A customer service system
By introducing an AI painting layer and a big data support layer into the customer service system, analyzing user needs and guiding user operations, the problem of difficult to quickly understand customer needs in the existing technology is solved, and service efficiency and customer satisfaction are improved.
Patent Information
- Application Number
- CN202411926509.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-25
- Publication Date
- 2025-04-08
AI Technical Summary
In the prior art, it is difficult to quickly understand customer needs, resulting in slow service efficiency and low customer satisfaction.
A customer service system was designed, including a business logic layer, a big data support layer and an AI painting layer. By integrating user behavior data and industry internal data, the AI painting layer analyzes user service habits and preferences, and the business logic layer integrates multiple service resources to guide users' operations and meet user service needs.
It achieves accurate reach of customer needs, reduces staff recommendation time, and improves service efficiency and customer satisfaction.
Smart Images
Figure CN119782378A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of information technology, and in particular to a customer service system. Background Art
[0002] The rapid development of financial technology has made banks more comprehensive, with more types of business handled at outlets, a wider range of services, and more customer needs. However, as digital transformation deepens, banks are also faced with the challenge of how to better meet consumer needs, improve service efficiency, and reduce operating costs.
[0003] When customers walk into the lobby of a business outlet, the service provider hopes to directly meet their needs and deliver the bank's products and services to customers in a selective manner, thus achieving a win-win situation. However, in reality, there may be customers who do not understand or only partially understand the bank's business, and are not directly familiar with the quick handling. They need to frequently ask customer service staff, scan various QR codes to follow public accounts and download APPs, which affects the experience; at the same time, banks need to pay more costs to carry out scattershot advertising and marketing promotions, and deploy more personnel at outlets for promotion and answering questions, so that grassroots employees repeatedly guide various customers to repeat operations, affecting efficiency.
[0004] Therefore, providing a customer service system for solving the above problems is an urgent problem to be solved by those skilled in the art. Summary of the invention
[0005] The purpose of the present invention is to provide a customer service system which has a simple structure, is safe, effective, reliable and easy to operate, can accurately meet customer needs, and improve service efficiency and customer satisfaction.
[0006] Based on the above objectives, the technical solution provided by the present invention is as follows: A customer service system, comprising: a business logic layer, a big data support layer and an AI drawing layer; The AI painting layer is connected to the business logic layer and the big data support layer respectively; The big data support layer is used to integrate user behavior data and industry internal data to obtain user data sets; The AI drawing layer is used to analyze the user's service habit preference according to the user data set to obtain the analysis result; The business logic layer is used to integrate multiple service resources and guide user operations according to the service resources and the analysis results to meet user service needs.
[0007] Preferably, the big data support layer includes: a user behavior module, an industry internal module and an integration module; The user behavior module is used to track user historical behaviors, obtain user historical behavior data for multiple preset time periods, and obtain a user behavior data set; The industry internal module is used to call the corresponding industry data and business outlet internal data according to user service requirements to obtain the industry internal data set; The integration module is used to integrate the user behavior data set and the industry internal data set to obtain the user data set.
[0008] Preferably, the AI drawing layer includes: a user portrait module, an initial model building module and a prediction model generation module; The user portrait module is used to generate a user portrait according to the user data set, and establish a prediction feature vector according to the user portrait; The initial model building module is used to build an initial prediction model; The prediction model generation module is used to train the initial prediction model according to the prediction feature vector to obtain a recommended service prediction model.
[0009] Preferably, the user portrait module includes: a data processing submodule and a prediction feature vector submodule; The data processing submodule is used to clean abnormal data and data that does not conform to the user's browsing habits in the user data set to obtain a cleaned data set, divide the cleaned data into multiple intervals according to the statistical days, obtain the characteristic value of each interval according to the preset time decay function, and obtain the user characteristic value after accumulation; The prediction feature vector submodule obtains the prediction feature vector according to the user feature value and the plurality of service resources.
