Service recommendation method and device and storage medium

Abstract

The invention provides a service recommendation method and device and a storage medium, relates to the technical field of communication, and can improve the overall efficiency of a telecom operator channel system. The method comprises the following steps: acquiring user information of a target user; based on the user information of the target user, identifying a user category of the target user, and determining a user portrait of the target user according to the user category; the user portrait is used for describing user features; based on the user portrait of the target user and a preset channel shunting principle, determining a service recommendation strategy for the target user; the service recommendation strategy is used for determining a target service recommended to the target user and a recommendation mode of the target service.

Description

Technical Field

[0001] This application relates to the field of communication technologies, and in particular, to a service recommendation method, apparatus, and storage medium. Background Art

[0002] The development of information technology has broken the channel system centered on physical channels and call center channels of telecom operators. Electronic channels have become an important form of information communication and transactions between telecom operators and customers, and thus the channel system of operators has become more complex. Therefore, how to provide service sharing and recommendation services to customers through the complex operator channel system has become a problem to be solved.

[0003] Currently, the channel system of telecom operators is built separately and operated independently, without giving play to the synergy effect between channels, resulting in a relatively low overall efficiency of the channel system. Summary of the Invention

[0004] This application provides a service recommendation method, apparatus, and storage medium, which can improve the overall efficiency of the operator channel system of telecom operators.

[0005] To achieve the above object, this application adopts the following technical solutions:

[0006] In a first aspect, this application provides a service recommendation method, which includes: obtaining user information of a target user; based on the user information of the target user, identifying the user category of the target user, and determining a user portrait of the target user according to the user category; the user portrait is used to describe user characteristics; based on the user portrait of the target user and a preset channel diversion principle, determining a service recommendation strategy for the target user; the service recommendation strategy is used to determine the target service to be recommended to the target user and the recommendation method of the target service.

[0007] In a possible implementation manner, the user characteristics include at least one of the following: the historical service value of the user; the consumption habits of the user; the service requirements of the user; the preferred recommendation method of the user.

[0008] In a possible implementation manner, the preset channel diversion principle includes a value principle and / or an efficiency principle; wherein, the value principle means selecting a recommendation method according to the historical service value of the user, and the efficiency principle means selecting a recommendation method according to the type of service; wherein, the recommendation methods include an online recommendation method and an offline recommendation method.

[0009] In a possible implementation manner, determining a service recommendation strategy for the target user based on the user portrait of the target user and the preset channel diversion principle includes: determining the target service based on the consumption habits and service requirements of the target user; determining the recommendation method of the target service based on the historical service value, preferred recommendation method of the target user, and the preset channel diversion principle.

[0010] In a possible implementation, after the target user handles the target service, the method further includes: sending a reminder message to the target user according to the service usage situation of the target user.

[0011] In a possible implementation, sending a reminder message to the target user according to the service usage situation of the target user includes: determining the information sending timing based on the service usage situation of the target user; and sending a reminder message to the target user according to the information sending timing.

[0012] In a second aspect, the present application provides a service recommendation device, which includes: a communication unit and a processing unit; the communication unit is used to obtain user information of the target user; the processing unit is used to identify the user category of the target user based on the user information of the target user, and determine the user portrait of the target user according to the user category; the user portrait is used to describe user characteristics; the processing unit is further used to determine a service recommendation strategy for the target user based on the user portrait of the target user and a preset channel diversion principle; the service recommendation strategy is used to determine the target service to be recommended to the target user and the recommendation method of the target service.

[0013] In a possible implementation, the user characteristics include at least one of the following: the historical service value of the user; the consumption habits of the user; the service requirements of the user; the preferred recommendation method of the user.

[0014] In a possible implementation, the preset channel diversion principle includes a value principle and / or an efficiency principle; wherein, the value principle means selecting a recommendation method according to the historical service value of the user, and the efficiency principle means selecting a recommendation method according to the type of the service; wherein, the recommendation methods include an online recommendation method and an offline recommendation method.

[0015] In a possible implementation, the processing unit is further used to determine the target service based on the consumption habits and service requirements of the target user; the processing unit is further used to determine the recommendation method of the target service based on the historical service value, preferred recommendation method of the target user, and the preset channel diversion principle.

[0016] In a possible implementation, after the target user handles the target service, the processing unit is further used to send a reminder message to the target user according to the service usage situation of the target user.

[0017] In a possible implementation, the processing unit is further used to determine the information sending timing based on the service usage situation of the target user; the processing unit is further used to send a reminder message to the target user according to the information sending timing.

[0018] In a third aspect, the present application provides a service recommendation device, which includes: a processor and a communication interface; the communication interface is coupled to the processor, and the processor is configured to run a computer program or instruction to implement the service recommendation method described in the first aspect and any possible implementation manner of the first aspect.

[0019] In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions are stored. When the instructions are run on a terminal, the terminal is caused to execute the service recommendation method described in the first aspect and any possible implementation manner of the first aspect.

[0020] In a fifth aspect, the present application provides a computer program product containing instructions. When the computer program product runs on a service recommendation device, the service recommendation device is caused to execute the service recommendation method described in the first aspect and any possible implementation manner of the first aspect.

