Intelligent CRM customer management method and system supporting cross-platform integration

Abstract

The invention discloses an intelligent CRM customer management method and system supporting cross-platform integration. The method comprises the steps of obtaining customer information for the same customer in at least two different network platforms; according to the customer information, utilizing a trained federal learning model to predict first preference information and second preference information of the customer; according to the first preference information, selecting a service carrier conforming to the preference of the customer, and displaying the second preference information to the service carrier; and receiving demand information obtained based on the service carrier, and recommending a target service or a target commodity to the customer according to the demand information and the second preference information. Therefore, efficient, centralized and accurate customer management is realized.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an intelligent CRM customer management method and system supporting cross-platform integration. Background Art

[0002] In the current context of digital transformation, companies are increasingly focusing on the intelligence and cross-platform integration capabilities of customer relationship management (CRM) systems in order to achieve unified data management and intelligent decision-making.

[0003] In the existing technology, for example, CN119940425A discloses a human-machine collaborative intelligent control system based on AIGC (Artificial Intelligence Generated Content), which has made innovations in human-machine interaction and decision consistency, but has not proposed a solution to the cross-platform data integration problem unique to the CRM field; for example, CN118245677A discloses a method for developing a front-end big data platform for power grid marketing. Although it has made efforts in data utilization efficiency and security, its scope of application is mainly limited to the power grid industry, and it is difficult to directly apply it to the cross-industry, multi-source data synchronization and intelligent analysis scenarios of the CRM system.

[0004] As a result, existing technologies for cross-platform integrated customer management primarily create data silos. For example, customer information is scattered across different business platforms, lacking unified management. This leads to ineffective customer management systems. Specifically, product or service recommendations made using these systems are inaccurate, hindering customer conversion rates and resulting in low commercial value. Consequently, improving the effectiveness of existing customer management systems has become a pressing technical challenge. Summary of the Invention

[0005] In view of this, the main purpose of the present invention is to provide an intelligent CRM customer management method and system that supports cross-platform integration, aiming at more efficient, centralized and accurate customer management.

[0006] To achieve the above object, the technical solution of the present invention is achieved as follows: An embodiment of the present invention provides an intelligent CRM customer management method supporting cross-platform integration, the method comprising: Obtain customer information for the same customer on at least two different online platforms; Based on customer information, use the trained federated learning model to predict the customer's first and second preference information; selecting a service carrier that matches the customer's preference based on the first preference information, and presenting the second preference information to the service carrier; Receive service-based carriers or obtain demand information, and recommend target services or target products to customers based on the demand information and the second preference information.

[0007] In the above solution, obtaining customer information for the same customer on at least two different network platforms includes: Obtaining Nth customer information of a customer on the Nth network platform through an API interface of the Nth network platform, wherein the API interface is an accessible interface and N is a positive integer greater than or equal to 2; Aggregate N customer information to obtain first customer information, and determine whether the first customer information is complete; If the first customer information is complete, the aggregated first customer information is used as the customer information of the customer.

[0008] In the above solution, the method further includes: If the first customer information is incomplete, continue to obtain the N+1th customer information of the customer in the N+1 network platform through the API interface of the N+1th network platform; aggregate the N+1 customer information to obtain the second customer information until the second customer information is complete.

[0009] In the above solution, if the customer information is incomplete, determining the missing information of the customer information; Supplement missing information through trained customer analysis models; Determine the customer's customer information based on the missing information.

[0010] In the above solution, presenting the second preference information to the service carrier includes: encrypting the second preference information and displaying the encrypted second preference information to the service carrier; or, The second preference information is displayed to a service carrier having access rights.

[0011] In the above solution, the customer information includes: first customer information and second customer information, where the second customer information represents the compliance attribute of the first customer information; The method of predicting the first preference information and the second preference information of the customer using the trained federated learning model based on the customer information includes: Selecting, based on the first customer information, the first customer information having compliance attributes as the third customer information; Based on the third customer information, the trained federated learning model is used to predict the customer's second preference information.

