Method, device and equipment for recommending marketing scheme and readable storage medium

Abstract

The invention provides a method, device and equipment for recommending a marketing scheme and a readable storage medium, and the method comprises the steps: obtaining historical customer information in a database, and the historical customer information comprises the identification information of different customers, subjective call data and objective basic data; historical customer information is recognized through a preset marketing recommendation quantitative model, a marketing recommendation scheme of the target customer is obtained, and the marketing recommendation quantitative model is obtained by training a basic quantitative model through the label information and historical transaction data of different customers; the label information is obtained by extracting key information in historical call records and historical objective basic information, the historical call records and the historical objective basic information are obtained from a database, and the marketing recommendation scheme comprises a plurality of labels and marketing information corresponding to the labels. Through the method, the effects of reasonably recommending the marketing scheme and realizing refined intelligent operation can be achieved.

Description

Technical Field

[0001] The present application relates to the field of marketing operations, and in particular, to a method, apparatus, device and readable storage medium for recommending a marketing plan. Background Art

[0002] At present, the corporate WeChat social customer relationship management systems on the market can usually only rely on the company's WeChat historical marketing interactions and some objective customer data to characterize and classify customer portraits, and then conduct targeted push to promote transactions.

[0003] The above method can only use a small amount of data for marketing in the marketing process, and cannot achieve more refined stratification and characterization of customer groups to achieve more refined intelligent operations.

[0004] Therefore, how to reasonably recommend marketing plans and achieve refined intelligent operations is a technical problem that needs to be solved. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a method for recommending marketing plans. Through the technical solutions of the embodiments of the present application, it is possible to reasonably recommend marketing plans and achieve the effect of refined intelligent operations.

[0006] In a first aspect, an embodiment of the present application provides a method for recommending a marketing plan, including obtaining historical customer information from a database, wherein the historical customer information includes: identification information of different customers, subjective call data, and objective basic data; identifying the historical customer information through a preset marketing recommendation quantitative model to obtain a marketing recommendation plan for the target customer, wherein the marketing recommendation quantitative model is obtained by training a basic quantitative model with label information and historical transaction data of different customers, the label information is obtained by extracting key information from historical call records and historical objective basic information, the historical call records and historical objective basic information are obtained from a database, and the marketing recommendation plan includes multiple labels and marketing information corresponding to the labels.

[0007] In the above embodiments of the present application, the identification information, subjective and objective data of each channel are aggregated by connecting customer information from multiple channels. Based on the aggregated data, the marketing recommendation quantitative model is used to analyze the marketing scenarios, etc., and a targeted marketing recommendation plan is output for the specified marketing scenario, so as to achieve a reasonable marketing plan recommendation and achieve the effect of refined intelligent operation.

[0008] In some embodiments, before obtaining historical customer information in the database, it also includes: obtaining historical call records and historical objective basic information of different customers from the database; extracting label information corresponding to key information in the historical call records and historical objective basic information; training a basic quantitative model through label information and historical transaction data of target customers to obtain a marketing recommendation quantitative model, wherein the historical transaction data includes historical transaction results of different customers and corresponding transaction records.

[0009] In the above embodiments of the present application, historical related information of different users is used as samples, and the labels of the extracted samples and the key information corresponding to the labels can be used as training samples to train a marketing recommendation quantitative model, which can accurately output marketing recommendation plans based on customer information.

[0010] In some embodiments, before acquiring historical call records and historical objective basic information of different customers from the database, the method further includes: aggregating the call records of different customers acquired through multiple channels and storing them in the database.

[0011] In the above-mentioned embodiment of the present application, by aggregating the call records of different customers obtained through multiple channels, more complete user information can be obtained when using database information, thereby accurately generating marketing recommendation plans.

[0012] In some embodiments, historical customer information is identified through a preset marketing recommendation quantitative model to obtain a marketing recommendation plan for target customers, including: identifying historical customer information through a marketing recommendation quantitative model to obtain portrait information and user stratification information of different customers; selecting target customers and generating a marketing recommendation plan based on the current marketing scenario, portrait information and user stratification information through a marketing recommendation quantitative model, wherein the marketing recommendation plan also includes a standard operating procedure.

[0013] In the above embodiments of the present application, analysis is performed based on user-related data, marketing scenarios, and extracted user stratification information, and targeted user stratification and user portraits can be output according to the marketing scenarios; corresponding recommended marketing plans can be output for multi-dimensional information such as different products, customer groups, and market environments.