[0021] In a sixth aspect, the present application provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor, and the processor is configured to run a computer program or instruction to implement the service recommendation method described in the first aspect and any possible implementation manner of the first aspect.

[0022] Specifically, the chip provided in the present application further includes a memory for storing a computer program or instruction.

[0023] The above technical solutions at least bring the following beneficial effects: obtaining user information of a target user, identifying the user category of the target user based on the user information, and determining the user portrait of the target user according to the user category. Based on the user portrait of the target user and a preset channel diversion principle, determining a service recommendation strategy for the target user. Among them, the service recommendation strategy is used to determine the target service to be recommended to the target user and the recommendation method of the target service. That is to say, the service recommendation method provided in the embodiments of the present application determines the target service according to the user portrait and the preset channel diversion principle, and selects different recommendation methods for service recommendation, thereby being able to improve the overall efficiency of the operator's recommendation channel system. Description of the Drawings

[0024] Figure 1 It is a schematic composition diagram of a service recommendation device provided in an embodiment of the present application;

[0025] Figure 2 It is a schematic module diagram of a service recommendation platform provided in an embodiment of the present application;

[0026] Figure 3 It is a flowchart of a service recommendation method provided in an embodiment of the present application;

[0027] Figure 4Flowchart of another service recommendation method provided by an embodiment of this application;

[0028] Figure 5 Flowchart of another service recommendation method provided by an embodiment of this application;

[0029] Figure 6 Flowchart of another service recommendation method provided by an embodiment of this application;

[0030] Figure 7 Structural schematic diagram of a service recommendation device provided by an embodiment of this application. Detailed implementation manners

[0031] The service recommendation method, device, and storage medium provided by an embodiment of this application will be described in detail below with reference to the accompanying drawings.

[0032] The term "and / or" in this article is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone.

[0033] The terms "first" and "second" in the description and drawings of this application are used to distinguish different objects or different processes for the same object, rather than to describe the specific order of the objects.

[0034] In addition, the terms "include" and "have" and any variations thereof mentioned in the description of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes other unlisted steps or units, or optionally further includes other steps or units inherent to these processes, methods, products, or devices.

[0035] It should be noted that in the embodiments of this application, words such as "exemplary" or "for example" are used to represent examples, illustrations, or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "for example" is intended to present relevant concepts in a specific manner.

[0036] In the description of this application, unless otherwise specified, the meaning of "a plurality" refers to two or more.

[0037] With the continuous development and wide application of global information technology and network technology, the traditional channel system of telecom operators centered on physical channels and call center channels is facing impacts. Customers are becoming more and more proficient in using information means. Electronic channels have become an important form of information communication and transactions between telecom operators and customers, and are becoming more closely related to customers' lives. As a result, the channel system of operators has become more complex.

[0038] With the intensification of market competition, telecom operators need to improve the business promotion effect and user satisfaction through business sharing and recommendation. Business sharing and recommendation can better meet user needs and enhance brand influence. Therefore, how to provide business sharing and recommendation services to customers through the complex operator channel system has become a problem to be solved.

[0039] The complexity of the operator channel system also brings problems of channel coordination. At present, the channel system of telecom operators is built separately and operated independently. There is a lack of information sharing between channels, the channel service cost does not match the customer value, there is no sufficient guidance and diversion according to the characteristics of the channels, and the channel coordination effect is not fully exerted, resulting in a relatively low overall efficiency of the channel system.

[0040] In view of this, the embodiments of the present application provide a business recommendation method, which includes: obtaining user information of a target user, identifying the user category of the target user based on the user information, and determining the user portrait of the target user according to the user category. Based on the user portrait of the target user and the preset channel diversion principle, determine the business recommendation strategy for the target user. Among them, the business recommendation strategy is used to determine the target business to be recommended to the target user and the recommendation method of the target business. That is to say, the business recommendation method provided by the embodiments of the present application determines the target business according to the user portrait and the preset channel diversion principle, and selects different recommendation methods for business recommendation, thereby being able to improve the overall efficiency of the operator's recommendation channel system.

[0041] Exemplarily, Figure 1 is a schematic diagram of the composition of a business recommendation device 10 provided by the embodiments of the present application. As Figure 1 shown, the business recommendation device 10 may include a processor 101 and a bus 102.

[0042] Furthermore, the business recommendation device 10 may further include a communication interface 103 and a memory 104. Among them, the processor 101, the memory 104, and the communication interface 103 may be connected through the bus 102.

[0043] Among them, the processor 101 is a central processing unit (CPU), a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. The processor 101 can also be other devices with processing functions, such as circuits, devices, or software modules, without limitation.

[0044] The bus 102 is used to transmit information between the components included in the service recommendation device 10.

[0045] The communication interface 103 is used to communicate with other devices or other communication networks. The other communication network can be an Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc. The communication interface 103 can be a module, a circuit, a communication interface, or any device capable of implementing communication.

[0046] The memory 104 is used to store instructions. Among them, the instructions can be computer programs.

[0047] Among them, the memory 104 can be a read-only memory (ROM) or other types of static storage devices that can store static information and / or instructions, can also be a random access memory (RAM) or other types of dynamic storage devices that can store information and / or instructions, can also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, without limitation.