[0012] In the above solution, the service carrier includes: a robot device or a waiter; the first preference information includes: service preference; The selecting, based on the first preference information, a service carrier that matches the customer's preference, and presenting the second preference information to the service carrier includes: If the customer's service preference is unmanned service, selecting a robot device that matches the customer's preference as the service carrier, and displaying the second preference information on a display screen of the robot device; or, If the customer's service preference is to be served by someone, a waiter who matches the customer's preference is selected as the service carrier, and the second preference information is displayed on the waiter's wearable device.

[0013] In addition, an embodiment of the present invention further provides an intelligent CRM customer management system supporting cross-platform integration, the system comprising: an acquisition module, configured to acquire customer information for the same customer from at least two different network platforms; A prediction module is used to predict the customer's first preference information and second preference information based on the customer information using the trained federated learning model; a selection module for selecting a service carrier that matches the customer's preference based on the first preference information and presenting the second preference information to the service carrier; The recommendation module is used to receive demand information obtained based on the service carrier and recommend target services or target products to customers based on the demand information and the second preference information.

[0014] To achieve the above objectives, an embodiment of the present invention further provides a computing device, comprising: processor; A memory for storing processor-executable instructions; wherein the processor is used to execute the intelligent CRM customer management method supporting cross-platform integration as described in any of the above solutions.

[0015] To achieve the above-mentioned objectives, an embodiment of the present invention also provides a computer storage medium, including: the computer storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to enable the one or more processors to execute the intelligent CRM customer management method supporting cross-platform integration as described in any of the above-mentioned solutions.

[0016] An embodiment of the present invention provides an intelligent CRM customer management method and system supporting cross-platform integration. The method and system obtain customer information for the same customer from at least two different network platforms; predict the customer's first preference information and second preference information using a trained federated learning model based on the customer information; select a service carrier that matches the customer's preferences based on the first preference information, and display the second preference information to the service carrier; receive demand information obtained based on the service carrier, and recommend target services or target products to the customer based on the demand information and the second preference information. Therefore, the embodiment of the present invention constructs a more global customer information by obtaining customer information for the same customer from different network platforms, and the use of a federated learning model can protect the privacy of customer information from being leaked. At the same time, by predicting the customer's dual preferences, quickly matching service carriers based on the first preference, and then promoting the service carrier to quickly obtain the customer's current real demand information based on the second preference, the desired product or service can be accurately recommended to the customer based on the current real demand information and the second preference information, thereby improving the recommendation conversion rate, thereby improving the effectiveness and commercial value of customer analysis and management using an intelligent CRM customer management system supporting cross-platform integration. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flowchart of an intelligent CRM customer management method supporting cross-platform integration provided in some embodiments of the present invention; Figure 2 A schematic diagram of the federated learning model architecture provided for some embodiments of the present invention; Figure 3 A schematic diagram of the structure of an intelligent CRM customer management system supporting cross-platform integration provided in some embodiments of the present invention; Figure 4 A schematic diagram of the hardware structure of a computing device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The embodiment of the present invention aims to obtain multiple preference information of a customer based on the customer information of the same customer obtained from different network platforms through a trained federated learning model, and provide customers with more accurate recommendations of goods or services based on the multiple preference information, thereby increasing the purchase rate of goods or services and the customer conversion rate, thereby facilitating the management effectiveness of the customer management system and improving the value of the customer management system.

[0019] The embodiments of the present invention are described in detail below with reference to the accompanying drawings so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby making a clearer and more precise definition of the protection scope of the present invention.

[0020] It's understandable that CRM (Customer Relationship Management) is a system of technologies, strategies, and processes used to manage interactions between businesses and their customers. Its core goal is to optimize the customer experience, improve customer satisfaction, enhance customer loyalty, and ultimately increase revenue and profitability. CRM's core functions include, but are not limited to, customer data management, sales management, marketing automation, customer service and support, as well as data analytics and business intelligence. In short, CRM is more than just a storage tool for customer data; it's a core system for businesses to enhance the customer experience, optimize business processes, and drive growth. Choosing the right CRM and effectively leveraging technologies like data analytics, automation, and AI can help businesses gain a competitive advantage.