[0010] Preferably, it also includes: a human-computer interaction layer; The human-computer interaction layer is provided with a plurality of operation modules, each operation module corresponding to the customer service provided by the business outlet.
[0011] Preferably, the business logic layer includes: a resource integration module, a resource calling module and a guiding module; The resource integration module is used to integrate APP resources, public account resources, web resources and offline resources as a resource set; The resource calling module is used to determine the user preferred resources according to the analysis result, call the corresponding real-time service resources from the resource set, and map the real-time service resources to the operation module; The guiding module is used to guide the user to perform human-computer interaction with the operating module according to the user service requirements, so as to obtain the corresponding user service.
[0012] Preferably, the business logic layer is constructed using a Python high-performance web framework.
[0013] Preferably, the AI painting layer is constructed using a deep learning model of a self-attention mechanism, a Diffusion model, and a multimodal pre-training model.
[0014] Preferably, the human-computer interaction layer is constructed using a JavaScript framework for constructing a user interface and a static module packaging tool for JavaScript applications.
[0015] The customer service system provided by the present invention is provided with a business logic layer, a big data support layer and an AI drawing layer; wherein the AI drawing layer is respectively connected to the business logic layer and the big data support layer, and the user behavior data and the internal industry data are integrated through the big data support layer to obtain a user data set; the AI drawing layer performs corresponding analysis on the user service habit preferences according to the user data set to obtain the analysis results; the business logic layer integrates multiple service resources, guides user operations according to the integrated service resources and analysis results, realizes user services, and meets user service needs.
[0016] Compared with the existing technology, the present invention accurately meets customer needs, reduces staff promotion time, and improves service efficiency and customer satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0018] Figure 1 A schematic diagram of the structure of a customer service system provided by an embodiment of the present invention; Figure 2 A schematic diagram of the structure of a big data support layer provided by an embodiment of the present invention; Figure 3 A schematic diagram of the structure of the AI painting layer provided in an embodiment of the present invention; Figure 4 A schematic diagram of the structure of a user portrait module provided by an embodiment of the present invention; Figure 5 A schematic diagram of the structure of the business logic layer provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0020] The embodiments of the present invention are written in a progressive manner.
[0021] The embodiment of the present invention provides a customer service system, which mainly solves the technical problem in the prior art that it is difficult to quickly understand customer needs, resulting in slow service efficiency and low customer satisfaction.
[0022] like Figure 1 As shown, a customer service system includes: a business logic layer, a big data support layer and an AI drawing layer; The AI painting layer is connected to the business logic layer and the big data support layer respectively; Big data support layer, used to integrate user behavior data and industry internal data to obtain user data sets; The AI drawing layer is used to analyze user service habits and preferences based on user data sets to obtain analysis results; The business logic layer is used to integrate multiple service resources and guide user operations based on service resources and analysis results to meet user service needs.
[0023] During actual application, the customer service system is equipped with a business logic layer, a big data support layer and an AI drawing layer; the AI drawing layer is connected to the business logic layer and the big data support layer respectively, and the user behavior data and internal industry data are integrated through the big data support layer to obtain the user data set; the AI drawing layer performs corresponding analysis on the user service habits and preferences based on the user data set to obtain the analysis results; the business logic layer integrates multiple service resources, guides user operations according to the integrated service resources and analysis results, realizes user services, and meets user service needs.
[0024] In this embodiment, the big data support layer provides data support for the AI drawing layer; the AI conversation layer performs corresponding analysis based on user service preferences to accurately meet customers' potential needs; the business logic layer brings together multiple service resources of the bank's internal and external services, products and rights to fully meet the services required by customers.
[0025] like Figure 2 As shown, preferably, the big data support layer includes: a user behavior module, an industry internal module and an integration module; The user behavior module is used to track the user's historical behavior, obtain the user's historical behavior data for multiple preset time periods, and obtain the user behavior data set; The internal industry module is used to call the corresponding industry data and internal data of business outlets according to user service needs to obtain the internal industry data set; The integration module is used to integrate the user behavior dataset and the industry internal dataset to obtain the user dataset.
