Marketing verbal skill generation method and device based on sales crown data

Abstract

The invention provides a marketing verbal skill generation method and device based on sales crown data, and the method comprises the steps: providing initial marketing verbal skill information through an AI large model, and carrying out a marketing activity according to the initial marketing verbal skill information to collect marketing data; counting the marketing data to determine crown sales data of which the marketing performance ranks in the top within specified time; obtaining a marketing verbal skill used by a salesman corresponding to the sales crown data in actual marketing, and comparing the marketing verbal skill with the initial marketing verbal skill information to determine distinguishing features in the marketing verbal skill information; and training and updating the AI large model based on the distinguishing features to generate second marketing verbal skill information. According to the method, crown sales data and AI large model intelligent prediction can be fused, and accurate generation and optimization of marketing verbal skills are realized.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and in particular to a method and device for generating marketing scripts based on sales champion data. Background Art

[0002] In the current business environment, the success of marketing activities often depends on multiple factors, among which the accuracy and personalization of marketing language play a vital role. Traditional marketing language often relies on the personal experience and intuition of sales staff, lacks scientific data support and intelligent optimization methods, resulting in uneven marketing results and difficulty in achieving the best state.

[0003] With the rapid development of artificial intelligence technology, AI big models are increasingly used in various fields, and their application in the marketing field is gradually gaining attention. Through big data analysis and machine learning algorithms, AI big models can deeply explore users' behavior habits, preferences and needs, thereby generating more accurate and personalized marketing words. However, most of the AI ​​marketing tools on the market currently remain at the initial level of intelligent recommendation and automatic generation, lacking deep integration with actual combat experience, resulting in the generated marketing words often being too mechanical and templated, lacking authenticity and persuasiveness. Summary of the invention

[0004] In view of this, the embodiments of the present application provide a method and device for generating marketing scripts based on top-selling data, which can integrate top-selling data with intelligent prediction of AI big models to achieve accurate generation and optimization of marketing scripts.

[0005] The technical solution of the embodiment of the present application is implemented as follows:

[0006] In a first aspect, an embodiment of the present application provides a method for generating marketing words based on sales champion data, wherein a first marketing words information is provided through an AI big model and marketing is performed based on the first marketing words information to obtain marketing data; the method comprises:

[0007] The marketing data is statistically analyzed to obtain the top-selling data; wherein the top-selling data represents the sales data of marketing performance in a specific ranking within a specified time;

[0008] Acquire actual marketing speech information of the salesperson corresponding to the top-selling data when conducting marketing based on the first marketing speech information;

[0009] Determine distinguishing feature information based on the actual marketing speech information and the first marketing speech information; wherein the distinguishing feature information represents the content that distinguishes the actual marketing speech information from the first marketing speech information;

[0010] The AI ​​big model is trained and updated based on the distinguishing feature information, and the second marketing speech information is provided through the updated AI big model.

[0011] In a second aspect, an embodiment of the present application further provides a device for generating marketing speech based on sales champion data, which provides first marketing speech information through an AI big model and performs marketing based on the first marketing speech information to obtain marketing data; the device includes:

[0012] A statistical module, used to collect statistics on the marketing data to obtain the top-selling data; wherein the top-selling data represents the sales data of marketing performance in a specific ranking within a specified time;

[0013] An acquisition module, used to acquire actual marketing speech information of the salesperson corresponding to the top-selling data when conducting marketing based on the first marketing speech information;

[0014] A determination module, configured to determine distinguishing feature information based on the actual marketing speech information and the first marketing speech information; wherein the distinguishing feature information represents the content that distinguishes the actual marketing speech information from the first marketing speech information;

[0015] An updating module is used to train and update the AI ​​big model based on the distinguishing feature information, and provide second marketing speech information through the updated AI big model.

[0016] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium through the bus, and the processor executes the machine-readable instructions to execute the marketing script generation method based on sales champion data as described in any one of the first aspects.

[0017] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for generating marketing scripts based on sales champion data as described in any one of the first aspects is executed.