[0021] The intelligent CRM customer management mentioned in this embodiment is an intelligent customer management system based on cross-platform integration. The system runs on a computing device and is used to perform the following method steps: like Figure 1 As shown, Figure 1 This is a flow chart of an intelligent CRM customer management method supporting cross-platform integration provided by some embodiments of the present invention. Embodiments of the present invention provide an intelligent CRM customer management method supporting cross-platform integration, applied to a computing device, the method comprising: Step 101: Obtain customer information for the same customer from at least two different network platforms; The computing device here may be a terminal device, which may be a fixed terminal or a mobile terminal. The fixed terminal may be a desktop computer or an all-in-one computer, and the mobile terminal may be a laptop computer, a tablet computer, or a mobile phone. In some embodiments, the computing device here may be a device for running an intelligent CRM customer management system that supports cross-platform integration.

[0022] In some embodiments, before obtaining customer information for the same customer on at least two different online platforms, the method further includes: checking the API policies and user authorization status of the at least two different online platforms. The obtaining of customer information for the same customer on the at least two different online platforms includes: if the API policies of the at least two different online platforms are open, obtaining user data for the same customer that is authorized to be accessed by the user on the at least two different online platforms. In this way, the obtained user data is compliant and legal, providing a legal and compliant foundation and strong guarantee for subsequent customer management based on the customer data.

[0023] It should be noted that, in some embodiments, the two different online platforms may refer to two different online platforms of the same category, such as JD.com or Taobao, both of which are shopping websites. Thus, by obtaining customer information from two online platforms of the same category but different categories, more targeted customer information, such as information about shopping, can be obtained, thereby facilitating the creation of a customer profile that is more conducive to shopping recommendations. In other embodiments, the two different online platforms may refer to two online platforms of different categories, such as one social networking platform, such as Weibo, and the other a shopping platform, such as Taobao. Thus, by obtaining customer information from at least two online platforms of different categories, it is possible to analyze the customer information from different perspectives to obtain a more comprehensive customer profile. Of course, in other embodiments, obtaining customer information for the same customer from at least two different online platforms may include obtaining customer information for the same customer from multiple online platforms of different and same categories, thereby facilitating the creation of a more comprehensive and targeted or more applicable customer profile, thereby facilitating more accurate customer management based on the customer profile.

[0024] Step 102: Based on the customer information, use the trained federated learning model to predict the customer's first preference information and second preference information.

[0025] It's important to understand that federated learning is a distributed machine learning technology whose core goal is to "keep the data moving while the model moves." Multiple participants, such as businesses or devices, can jointly train a global model without sharing their original data, while also protecting data privacy. Traditional machine learning models centralize all data for model training, resulting in a high risk of privacy leaks. Federated learning, on the other hand, keeps data local, meaning that each participant's raw data never leaves the local server. Model parameters are then exchanged, meaning each participant trains the model using their local data and uploads model parameters, such as gradients or weights, to a central server. Global model aggregation is then performed, with the central server securely aggregating and updating the model parameters from all parties, distributing the new model to all participants. This ensures that the original data remains on-site, complying with regulations such as the GDPR (General Data Protection Regulation) and the CCPA (California Consumer Privacy Act), and ensuring data privacy protection. The distributed training method, in which models are trained in parallel on multiple data sources, improves model training efficiency. Encryption technology protects parameter transmission and prevents man-in-the-middle attacks, thereby ensuring the security of aggregation. Data in different feature spaces, such as data from different network platforms, is supported, ensuring the compatibility of heterogeneous data.

[0026] It is understandable that the types of federated learning include: horizontal federated learning, vertical federated learning, and federated transfer learning. Horizontal federated learning is applicable to scenarios where the data features of the participants are the same but the samples are different, such as the input habits of Apple users and iPhone users jointly training the input method prediction model, but the user data here is limited to mobile phones. Vertical federated learning is applicable to scenarios where the data samples of the participants are the same but the features are different, such as the e-commerce and social data of the same user on different platforms, such as banks and e-commerce platforms jointly modeling to assess user credit risks, but the two parties do not exchange original data. Federated transfer learning is applicable when there is little overlap in the data and samples of the participants, and efficiency is improved through transfer learning. For example, hospital A has a small amount of cancer data and jointly trains a disease prediction model with hospital B, which has a large amount of diabetes data.

[0027] The first preference information and the second preference information here are information that characterize the customer's preferences from two different dimensions. It can be understood that the first preference information is used to characterize the user's preferences in the shopping process, and the second preference information characterizes the user's preferences in the purchase results.