[0014] In some embodiments, after identifying historical customer information through a preset marketing recommendation quantitative model and obtaining a marketing recommendation plan for the target customer, it also includes: selecting a marketing channel corresponding to the marketing recommendation plan to provide a marketing panel for marketers, wherein the marketing panel includes a marketing tag and corresponding marketing content.

[0015] In the above embodiments, the present application can display marketing labels and corresponding marketing content to marketers, making marketing more convenient for marketers.

[0016] In some embodiments, after identifying historical customer information through a preset marketing recommendation quantitative model and obtaining a marketing recommendation plan for the target customer, it also includes: obtaining the marketing personnel's score and recommendation level for the marketing recommendation quantitative model; and adjusting and optimizing the marketing recommendation quantitative model based on the score and recommendation level.

[0017] In the above-mentioned embodiments of the present application, the marketing personnel's use of the marketing recommendation quantitative model can be scored, and the model can be optimized to enable the model to generate marketing recommendation plans more accurately.

[0018] In some embodiments, historical customer information is identified through a preset marketing recommendation quantitative model to obtain a marketing recommendation plan for target customers, including: formulating a marketing strategy for marketers through the recommendation algorithm in the marketing recommendation quantitative model in combination with the current marketing scenario, and the marketing strategy includes at least one of marketing frequency, marketing channels, marketing time and specific marketing content.

[0019] In the above embodiments, the present application can formulate marketing strategies for corresponding scenarios in combination with the current marketing scenarios to achieve targeted marketing recommendations.

[0020] In a second aspect, an embodiment of the present application provides a device for recommending a marketing plan, including:

[0021] An acquisition module is used to acquire historical customer information in a database, wherein the historical customer information includes: identification information, subjective call data and objective basic data of different customers;

[0022] The recommendation module is used to identify historical customer information through a preset marketing recommendation quantitative model to obtain a marketing recommendation plan for target customers, wherein the marketing recommendation quantitative model is obtained by training a basic quantitative model with label information and historical transaction data of different customers, the label information is obtained by extracting key information from historical call records and historical objective basic information, the historical call records and historical objective basic information are obtained from a database, and the marketing recommendation plan includes multiple labels and marketing information corresponding to the labels.

[0023] Optionally, the device further comprises:

[0024] A training module, used for the acquisition module to acquire historical call records and historical objective basic information of different customers from the database before acquiring historical customer information in the database;

[0025] Extract label information corresponding to key information in historical call records and historical objective basic information;

[0026] The basic quantitative model is trained by using label information and historical transaction data of target customers to obtain a marketing recommendation quantitative model, wherein the historical transaction data includes historical transaction results of different customers and corresponding transaction records.

[0027] Optionally, the device further comprises:

[0028] The summarizing module is used to summarize the call records of different customers obtained from multiple channels and store them in the database before the training module obtains the historical call records and historical objective basic information of different customers from the database.

[0029] Optional, recommended modules specifically for:

[0030] Identify historical customer information through marketing recommendation quantitative models to obtain profile information and user stratification information of different customers;

[0031] Through the marketing recommendation quantitative model, target customers are selected and marketing recommendation plans are generated based on the current marketing scenario, portrait information and user stratification information. The marketing recommendation plan also includes standard operating procedures.

[0032] Optionally, the device further comprises:

[0033] The display module is used for the recommendation module to identify historical customer information through a preset marketing recommendation quantitative model, obtain the marketing recommendation plan for the target customer, select the marketing channel corresponding to the marketing recommendation plan, and provide a marketing panel for the marketing personnel, wherein the marketing panel includes a marketing label and corresponding marketing content.

[0034] Optionally, the device further comprises:

[0035] An optimization module is used to obtain the marketing personnel's scoring and recommendation degree of the marketing recommendation quantitative model after the recommendation module identifies historical customer information through a preset marketing recommendation quantitative model and obtains the marketing recommendation plan for the target customer;

[0036] According to the scoring situation and the degree of recommendation, the marketing recommendation quantitative model is adjusted and optimized.

[0037] Optional, recommended modules specifically for:

[0038] Through the recommendation algorithm in the marketing recommendation quantitative model, combined with the current marketing scenario, a marketing strategy is formulated for marketers. The marketing strategy includes at least one of marketing frequency, marketing channel, marketing time and specific marketing content.

