimization.

The invention relates to the field of data analysis, in particular to a customer loss early warning feedback method, system, device and product based on customer behavior analysis, and the method comprises the steps: S1, obtaining the historical data of the delivery amount of a customer, and obtaining the time sequence data of the delivery amount; s2, performing seasonal identification on the delivery quantity time sequence data to obtain a main seasonal period; s3, based on the main seasonal period, performing characteristic decomposition on the delivery quantity time sequence data by adopting an STL time sequence decomposition algorithm to obtain a trend item, a seasonal item and a residual item of the delivery quantity time sequence data; s4, based on the obtained trend item, marking the customer as a potential loss customer; s5, early warning information is pushed to a customer manager, customer communication is carried out, and negative labels are marked for the customers based on the customer communication result; and S6, implementing an operation intervention strategy for customer retention for the customers marked with the negative labels. According to the invention, automatic analysis of the customer loss risk can be realized, and accurate and timely customer loss risk reminding is carried out.

The invention provides an intelligent lease operation system based on multi-dimensional data analysis, and the system comprises a multi-dimensional data collection module which is used for carrying out the three-dimensional modeling of a lease space, and collecting the multi-dimensional data; the data analysis processing module is used for inputting the multi-dimensional data into a pre-constructed dynamic pricing, contract risk, cash flow prediction and customer loss early warning model, and outputting an optimal listing price, a risk score, cash flow probability distribution and a loss probability curve; the intelligent decision execution module is used for automatically generating a strategy packet, and issuing the strategy packet to a corresponding execution unit after approval; and the visual interaction module is used for displaying the comprehensive operation state of each space unit in the three-dimensional rental model in real time, generating a differentiated data view, receiving user input and feeding back the user input to the intelligent decision execution module in real time. Through data driving and automatic intelligent decision making, experience-driven to data-driven transformation is realized for lease operation, so that balance between asset value maximization and operation risk minimization is achieved.

The invention relates to the field of logistics, and discloses a cross-domain customer loss early warning method, device and equipment and a storage medium, and the method is used for predicting and early warning customer loss conditions. The method comprises the steps of obtaining source domain local customer data and target domain local customer data, and performing feature alignment and preprocessing to obtain source domain preprocessing features and target domain preprocessing features; identifying and obtaining key causal features of a source domain and key causal features of a target domain by using a causal inference method, carrying out domain self-adaption by using a federated transfer learning technology, transferring knowledge of the source domain to the target domain, and generating domain-invariant shared feature representation; based on the domain-invariant shared feature representation and the local customer loss label, updating a pre-trained local customer loss classifier, updating a pre-trained global customer loss early warning model, and obtaining a cross-domain customer loss early warning model; and inputting the new customer data of the target domain into the cross-domain customer loss early warning model to obtain a predicted loss probability, and generating an early warning signal.

The invention provides a processing method and device for coping with customer loss, equipment, a medium and a program product, and relates to the technical field of artificial intelligence. The method comprises the steps that in response to a received loss early warning event of a target customer, data of the target customer is inquired from multiple internal systems to obtain a comprehensive data snapshot of the target customer, and different systems in the multiple internal systems are used for recording data of different dimensions of the customer; generating a first prompt word based on the comprehensive data snapshot of the target customer; and using the first prompt word to indicate the fine-tuned large language model to generate a risk abstract of the target customer. In this way, when customer loss early warning needs to be analyzed, the trouble of manually switching data checking, data arrangement and analysis among a plurality of systems can be avoided, and the analysis efficiency of customer loss is improved.

The invention discloses a customer service dialogue evaluation method and device, equipment, a storage medium and a product, and is applied to the technical field of data processing, and the method comprises the steps: obtaining multi-modal dialogue data generated in a customer service process, carrying out the preprocessing of the multi-modal dialogue data, and generating structured dialogue data; based on the structured dialogue data, basic dialogue evaluation indexes are calculated, and the basic dialogue evaluation indexes comprise a service efficiency index, a service quality index, a business capability index, a compliance index and a customer stickiness index; based on the structured dialogue data and the basic dialogue evaluation index, respectively generating a customer satisfaction index, a customer loss early warning index and a potential service demand identification index through a machine learning model; and inputting the basic dialogue evaluation index, the customer satisfaction index, the customer loss early warning index and the potential service demand identification index into the service dialogue evaluation model to obtain a service dialogue evaluation result, so that the actual service quality of the dialogue can be comprehensively and accurately reflected.