[0028] It is understandable that the step 102, combined with Figure 2 As shown, based on the customer information, the trained federated learning model is used to predict the customer's first preference information and second preference information, which may include: The central server 20 corresponding to the federated learning model sends the initial model to at least two network platforms. The following takes two network platforms A and B as an example; A uses, for example, the customer's purchase history to train the model 21 and calculate the gradient ΔW a ; B uses, for example, the customer’s like behavior to train model 22 and calculate the gradient ΔWᵦ; The central server 20 obtains the global gradient ΔW = (ΔW a + ΔWᵦ) / 2; The central server 20 updates the global model and sends the new parameters to the local models of A and B. A and B synchronize the new parameters. Each network platform uses the final model to predict the preferences of local customers. For example, it predicts customers' preferences for the purchasing process and purchase results. For example, it predicts that customers prefer the purchase process of independent selection, such as not needing waiters to promote their products, and other purchase process preferences. For example, it predicts that customers prefer to buy current mainstream models or non-mainstream models with high cost performance, and other purchase result preferences.

[0029] Furthermore, to ensure the privacy of the federated learning model during the prediction process, in some implementations, federated learning can prevent data leakage by: Differential privacy, which adds random noise to the gradient to prevent outsiders from inferring the original data; Homomorphic encryption, that is, model parameters are calculated in an encrypted state and the server cannot decrypt them; Secure multi-party computation means that when multiple parties collaborate on a computation, no one party can obtain the input of other parties.

[0030] In this way, federated learning solves the contradiction between data privacy and sharing through a distributed collaborative model, and is particularly suitable for cross-enterprise and cross-platform joint analysis. Therefore, through federated learning, enterprises can manage platform customers legally and compliantly without sharing original data, while meeting regulatory requirements such as GDPR, and support cross-platform customer management under the premise of compliance, thereby reducing the data silos in cross-platform process customer management in existing technologies and ensuring the effectiveness of customer management systems.

[0031] Step 103: Select a service carrier that matches the customer's preference based on the first preference information, and display the second preference information to the service carrier.

[0032] As mentioned above, the first preference information represents the customer's preference for the purchasing process. For example, some customers hope that the salesperson will give a detailed introduction and experience of the product or service during the purchasing process; while some customers hope to make purchases based on their own understanding and do not want the salesperson to introduce and promote the product. They may think that the salesperson's introduction and promotion are somewhat directional and not conducive to their real needs and choices.

[0033] The service carrier here can be understood as the person who provides services for customers in this purchasing activity.

[0034] The second preference information here may include, but is not limited to, payment preferences, channel preferences, functional attribute preferences, experience and emotional preferences, social and recommendation preferences, risk preferences, scenario-based preferences, and product and regional preferences. Payment preferences may include, for example, payment time preferences and payment method preferences. Channel preferences may include purchase channel preferences, interaction channel preferences, and promotional channel preferences. Functional attribute preferences may include product feature preferences, such as sugar-free or sugar-free, technical parameter preferences, and service add-ons. Experience and emotional preferences may include preferences for purchasing after experiencing a product. Social and recommendation preferences may include preferences for purchasing through friend referral links. By displaying the second preference information to the service provider, the service provider can select appropriate marketing strategies based on the customer's second preferences. For example, if one of the customer's preferences is to purchase after experiencing a product, the service provider may recommend one or two experiences for the customer to try first during the interaction. If one of the customer's preferences is product feature preferences, the service provider may provide a detailed display or introduction to the product features during the interaction.

[0035] In this embodiment, by first selecting a service carrier that matches the customer's first preference to serve the customer, it is helpful to reduce customer churn during the purchase process and increase the customer's purchase rate; then by displaying the customer's second preference to the service carrier, so that the service carrier can interact based on the second preference, the customer's preferences can be grasped more accurately to help the customer choose a product or service that better suits his or her needs, further increasing the customer's purchase rate and enhancing the commercial value of the customer management system.