[0039] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the method provided in the first aspect are performed.

[0040] In a fourth aspect, an embodiment of the present application provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the method provided in the first aspect are performed.

[0041] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or be understood by practicing the embodiments of the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 A flowchart of a method for recommending a marketing plan provided in an embodiment of the present application;

[0044] Figure 2 A schematic block diagram of a device for recommending a marketing plan provided in an embodiment of the present application;

[0045] Figure 3 A schematic block diagram of the structure of a device for recommending a marketing plan provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0047] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0048] First, some terms involved in the embodiments of the present application are explained to facilitate understanding by those skilled in the art.

[0049] SOP (Standard Operating Procedure) refers to the description of the standard operating steps and requirements of an event in a unified format to guide and standardize daily work.

[0050] SCRM (Social Customer Relationship Management), or social customer relationship management, is a customer relationship management system based on social media.

[0051] This application is applied to marketing operation scenarios. The specific scenario is to open a comprehensive customer information operation platform that connects multiple channels such as WeChat, phone and SMS, and aggregate the subjective and objective data of each channel. Through the model, based on the aggregated data, marketing scenarios and extracted user characteristics, etc., targeted user stratification and user portraits are output for general marketing scenarios and specified marketing scenarios; marketing recommendation plans are generated for multi-dimensional information such as different products, customer groups, and market environments.

[0052] At present, the WeChat social customer relationship management systems for enterprises on the market usually rely on the historical marketing interactions of the WeChat account and some objective data of customers to characterize and classify customers, and then push targeted information to promote transactions. In the above method, operators can only use a small amount of data for marketing, and cannot achieve more refined stratification and characterization of customer groups to achieve more refined intelligent operations.

[0053] To this end, this application obtains historical customer information from a database, wherein the historical customer information includes: identification information of different customers, subjective call data, and objective basic data; identifies historical customer information through a preset marketing recommendation quantitative model to obtain a marketing recommendation plan for the target customer, wherein the marketing recommendation quantitative model is obtained by training a basic quantitative model with label information and historical transaction data of different customers, the label information is obtained by extracting key information from historical call records and historical objective basic information, the historical call records and historical objective basic information are obtained from a database, and the marketing recommendation plan includes multiple labels and marketing information corresponding to the labels. By connecting customer information from multiple channels, the identification information, subjective and objective data of each channel are aggregated. Based on the aggregated data, the marketing recommendation quantitative model is used in combination with marketing scenarios to analyze and output targeted marketing recommendation plans for specified marketing scenarios, so as to achieve reasonable marketing plan recommendations and achieve the effect of refined intelligent operations.

[0054] In the embodiment of the present application, the executing entity may be a recommended marketing plan device in the recommended marketing plan system. In actual applications, the recommended marketing plan device may be electronic devices such as terminal devices and servers, and no limitation is made here.

[0055] Combine the following Figure 1 The method for recommending a marketing plan in an embodiment of the present application is described in detail.

[0056] Please see Figure 1 , Figure 1 A flowchart of a method for recommending a marketing plan provided in an embodiment of the present application, such as Figure 1 The methods of recommending marketing programs shown include:

[0057] Step 110: Obtain historical customer information in the database.

[0058] Among them, historical customer information includes: identification information of different customers, subjective call data and objective basic data. Identification information includes basic information, reach, current progress, next reach suggestion, next follow-up and follow-up focus, etc. The reach includes reach frequency (such as 3 days, 7 days, 1 month, etc.), reach channel (telephone, corporate WeChat, etc.), reach time (morning, noon, evening, weekends, etc.). Subjective call data includes call voice and corresponding text, and can also include key information in the text, such as keywords. Objective basic data includes region, gender, age, business status, turnover, liabilities, reach rate, reach channel and interaction time.

[0059] In some embodiments of the present application, before obtaining historical customer information in the database, Figure 1The method shown also includes: obtaining historical call records and historical objective basic information of different customers from a database; extracting label information corresponding to key information in the historical call records and historical objective basic information; training a basic quantitative model through label information and historical transaction data of target customers to obtain a marketing recommendation quantitative model, wherein the historical transaction data includes historical transaction results of different customers and corresponding transaction records.