[0026] During actual application, the big data support layer is provided with a user behavior module, an industry internal module and an integration module; the user's historical behavior is tracked through the user behavior module, that is, the services obtained by the user in the bank in the past time period and the related services viewed online through the APP or web page; the user's historical behavior data of multiple preset time periods in the user behavior module are called to obtain a user behavior data set; through the industry internal module, according to the user's service needs, the corresponding industry data is called, specifically bank data such as deposit and withdrawal interest rates, fund increases and other industry internal data, as well as the internal data of the user's business outlets such as the amount of cash stored in the outlets, etc., to obtain the industry internal data set; through the integration module, the user behavior data set and the industry internal data set are integrated to obtain the user data set.
[0027] like Figure 3 As shown, preferably, the AI painting layer includes: a user portrait module, an initial model building module and a prediction model generation module; User portrait module, used to generate user portraits based on user data sets and establish prediction feature vectors based on user portraits; An initial model building module, used to build an initial prediction model; The prediction model generation module is used to train the initial prediction model according to the prediction feature vector to obtain the recommendation service prediction model.
[0028] In actual application, the AI drawing layer is equipped with a user portrait module, an initial model building module and a prediction model generation module; the user portrait module receives the user data set transmitted by the big data support layer, generates a user portrait based on the user data set, and establishes a prediction feature vector through the user portrait; In this example, the pandas library is used to read the user data set, and simple data cleaning and preprocessing are performed. Then the KMeans algorithm is used for modeling and training, and the users are divided into three groups. Finally, the matplotib library is used to display the user portraits. After the user portrait is established, a prediction feature vector is established based on the user portrait; The initial model is constructed through the initial model construction module, and the prediction feature vector is introduced through the prediction model generation module to train the initial prediction model to obtain the recommendation service prediction model.
[0029] like Figure 4As shown, preferably, the user portrait module includes: a data processing submodule and a prediction feature vector submodule; The data processing submodule is used to clean abnormal data and data that does not conform to the user's browsing habits in the user data set to obtain a cleaned data set, divide the cleaned data into multiple intervals according to the statistical days, obtain the characteristic value of each interval according to the preset time decay function, and obtain the user characteristic value after accumulation; The prediction feature vector submodule obtains the prediction feature vector according to the user feature value and multiple service resources.
[0030] In actual application, the user portrait module is provided with a data processing submodule and a prediction feature vector submodule; the data processing submodule is used to clean abnormal data and data that does not conform to the user's browsing habits in the user data set, and the normal data is retained as the cleaned data set; the cleaned data set is divided into M intervals according to the statistical days, and the characteristic value of each interval is obtained according to the time decay function, and the user characteristic value is obtained by accumulating the various characteristic values; the prediction feature vector is established according to the user characteristic value and service resources.
[0031] Preferably, it also includes: a human-computer interaction layer; The human-computer interaction layer has multiple operation modules, each of which corresponds to the customer service provided by the business outlets.
[0032] In actual use, the system also has a human-computer interaction layer, in which a plurality of operation modules are set in the display interface, and each operation module corresponds to the customer service provided by the business outlets; In this embodiment, existing banks already have a human-computer interaction system that can provide self-service, and the human-computer interaction system in this system is set up in advance by the business outlets to provide the services that can be provided in the business outlets. When some services are lacking, the users and staff are reminded respectively and the service is switched to manual reception and processing.
[0033] like Figure 5 As shown, preferably, the business logic layer includes: a resource integration module, a resource calling module and a guiding module; Resource integration module, used to integrate APP resources, public account resources, web resources and offline resources as a resource set; The resource calling module is used to determine the user's preferred resources based on the analysis results, call the corresponding real-time business resources from the resource set, and map the real-time business resources to the operation module; The guidance module is used to guide the user to perform human-computer interaction with the operation module according to the user's service requirements to obtain the corresponding user services.