The invention belongs to the technical field of intelligent research and judgment of insurance data, and particularly relates to an insurance customer loss early warning method and system fusing causal inference large model learning. The method comprises the steps of collecting multi-source data such as customer behavior data, insurance policy information and claim settlement records and performing standardization processing; constructing a causal map based on the structure equation model, and extracting a high causal degree path set; constructing a multi-layer recurrent neural network model for supervised training by taking the path structure as prior; analyzing and optimizing a model structure through path stability; and finally, in combination with the prediction probability and a path backtracking result, outputting a customer risk level and a reversible intervention node. The method realizes causal interpretable prediction and operable path intervention of customer loss, and is suitable for intelligent customer management and personalized operation scenes in the insurance industry.

The application relates to the technical field of loss prediction, and discloses a marketing intervention method and system based on customer loss prediction, which comprises the following steps: performing abnormal fluctuation detection on the interactive behavior data of customers to obtain loss sign data; performing state evolution analysis on the loss sign data to obtain active decline characteristics; performing time sequence trajectory fitting on the loss sign data to obtain an active decline trajectory graph; matching the active decline trajectory graph with the life cycle of the customers, and fusing the static attribute data of the customers to obtain a loss risk multidimensional portrait; performing decision factor analysis on the loss risk driving factors of the customers, comprehensively judging the root cause characteristics after the analysis, and obtaining a loss risk grade; mapping the root cause characteristics and the loss risk grade to a preset strategy intervention library, combining the static attribute data, and generating an individualized intervention strategy; and the application can improve the efficiency of marketing intervention based on customer loss prediction.

The invention relates to the technical field of loss prediction, and discloses a marketing intervention method and system based on customer loss prediction, and the method comprises the steps: carrying out the abnormal fluctuation detection of the interaction behavior data of a customer, and obtaining loss symptom data; carrying out state evolution analysis on the loss symptom data to obtain active decline features; performing time sequence trajectory fitting on the loss symptom data to obtain an activity decline trajectory diagram; performing stage matching on the activity decline trajectory diagram and the life cycle of the customer, and fusing static attribute data of the customer to obtain a loss risk multi-dimensional portrait; performing decision factor analysis on the loss risk driving factor of the customer, and performing risk comprehensive research and judgment on the analyzed root cause feature to obtain a loss risk level; mapping the root cause feature and the loss risk level to a preset strategy intervention library, and generating a personalized intervention strategy in combination with the static attribute data; according to the invention, the efficiency of marketing intervention based on customer loss prediction can be improved.

The invention relates to the technical field of animal epidemic disease epidemiological survey data analysis and processing systems, and discloses an animal epidemic disease epidemiological survey data analysis and processing system. The exploration data warehouse is used for reading survey data of animal epidemic situation epidemiology, the model library is used for storing various calculation models and algorithm formulas, and the component library is used for storing customer division data, customer loss data and customer product data of different industries. The mining algorithm library is used for performing mining calculation on data according to information of the model library, the component library and the exploration data warehouse and importing a calculation result into the survey data client, the knowledge storage end is used for receiving and storing the data imported by the data mining algorithm library, and the survey data client is used for reading the data of the knowledge storage end for query. The problems that a traditional data analysis and processing system is complex in architecture design structure and low in efficiency are solved.