[0060] In the above embodiments of the present application, historical related information of different users is used as samples, and the labels of the extracted samples and the key information corresponding to the labels can be used as training samples to train a marketing recommendation quantitative model, which can accurately output marketing recommendation plans based on customer information.

[0061] Among them, key information can be a keyword or a sentence. Tag information includes reach, current progress, next reach suggestion, next follow-up and follow-up focus. Historical transaction results include transaction content when the transaction is successful and when the transaction is not successful. The basic quantitative model can use the open source LLM3.1 after fine-tuning.

[0062] Optionally, the basic quantitative model can be trained by using label information and historical transaction data of target customers. The label information and historical transaction data of target customers can be divided into training data and verification data. The training data is used to train the basic quantitative model, and the verification data is used to verify the obtained marketing recommendation quantitative model.

[0063] In some embodiments of the present application, before obtaining historical call records and historical objective basic information of different customers from the database, Figure 1 The method shown also includes: aggregating the call records of different customers obtained through multiple channels and storing them in a database.

[0064] In the above-mentioned embodiment of the present application, by aggregating the call records of different customers obtained through multiple channels, more complete user information can be obtained when using database information, thereby accurately generating marketing recommendation plans.

[0065] Different channels may include WeChat, phone calls, and text messages. Call records include call voice and the text corresponding to the voice. Before aggregating the call records of different customers obtained through multiple channels and storing them in the database, the call records can be converted into text form, and then key information can be obtained through keywords or key information extraction technology, and the key information can be labeled and stored in the database.

[0066] Optionally, each sales / operation staff can have an independent account on the WeChat private domain operation platform, under which they can see all their customers. The platform has objective customer information as well as historical communication and transaction records; each sales / operation staff has an independent account on the outbound calling platform, under which they can see the full objective information of all their customers; sales / operation staff perform sales and marketing work on the outbound calling platform every day, maintaining old customers and developing new customers through telephone and WeChat channels respectively; after reaching the customer by phone, WeChat, and text message, the system translates all voice offline (daily frequency) into text through a translation tool, and at the same time, the voice-translated text, text, pictures, and emoticons in the communication process are all persistently stored in the database, and aggregated with the customer's historical objective data (region, surname, gender, etc.).

[0067] Step 120: Identify historical customer information through a preset marketing recommendation quantitative model to obtain a marketing recommendation plan for the target customer.

[0068] Among them, the marketing recommendation quantitative model is obtained by training the basic quantitative model through label information and historical transaction data of different customers. The label information is obtained by extracting key information from historical call records and historical objective basic information. The historical call records and historical objective basic information are obtained from the database. The marketing recommendation plan includes multiple labels and marketing information corresponding to the labels.

[0069] In some embodiments of the present application, historical customer information is identified through a preset marketing recommendation quantitative model to obtain a marketing recommendation plan for target customers, including: identifying historical customer information through a marketing recommendation quantitative model to obtain portrait information and user stratification information of different customers; selecting target customers and generating a marketing recommendation plan based on the current marketing scenario, portrait information and user stratification information through a marketing recommendation quantitative model, wherein the marketing recommendation plan also includes a standard operating procedure.

[0070] In the above process, this application conducts analysis based on user-related data, marketing scenarios, and extracted user stratification information, and can output targeted user stratification and user portraits based on the marketing scenarios; and output corresponding recommended marketing plans based on multi-dimensional information such as different products, customer groups, and market environments.

[0071] Among them, the portrait information includes the portraits of different customers. The user stratification information includes the marketing product categories of different customers and the classification and stratification of different customers. The target customers are selected based on the current marketing scenario and customer category, and are obtained according to the arrangement order of different customers in the database.

[0072] In some embodiments of the present application, historical customer information is identified through a preset marketing recommendation quantitative model to obtain a marketing recommendation plan for the target customer, including: formulating a marketing strategy for marketers through a recommendation algorithm in the marketing recommendation quantitative model in combination with the current marketing scenario, and the marketing strategy includes at least one of marketing frequency, marketing channels, marketing time and specific marketing content.

[0073] In the above process, the present application can formulate marketing strategies for corresponding scenarios in combination with the current marketing scenarios to achieve targeted marketing recommendations.

[0074] Among them, the marketing recommendation plan and marketing strategy include some tags and action instructions corresponding to the tags, which are used to instruct marketers on the next marketing work.

