26 results about "Customer classification" patented technology

The invention discloses a customer classification method, business processing method and system based on causal inference and interpretability, and the method comprises the steps: obtaining a customer classification model through pre-training: collecting historical data to obtain a training data set, the historical data comprising customer features corresponding to customers, business processing variables and result variables; inputting the training data set into a basic model based on a causal forest model and interpretability for training until the model converges to obtain a customer classification model; based on the causal forest model, determining an individual processing effect value of a customer according to customer characteristics, business processing variables and result variables; and calculating contribution values of the customer features to individual processing effects of the customers based on the interpretability, classifying the customers according to the individual processing effect values, the contribution values and the customer features, collecting the customer features to be classified, and inputting the customer features to a customer classification model to output a customer classification result. The accuracy and rationality of the customer classification result can be improved.

The application discloses a passenger group classification method and device based on a clustering and factor analysis model, and relates to the field of data analysis and processing.The method comprises the following steps: connecting a big data platform to a T-BOX to receive Internet of Vehicles data uploaded by the T-BOX, and performing cleaning processing on the received Internet of Vehicles data; dividing each trip of a vehicle based on the Internet of Vehicles data, extracting a resident feature, and obtaining a plurality of preliminary feature indexes for describing driving habits; performing a sufficiency test on the preliminary feature indexes, and performing dimension reduction processing on the preliminary feature indexes after the test is passed, so as to retain a preset number of preliminary feature indexes; fusing the retained preliminary feature indexes with driving-related main factors, performing K-Means clustering processing on the fused driving-related main factors, and forming passenger group labels.The application can accurately realize passenger group classification and avoid classification deviation.

This invention provides a blockchain-based method, system, and medium for managing digital financial customer files, belonging to the field of file management. It solves the problem of low efficiency in financial customer file management. Specifically, it involves: acquiring customer identity and financial information; designing identity identifiers based on the identity information; constructing a Merkle tree to store financial information and deploying it on the blockchain; classifying customers into high-net-worth and ordinary customers; calculating credit scores for high-net-worth customers and determining loan interest rates for them; analyzing the transaction time, transaction partners, and transaction amounts of ordinary customers to determine their frequently visited shops, further classifying them, and obtaining customer consumption behavior reports; summarizing customer consumption behavior reports and providing feedback; and synchronously updating financial information on the blockchain. This invention improves the security of financial information and enables financial institutions to understand changes in customer consumption in real time by digitizing and storing customer financial information.

The invention discloses a power utilization mode consistency analysis method, system and device based on load time-frequency domain feature fusion and a medium, and the method comprises the steps: obtaining power utilization load mode data of a client, extracting time domain features through dimension reduction, carrying out the Fourier transformation of the power utilization load mode data, calculating the amplitude of current harmonic waves, and obtaining the consistency of the current harmonic waves; selecting a preset number of significant harmonics to construct a frequency domain load feature vector; inputting the load characteristic template library and the transient current waveform template library into a clustering algorithm for time domain dominant clustering to obtain an initial clustering result, performing quality analysis, and triggering frequency domain clustering correction if the initial clustering result does not meet the standard; and the initial clustering result is combined with the frequency domain load feature vector to be input into an improved following leader algorithm to be corrected, so that a final consistency result is obtained. According to the method, time domain and frequency domain collaborative optimization is combined with the dynamic cluster number to adapt to a complex scene to ensure quality analysis reliability, accurate customer classification is achieved, and the method is suitable for personalized services of the electricity market.

The application discloses a bank fixed deposit target customer classification method based on a quantum neural network, relates to the technical field of classification based on quantum computing, and comprises the following steps: preprocessing a bank fixed deposit data set, obtaining feature information of bank fixed deposit customers, and loading the feature information into a quantum state; processing the quantum state by using a quantum neural network to obtain a prediction result of the feature information of the bank fixed deposit customers, constructing a loss function according to the prediction result of the feature information of the bank fixed deposit customers and a real label of the bank fixed deposit customers, updating parameters of the quantum neural network according to the loss function until a termination condition is met; and classifying feature information of a bank fixed deposit customer of a preset user according to the latest obtained quantum neural network. The quantum neural network is superior to a classical neural network in extraction of global features of bank deposit customer information and convergence speed, and requires less data for training.

The application provides a government and enterprise customer large customer classification method and device, electronic equipment and computer readable storage medium, and relates to the technical field of data processing. The method comprises the following steps: obtaining a government and enterprise customer name set and a large customer name set; respectively splitting a first government and enterprise customer name and a first large customer name to obtain a first government and enterprise customer name segmentation result and a first large customer name segmentation result, wherein the first large customer name segmentation result comprises N-level distance weight words; calculating the sum of the edit distances between the first government and enterprise customer name segmentation result and the N-level distance weight words of the first large customer name; and in response to the sum of the edit distances being less than a preset classification threshold, classifying the first government and enterprise customer name to the first large customer name. The application at least solves the problem of low accuracy of government and enterprise customer classification in the related art. The application is suitable for data analysis, customer marketing and the like.