[0048] It should be noted that the memory 104 can exist independently of the processor 101 or be integrated with the processor 101. The memory 104 can be used to store instructions, program codes, or some data, etc. The memory 104 can be located inside or outside the service recommendation device 10, without limitation. The processor 101 is used to execute the instructions stored in the memory 104 to implement the service recommendation method provided in the following embodiments of the present application.

[0049] In one example, the processor 101 may include one or more CPUs. For example, CPU0 and CPU1 (not shown in the figure).

[0050] As an alternative implementation, the service recommendation device 10 includes multiple processors.

[0051] As an alternative implementation, the service recommendation device 10 further includes an output device and an input device. Exemplarily, the input device is a device such as a keyboard, mouse, microphone, or joystick, and the output device is a device such as a display screen or speaker.

[0052] It should be noted that the service recommendation device 10 can be a desktop computer, a portable computer, a network server, a mobile phone, a tablet computer, a wireless terminal, an embedded device, a chip system, or a device with a Figure 1 similar structure. In addition, Figure 1 the component structure shown in Figure 1 does not constitute a limitation on each device in Figure 1 In addition to the components shown, Figure 1 each device in

[0053] In the embodiments of the present application, the chip system can be composed of chips or can include chips and other discrete devices.

[0054] In addition, actions, terms, etc. involved between the embodiments of the present application can be referred to each other without limitation. The message names or parameter names in the messages exchanged between the devices in the embodiments of the present application are only examples, and other names can also be used in specific implementations without limitation.

[0055] Exemplarily, Figure 2 is a schematic diagram of the modules of a service recommendation platform provided in the embodiments of the present application. As Figure 2 shown, the service recommendation platform includes: a contact management module, a marketing function module, an interactive push module, a support service module, a data processing module, a service reminder module, and a system interface module.

[0056] Among them, the contact management module is used to establish a connection between the business recommendation platform and users. Through the contact management module, the basic information, communication records, and location information of users can be managed and maintained, and thus accurate business recommendations can be realized.

[0057] It should be noted that a contact refers to the medium for establishing connection and interaction between the platform and users. As a promotion tool, a contact can include any one of the following: the fifth-generation hypertext markup language (HTML5) web page on the mobile phone, APP, WeChat portal, and official account.

[0058] The marketing function module is used to plan and execute business promotion and marketing activities. The marketing function module can analyze user data, identify potential user groups, and formulate personalized marketing strategies for users based on user portraits and behavior habits. The marketing function module includes the capable person space, personal center, and registration and joining. Among them, the capable person space includes talent display, content creation and sharing, interaction and community. The personal center includes user information management, order management, and personalized settings. Registration and joining include franchisee registration, joining support and training. In addition, the marketing function module also supports various marketing means such as coupon issuance, points redemption, and activity promotion to improve user participation and business conversion rate.

[0059] The interactive push module is used to send business recommendation information to users. According to factors such as user characteristics, channel coverage, and cost-effectiveness, a suitable recommendation method (such as text message, APP, or email, etc.) is selected to be able to convey information to users in a timely and accurate manner. In addition, the marketing function module can also combine factors such as festivals and activities to send promotional strategies such as limited-time offers and points redemption to attract users' attention.

[0060] The support service module includes a workbench, commodity management, customer management, order management, points management, report statistics, commission management, system management, interface management, configuration management, server maintenance, network security, data storage, permission management, and log management, and is used to provide stable and efficient technical support to ensure the stable operation of the platform and data security. In addition, the support service module can also provide an online customer service function and a user feedback function. Among them, the online customer service function is used to answer users' questions and handle users' complaints to improve user satisfaction. The user feedback function is used to collect users' opinions and suggestions on the platform and business, and continuously optimize the functions of the business recommendation platform according to users' opinions and suggestions to improve the user experience.

[0061] Furthermore, the support service module uses analysis tools to statistically analyze users' sharing and recommendation behaviors. By introducing a multi-level distribution model, users are encouraged to share and recommend the business to their relatives and friends. After the recommended users successfully handle the business, the recommending users can receive rewards such as commissions, points, coupons, free trials, etc., to increase users' sharing motivation. Moreover, according to the consumption situation of the recommended users, the recommending users can obtain continuous benefits.

[0062] The data processing module consists of a database and a memory library, including an order library, a product library, a customer library, a statistics library, and a configuration library, etc., for storing, analyzing, and mining user data. The data processing module deeply analyzes user data through big data technology and machine learning algorithms to mine potential business opportunities and user needs. In addition, the data processing module can also visually display the data, providing intuitive data support for decision-making.

[0063] The service reminder module is used to send service notifications and reminder messages to users, including order status reminders, payment success reminders, promotional activity reminders, traffic reminders, service expiration reminders. In this way, through timely reminder services, it can help users better manage their communication services and expense expenditures.

[0064] The system interface module is used to provide the data interaction ability between the business recommendation platform and other systems, including the customer relationship management (CRM) system, the billing and accounting system, the payment system, the business system, the business operations support system (BOSS), and the business intelligence (BI) system. Moreover, the system interface module can also be docked with other modules of the business recommendation platform. In addition, the system interface module supports the opening of application programming interfaces (APIs) and the development of software development kits (SDKs) to facilitate the quick access and use of the business recommendation platform by third parties.