[0018] The embodiments of the present application have the following beneficial effects:

[0019] By using the AI ​​big model to initially generate marketing words, and then deeply analyzing the actual marketing words in the sales crown data, successful communication skills and strategies are accurately extracted through comparison and optimization. This process not only achieves a high degree of automation and intelligence, greatly reduces manual intervention, improves work efficiency, but also ensures the timeliness and pertinence of marketing words. At the same time, the embodiment of the present application tailors unique marketing words for each customer through the generation of user portraits and family portraits, greatly enhancing customer experience and satisfaction. In addition, the embodiment of the present application also has the ability of continuous optimization and iteration. By continuously collecting sales crown data and feedback, the AI ​​big model is trained and updated to keep it competitive. This precise marketing language and personalized marketing strategy not only improves customers' willingness to buy and conversion rate, promotes the improvement of sales performance, but also helps companies better adapt to market changes and customer needs, expand market share, and enhance brand influence. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments 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.

[0021] Figure 1 It is a flowchart of steps S101-S104 provided in an embodiment of the present application;

[0022] Figure 2 It is a flowchart of steps S201-S203 provided in an embodiment of the present application;

[0023] Figure 3 It is a flowchart of steps S301-S302 provided in an embodiment of the present application;

[0024] Figure 4 It is a flowchart of steps S401-S404 provided in an embodiment of the present application;

[0025] Figure 5 It is a flowchart of steps S501-S502 provided in an embodiment of the present application;

[0026] Figure 6 It is a structural schematic diagram of a device for generating marketing words based on sales champion data provided in an embodiment of the present application;

[0027] Figure 7 It is a schematic diagram of the composition structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0028] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0029] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0030] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various 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.

[0031] In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0032] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0033] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0034] See also Figure 1 , Figure 1This is a flow chart of steps S101-S104 of the method for generating marketing words based on sales champion data provided in an embodiment of the present application, which will be combined with Figure 1 Steps S101-S104 are shown for explanation.

[0035] In step S101, the marketing data is statistically analyzed to obtain the top-selling data; wherein the top-selling data represents sales data with marketing performance ranking in a specific ranking within a specified time.

[0036] In step S102, actual marketing speech information of the salesperson corresponding to the top-selling data when conducting marketing based on the first marketing speech information is obtained.

[0037] In step S103, distinguishing feature information is determined based on the actual marketing speech information and the first marketing speech information; wherein the distinguishing feature information represents the content that distinguishes the actual marketing speech information from the first marketing speech information.

[0038] In step S104, the AI ​​big model is trained and updated based on the distinguishing feature information, and the second marketing speech information is provided through the updated AI big model.

[0039] Here, first, preliminary marketing words information (first marketing words information) is provided through the AI ​​big model. These preliminary marketing words are used to carry out actual marketing activities and collect corresponding marketing data. These marketing data are statistically analyzed to identify sales data with marketing performance in a specific ranking (such as sales champion) within a specified time period. These data are sales champion data.

[0040] Next, obtain the marketing words information actually used by the sales staff in the marketing process corresponding to these sales champion data. These actual marketing words information have been verified to be effective through practice, so they have a high reference value. Compare the first marketing words information (the words originally provided by the AI ​​big model) and the actual marketing words information of the sales champion to find out the distinguishing feature information between the two. These distinguishing feature information may be the key factor leading to differences in sales performance.

[0041] Based on these distinguishing feature information, the AI ​​big model is trained and optimized. This includes adjusting model parameters, learning algorithms, etc., so that the model can better understand and generate effective marketing words. After training, the AI ​​big model is updated so that it can provide new and more optimized marketing words information (second marketing words information).

[0042] The above method can form a cyclical iterative process. In each iteration, the AI ​​model will be updated and optimized based on the new sales champion data and distinguishing feature information, thereby continuously improving the effectiveness and pertinence of marketing tactics.

[0043] In some embodiments, see Figure 2 , Figure 2 It is a flowchart of steps S201-S203 provided in an embodiment of the present application. The statistics of the marketing data to obtain the top-selling data can be achieved through steps S201-S203, which will be explained in combination with each step.

[0044] In step S201, the marketing data is cleaned and preprocessed.

[0045] In step S202, the performance indicator and the time range are determined, and ranking data under business requirements are statistically generated according to the performance indicator and the time range.