A method for classifying customers via probabilistic scores from a predictive model, where each probabilistic score represents the probability that a customer will achieve a predicted outcome. The method includes: recording previous probabilistic scores and grouping them within a dataset; sorting the dataset by increment; deriving a reference quantile set based on the sorted previous probabilistic scores in the dataset; determining an action threshold that limits a target quantile range within the reference quantile set; receiving a probabilistic score from the predictive model for a first customer in the current interaction; comparing the first customer's probabilistic score with the probabilistic scores in the reference quantile set to determine a matching quantile; and determining whether the matching quantile is within the target quantile range and selectively classifying the first customer into a target audience based on this.

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 invention relates to the technical field of data analysis, can be applied to business system platforms of financial science and technology, medical treatment and health and the like, and discloses a customer classification method, device, equipment and medium, and the method comprises the steps: obtaining multi-dimensional data of a customer, and carrying out the effective feature extraction of the multi-dimensional data according to a preset effective customer standard, and obtaining a customer validity feature; creating derivative features according to the client validity features, and combining the client validity features and the derivative features into a feature data set; constructing a customer classification model according to the feature data set, and adjusting and optimizing the customer classification model to obtain an optimized customer classification model; performing key feature screening on the feature data set according to the optimized customer classification model to obtain key features; and performing customer classification on preset customer data according to the key features and the optimized customer classification model, and outputting a customer classification result. By acquiring the multi-dimensional data and creating the derivative features, the depiction ability of the customer features is improved, and the accuracy of customer classification is improved.

The invention discloses a customer group classification method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence or other related fields, and the method comprises the steps: retrieving target customer group data from a financial database, and carrying out the preprocessing of the target customer group data, the target customer group data comprises M pieces of target customer data, and M is a positive integer; performing feature extraction on each piece of target customer data based on predetermined feature items to obtain a customer group intention feature set containing M customer intention features; performing iterative clustering processing on the customer group intention feature set based on a preset clustering algorithm, and ending iterative clustering to obtain K classification clusters under the condition of meeting a preset convergence requirement, K being a positive integer; and generating a classification result based on the K classification clusters, and displaying the classification result. According to the method and the device, the technical problem of relatively low accuracy of processing large-scale customer data by a traditional customer group classification method in related technologies is solved.

We provide the system. [Solution] Means for collecting customer data, A means of analyzing collected customer data and classifying customers into segments, A means of generating optimal pricing plans and sales strategies for each customer based on analysis, A means of delivering generated pricing plans and sales strategies to customers in real time, A means to monitor the effectiveness of each measure and reflect the results in the next data analysis, A system that includes this.

To realize payment settlement with high accuracy and low workload even when the source of payment for receivables changes each time. [Solution] According to this embodiment, the deposit reconciliation device comprises: a deposit input means for creating deposit data including the deposit date, specific information, deposit amount, reconciled deposit amount, and customer classification obtained from the billing master using the specific information as a key; and a reconciliation means for aggregating the scheduled collection amounts of the collection schedule data by scheduled collection date in the receivables master, in order of customer granularity specified in the customer classification of the deposit data to customer granularity decreasing, excluding records other than the customer classification of the receivables origination reason master linked to the reason for the receivable of the collection schedule data, creating reconciliation candidate pattern list data, and comparing the scheduled collection amounts and deposit amounts in the reconciliation candidate pattern list data in order of customer granularity decreasing, and performing automatic reconciliation.

The embodiment of the application provides a customer classification method and device, relates to the field of data analysis, and can also be applied to the financial field. The method comprises the following steps: dividing a customer set into an online consumption customer set and an offline consumption customer set, and respectively determining consumption intervals, consumption frequencies and consumption amounts; respectively performing clustering, and determining the dividing points of the consumption intervals, the consumption frequencies and the consumption amounts of the online consumption customer set and the offline consumption customer set according to the clustering results; and respectively determining the value classification results of each customer in the online consumption customer set and the offline consumption customer set according to the dividing points and a value classification rule. The embodiment of the application considers the differences in customer consumption behaviors in multiple scenarios, adopts a differentiated RFM value calculation mode, constructs different models and uses a segmentation mode, and finally obtains individualized classification results.