The invention provides a customer loss early warning system based on behavior burying points, which relates to the field of behavior data processing, and comprises the following steps: dividing a behavior period into three sequential execution time periods, and sequentially running a behavior latent language module, a behavior judgment module and a ghost reverse verification module; the behavior latent language module converts the user interface operation event sequence into a behavior representation path to reflect a behavior intention; the behavior judgment module constructs a multi-dimensional behavior phase space, generates a disturbance path and establishes a mirror image loop as a comparison reference; the ghosting reverse verification module compares nodes which cannot be explained mutually in the two paths and marks the nodes as ghosting nodes, and a ghosting link is constructed to track an irregressive trend; the dislocation closing module only allows a ghost link to transmit a state; and when the ghosting link forms a head-tail closed structure in three continuous periods, interpretation continues and fails and a node growth rate exceeds a threshold value, determining that the ghosting link is a reverse detection chain path and triggering a structural customer loss early warning signal.

The invention relates to a marketing business intelligent early warning method based on big data analysis, and the method comprises the following steps: S1, obtaining internal data and external data related to a marketing business, and carrying out the preprocessing; s2, multi-source data of the preprocessed data is stored as a unified model through a data lake, and the unified model adopts a theme domain modeling mode including a marketing domain, a customer domain, a sales domain and a channel domain; s3, constructing a multi-level anomaly detection model, and identifying an abnormal condition in the marketing data; s4, constructing a customer loss prediction model, predicting a customer loss probability based on the preprocessed data, and identifying a high-risk customer group; and S5, realizing intelligent early warning based on an intelligent early warning algorithm in combination with the abnormal condition and the customer loss probability in the marketing data. According to the invention, the reliability of marketing business management is effectively improved.

The invention relates to the technical field of customer relationship management, in particular to an edge-deployed customer loss prediction method and system based on machine learning, and the method comprises the following steps: obtaining historical behavior data, attribute data and service use record data of a target user, the data comprises but is not limited to communication frequency, call duration, internet traffic, bill amount, complaint record and package change information; the method has the beneficial effects that an integrated model (such as XGBoost and LightGBM) based on a gradient boosting decision tree is adopted, and nonlinear features and complex interaction relationships in customer churn behaviors can be effectively modeled. Compared with a traditional logistic regression model, the method has the advantage that the prediction precision on an actual operation data set is remarkably improved. Through K-fold cross validation and a regularization mechanism (such as L1 / L2 constraint), the volatility of the model in different time periods or different service scenes is remarkably reduced, and the robustness of data disturbance is improved.

The invention relates to the technical field of digital data processing, in particular to a multi-modal electric power marketing data intelligent fusion system and method based on reinforcement learning. The invention discloses a multi-modal electric power marketing data intelligent fusion system based on reinforcement learning. The multi-modal electric power marketing data intelligent fusion system comprises a multi-source data access layer, a ternary state sensing layer, an intelligent decision-making layer, a fusion execution layer and a feedback optimization layer. According to the method, through a special adaptive channel and feature standardization, the information entropy loss is reduced by 60%, and the standardization feature vector dimension unification degree reaches 100%; according to the exception handling mechanism, the service interruption duration is shortened to be less than 10 seconds, the fusion accuracy rate is stabilized to be more than 96%, the customer loss early warning response time is less than or equal to 3 seconds, and the precision marketing accuracy rate is greater than or equal to 98%.

The present disclosure provides a user group-based off-network prediction method and device, terminal equipment and computer readable storage medium to solve the problem that the current operator does not know the life cycle status of the overall customer group, resulting in customer loss and other problems, wherein the method comprises: creating an off-network prediction model; grouping users to obtain user grouping results; and predicting the off-network trend of users in each group in the user grouping results based on the off-network prediction model. The present disclosure groups users, then predicts the off-network of users in each user group based on the created off-network prediction model, realizes the purpose of efficient and accurate off-network trend analysis of operator users, reserves sufficient time for user retention activities, helps marketing personnel to develop a feasible customer retention plan, effectively avoids customer loss and other problems, and has a wide industry application prospect.

The invention relates to a telephone traffic system missed call priority ranking and real-time distribution method and system based on multi-feature machine learning, and the method comprises the following steps: 1) monitoring a missed call event that the ringing of an incoming call is finished and the incoming call is not answered, and generating a missed call record and a trigger signal; 2) obtaining multi-dimensional feature data according to the trigger signal; 3) performing data cleaning and standardization on the multi-dimensional feature data to obtain a structured feature vector; 4) taking the structured feature vector as an input quantity of a pre-trained machine learning model to obtain a priority score; and 5) according to the priority score and the real-time seat state data, executing an intelligent routing decision, and allocating the missed call information to the target seat in real time, thereby realizing real-time, accurate and active allocation of the high-value missed calls, and through a return visit feedback data optimization model, the high-value missed call identification accuracy and recall rate are significantly improved, and the customer loss risk is reduced.