[0034] In actual use, the business logic layer is equipped with a resource integration module, a resource call module, and a guidance module. The resource integration module integrates APP resources, public account resources, web resources, and offline resources, and the data sources of multiple terminals, which is conducive to expanding the scope of user historical behavior data collection, so that the collected historical behavior data can more accurately reflect the user's historical needs, and provide a more accurate historical data basis for the generation of subsequent service recommendation lists. When the resource call module receives the analysis results, it determines the user's preferred resources, calls the corresponding real-time business resources from the integrated resource set, and maps the real-time business resources to the operation module; through the guidance module, according to the user's service needs, guide the user to interact with the corresponding operation module to obtain the corresponding service.
[0035] Preferably, the business logic layer is built using a Python high-performance web framework.
[0036] In this embodiment, the business logic layer is specifically constructed using FastAPI to implement the business logic functions of banking services.
[0037] It should be noted that Fastapi is a modern, fast (high-performance) web framework for building APIs. Fastapi has two core components: Starette and Pydantic; Fastapi is built on Starlette and Pydantic, a library that defines data validation, serialization, and documentation based on Python type hints. Starlette is a lightweight ASGI framework / toolkit that is a rational choice for building high-performance Asyncio services.
[0038] Preferably, the AI painting layer is constructed using a deep learning model with a self-attention mechanism, a Diffusion model, and a multimodal pre-training model.
[0039] In this embodiment, the AI painting layer specifically uses Transform+Diffusion and CLIP to complete the generation of user portraits based on the latest semantic analysis model and stable diffusion model, and fine-tunes based on VAE to create user portraits that meet the requirements; It should be noted that the Transformer model is a deep learning model based on the self-attention mechanism, which was originally proposed by Google in 2017 and is mainly used for natural language processing (NLP) and other sequence-to-sequence tasks. The core of the Transformer model lies in its self-attention mechanism, which enables the model to consider all positions in the input sequence at the same time, rather than processing data step by step like traditional recurrent neural networks (RNNs) or convolutional neural networks (CNNs); The Diffusion model is a generative model that is mainly used to generate data such as images and videos. The core idea is to simulate the data generation process by gradually adding noise, and then gradually remove the noise by training a decoder to finally generate real samples; The CLIP (Contrastive Language-Image Pre-training) model is a multimodal pre-trained neural network released by OpenAI in 2021. The model is pre-trained with a large amount of paired data of images and texts to learn the alignment relationship between images and texts, thereby achieving multimodal learning. The core idea of CLIP is to use contrastive learning to learn representations by minimizing the distance between positive samples while maximizing the distance between negative samples.
[0040] Preferably, the human-computer interaction layer is constructed using a JavaScript framework for constructing a user interface and a static module packaging tool for JavaScript applications.
[0041] In this embodiment, the human-computer interaction layer is specifically constructed using Vue3+Webpack, using full separation of the front-end and back-end and HTTP Rest requests to complete the construction of the front-end customer display page and the management end; It should be noted that Vue is a JavaScript framework for building user interfaces. It is built on standard HTML, CSS, and JavaScript, and provides a declarative, component-based programming model that can efficiently develop user interfaces. Whether it is a simple or complex interface, Vue can handle it; Webpack is a static module packaging tool for modern JavaScript applications. It treats various resources (such as JavaScript, CSS, images, etc.) as modules, and generates a dependency graph by analyzing the dependencies between these modules. It is finally packaged into one or more output files for use in the browser.
[0042] In the embodiments provided in the present application, it should be understood that the disclosed system can be implemented in other ways. The system embodiments described above are merely schematic. For example, the division of modules is only a logical function division. There may be other division methods in actual implementation, such as: multiple modules or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.