This application belongs to the fields of artificial intelligence and fintech, and relates to an AI-based customer classification method, including: acquiring customer data and constructing a topological relationship network corresponding to the customer data; inputting the topological relationship network into a graph convolutional neural network for training to obtain a trained graph convolutional neural network; acquiring a target topological relationship network corresponding to target customer data, and processing the target topological relationship network through a customer segmentation model to generate segmentation results. This application also provides an AI-based customer classification device, computer equipment, and storage medium. Furthermore, this application relates to blockchain technology, and the customer segmentation model can be stored in the blockchain. The customer classification method of this application can be applied to user identification in the financial field, requires no labeled data for training, has low time complexity, and the use of the customer segmentation model can achieve fast and accurate generation of customer segmentation results.

Based on behavioral logs and customer attribute information of prospective customers, the system can generate and display talk scripts or strategy points tailored to each prospective customer for callers. [Solution] An information processing system comprising at least one control unit, the control unit acquires behavioral logs and customer attribute information relating to prospective customers, classifies prospective customers into segments based on the behavioral logs and customer attribute information, identifies information missing from prospective customers based on the difference between the customer group in which a success event occurred and the customer group in which a success event did not occur for the customer group belonging to the segment, determines appeal axes to supplement the missing information, generates a talk script for callers or strategy points for securing appointments based on the appeal axes, and displays the talk script or strategy points on a display unit in association with prospective customers.

The application discloses a kind of based on commercial circle big data to the method, device and electronic equipment of customer classification, the method includes: obtaining sales area, and the commercial data corresponding to sales area and the customer information of customer;Sales area is divided into commercial circle grid, and according to customer information, customer is mapped into corresponding commercial circle grid;According to commercial data, data filling is carried out to commercial circle grid;After data filling, commercial circle grid is classified, and the commercial circle type of each commercial circle grid is obtained;Customer is classified based on customer information and commercial circle type.The application divides region to sales market, and according to the commercial data of each region, the customer in region is classified more accurately, establishes the analysis level with commercial circle grid as core, realizes the fine intelligent management of customer, and through more accurate customer classification, effectively improve the level of accurate marketing to customer, promote the accurate delivery of goods source.

The application provides an AI voice interaction method and system, which obtains customer type information and customer car purchase preference records from a historical sales interaction database of a car OEM; generates a customer type identifier using preset customer classification rules; analyzes the customer car purchase preference records to generate a preference feature vector, combines the customer type identifier and a preset car sales script template to generate a car sales script text containing vehicle function keywords; processes the car sales script text to obtain acoustic physical parameters representing voice prosody characteristics; generates synthesized speech associated with the vehicle function keywords using the parameters; and plays the synthesized speech during the sales process and synchronously triggers a three-dimensional display of car functions corresponding to the car sales script text. The technical solution provided by the application automatically generates personalized car sales speech according to customer types and car purchase preferences, thereby improving the intelligence, personalization level and user experience of the car sales process.

The invention discloses a production schedule generation method and system based on incoming material feedback, and relates to the technical field of intelligent manufacturing. The method comprises the following steps: collecting incoming material related data, and obtaining historical incoming material data; extracting incoming historical material features and performing clustering analysis to obtain a dynamic customer classification result; calculating a risk factor, and determining a default scheduling strategy corresponding to the customer category according to the dynamic customer classification result and the risk factor; and predicting to obtain predicted material incoming time, and adjusting the initial default scheduling strategy to obtain a production scheduling strategy. According to the method, the client material providing mode is accurately modeled, the scheduling accuracy is remarkably improved, plan failure caused by material incoming deviation is reduced, meanwhile, frequent plan adjustment caused by material changes can be reduced, the stability and the performability of a production plan are improved, more accurate material prediction and more intelligent resource allocation are achieved, and the production efficiency is improved. The equipment and personnel utilization rate is improved.

To accurately classify customer loyalty by product brand and easily visualize their characteristics. [Solution] The information processing system comprises a control unit. The control unit acquires purchase history information, including the number of purchases and the number of units purchased for each brand of a predetermined category of products for multiple customers over a predetermined period. Based on the number of purchases for each brand and the ratio of the number of units purchased for each brand to the total number of units purchased for all brands, the control unit determines the loyalty classification of each customer for each brand from at least a first customer classification, a second customer classification lower than the first customer classification, and a third customer classification lower than the second customer classification. In response to the brand selection by the user terminal, the control unit outputs a predetermined statistical chart to the user terminal based on the number of units purchased for each determined loyalty classification of that brand.