[0065] The following describes the business recommendation method provided by the embodiments of the present application in conjunction with the accompanying drawings. Among them, the actions, terms, etc. involved between the embodiments of the present application can be referred to each other without limitation. The message names or parameter names in the messages exchanged between various devices in the embodiments of the present application are only examples, and other names can also be used in specific implementations without limitation. The actions involved in the embodiments of the present application are only examples, and other names can also be used in specific implementations, such as: "included in" in the embodiments of the present application can also be replaced by "carried by" or "carried on", etc.

[0066] As Figure 3 shown, an embodiment of the present application proposes a service recommendation method, which includes:

[0067] S301. Obtain the user information of the target user.

[0068] Among them, the target user refers to a user who registers on the service recommendation platform for the first time.

[0069] In a possible implementation manner, in response to the registration operation of the target user, obtain the user information of the target user.

[0070] Exemplarily, the above user information may include at least one of the following: name, age, gender, occupation, or geographical location.

[0071] It should be noted that the user information involved in the embodiments of the present application may be information authorized by the user or fully authorized by all parties.

[0072] Optionally, the implementation process of the user registering on the service recommendation platform may be: the user selects a mobile phone number or email as the registration account, enters the identity information according to the prompt, and sets the login password to successfully register.

[0073] Furthermore, after the user successfully registers, the user can log in to the service recommendation platform to browse and share services.

[0074] S302. Based on the user information of the target user, identify the user category of the target user, and determine the user portrait of the target user according to the user category.

[0075] Among them, the user portrait is used to describe user characteristics. User characteristics include at least one of the following: the historical business value of the user, the consumption habits of the user, the business needs of the user, the preferred recommendation method of the user.

[0076] The following will specifically describe the above four user characteristics.

[0077] 1-1. The historical business value of the user

[0078] Among them, the historical business value of the user refers to the total amount of historical services successfully handled by the user, which can reflect the consumption ability of the user.

[0079] Exemplarily, if user A purchases a traffic card worth 500 yuan, handles a broadband service with a cost of 1000 yuan, and the amount spent on recharge and traffic packages is 800 yuan, then the historical business value of user A is 500 + 1000 + 800 = 2300 yuan.

[0080] 1-2. The consumption habits of the user

[0081] A user's consumption habit refers to the behavior pattern demonstrated by the user when purchasing products or services. For example, paying attention to low prices, emphasizing convenience, and impulse buying.

[0082] As an example, if a user frequently changes packages and always selects the package with the lowest price, or is very sensitive to the price of value-added services and only subscribes to free or low-cost value-added services, it can be determined that the user has a consumption habit of paying attention to low prices.

[0083] Another example, if a user often complains about issues such as inconvenient recharge channels and cumbersome business handling processes, it can be determined that the user has a consumption habit of emphasizing convenience.

[0084] Another example, if a user has a high purchase frequency and often buys data packages, value-added services, etc. without prior planning, it can be determined that the user has a consumption habit of impulse buying.

[0085] 1-3. The business needs of the user

[0086] The business needs of the user refer to the requirements and expectations of the user for the functions, performance, and price of products or services.

[0087] 1-4. The preferred recommendation method of the user

[0088] The preferred recommendation method of the user refers to the way in which the user is more inclined to obtain product or service information. For example, the young user group tends to obtain product or service information through online methods such as social media and short video platforms. The middle-aged and elderly user group tends to obtain product or service information through traditional offline methods such as newspapers, magazines, and business halls.

[0089] In a possible implementation, according to the user information of the target user and the user classification model, the user category of the target user is obtained, and the user portrait corresponding to this user category is used as the user portrait of the target user. Specifically, the user information of the target user is input into the user classification model. The user classification model determines the clustering center closest to this data point based on the data points corresponding to this user information, and uses the user portrait corresponding to this closest clustering center as the user portrait of the target user.

[0090] It should be noted that the above user categories are user categories obtained by combining multiple classification criteria. For example, the classification criteria can include: the age of the user, the gender of the user, the historical business value of the user, the consumption habits of the user, the business needs of the user, and the preferred recommendation method of the user.

[0091] Exemplarily, taking the user's age as the classification criterion, the above user categories may include: teenage users, young users, middle-aged users, and elderly users. Among them, the age range corresponding to teenage users is between 13 and 18 years old. The age range corresponding to young users is between 19 and 35 years old. The age range corresponding to middle-aged users is between 36 and 60 years old. The age range corresponding to elderly users is over 60 years old.

[0092] Exemplarily, taking the user's historical business value as the classification criterion, the above user categories may include: high-value users and low-value users. For example, taking 500 yuan of the average monthly consumption amount as the boundary, the average monthly value of the historical business value of high-value users is greater than or equal to 500 yuan, and the average monthly value of the historical business value of low-value users is less than 500 yuan.

[0093] Exemplarily, taking the user's consumption habits as the classification criterion, the above user categories may include: price-sensitive users, impulse-consuming users, and high-frequency purchasing users. Among them, price-sensitive users refer to the user group that values price factors in the purchase decision-making process and tends to look for products or services with high cost performance. Impulse-consuming users refer to the user group that is easily stimulated and tempted by external factors, such as the product's functions, advertisements, or recommendations from others, and quickly makes a purchase decision. High-frequency purchasing users refer to the user group with a relatively high purchase frequency and continuous demand for specific products or services.