[0046] In step S203, the specifically scheduled sales data is taken from the ranking data as the top-selling data.

[0047] Marketing data often contains various noises and outliers, such as duplicate data, missing data, and erroneous data. Before counting the sales data, the data needs to be cleaned to ensure the accuracy and consistency of the data. Preprocessing steps may include data format conversion, data standardization, data normalization, etc., for subsequent analysis and statistics. Performance indicators are key indicators for measuring sales performance of sales personnel, such as sales volume, sales volume, customer satisfaction, etc. According to business needs, select appropriate performance indicators for statistics. Time range refers to the time period for statistical sales performance, such as one month, one quarter, one year, etc. According to business needs and time requirements, determine the appropriate time range for statistics. After determining the performance indicators and time range, the marketing data is counted according to these conditions to obtain the performance ranking data of the sales personnel. Ranking data usually includes information such as the name of the salesperson, performance indicator value, and ranking.

[0048] From the ranking data, take the sales data of a specific ranking as the top-selling data according to business needs. For example, you can take the sales data ranked first as the top-selling data, or take the sales data of the top few rankings as the top-selling data set.

[0049] In some embodiments, see Figure 3 , Figure 3 It is a flow chart of steps S301-S302 provided in an embodiment of the present application. The actual marketing speech information of the salesperson corresponding to the sales champion data when conducting marketing based on the first marketing speech information can be obtained through steps S301-S302, which will be explained in combination with each step.

[0050] In step S301, for the salesperson corresponding to the top-selling data, the communication voice information of the salesperson during the marketing process is collected.

[0051] In step S302, the communication voice information is converted to obtain communication text information, and the communication text information is used as the actual marketing speech information.

[0052] Here, for the sales personnel corresponding to the top-selling data, their communication voice information during the marketing process is collected. This voice information may come from various scenarios such as telephone marketing, video conferencing, customer interviews, etc. The voice information can be collected by recording equipment, telephone recording systems, video conference records, etc. Ensure that the collected voice information is clear and complete, and complies with the requirements of privacy policies and laws and regulations. Convert the collected communication voice information into readable communication text information. The converted communication text information is used as the actual marketing speech information of the sales personnel. This text information reflects the language and expression actually used by the sales personnel in the marketing process. The actual marketing speech information can be used for subsequent analysis, comparison and optimization. By comparing the first marketing speech information with the actual marketing speech information, effective marketing speech elements and strategies can be identified, and then the AI ​​big model can be trained and optimized.

[0053] In some embodiments, see Figure 4 , Figure 4 It is a flowchart of steps S401-S404 provided in an embodiment of the present application. The determination of distinguishing feature information based on the actual marketing speech information and the first marketing speech information can be achieved through steps S401-S404, which will be explained in combination with each step.

[0054] In step S401, the actual marketing speech information is compared with the first marketing speech information to obtain first different contents in terms of content, structure and expression.

[0055] In step S402, the interactive strategy used in the actual marketing speech is determined, and compared with the interactive strategy in the first marketing speech information to determine the second difference content.

[0056] In step S403, feedback from sales staff and customers is collected and used as a reference factor.

[0057] In step S404, the distinguishing feature information is determined based on the first distinguishing content, the second distinguishing content, and the reference factor.

[0058] Here, the actual marketing speech information is compared with the first marketing speech information, and the content of the comparison may include the specific content, structural arrangement and expression of the speech. Through the comparison, the similarities and differences between the two in content can be identified, such as the use of keywords, the presentation of information, etc. These similarities and differences constitute the first difference content.

[0059] Determine the interactive strategies used in the actual marketing speech, such as questioning methods, response techniques, emotional guidance, etc. Compare these interactive strategies with the interactive strategies in the first marketing speech information, and analyze the differences and effects of the two strategies. These differences constitute the second distinction content.

[0060] In addition to directly comparing the content of the sales pitch, it is also necessary to collect feedback from sales staff and customers. Sales staff can provide information on the effectiveness of the sales pitch, customer reactions, etc.; customers can provide feedback on the acceptance and satisfaction of the sales pitch. These feedbacks, as reference factors, help to more comprehensively understand the actual effectiveness of the sales pitch and provide an important basis for determining distinguishing characteristic information.