[0043] In addition, all functional modules in the embodiments of the present invention may be integrated into one processor, or each module may be a separate device, or two or more modules may be integrated into one device; each functional module in the embodiments of the present invention may be implemented in the form of hardware or in the form of hardware plus software functional units.
[0044] It should be understood that the use of "system", "device", "unit" and / or "module" in this application is only a method for distinguishing different components, elements, parts, parts or assemblies at different levels. However, if other words can achieve the same purpose, the word can be replaced by other expressions.
[0045] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "a kind" and / or "the" do not refer to the singular, but also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements. The elements defined by the sentence "includes a..." do not exclude the existence of other identical elements in the process, method, commodity or device that includes the elements.
[0046] The above is a detailed introduction to a customer service system provided by the present invention. The above description of the disclosed embodiments enables professionals and technicians in the field to implement or use the present invention. Various modifications to these embodiments will be obvious to professionals and technicians in the field, and the general principles defined in this article can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown in this article, but will conform to the widest scope consistent with the principles and novel features disclosed in this article.
Claims
1. A customer service system, characterized in that: include: Business logic layer, big data support layer and AI drawing layer; The AI painting layer is connected to the business logic layer and the big data support layer respectively; The big data support layer is used to integrate user behavior data and industry internal data to obtain user data sets; The AI drawing layer is used to analyze the user's service habit preference according to the user data set to obtain the analysis result; The business logic layer is used to integrate multiple service resources and guide user operations according to the service resources and the analysis results to meet user service needs.
2. The customer service system according to claim 1, characterized in that: The big data support layer includes: user behavior module, industry internal module and integration module; The user behavior module is used to track user historical behaviors, obtain user historical behavior data for multiple preset time periods, and obtain a user behavior data set; The industry internal module is used to call the corresponding industry data and business outlet internal data according to user service requirements to obtain the industry internal data set; The integration module is used to integrate the user behavior data set and the industry internal data set to obtain the user data set.
3. The customer service system according to claim 2, characterized in that: The AI painting layer includes: a user portrait module, an initial model building module and a prediction model generation module; The user portrait module is used to generate a user portrait according to the user data set, and establish a prediction feature vector according to the user portrait; The initial model building module is used to build an initial prediction model; The prediction model generation module is used to train the initial prediction model according to the prediction feature vector to obtain a recommended service prediction model.
4. The customer service system according to claim 2, characterized in that: The user portrait module includes: a data processing submodule and a prediction feature vector submodule; The data processing submodule is used to clean abnormal data and data that does not conform to the user's browsing habits in the user data set to obtain a cleaned data set, divide the cleaned data into multiple intervals according to the statistical days, obtain the characteristic value of each interval according to the preset time decay function, and obtain the user characteristic value after accumulation; The prediction feature vector submodule obtains the prediction feature vector according to the user feature value and the plurality of service resources.
5. The customer service system according to claim 1, characterized in that: Also includes: Human-computer interaction layer; The human-computer interaction layer is provided with a plurality of operation modules, each operation module corresponding to the customer service provided by the business outlet.
6. The customer service system according to claim 5, characterized in that: The business logic layer includes: a resource integration module, a resource calling module and a guiding module; The resource integration module is used to integrate APP resources, public account resources, web resources and offline resources as a resource set; The resource calling module is used to determine the user preferred resources according to the analysis result, call the corresponding real-time service resources from the resource set, and map the real-time service resources to the operation module; The guiding module is used to guide the user to perform human-computer interaction with the operating module according to the user service requirements, so as to obtain the corresponding user service.
7. The customer service system according to claim 1, characterized in that: The business logic layer is built using the Python high-performance web framework.
8. The customer service system according to claim 1, characterized in that: The AI painting layer is constructed using a deep learning model with a self-attention mechanism, a Diffusion model, and a multimodal pre-training model.
9. The customer service system according to claim 5, characterized in that: The human-computer interaction layer is constructed using a JavaScript framework for constructing a user interface and a static module packaging tool for JavaScript applications.