[0094] Exemplarily, taking the user's business needs as the classification criterion, the above user categories may include: quality-pursuing users, convenience-needing users, and service-experiencing users. Among them, quality-pursuing users refer to the user group that gives top priority to product quality and performance when purchasing products or services. Convenience-needing users refer to the user group that pays more attention to simple operation and fast process when purchasing and using products or services. Service-experiencing users refer to the user group that pays more attention to service quality and after-sales service when purchasing products or services.

[0095] Exemplarily, taking the user's preferred recommendation method as the classification criterion, the above user categories may include: online-method users and offline-method users. Among them, online-method users refer to the users who mainly receive and respond to operator business information through online recommendation methods. Online-method users are accustomed to obtaining operator business recommendations, preferential activities, etc. conveniently through online channels such as official websites, mobile applications, and social media platforms. Offline-method users refer to the users who tend to understand and select operator services through offline recommendation methods. Offline-method users are accustomed to communicating face-to-face with salespersons in operator business halls, authorized agencies, etc., and experiencing products or services personally to make purchase decisions.

[0096] It can be understood that through the user classification model, customer screening, customer value judgment, customer consumption habit analysis, customer demand analysis, and customer preference recommendation method analysis can be carried out, and the target users can be classified into the corresponding customer groups.

[0097] S303. Determine the business recommendation strategy for the target user based on the user portrait of the target user and the preset channel diversion principle.

[0098] Among them, the business recommendation strategy is used to determine the target business to be recommended to the target user and the recommendation method of the target business.

[0099] The recommendation methods include online recommendation methods and offline recommendation methods. Among them, the online recommendation method is the electronic recommendation method. The offline recommendation methods include social agency recommendation methods and operator self-operated recommendation methods.

[0100] The preset channel diversion principle includes the value principle and / or the efficiency principle. Among them, the value principle means selecting the recommendation method according to the historical business value of the user. For example, for high-value users, if the preferred recommendation method of the user is the online recommendation method, then select the official website, mobile application, and social media recommendation methods. For low-value users, select low-cost recommendation methods (such as SMS and email recommendation methods). The efficiency principle means selecting the recommendation method according to the type of business. For example, for process-convenient services, select the electronic recommendation method; for low-value services, select the electronic recommendation method or the social agency recommendation method; for standardized services, select the social agency recommendation method.

[0101] In a possible implementation manner, according to the user portrait of the target user, obtain the historical business value, consumption habits, business needs, and preferred recommendation methods of the target user. Based on the value, consumption habits, business needs, preferred recommendation methods of the target user, and the preset channel diversion principle, determine the business recommendation strategy for the target user. Specifically, reference can be made to the Figure 4 described embodiments, which will not be elaborated here.

[0102] Exemplarily, the above-mentioned process-convenient services refer to services that do not require much communication and interaction between the service provider and the user, and are simple to handle, and the risks faced by the operator when providing these services are relatively low. For example, bill inquiry, phone bill recharge, package change, and data package purchase.

[0103] Exemplarily, the above-mentioned low-value services refer to services with relatively low costs. For example, bill reminder, basic ringtone, and caller ID.

[0104] Exemplarily, the above-mentioned standardized services refer to services with unified technical standards, service specifications, and price strategies. For example, standard packages, prepaid communication cards, and Internet of Things cards.

[0105] It can be understood that different recommendation methods are selected according to the user value and the type of business, so that the recommendation cost matches the user value. Moreover, full guidance and diversion are carried out according to the characteristics of the recommendation methods, so that the business volume among different recommendation methods is balanced, thereby reducing the pressure on the manual channel and improving the efficiency of the electronic channel.

[0106] In the business recommendation method provided by this application, user information of a target user is obtained, the user category of the target user is identified based on the user information, and the user portrait of the target user is determined according to the user category. Based on the user portrait of the target user and the preset channel diversion principle, a business recommendation strategy for the target user is determined. Among them, the business recommendation strategy is used to determine the target business to be recommended to the target user and the recommendation method of the target business. That is to say, the business recommendation method provided by the embodiments of this application determines the target business according to the user portrait and the preset channel diversion principle, and selects different recommendation methods for business recommendation, thereby being able to improve the overall efficiency of the operator's recommendation channel system.

[0107] Optionally, after S303, the target business can be recommended to the target user according to the business recommendation strategy of the target user, and a notification message can be sent to the user according to the business handling and usage situation of the user. Specifically, obtain the order payment status information of the target user from the user order and payment system; integrate the usage data of the user's communication service (for example, call duration, number of text messages, data traffic); classify the user according to the user's historical data and behavior habits, such as classification by payment habit, service usage volume, cost sensitivity, etc.; design personalized notification messages for the user according to the classification result; where the notification message includes the order status, service expiration time, and current cost. In addition, for users whose expenses are about to exceed, saving suggestions or preferential activity information can also be added to the notification message.

[0108] Furthermore, before S302, it is necessary to construct a user classification model so that the user category to which the target user belongs can be determined according to the user classification model in the follow-up. Specifically, the implementation process of constructing the user classification model can include the following steps.