[0061] Based on the first distinguishing content, the second distinguishing content and reference factors, a comprehensive analysis and judgment is conducted to determine which distinguishing feature information plays a key role in improving marketing effectiveness, such as specific expressions, effective interaction strategies, etc. These distinguishing feature information will be used for subsequent training and optimization of the AI ​​big model to improve the effectiveness and pertinence of marketing techniques.

[0062] In some embodiments, the AI ​​big model queries the user's family information by receiving a user identifier representing a user portrait, generates a corresponding family portrait through the family information, and generates first marketing speech information based on the family portrait; wherein the first marketing speech information includes marketing speech for each family member of the user.

[0063] Here, the AI ​​big model first receives a user identifier that represents the user portrait. This identifier may be the user's ID, mobile phone number, email address, etc., which is used to uniquely identify a user. Using the received user identifier, the AI ​​big model queries the user's family information in the database. This information may include the name, age, gender, occupation, hobbies, consumption habits, etc. of family members. Based on the queried family information, the AI ​​big model generates a corresponding family portrait. A family portrait is a data model that integrates various characteristics of family members, which reflects the overall situation and needs of family members. The AI ​​big model generates the first marketing speech information based on the family portrait. This process may involve steps such as the selection of speech templates, the replacement of keywords, and the insertion of personalized information. Importantly, the first marketing speech information is not only for the user himself, but also includes marketing speech for each family member of the user. This requires the AI ​​big model to understand and analyze the relationship and demand differences between family members in order to provide more accurate marketing information.

[0064] In some embodiments, see Figure 5 , Figure 5It is a flowchart of steps S501-S502 provided in an embodiment of the present application. The method also includes the implementation of steps S501-S502, which will be explained in combination with each step.

[0065] In step S501, a marketing activity is determined based on business needs, and marketing features are extracted from the marketing activity; wherein the marketing features represent features associated with the marketing activity.

[0066] In step S502, the AI ​​big model is trained and updated based on the marketing features.

[0067] Determine the marketing activities to be carried out according to business needs. These activities may include promotional activities, new product launches, member day activities, etc., which are aimed at attracting user attention, increasing sales or enhancing brand influence. Extract the features associated with the activities from the determined marketing activities, which constitute the marketing feature set. Marketing features may include the theme, time, target user group, discount strength, marketing channels, etc. of the activity. The process of extracting marketing features requires an in-depth understanding of the core elements and goals of the marketing activities to ensure that the extracted features can accurately reflect the characteristics and needs of the activities. Train the AI ​​big model based on the extracted marketing features. The training process may include steps such as data preprocessing, model selection, parameter adjustment, and performance evaluation. Through training, the AI ​​big model can learn the correlation between marketing features and marketing effects, thereby generating more accurate and effective marketing words. After training, update the AI ​​big model so that it can better adapt to business needs in actual applications.

[0068] In some embodiments, the AI ​​big model automatically terminates its dependency on the marketing feature after the marketing campaign ends.

[0069] Here, after the marketing activity is completed according to the predetermined plan or goal, it enters the end stage. This means that the duration of the activity has been reached, or the goal of the activity (such as sales, attention, etc.) has been achieved. After monitoring the end of the marketing activity, the AI ​​big model automatically terminates the dependency on the previously extracted marketing features. This means that the model will no longer generate marketing words or make other decisions based on these features. This step involves adjusting the internal logic of the model, such as deleting or disabling the algorithm modules and weight parameters related to these features. After terminating the dependency on marketing features, the AI ​​big model may need further adjustments and optimizations. This may include re-evaluating the performance of the model, updating the training data of the model, introducing new features, etc. These adjustments and optimizations are designed to ensure that the model can continue to adapt to changes in business needs and market environment, and maintain its competitiveness and effectiveness.