[0036] In some embodiments, the service carrier includes: a robotic device or a waiter, and the first preference information includes: a service preference; Step 103, i.e., selecting a service carrier that matches the customer's preference based on the first preference information, and presenting the second preference information to the service carrier, includes: If the customer's service preference is unmanned service, a robot device that matches the customer's preference is selected as the service carrier, and the second preference information is displayed on the display screen of the robot device; or, If the customer's service preference is to be served by someone, a waiter who matches the customer's preference is selected as the service carrier, and the second preference information is displayed on the waiter's wearable device.

[0037] The wearable device here can be a waiter's smart watch or smart glasses and other devices.

[0038] In this embodiment, by predicting the customer's preferences for the purchase process, such as a preference for detailed explanations during the purchase process or a preference for no human intervention during the purchase process, a service carrier is first matched based on the preferences of the purchase process, and then the second preference information is informed to the service carrier, thereby effectively retaining the customer at least during the purchase process, reducing the customer churn rate during the purchase process, and increasing the purchase rate.

[0039] Step 104: Receive demand information obtained based on the service carrier, and recommend target services or target products to the customer based on the demand information and the second preference information.

[0040] The demand information here can be the customer's current purchasing needs obtained through the interaction between the service carrier and the customer, such as information about items that the customer needs to purchase after entering the store. The item information here includes but is not limited to the signal, function, and appearance description of the item. Then, combined with the second preference information, the target service or target product is accurately recommended to the customer. For example, based on the customer's price range preference, products or services that the customer may continue to learn about are recommended to the customer, thereby increasing the customer's purchase rate.

[0041] In some embodiments, before receiving the demand information obtained based on the service carrier, the method further includes: The service carrier generates query information adapted to the second preference information based on the second preference information; Based on the inquiry information, obtain customer demand information.

[0042] It is understandable that, taking offline store shopping as an example, the service carrier may be that when the waiter learns the customer's second preference, such as a preference for organic cotton materials, he generates inquiry information that is adapted to the second preference information. For example, he may directly ask whether a certain type of product in the organic cotton area is needed, thereby reducing communication costs and improving transaction efficiency between merchants and customers.

[0043] In some implementations, the method further includes: receiving demand information obtained based on a service carrier, and correcting the first preference information according to the demand information.

[0044] It is understandable that for some customers, their preferences in the purchasing process are not static. In some scenarios, when the first preference information obtained at the beginning represents the customer's detailed explanatory preference service process, if it is detected that the customer shows a tendency to make independent decisions, such as frequently looking at the mobile phone for comparison, it is necessary to notify the clerk in real time to switch to low-intervention mode, that is, adjust the first preference information according to the real-time demand information received, so as to facilitate the smooth progress of the purchasing process, reduce customer churn rate, and increase purchase rate.

[0045] In summary, in the above embodiment, by obtaining customer information of the same customer from different network platforms to build a more comprehensive customer information, and then using the federated learning model to protect the privacy of customer information from being leaked, at the same time, by predicting the customer's dual preferences, matching the service carrier through the first preference, and then promoting the service carrier through the second preference to obtain the customer's current real demand information, then based on the current demand information and the second preference information, the desired goods or services can be accurately recommended to the customer, thereby improving the recommendation conversion rate and increasing the customer's purchase rate. Therefore, compared with traditional cross-platform customer management, the intelligent CRM customer management method that supports cross-platform integration provided in this embodiment can make customer management more efficient and have higher commercial value.

[0046] In some embodiments, step 101, i.e., obtaining customer information for the same customer on at least two different network platforms, may include: Obtaining Nth customer information of a customer on the Nth network platform through an API interface of the Nth network platform, wherein the API interface is an accessible interface, and N is a positive integer greater than or equal to 2; Aggregate N customer information to obtain first customer information, and determine whether the first customer information is complete; If the first customer information is complete, the aggregated first customer information is used as the customer information of the customer.

[0047] In some other embodiments, the method further comprises: If the first customer information is incomplete, continue to obtain the N+1 customer information of the customer in the N+1 network platform through the API interface of the N+1 network platform; aggregate the N+1 customer information to obtain the second customer information until the second customer information is complete.

[0048] Exemplarily, obtaining the customer information of the customer in the Nth network platform through the API interface of the Nth network platform may include: concurrently calling the API interfaces of each network platform by using an asynchronous thread pool, thereby shortening the response time; the asynchronous thread pool here is such as Java's CompletableFuture or Python's asyncio.