[0109] Step 1: Obtain historical user data.

[0110] Optionally, the user information data, consumption information data, recommendation method contact data, and behavior data of multiple users are collected through the contact management module.

[0111] Exemplarily, the above user information data may include data such as the user's name, age, gender, occupation, and geographical location. The above consumption information data may include data such as the user's purchase history, purchase frequency, purchase amount, and purchase preferences. The above recommended method contact data may be the interaction information of the user with different recommended methods, including data such as the user's visit volume, stay time, and conversion rate for online and offline recommended methods. The above behavior data may include data such as the user's search, browsing, click, and purchase.

[0112] Step 2: Perform clustering analysis on the historical user data to construct an initial user classification model.

[0113] 2-1. Preprocess the historical user data

[0114] Specifically, perform data cleaning, data transformation, and data integration operations on the historical user data. Among them, data cleaning refers to removing duplicate, incorrect, or incomplete data. Data transformation refers to converting the original data into data in a format suitable for analysis (for example, numerical data). Data integration refers to integrating data from different sources into a unified dataset.

[0115] 2-2. Determine the data points corresponding to each user

[0116] Specifically, for each user, select feature values from the preprocessed data corresponding to the user, and combine the selected feature values to obtain the data points corresponding to the user. Among them, the feature value is a feature related to the clustering target, which can describe the user's characteristics, consumption behavior, or preferred recommendation method.

[0117] 2-3. Determine the target K value

[0118] In a possible implementation, the target K value is determined by the elbow method. Specifically, perform clustering analysis on the data, and select different K values (for example, from 1 to 10). For each K value, calculate the corresponding clustering error. Plot a graph of the clustering error versus the K value. According to the graph, find the inflection point, and use the K value at this inflection point as the target K value.

[0119] In another possible implementation, the target K value is determined by the silhouette score. Specifically, perform clustering analysis on the data, and select different K values. For each K value, calculate the silhouette coefficient of each data point, and calculate the average value of the silhouette coefficients of all data points to obtain the silhouette coefficient corresponding to this K value. Compare the silhouette coefficients corresponding to different K values, and use the K value with the largest silhouette coefficient as the target K value.

[0120] 2-4. Determine K initial clustering centers

[0121] 2-4-1. Determine the first cluster center

[0122] Specifically, randomly select a data point from the dataset and use it as the first cluster center.

[0123] 2-4-2. Calculate the squared distance from each data point to the nearest cluster center

[0124] Specifically, for each data point in the dataset, calculate the squared Euclidean distance between it and the nearest cluster center among the currently selected cluster centers.

[0125] 2-4-3. Determine the next cluster center

[0126] Specifically, based on the squared distance from each data point to the nearest cluster center, calculate the probability of each data point being selected as the next cluster center. Use the roulette wheel method to select the next cluster center according to the calculated probability.

[0127] 2-4-4. Determine K initial cluster centers

[0128] Specifically, repeat the above steps 2-4-2 and 2-4-3 until K cluster centers are selected.

[0129] 2-5. Execute the clustering algorithm

[0130] Exemplarily, the K-means algorithm is used as an example for illustration below.

[0131] 2-5-1. Assign data points

[0132] Specifically, for each data point x i , calculate the distance between x i and each cluster center μ j , and assign x i to the cluster j corresponding to the nearest cluster center μ j . Among them, 1 ≤ i ≤ N, 1 ≤ j ≤ K, N represents the number of data points, K represents the number of cluster centers, and both N and K are positive integers.

[0133] 2-5-2. Recalculate the cluster centers

[0134] For each cluster j, calculate the average value of all data points in cluster j and use this average value as the new cluster center μ j of cluster j.

[0135] 2-5-3. Iteration

[0136] Repeat the above steps 2-5-1 and 2-5-2 until the stopping condition is met to obtain the initial user classification model.

[0137] Exemplarily, the above stopping condition may be that the cluster centers no longer change or a preset number of iterations is reached. Among them, the cluster centers no longer changing means that after a certain iteration, all the cluster centers have not changed. Reaching the preset number of iterations means that the total number of iterations meets the preset number of iterations.

[0138] It can be understood that by continuously updating the cluster centers and reassigning the data points, the K-means algorithm can determine a compact clustering result. In this way, the data points in each cluster represent users with highly similar characteristics in terms of user information, consumption behavior, and recommended method selection.

[0139] Step Three: Optimize the initial user classification model

[0140] 3-1. Verify the initial user classification model

[0141] Specifically, use business data to verify the initial user classification model, and evaluate the accuracy and effectiveness of the model according to preset metrics. For example, use the sum of squared errors (SSE) as the preset metric for evaluating the model effect. The calculation formula of SSE can be expressed by the following Formula 1.

[0142]

[0143] Among them, x i represents the i-th data point, μ j represents the cluster center of the j-th cluster, ||x i -μ j || represents the Euclidean distance between x i and μ j .

[0144] 3-2. Optimize the initial user classification model according to the verification result

[0145] Specifically, since the smaller the SSE, the closer the clustering result, the parameters of the clustering algorithm can be adjusted, eigenvalues can be added or deleted to make the SSE decrease, and the final user classification model can be obtained.