[0070] In summary, the embodiments of the present application have the following beneficial effects:

[0071] By using the AI ​​big model to initially generate marketing words, and then deeply analyzing the actual marketing words in the sales crown data, successful communication skills and strategies are accurately extracted through comparison and optimization. This process not only achieves a high degree of automation and intelligence, greatly reduces manual intervention, improves work efficiency, but also ensures the timeliness and pertinence of marketing words. At the same time, the embodiment of the present application tailors unique marketing words for each customer through the generation of user portraits and family portraits, greatly enhancing customer experience and satisfaction. In addition, the embodiment of the present application also has the ability of continuous optimization and iteration. By continuously collecting sales crown data and feedback, the AI ​​big model is trained and updated to keep it competitive. This precise marketing language and personalized marketing strategy not only improves customers' willingness to buy and conversion rate, promotes the improvement of sales performance, but also helps companies better adapt to market changes and customer needs, expand market share, and enhance brand influence.

[0072] Based on the same inventive concept, an embodiment of the present application also provides a marketing script generation device based on top-selling data corresponding to the marketing script generation method based on top-selling data in the first embodiment. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the above-mentioned marketing script generation method based on top-selling data, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0073] like Figure 6 As shown, Figure 6 1 is a schematic diagram of the structure of a marketing speech generation device 600 based on sales champion data provided in an embodiment of the present application. The first marketing speech information is provided by an AI big model and marketing is performed based on the first marketing speech information to obtain marketing data; the marketing speech generation device 600 based on sales champion data includes:

[0074] A statistics module 601 is used to collect statistics on the marketing data to obtain the top-selling data; wherein the top-selling data represents the sales data of marketing performance in a specific ranking within a specified time;

[0075] An acquisition module 602 is used to acquire actual marketing speech information of the salesperson corresponding to the top-selling data when performing marketing based on the first marketing speech information;

[0076] A determination module 603 is used to determine distinguishing feature information based on the actual marketing speech information and the first marketing speech information; wherein the distinguishing feature information represents the content that distinguishes the actual marketing speech information from the first marketing speech information;

[0077] The updating module 604 is used to train and update the AI ​​big model based on the distinguishing feature information, and provide the second marketing speech information through the updated AI big model.

[0078] Those skilled in the art should understand that Figure 6 The implementation functions of each unit in the marketing speech generation device 600 based on sales champion data can be understood by referring to the relevant description of the marketing speech generation method based on sales champion data mentioned above. Figure 6 The functions of each unit in the marketing speech generation device 600 based on sales champion data shown can be implemented by a program running on a processor, or can be implemented by a specific logic circuit.

[0079] In a possible implementation, the statistical module 601 collects statistics on the marketing data to obtain the top-selling data, including:

[0080] Performing data cleaning and preprocessing on the marketing data;

[0081] Determine performance indicators and time ranges, and compile ranking data based on business needs according to the performance indicators and time ranges;

[0082] The specifically scheduled sales data is taken from the ranking data as the top-selling data.

[0083] In a possible implementation, the acquisition module 602 acquires actual marketing speech information of the salesperson corresponding to the top-selling data when performing marketing based on the first marketing speech information, including:

[0084] For the salesperson corresponding to the top-selling data, collect the communication voice information of the salesperson during the marketing process;

[0085] The communication voice information is converted to obtain communication text information, and the communication text information is used as the actual marketing speech information.

[0086] In a possible implementation, the determination module 603 determines the distinguishing feature information based on the actual marketing speech information and the first marketing speech information, including:

[0087] Comparing the actual marketing speech information with the first marketing speech information to obtain first different contents in terms of content, structure, and expression;

[0088] Determine the interactive strategy used in the actual marketing speech, and compare it with the interactive strategy in the first marketing speech information to determine the second difference content;

[0089] Gather feedback from sales staff and customers and factor in said feedback;

[0090] The distinguishing feature information is determined based on the first distinguishing content, the second distinguishing content, and the reference factor.

[0091] In one possible implementation, the AI ​​big model queries the user's family information by receiving a user identifier representing a user portrait, generates a corresponding family portrait through the family information, and generates first marketing speech information based on the family portrait; wherein the first marketing speech information includes marketing speech for each family member of the user.

[0092] In a possible implementation, the updating module 604 further includes:

[0093] Determine a marketing activity based on business needs, and extract marketing features from the marketing activity; wherein the marketing features represent features associated with the marketing activity;

[0094] The AI ​​big model is trained and updated based on the marketing characteristics.