[0049] Exemplarily, each API interface is configured with an OAuth 2.0 token or API key, and authentication information is appended to the request header to ensure the security of customer information.

[0050] Illustratively, aggregating N pieces of customer information may include: aggregating customer information from network platforms of the same category with higher credibility using a priority strategy, thereby ensuring the credibility of the customer information obtained.

[0051] Exemplarily, determining whether the first customer information is complete includes: based on preset customer information attributes, determining whether all attributes of the first customer information are marked, and then the customer information is considered complete; if any attribute in the first customer information is not marked, then the customer information is considered incomplete.

[0052] The attribute here represents a certain type of information in the customer information. Different attributes correspond to different types of information. For example, the account information in the customer information and the gender information in the customer information are different types of information.

[0053] In this embodiment, by aggregating customer information in multiple network platforms, the integrity of customer information is guaranteed, providing a more accurate and favorable guarantee for subsequent prediction of customer preferences based on customer information, thereby improving the reliability of the customer management system.

[0054] In some embodiments, the method further comprises: If the customer information is incomplete, determine the missing information of the customer; Supplement this missing information through a trained customer analysis model; Determine the customer's customer information based on the missing information.

[0055] It should be added that the customer analysis model can use historical complete customer data to train the following models: classification model, regression model and generation model. Among them, the classification model is used to predict discrete fields such as occupation, education level, etc., and the regression model is used to predict continuous fields such as income and credit score; the generation model is used to generate reasonable but fictitious temporary values, such as generating a temporary email address based on the name.

[0056] For example, if a customer information field cannot be completed across platforms, it can be completed by calling the model and retrograde prediction.

[0057] In some embodiments, after the missing information is supplemented by the trained customer analysis model, the missing information is verified. For example, it is checked whether the supplemented value is logical, such as whether the age is consistent with the date of birth.

[0058] In order to ensure the accuracy of the customer analysis model, manually corrected data can be added to the training set to continuously optimize the model.

[0059] In this embodiment, by using the customer analysis model to supplement incomplete customer information, the integrity of the customer information is ensured, providing a more accurate and favorable guarantee for subsequent prediction of customer preferences based on the customer information, thereby improving the reliability of the customer management system.

[0060] In some embodiments, presenting the second preference information to a service carrier includes: encrypting the second preference information and displaying the encrypted second preference information to the service carrier; or, The second preference information is displayed to a service carrier having access rights.

[0061] In this embodiment, by keeping the second preference information confidential, the reliability and credibility of the customer management system are improved, providing a strong guarantee for protecting the privacy of customer information and customer preferences.

[0062] In some embodiments, the customer information includes: first customer information and second customer information, the second customer information representing a compliance attribute of the first customer information; The method of predicting the first preference information and the second preference information of the customer using the trained federated learning model based on the customer information includes: Determining second customer information in the first customer information based on the first customer information; Selecting the first customer information having compliance attributes as the third customer information based on the second customer information; Based on the third customer information, the trained federated learning model is used to predict the customer's second preference information.

[0063] It is understandable that the first customer information may include but is not limited to: basic customer information, customer environment information, customer social relationship information, customer historical behavior information, customer credit information, etc.

[0064] The second customer information represents the compliance attribute of the first customer information. In other words, for basic customer information, the second customer information represents the attribute information that indicates whether the basic customer information is compliant. In this embodiment, by only predicting first customer information with compliant attributes, the use of non-compliant customer information is reduced, thereby ensuring the security and reliability of the customer management system.

[0065] To achieve the above objectives, the present invention also provides an intelligent CRM customer management system that supports cross-platform integration. Figure 3 , the system comprising: An acquisition module 31 is configured to acquire customer information for the same customer from at least two different network platforms; Prediction module 32, configured to predict the customer's first preference information and second preference information based on the customer information using the trained federated learning model; A selection module 33 is configured to select a service carrier that matches the customer's preference based on the first preference information and to present the second preference information to the service carrier; The recommendation module 34 is configured to receive demand information obtained based on the service carrier, and recommend target services or target products to the customer based on the demand information and the second preference information.