The invention relates to the field of artificial intelligence, and provides a customer loss prediction model establishment method and device and an early warning method and device.The model establishment method comprises the steps that stock customers are classified; determining a loss index of each type of customer in each business scene; screening out a loss index meeting a preset condition from the loss indexes of the various types of customers in the various business scenes, and determining a key attention business scene and a key attention customer group; determining transaction feature information and a loss label according to the transaction behavior information of the focused customers focusing on the business scene within a second preset time period; and establishing a loss prediction model by using the transaction feature information and the loss label. According to the method and the device, model training resources can be saved and interference of non-loss data can be reduced only on the basis of the key attention customers in the key attention business scene, the model training precision and efficiency are improved, and then the accuracy of loss prediction of the key attention newly-added customers in the key attention business scene is improved.

The present application belongs to the technical field of insurance data intelligent research and judgment, and particularly relates to an insurance customer loss early warning method and system fusing a causal inference large model learning. The method comprises: collecting customer behavior data, policy information, claim records and other multi-source data and standardizing processing; constructing a causal graph based on a structural equation model, and extracting a high causal degree path set; constructing a multi-layer recurrent neural network model for supervised training with the path structure as a priori; optimizing the model structure through path stability analysis; and finally combining the prediction probability with the path backtracking result to output the customer risk level and reversible intervention node. The method realizes causal interpretable prediction and operable path intervention of customer loss, and is suitable for intelligent customer management and personalized operation scenarios in the insurance industry.

The invention relates to the technical field of digital twinning of artificial intelligence, in particular to a bank outlet resource allocation simulation method and system based on digital twinning, and the method comprises the steps: collecting passenger flow data and business data of a bank outlet, obtaining target passenger flow data and business data, and inputting the target passenger flow data and business data into a target prediction model, the method comprises the steps of determining customer visiting amount and service type distribution data in a future time period, inputting the customer visiting amount and service type distribution data in the future time period into a digital twin based on preset resource configuration strategies, performing simulation to obtain simulation results corresponding to the preset resource configuration strategies, and determining a target resource configuration strategy based on a plurality of simulation results. The technical problems that in the prior art, a new strategy needs to be subjected to trial and error in an actual website, cost rise or customer loss is directly caused once errors occur, short-term passenger flow and business volume cannot be accurately predicted, decision lag is caused, and bank website operation is not convenient due to passivity all the time are solved. The method has the effect of improving the bank operation efficiency.

The embodiment of the invention provides a customer loss prediction method and device, equipment, a storage medium and a program product, and relates to the field of artificial intelligence. The method comprises the steps that historical customer data of multiple source domains are subjected to comparative learning training to obtain a prediction model, the historical customer data of the multiple source domains are distributed differently, the historical customer data of each source domain comprises customer data of a lost category and customer data of a non-lost category, and real-time customer data are obtained to obtain real-time customer data; and inputting the real-time customer data into the trained prediction model so as to output the customer corresponding to the real-time customer data and the loss probability of the customer through the prediction model. According to the method provided by the invention, the prediction accuracy and reliability of the cross-regional customer loss risk are improved.

The invention discloses a service pushing method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the following steps: in response to a received service work order, obtaining customer information and a target service item from the service work order; the client type is determined based on the client information, a corresponding selectable service package is obtained according to the client type, and the selectable service package is generated based on a dynamic planning algorithm according to a service package budget and service data corresponding to the client type; and selecting a target service package from the selectable service packages based on the target service item, and carrying out service pushing. According to the embodiment, accurate matching between the service package and the customer demand and budget can be ensured, and the flexibility of the service package is improved; the real-time performance of service pushing is improved while the calculation precision is ensured, the pushing conversion rate is improved, and the customer loss is reduced.