[0095] In a possible implementation, the AI ​​big model automatically terminates its dependency on the marketing feature after the marketing activity ends.

[0096] The above-mentioned marketing speech generation device based on sales crown data generates marketing speech preliminarily by using the AI ​​big model, and then deeply analyzes the actual marketing speech in the sales crown data, and accurately extracts successful communication skills and strategies through comparison and optimization. This process not only achieves high automation and intelligence, greatly reduces manual intervention, improves work efficiency, but also ensures the timeliness and pertinence of marketing speech. At the same time, the embodiment of the present application tailors unique marketing speech for each customer through the generation of user portraits and family portraits, greatly enhancing customer experience and satisfaction. In addition, the embodiment of the present application also has the ability of continuous optimization and iteration. By continuously collecting sales crown data and feedback, the AI ​​big model is trained and updated to keep it competitive. This precise marketing speech and personalized marketing strategy not only improves customers' willingness to buy and conversion rate, promotes the improvement of sales performance, but also helps companies better adapt to market changes and customer needs, expand market share, and enhance brand influence.

[0097] like Figure 7 As shown, Figure 7 The present invention provides a schematic diagram of the structure of an electronic device 700, wherein the electronic device 700 includes:

[0098] A processor 701, a storage medium 702 and a bus 703, wherein the storage medium 702 stores machine-readable instructions executable by the processor 701. When the electronic device 700 is running, the processor 701 communicates with the storage medium 702 via the bus 703, and the processor 701 executes the machine-readable instructions to perform the steps of the method for generating marketing scripts based on sales champion data described in the embodiment of the present application.

[0099] In actual application, the components in the electronic device 700 are coupled together via the bus 703. It is understood that the bus 703 is used to realize the connection and communication between these components. In addition to the data bus, the bus 703 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, Figure 7 Various buses are labeled as bus 703.

[0100] The above-mentioned electronic device preliminarily generates marketing words by using the AI ​​big model, and then deeply analyzes the actual marketing words in the sales crown data, and accurately extracts successful communication skills and strategies through comparison and optimization. This process not only achieves a high degree of automation and intelligence, greatly reduces manual intervention, improves work efficiency, but also ensures the timeliness and pertinence of marketing words. At the same time, the embodiment of the present application tailors unique marketing words for each customer through the generation of user portraits and family portraits, greatly enhancing customer experience and satisfaction. In addition, the embodiment of the present application also has the ability of continuous optimization and iteration. By continuously collecting sales crown data and feedback, the AI ​​big model is trained and updated to keep it competitive. This precise marketing words and personalized marketing strategy not only improve customers' willingness to buy and conversion rate, promote the improvement of sales performance, but also help companies better adapt to market changes and customer needs, expand market share, and enhance brand influence.

[0101] The embodiment of the present application also provides a computer-readable storage medium, which stores executable instructions. When the executable instructions are executed by at least one processor 701, the method for generating marketing scripts based on top-selling data described in the embodiment of the present application is implemented.

[0102] In some embodiments, the storage medium can be a magnetic random access memory (FRAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic surface storage, an optical disk, or a compact disc read-only memory (CDROM); it can also be various devices including one or any combination of the above memories.

[0103] In some embodiments, executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0104] As an example, executable instructions may, but do not necessarily, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, for example, in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (for example, files storing one or more modules, subroutines, or code portions).

[0105] By way of example, executable instructions may be deployed to be executed on one computing device, or on multiple computing devices located at one site, or on multiple computing devices distributed across multiple sites and interconnected by a communication network.

[0106] The above-mentioned computer-readable storage medium preliminarily generates marketing words by using the AI ​​big model, and then deeply analyzes the actual marketing words in the sales crown data, and accurately extracts successful communication skills and strategies through comparison and optimization. This process not only achieves high automation and intelligence, greatly reduces manual intervention, improves work efficiency, but also ensures the timeliness and pertinence of marketing words. At the same time, the embodiment of the present application tailors unique marketing words for each customer through the generation of user portraits and family portraits, greatly enhancing customer experience and satisfaction. In addition, the embodiment of the present application also has the ability of continuous optimization and iteration. By continuously collecting sales crown data and feedback, the AI ​​big model is trained and updated to keep it competitive. This precise marketing words and personalized marketing strategy not only improve customers' willingness to buy and conversion rate, promote the improvement of sales performance, but also help companies better adapt to market changes and customer needs, expand market share, and enhance brand influence.