[0066] In some embodiments, the acquisition module 31 is further configured to: Obtaining Nth customer information of the customer in the Nth network platform through an API interface of the Nth network platform, wherein the API interface is an access-allowed interface and N is a positive integer greater than or equal to 2; Aggregating N pieces of customer information to obtain first customer information, and determining whether the first customer information is complete; If the first customer information is complete, the aggregated first customer information is used as the customer information of the customer.

[0067] In some embodiments, the system further includes: a first processing module configured to: If the first customer information is incomplete, continue to obtain the N+1th customer information of the customer in the N+1th network platform through the API interface of the N+1th network platform; aggregate the N+1 customer information to obtain the second customer information until the second customer information is complete.

[0068] In some embodiments, the system further includes: a second processing module configured to: If the customer information is incomplete, determine the missing information of the customer information; Supplement the missing information through the trained customer analysis model; The customer information of the customer is determined based on the missing information.

[0069] In some embodiments, the recommendation module 34 is further configured to: encrypting the second preference information, and displaying the encrypted second preference information to the service carrier; or, The second preference information is displayed to the service carrier having access rights.

[0070] In some embodiments, the customer information includes: first customer information and second customer information, the second customer information representing a compliance attribute of the first customer information; The prediction module 32 is further configured to: determining second customer information in the first customer information based on the first customer information; selecting, based on the second customer information, the first customer information having compliance attributes as the third customer information; Based on the third customer information, the second preference information of the customer is predicted using a trained federated learning model.

[0071] In some embodiments, the service carrier includes: a robot device or a waiter; the first preference information includes: a service preference; The selection module 33 is further configured to: If the customer's service preference is unmanned service, selecting a robot device that matches the customer's preference as the service carrier, and displaying the second preference information on a display screen of the robot device; or, If the customer's service preference is human service, a waiter who matches the customer's preference is selected as the service carrier, and the second preference information is displayed on the waiter's wearable device.

[0072] It should be noted that the description of the intelligent CRM customer management system supporting cross-platform integration described above is similar to the description of the intelligent CRM customer management method supporting cross-platform integration described above. The beneficial effects of the same method will not be elaborated upon here. For technical details not disclosed in the embodiment of the intelligent CRM customer management system supporting cross-platform integration according to the present invention, please refer to the description of the embodiment of the intelligent CRM customer management method supporting cross-platform integration according to the present invention.

[0073] To achieve the above objectives, an embodiment of the present invention further provides a computing device, such as Figure 4 As shown, the computing device includes a processor 401 and a memory 402 connected to the processor 401 via a communication bus 403; wherein the memory 402 is used to support the intelligent CRM customer management program for cross-platform integration; the processor 401 is used to execute the intelligent CRM customer management program for cross-platform integration to implement the method for intelligent CRM customer management supporting cross-platform integration described in any of the above solutions.

[0074] Optionally, the processor 401 may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. Here, the program executed by the processor 401 may be stored in a memory 402 connected to the processor 401 via a communication bus 403. The memory 402 may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), ferromagnetic random access memory (FRAM), flash memory, magnetic surface storage, optical disk, or compact disc read-only memory (CD-ROM); magnetic surface storage can be magnetic disk storage or magnetic tape storage. Volatile memory can be random access memory (RAM), which is used as an external cache.By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus random access memory (DRRAM). The memory 402 described in the embodiments of the present invention is intended to include, but is not limited to, these and any other suitable types of memory 402. The memory 402 in the embodiments of the present invention is used to store various types of data to support the operations of the processor 401. Examples of such data include: any computer program operated by the processor 401, such as an operating system and application programs; contact data; phone book data; messages; images; videos, etc. The operating system includes various system programs, such as a framework layer, a core library layer, and a driver layer, which are used to implement various basic services and handle hardware-based tasks.

[0075] In some embodiments, the memory 402 in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. The non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDRSDRAM), enhanced synchronous DRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus RAM (DRRAM). The memory 402 of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0076] Processor 401 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits or software instructions within processor 401. Processor 401 may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in conjunction with the embodiments of the present invention can be directly implemented and executed by a hardware decoding processor or by a combination of hardware and software modules within the decoding processor. The software modules can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 402. Processor 401 reads information from memory 402 and, in conjunction with its hardware, completes the steps of the above method. In some embodiments, the embodiments described herein may be implemented using hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit may be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described herein, or a combination thereof.