[0075] In some embodiments of the present application, after identifying historical customer information through a preset marketing recommendation quantitative model and obtaining a marketing recommendation plan for a target customer, Figure 1 The method shown also includes: selecting a marketing channel corresponding to the marketing recommendation plan to provide a marketing panel for the marketer, wherein the marketing panel includes a marketing tag and corresponding marketing content.

[0076] During the above process, this application can display marketing labels and corresponding marketing content to marketers, making marketing more convenient for marketers.

[0077] Among them, marketing labels include basic information, reach status, current progress, next reach suggestion, next follow-up and follow-up focus, and corresponding marketing content includes basic information: region, age, small fruit shop, transferred to son for operation, monthly turnover, no debt, no invoices, own independent housing, and company WeChat account added; reach status: phone, time, call time 2 minutes; current progress: demand collection; next reach suggestion: company WeChat account; next follow-up time: 2024-11-08 morning; follow-up focus: contact the actual operator.

[0078] Optionally, the integrated operation platform provides sales operations personnel with a "Customer Dashboard" page tool based on model recommendations. This function updates recommended customers suitable for sales personnel to follow up in real time. Sales personnel can select customers who need to be followed up based on the current situation and model recommendations, and reach customers through recommended channels.

[0079] In some embodiments of the present application, after identifying historical customer information through a preset marketing recommendation quantitative model and obtaining a marketing recommendation plan for a target customer, Figure 1 The method shown also includes: obtaining the marketing personnel's scoring and recommendation level for the marketing recommendation quantitative model; and adjusting and optimizing the marketing recommendation quantitative model based on the scoring and recommendation level.

[0080] In the above process, this application can score marketers based on their use of the marketing recommendation quantitative model, and then optimize the model to enable the model to more accurately generate marketing recommendation plans.

[0081] Among them, adjusting and optimizing the marketing recommendation quantitative model according to the scoring situation and the recommendation degree includes, when at least one of the scoring situation and the recommendation degree is less than or equal to a preset threshold, it is necessary to re-acquire customer-related data for optimization training of the marketing recommendation quantitative model, or directly adjust the parameters of the marketing recommendation quantitative model to obtain the optimized marketing recommendation quantitative model.

[0082] Optionally, historical customer information can be identified through a preset marketing recommendation quantitative model to obtain marketing recommendation plans for target customers. Historical customer information can also be identified through a marketing recommendation quantitative model to obtain user portrait features and stratification features. The obtained portrait features and stratification features are combined with multi-dimensional information such as different products, customer groups, and market environments in the current marketing scenario, and combined with general marketing SOP tools to intelligently generate new customized marketing recommendation plans.

[0083] In the above Figure 1 In the process shown, the present application obtains historical customer information from a database, wherein the historical customer information includes: identification information of different customers, subjective call data, and objective basic data; identifies historical customer information through a preset marketing recommendation quantitative model, and obtains a marketing recommendation plan for the target customer, wherein the marketing recommendation quantitative model is obtained by training a basic quantitative model with label information and historical transaction data of different customers, the label information is obtained by extracting key information from historical call records and historical objective basic information, the historical call records and historical objective basic information are obtained from a database, and the marketing recommendation plan includes multiple labels and marketing information corresponding to the labels. By connecting customer information from multiple channels, the identification information, subjective and objective data of each channel are summarized. Based on the summarized data, the marketing recommendation quantitative model is used in combination with marketing scenarios for analysis, and targeted marketing recommendation plans are output for specified marketing scenarios, so as to achieve reasonable marketing plan recommendations and achieve the effect of refined intelligent operations.

[0084] Previous article Figure 1 Describes the method of recommending marketing plans, combined with Figure 2-Figure 3 Describe the device that recommends marketing programs.

[0085] Please refer to Figure 2 , is a schematic block diagram of a device 200 for recommending a marketing plan provided in an embodiment of the present application, and the device 200 may be a module, program segment or code on an electronic device. Figure 1 The method embodiment corresponds to and can be executed Figure 1The various steps involved in the method embodiment and the specific functions of the device 200 can be found in the description below. To avoid repetition, the detailed description is appropriately omitted here.