A method and processing unit for recommending pricing value for products to customers is disclosed. Values of customer factors, and product factors are retrieved. Customer factors include current end market positions, current customer revenue, desired growth value, product purchase volume, and gross margin of customer. Product factors comprise product revenue, purchase frequency, and competitiveness values of product. Further, each customer is classified to be associated with customer tier based on customer factors. Each product is classified to be associated with a product tier, based on product factors. Grid is generated for each competitiveness value. The grid represents the relation between product revenue and purchase frequency, and customer tiers. Grid is analyzed to finalize pricing value of products. In response to a request for pricing value of desired product to desired customer, pricing value of desired product is determined based on the analysis, to provide to desired customer.

The invention discloses a financial customer credit classification method and device, electronic equipment and a program product, and relates to the financial science and technology field, and the method comprises the steps: employing a decision classifier to carry out the classification screening of a target data set and a to-be-predicted credit data set, and carrying out the parameter adjustment of a multi-classification machine learning model through a final data set, a multi-classification machine learning model is adopted to execute classification prediction of financial customer credit, the credit category of the financial customer is output, and the target data set is a data set with balanced data distribution obtained after the initial balance data set and the synthetic data set are merged. The initial balance data set is generated by performing adaptive synthesis and oversampling on minority customer samples in the original data set, and the synthesized data set is generated by performing deep learning on the initial balance data set by using a generative adversarial network model. According to the invention, the technical problem that the classification accuracy is affected due to low classification precision of minority types of customers during financial customer credit classification in the prior art is solved.

The invention belongs to the technical field of customer data management, and discloses a customer classification and grading management method, system and equipment based on business semantics. Comprising the steps of performing semantic analysis and format conversion on unstructured customer data, extracting core information related to a business scene, performing standardization processing on the structured customer data, generating a standardized customer data pool, inputting the standardized customer data pool into a classification and grading rule engine constructed based on grading indexes of customers, performing entity matching and semantic similarity calculation, and performing classification and grading. Outputting a client grading result; and on the basis of a set timing updating period and a service event triggering condition, the grading result is updated in a timing manner, and differentiated data security access control is implemented according to customer grades. By means of the scheme, full-process automation of classification and grading of enterprise customers is achieved, refined classification and grading management requirements of large enterprises with complex customer systems and remarkable cross-business unit operation characteristics on customer data are accurately matched, and collaboration of data use and business operation is guaranteed.

The invention discloses a power consumption behavior similarity evaluation method and system, and the method comprises the steps: obtaining the original load data of the power consumption of a residential user, and constructing a time domain load feature set according to the original load data; acquiring a load current waveform of electricity utilization of the residential user, and constructing a frequency domain load feature set according to the load current waveform; clustering the time domain load feature set to obtain a first user classification; and evaluating the first user classification sufficiency through the similarity index, and if the sufficiency is insufficient, performing clustering again by using the frequency domain feature data set to obtain a second user classification. According to the method, customer classification is obtained by using harmonic-wave-based features, and the frequency domain features are more robust to noise, so that signals and noise components can be better distinguished; and the quantity of information required to be stored for each client in the database of the electric power company can be reasonably reduced. In addition, when the clustering algorithm is operated, reduction of the number of the features plays a positive role in increasing the calculation speed.

The present disclosure provides a customer classification method, which can be applied to the technical fields of finance, artificial intelligence, cloud platform, etc. The customer classification method comprises: obtaining an evaluation index set of a customer to be classified, the evaluation index set of the customer to be classified comprising evaluation indexes of different index categories; matching, based on the evaluation indexes of different index categories of the customer to be classified, a preset basic index library to obtain index variables of different index categories, wherein the index variables and the evaluation indexes have a one-to-many correspondence in the preset basic index library; calculating an intermediate classification result based on the index variables of different index categories; and outputting the intermediate classification result as a final classification result when the intermediate classification result meets a preset classification output result. The present disclosure also provides a customer classification device, equipment, storage medium and program product.

To provide an information processing device, an information processing method, and an information processing program that can improve the profitability of stores. [Solution] According to the present disclosure, an information processing device for generating discount information relating to discounts on store products is provided, comprising: a target determination unit and a generation unit, wherein the target determination unit determines the target to which the discount information is to be provided based on classification information relating to customer classification and consumption information relating to the consumption of the product, and the generation unit generates the discount information based on the target to be provided.

Computer systems, apparatuses, processors, and non-transitory computer-readable storage devices configured for executing a method for generating proactive advisor recommendation using artificial intelligence. The method has the steps of: partitioning a plurality of clients using a clustering model based on data of the plurality of clients for clustering the plurality of clients into a plurality of client clusters; classifying the clients of at least a first client cluster of the plurality of client clusters into a plurality of client classifications by using one or more random-forest classifiers; and generating financial recommendations for the clients of at least a first client classification of the plurality of client classifications.