[0077] For software implementation, the techniques described herein can be implemented through modules (e.g., procedures, functions, etc.) that perform the functions described herein. The software code can be stored in a memory and executed by a processor. The memory can be implemented in the processor or external to the processor.

[0078] Another embodiment of the present invention provides a computer storage medium, which stores an executable program. When the executable program is executed by the processor 401, the steps of the intelligent CRM customer management method supporting cross-platform integration applied to the computing device can be implemented. For example, Figure 1-Figure 2 One or more of the methods shown.

[0079] In some embodiments, the computer storage medium may include various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0080] It should be noted that the technical solutions described in the embodiments of the present invention can be arbitrarily combined without conflict.

[0081] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention.

Claims

1. An intelligent CRM customer management method supporting cross-platform integration, characterized in that: The method comprises: Obtain customer information for the same customer on at least two different online platforms; Predicting the first preference information and the second preference information of the customer using a trained federated learning model based on the customer information; selecting a service carrier that matches the customer's preferences based on the first preference information, and presenting the second preference information to the service carrier; Receive demand information obtained based on the service carrier, and recommend a target service or target product to the customer based on the demand information and the second preference information.

2. The method according to claim 1, characterized in that The obtaining of customer information for the same customer on at least two different network platforms includes: Obtaining Nth customer information of the customer in the Nth network platform through an API interface of the Nth network platform, wherein the API interface is an accessible interface and N is a positive integer greater than or equal to 2; Aggregating N pieces of customer information to obtain first customer information, and determining whether the first customer information is complete; If the first customer information is complete, the aggregated first customer information is used as the customer information of the customer.

3. The method according to claim 2, characterized in that The method further comprises: If the first customer information is incomplete, continue to obtain the N+1th customer information of the customer in the N+1th network platform through the API interface of the N+1th network platform; aggregate the N+1 customer information to obtain the second customer information until the second customer information is complete.

4. The method according to claim 2, characterized in that The method further comprises: If the customer information is incomplete, determine the missing information of the customer information; Supplement the missing information through the trained customer analysis model; The customer information of the customer is determined based on the missing information.

5. The method according to claim 1, wherein The presenting the second preference information to the service carrier includes: encrypting the second preference information, and displaying the encrypted second preference information to the service carrier; or, The second preference information is displayed to the service carrier having access rights.

6. The method according to claim 1, characterized in that The customer information includes: first customer information and second customer information, where the second customer information represents the compliance attribute of the first customer information; The method of predicting the first preference information and the second preference information of the customer using a trained federated learning model according to the customer information includes: determining second customer information in the first customer information based on the first customer information; selecting, based on the second customer information, the first customer information having compliance attributes as the third customer information; Based on the third customer information, the second preference information of the customer is predicted using a trained federated learning model.

7. The method according to claim 1 or 5, characterized in that The service carrier includes: a robot device or a waiter; the first preference information includes: a service preference; The selecting, based on the first preference information, a service carrier that matches the customer's preference, and presenting the second preference information to the service carrier includes: If the customer's service preference is unmanned service, selecting a robot device that matches the customer's preference as the service carrier, and displaying the second preference information on a display screen of the robot device; or, If the customer's service preference is human service, a waiter who matches the customer's preference is selected as the service carrier, and the second preference information is displayed on the waiter's wearable device.

8. An intelligent CRM customer management system that supports cross-platform integration, characterized in that: The system comprises: an acquisition module, configured to acquire customer information for the same customer from at least two different network platforms; A prediction module, configured to predict the first preference information and the second preference information of the customer based on the customer information using a trained federated learning model; a selection module, configured to select a service carrier that matches the customer's preference based on the first preference information, and present the second preference information to the service carrier; The recommendation module is configured to receive demand information obtained based on the service carrier, and recommend a target service or target product to the customer based on the demand information and the second preference information.

9. A computing device, characterized in that include: processor; a memory for storing processor-executable instructions; The processor is configured to execute the method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that include: The computer storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to enable the one or more processors to perform the method according to any one of claims 1 to 7.

Images