[0086] Optionally, the device 200 includes:

[0087] An acquisition module 210 is used to acquire historical customer information in a database, wherein the historical customer information includes: identification information, subjective call data and objective basic data of different customers;

[0088] The recommendation module 220 is used to identify historical customer information through a preset marketing recommendation quantitative model to obtain a marketing recommendation plan for the target customer, wherein the marketing recommendation quantitative model is obtained by training a basic quantitative model with label information and historical transaction data of different customers, the label information is obtained by extracting key information from historical call records and historical objective basic information, the historical call records and historical objective basic information are obtained from a database, and the marketing recommendation plan includes multiple labels and marketing information corresponding to the labels.

[0089] Optionally, the device further comprises:

[0090] The training module is used for obtaining historical call records and historical objective basic information of different customers from the database before the acquisition module obtains the historical customer information in the database; extracting label information corresponding to key information in the historical call records and historical objective basic information; training the basic quantitative model through the label information and the historical transaction data of the target customers to obtain the marketing recommendation quantitative model, wherein the historical transaction data includes the historical transaction results of different customers and the corresponding transaction records.

[0091] Optionally, the device further comprises:

[0092] The summarizing module is used to summarize the call records of different customers obtained from multiple channels and store them in the database before the training module obtains the historical call records and historical objective basic information of different customers from the database.

[0093] Optional, recommended modules specifically for:

[0094] Through the marketing recommendation quantitative model, historical customer information is identified to obtain portrait information and user stratification information of different customers; through the marketing recommendation quantitative model, according to the current marketing scenario, portrait information and user stratification information, target customers are selected and marketing recommendation plans are generated, among which the marketing recommendation plan also includes standard operating procedures.

[0095] Optionally, the device further comprises:

[0096] The display module is used for the recommendation module to identify historical customer information through a preset marketing recommendation quantitative model, obtain the marketing recommendation plan for the target customer, select the marketing channel corresponding to the marketing recommendation plan, and provide a marketing panel for the marketing personnel, wherein the marketing panel includes a marketing label and corresponding marketing content.

[0097] Optionally, the device further comprises:

[0098] The optimization module is used for obtaining the marketing personnel's scoring and recommendation level of the marketing recommendation quantitative model after the recommendation module identifies historical customer information through a preset marketing recommendation quantitative model and obtains the marketing recommendation plan for the target customer; and adjusts and optimizes the marketing recommendation quantitative model according to the scoring and recommendation level.

[0099] Optional, recommended modules specifically for:

[0100] Through the recommendation algorithm in the marketing recommendation quantitative model, combined with the current marketing scenario, a marketing strategy is formulated for marketers. The marketing strategy includes at least one of marketing frequency, marketing channel, marketing time and specific marketing content.

[0101] Please refer to Figure 3 3 is a schematic block diagram of a device for recommending marketing plans provided in an embodiment of the present application. The device may include a memory 310 and a processor 320. Optionally, the device may also include: a communication interface 330 and a communication bus 340. The device is similar to the above-mentioned Figure 1 The method embodiment corresponds to and can be executed Figure 1 The various steps involved in the method embodiment and the specific functions of the device can be found in the description below.

[0102] Specifically, the memory 310 is used to store computer-readable instructions.

[0103] Processor 320, for processing readable instructions stored in the memory, capable of executing Figure 1 The steps in the method.

[0104] The communication interface 330 is used for signaling or data communication with other node devices, for example, for communication with a server or a terminal, or for communication with other device nodes, but the embodiments of the present application are not limited thereto.

[0105] The communication bus 340 is used to realize direct connection and communication among the above components.

[0106] The communication interface 330 of the device in the embodiment of the present application is used to communicate signals or data with other node devices. The memory 310 can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The memory 310 can also be at least one storage device located away from the aforementioned processor. The memory 310 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 320, the electronic device executes the aforementioned Figure 1 The method process shown. The processor 320 can be used on the device 200 and used to perform the functions in the present application. Exemplarily, the above-mentioned processor 320 can be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, and the embodiments of the present application are not limited thereto.

[0107] The embodiment of the present application also provides a readable storage medium, when the computer program is executed by a processor, Figure 1 The method process in the method embodiment shown is executed by the electronic device.

[0108] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method, and will not be described in detail here.