[0146] In one embodiment, as Figure 4 shown, the above S303 can be specifically determined by the following S401 to S402.

[0147] S401. Based on the consumption habits and business requirements of the target user, determine the target business.

[0148] In a possible implementation, various services provided by the operator are identified according to the consumption habits and business requirements of the target user, and the candidate services that match the consumption habits and business requirements of the user are obtained. According to the candidate services and a preset recommendation algorithm (for example, collaborative filtering, content filtering, etc. algorithms), the service with the highest matching degree with the consumption habits and business needs of the user is selected from the candidate services, and this service is used as the target service recommended to the target user.

[0149] It can be understood that by performing data analysis on the user portrait of the target user, more accurate and personalized service recommendations can be provided for the target user, thereby improving the user experience and enhancing user stickiness.

[0150] S402. Determine the recommendation method of the target service based on the historical business value, preferred recommendation method, and preset channel diversion principle of the target user.

[0151] In a possible implementation, according to the historical business value of the target user, it is determined whether the target user is a high-value user or a low-value user. If the target user is a high-value user, the preferred recommendation method of the target user is used as the recommendation method of the target service. If the target user is a low-value user, the social agent recommendation method or the electronic recommendation method is used as the recommendation method of the target service.

[0152] Furthermore, the recommendation method of the target service can also be determined according to the type of the target service. Specifically, if the target service is a service with convenient processes, the electronic recommendation method is used as the recommendation method of the target service. If the target service is a low-value service, the electronic recommendation method or the social agent recommendation method is used as the recommendation method of the target service. If the target service is a standardized service, the social agent recommendation method is used as the recommendation method of the target service. By this method, the service can be effectively guided to the electronic channel and the social agent channel, reducing the workload of the manual channel for processing simple and repetitive services.

[0153] Optionally, users can be guided to offline stores to experience services through an online service recommendation platform, and online services can also be recommended to users through offline stores. In this way, the integration and complementarity of online and offline services are conducive to cultivating the habit of users to switch between different channels, and can improve the service conversion rate and user satisfaction. In addition, online and offline activities can be combined to increase user participation and brand exposure.

[0154] Furthermore, after S303, the target service can be recommended to the target user according to the service recommendation strategy of the target user. If the target user successfully subscribes to the target service, a reminder message related to the target service can be sent to the target user. In view of this, as Figure 5 shown, the service recommendation method recorded in the embodiments of the present application may further include the following steps.

[0155] S501. Send a reminder message to the target user according to the business usage of the target user.

[0156] In a possible implementation, according to the business usage of the target user, determine the information sending time for sending a reminder message to the user. According to this information sending time, send a reminder message to the target user. Specifically, reference can be made to the Figure 6 described embodiments, which will not be elaborated here.

[0157] Exemplarily, the above reminder message may include at least one of the following: fee reminder, traffic reminder, service expiration reminder, preferential activity reminder.

[0158] In one embodiment, as Figure 6 shown, the above S501 can be specifically determined by the following S601 to S602.

[0159] S601. Based on the business usage of the target user, determine the information sending time.

[0160] As an example, taking sending a fee reminder message to the target user as an example, select the time period when the target user has a relatively low call frequency as the information sending time. For example, if the target user makes calls more frequently from 8:00 to 9:00 in the morning and from 19:00 to 21:00 in the evening, 12:00 to 13:00 at noon or 16:00 to 17:00 in the afternoon can be selected as the information sending time.

[0161] Another example, taking sending a traffic reminder message to the target user as an example, select the moment when the target user's traffic usage reaches the preset traffic threshold as the information sending time.

[0162] Another example, taking sending a service expiration reminder to the target user as an example, select 3 - 5 days before the expiration of the target user's package validity period as the information sending time.

[0163] It can be understood that by setting different information sending times to determine when to send a reminder message to the user, this can not only avoid over - disturbing the user but also ensure that the user can receive the reminder at key time points.

[0164] S602. According to the information sending time, send a reminder message to the target user.

[0165] In a possible implementation, when the current time meets the information sending time, send a reminder message to the target user.

[0166] As an example, the above reminder message can be a fee reminder message. For example: "Dear user, your phone bill balance is less than 10 yuan. Please recharge in time to avoid affecting normal use."

[0167] Another example is that the above reminder information can be traffic reminder information. For example: "Dear user, your traffic usage is approaching the package limit. Please use it reasonably or upgrade your package."

[0168] Another example is that the above reminder information can be service expiration reminder. For example: "Dear user, your package is about to expire. Please renew it in time to avoid affecting normal use."

[0169] It can be understood that the above business recommendation method can be implemented by a business recommendation device. In order to implement the above functions, the business recommendation device includes the corresponding hardware structure and / or software module for executing each function. Those skilled in the art should easily realize that, combining the modules and algorithm steps of each example described in the embodiments disclosed in this article, the disclosed embodiments of the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the disclosed embodiments of the present application.

[0170] The disclosed embodiments of the present application can perform function module division according to the business recommendation device generated by the above method examples. For example, each function module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of a software function module. It should be noted that the division of modules in the disclosed embodiments of the present application is illustrative, only a logical function division, and there may be other division methods in actual implementation.