[0107] In the several embodiments provided in the present application, it should be understood that the disclosed methods and electronic devices can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0108] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0109] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0110] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a platform server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks, or optical disks.

[0111] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the 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.

Claims

1. A method for generating marketing words based on sales champion data, characterized in that: Providing first marketing speech information through an AI big model and performing marketing based on the first marketing speech information to obtain marketing data; the method includes: The marketing data is statistically analyzed to obtain the top-selling data; wherein the top-selling data represents the sales data of marketing performance in a specific ranking within a specified time; Acquire actual marketing speech information of the salesperson corresponding to the top-selling data when conducting marketing based on the first marketing speech information; Determine distinguishing feature information based on the actual marketing speech information and the first marketing speech information; wherein the distinguishing feature information represents the content that distinguishes the actual marketing speech information from the first marketing speech information; The AI ​​big model is trained and updated based on the distinguishing feature information, and the second marketing speech information is provided through the updated AI big model.

2. The method according to claim 1, characterized in that The step of obtaining the top-selling data by collecting statistics on the marketing data includes: Performing data cleaning and preprocessing on the marketing data; Determine performance indicators and time ranges, and compile ranking data based on business needs according to the performance indicators and time ranges; The specifically scheduled sales data is taken from the ranking data as the top-selling data.

3. The method according to claim 1, characterized in that The obtaining of actual marketing speech information of the salesperson corresponding to the top-selling data when conducting marketing based on the first marketing speech information includes: For the salesperson corresponding to the top-selling data, collect the communication voice information of the salesperson during the marketing process; The communication voice information is converted to obtain communication text information, and the communication text information is used as the actual marketing speech information.

4. The method according to claim 1, characterized in that: The determining of distinguishing characteristic information based on the actual marketing speech information and the first marketing speech information includes: Comparing the actual marketing speech information with the first marketing speech information to obtain first different contents in terms of content, structure, and expression; Determine the interactive strategy used in the actual marketing speech, and compare it with the interactive strategy in the first marketing speech information to determine the second difference content; Gather feedback from sales staff and customers and factor in said feedback; The distinguishing feature information is determined based on the first distinguishing content, the second distinguishing content, and the reference factor.

5. The method according to claim 1, characterized in that The AI ​​big model queries the user's family information by receiving a user identifier representing the user portrait, generates a corresponding family portrait through the family information, and generates first marketing speech information based on the family portrait; wherein the first marketing speech information includes marketing speech for each family member of the user.

6. The method according to claim 1, characterized in that The method further comprises: Determine a marketing activity based on business needs, and extract marketing features from the marketing activity; wherein the marketing features represent features associated with the marketing activity; The AI ​​big model is trained and updated based on the marketing characteristics.

7. The method according to claim 6, characterized in that The AI ​​big model automatically terminates its dependency on the marketing feature after the marketing activity ends.

8. A device for generating marketing words based on sales champion data, characterized in that: Providing first marketing speech information through an AI big model and performing marketing based on the first marketing speech information to obtain marketing data; the device includes: A statistical module, used to collect statistics on the marketing data to obtain the top-selling data; wherein the top-selling data represents the sales data of marketing performance in a specific ranking within a specified time; An acquisition module, used to acquire actual marketing speech information of the salesperson corresponding to the top-selling data when conducting marketing based on the first marketing speech information; A determination module, configured to determine distinguishing feature information based on the actual marketing speech information and the first marketing speech information; wherein the distinguishing feature information represents the content that distinguishes the actual marketing speech information from the first marketing speech information; An updating module is used to train and update the AI ​​big model based on the distinguishing feature information, and provide second marketing speech information through the updated AI big model.

9. An electronic device, characterized in that: include: A processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to execute the method for generating marketing scripts based on sales champion data as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for generating marketing words based on sales champion data as described in any one of claims 1 to 7 is executed.

Images