[0109] In summary, the embodiments of the present application provide a method, device, equipment and readable storage medium for recommending a marketing plan, the method comprising: obtaining historical customer information from a database, wherein the historical customer information comprises: identification information of different customers, subjective call data and objective basic data; identifying historical customer information through a preset marketing recommendation quantitative model to obtain a marketing recommendation plan for the target customer, wherein the marketing recommendation quantitative model is obtained by training a basic quantitative model with label information and historical transaction data of different customers, the label information is obtained by extracting key information from historical call records and historical objective basic information, the historical call records and historical objective basic information are obtained from a database, and the marketing recommendation plan comprises multiple labels and marketing information corresponding to the labels. This method can achieve the effect of reasonable recommendation of marketing plans and refined intelligent operations.

[0110] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0111] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0112] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: 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.

[0113] The above description is only an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0114] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0115] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. A method for recommending a marketing plan, characterized in that: include: Acquire historical customer information in a database, wherein the historical customer information includes: identification information, subjective call data, and objective basic data of different customers; The historical customer information is identified through a preset marketing recommendation quantitative model to obtain a marketing recommendation plan for the target customer, wherein the marketing recommendation quantitative model is obtained by training a basic quantitative model with label information and historical transaction data of different customers, the label information is obtained by extracting key information from historical call records and historical objective basic information, the historical call records and the historical objective basic information are obtained from a database, and the marketing recommendation plan includes multiple labels and marketing information corresponding to the labels.

2. The method according to claim 1, characterized in that Before obtaining the historical customer information in the database, the method further includes: Acquire the historical call records and the historical objective basic information of the different customers from the database; Extracting label information corresponding to key information in the historical call records and the historical objective basic information; The basic quantitative model is trained by using the label information and the historical transaction data of the target customers to obtain the marketing recommendation quantitative model, wherein the historical transaction data includes the historical transaction results of the different customers and the corresponding transaction records.

3. The method according to claim 2, characterized in that Before acquiring the historical call records and the historical objective basic information of the different customers from the database, the method further includes: The call records of different customers obtained through multiple channels are aggregated and stored in the database.

4. The method according to any one of claims 1 to 3, characterized in that: The method of identifying the historical customer information through a preset marketing recommendation quantitative model to obtain a marketing recommendation plan for the target customer includes: Identify the historical customer information through the marketing recommendation quantitative model to obtain the portrait information and user stratification information of different customers; The marketing recommendation quantitative model selects the target customer and generates the marketing recommendation plan according to the current marketing scenario, the portrait information and the user stratification information, wherein the marketing recommendation plan also includes a standard operating procedure.

5. The method according to any one of claims 1 to 3, characterized in that: After identifying the historical customer information through the preset marketing recommendation quantitative model and obtaining the marketing recommendation plan for the target customer, the method further includes: Selecting a marketing channel corresponding to the marketing recommendation plan provides a marketing panel for the marketing personnel, wherein the marketing panel includes a marketing tag and corresponding marketing content.

6. The method according to any one of claims 1 to 3, characterized in that: After identifying the historical customer information through the preset marketing recommendation quantitative model and obtaining the marketing recommendation plan for the target customer, the method further includes: Obtaining the marketing personnel's scoring and recommendation level for the marketing recommendation quantitative model; The marketing recommendation quantitative model is adjusted and optimized according to the scoring situation and the recommendation degree.

7. The method according to any one of claims 1 to 3, characterized in that: The method of identifying the historical customer information through a preset marketing recommendation quantitative model to obtain a marketing recommendation plan for the target customer includes: Through the recommendation algorithm in the marketing recommendation quantitative model, combined with the current marketing scenario, a marketing strategy is formulated for the marketing personnel, and the marketing strategy includes at least one of marketing frequency, marketing channel, marketing time and specific marketing content.

8. A device for recommending marketing plans, characterized in that: include: An acquisition module, used to acquire historical customer information in a database, wherein the historical customer information includes: identification information, subjective call data and objective basic data of different customers; A recommendation module is used to identify the historical customer information through a preset marketing recommendation quantitative model to obtain a marketing recommendation plan for the target customer, wherein the marketing recommendation quantitative model is obtained by training a basic quantitative model with label information and historical transaction data of different customers, the label information is obtained by extracting key information from historical call records and historical objective basic information, the historical call records and the historical objective basic information are obtained from a database, and the marketing recommendation plan includes multiple labels and marketing information corresponding to the labels.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the method according to any one of claims 1 to 7 are executed.

10. A computer-readable storage medium, characterized in that: include: A computer program, when the computer program is run on a computer, causes the computer to execute the method according to any one of claims 1 to 7.

Images