[0171] Figure 7 It is a schematic structural diagram of a business recommendation device provided by an embodiment of the present application. As Figure 7 shown, the business recommendation device 70 can be used to execute Figures 3 - 6 the business recommendation method shown. The business recommendation device 70 includes: a communication unit 701 and a processing unit 702.

[0172] The communication unit 701 is used to obtain the user information of the target user; the processing unit 702 is used to identify the user category of the target user based on the user information of the target user, and determine the user portrait of the target user according to the user category; the user portrait is used to describe user characteristics; the processing unit 702 is further used to determine the business recommendation strategy for the target user based on the user portrait of the target user and the preset channel diversion principle; the business recommendation strategy is used to determine the target business to be recommended to the target user and the recommendation method of the target business.

[0173] In a possible implementation, the user characteristics include at least one of the following: the user's historical business value; the user's consumption habits; the user's business needs; the user's preferred recommendation method.

[0174] In a possible implementation, the preset channel diversion principle includes the value principle and / or the efficiency principle; wherein, the value principle means selecting a recommendation method according to the user's historical business value, and the efficiency principle means selecting a recommendation method according to the type of business; wherein, the recommendation methods include online recommendation methods and offline recommendation methods.

[0175] In a possible implementation, the processing unit 702 is further configured to determine a target business based on the consumption habits and business needs of the target user; the processing unit 702 is further configured to determine a recommendation method for the target business based on the historical business value, preferred recommendation method of the target user, and the preset channel diversion principle.

[0176] In a possible implementation, after the target user handles the target business, the processing unit 702 is further configured to send a reminder message to the target user according to the business usage situation of the target user.

[0177] In a possible implementation, the processing unit 702 is further configured to determine the information sending timing based on the business usage situation of the target user; the processing unit 702 is further configured to send a reminder message to the target user according to the information sending timing.

[0178] Through the description of the above embodiments, those skilled in the art can clearly understand that for the convenience and conciseness of description, only the above division of each functional module is used as an example. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be repeated here.

[0179] The present disclosure also provides a computer-readable storage medium, on which instructions are stored. When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device can execute the business recommendation method provided in the embodiments of the present disclosure.

[0180] The embodiments of the present disclosure also provide a computer program product containing instructions, which, when running on an electronic device, enables the electronic device to execute the business recommendation method provided in the embodiments of the present disclosure.

[0181] Among them, a computer-readable storage medium can be, for example, but not limited to, a system, device or component of electricity, magnetism, light, electromagnetic, infrared ray, or semiconductor, or any combination of the above. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a register, a hard disk, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above, or any other form of computer-readable storage medium well-known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). In the embodiments of the present application, the computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, device or component.

[0182] The above is only the specific implementation manners of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A business recommendation method, characterized in that: The method comprises: Get the user information of the target user; Based on the user information of the target user, identifying the user category of the target user, and determining the user profile of the target user according to the user category; The user portrait is used to describe user characteristics; Determine a service recommendation strategy for the target user based on the user profile of the target user and the preset channel diversion principle; The service recommendation strategy is used to determine the target service recommended to the target user and the recommendation method of the target service.

2. The method according to claim 1, characterized in that: The user characteristics include at least one of the following: The historical business value of the user; the consumption habits of the user; The business needs of the user; The user's preferred recommendation method.

3. The method according to claim 2, characterized in that The preset channel diversion principle includes a value principle and / or an efficiency principle; wherein, the value principle indicates selecting a recommendation method based on the user's historical business value, and the efficiency principle indicates selecting a recommendation method based on the type of business; wherein, the recommendation method includes an online recommendation method and an offline recommendation method.

4. The method according to claim 3, characterized in that: The determining of a service recommendation strategy for the target user based on the user profile of the target user and a preset channel diversion principle includes: Determine the target business based on the consumption habits and business needs of the target user; Based on the historical business value, preferred recommendation method and the preset channel diversion principle of the target user, the recommendation method of the target business is determined.

5. The method according to any one of claims 1 to 4, characterized in that After the target user handles the target service, the method further includes: Send reminder information to the target user according to the service usage of the target user.

6. The method according to claim 5, characterized in that The sending reminder information to the target user according to the service usage of the target user includes: Determining a time to send information based on the service usage of the target user; Send reminder information to the target user according to the information sending timing.

7. A business recommendation device, characterized in that: The device comprises: a communication unit and a processing unit; The communication unit is used to obtain user information of a target user; The processing unit is configured to identify a user category of the target user based on the user information of the target user, and determine a user profile of the target user according to the user category; The user portrait is used to describe user characteristics; The processing unit is further configured to determine a service recommendation strategy for the target user based on the user profile of the target user and a preset channel diversion principle; The service recommendation strategy is used to determine the target service recommended to the target user and the recommendation method of the target service.

8. A business recommendation device, characterized in that: include: A processor and a communication interface; the communication interface is coupled to the processor, and the processor is used to run a computer program or instruction to implement the service recommendation method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed on a computer, the computer is enabled to execute the business recommendation method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product comprises computer program instructions, and when the computer program instructions are executed by a processor, the service recommendation method according to any one of claims 1 to 6 is implemented.

Images