CN118350848A - Novel retail intelligent analysis and accurate marketing system based on AI - Google Patents
Novel retail intelligent analysis and accurate marketing system based on AI Download PDFInfo
- Publication number
- CN118350848A CN118350848A CN202410497492.3A CN202410497492A CN118350848A CN 118350848 A CN118350848 A CN 118350848A CN 202410497492 A CN202410497492 A CN 202410497492A CN 118350848 A CN118350848 A CN 118350848A
- Authority
- CN
- China
- Prior art keywords
- sales
- sales data
- data
- analysis
- analyzed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 96
- 230000006872 improvement Effects 0.000 claims abstract description 30
- 238000007405 data analysis Methods 0.000 claims abstract description 28
- 238000012545 processing Methods 0.000 claims abstract description 18
- 238000013528 artificial neural network Methods 0.000 claims abstract description 14
- 238000012847 principal component analysis method Methods 0.000 claims abstract description 14
- 238000012937 correction Methods 0.000 claims description 24
- 230000000052 comparative effect Effects 0.000 claims description 17
- 238000000034 method Methods 0.000 claims description 17
- 238000003062 neural network model Methods 0.000 claims description 17
- 238000007621 cluster analysis Methods 0.000 claims description 16
- 238000011156 evaluation Methods 0.000 claims description 14
- 238000004088 simulation Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000001186 cumulative effect Effects 0.000 claims description 8
- 238000004519 manufacturing process Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 230000000737 periodic effect Effects 0.000 claims description 6
- 238000005315 distribution function Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000012417 linear regression Methods 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 238000013480 data collection Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 11
- 230000006870 function Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of marketing, and provides a novel intelligent retail analysis and accurate marketing system based on AI, which comprises: the to-be-analyzed sales data acquisition module is used for acquiring, integrating and processing the multi-platform product sales data put on the market to obtain to-be-analyzed sales data; the to-be-analyzed sales data analysis module is used for correcting the first comparison sales data predicted and obtained by the sales data prediction model to obtain second comparison sales data, analyzing the to-be-analyzed sales data and the second comparison sales data by using a principal component analysis method, and sending an analysis result to the marketing strategy adjustment module; and the marketing strategy adjustment module is used for predicting the sales index improvement achievement rate by utilizing a neural network prediction model according to the analysis result and adjusting the initial marketing strategy according to the prediction result. The invention can improve the quality of new retail intelligent analysis and provide targeted scientific decision support for accurate marketing.
Description
Technical Field
The invention relates to the technical field of marketing, in particular to a novel retail intelligent analysis and accurate marketing system based on AI.
Background
The traditional retail mode takes an off-line scene as a main part, a user selects and purchases commodities in an entity store, the importance of the on-line consumption scene is increasingly remarkable along with the change of the consumption habit of a new generation of consumer groups under the condition of the digital wave, and the new retail mode becomes an important mode of product sales and products are sold through a network platform;
In the new retail mode, products can be intelligently recommended to users by utilizing big data analysis and recommendation technology according to the characteristics of new retail, the client needs are guided, the user experience is improved, and therefore targeted marketing is achieved, marketing cost is reduced, and income is improved.
The analysis of sales data in the current new retail sales is not intelligent enough, so that the analysis of sales data is not timely and accurate enough, the adjustment of the existing sales strategy is affected, the effective and accurate marketing can not be realized, and the achievement of sales indexes is affected.
The application document with the application number of CN202111451835.5 discloses a new retail terminal sales prediction method based on machine learning and advanced classification, which adopts the following technical scheme: 1. and establishing a perfect early warning system. 2. And acquiring effective retail customer basic information and sales data. 3. The retail sales data is cleaned and multi-dimensional features are determined. 4. The groups of retailers are grouped reasonably based on the selected features. 5. Sales predictions are made for retailers based on determined features using machine learning algorithms, which only aim to improve the accuracy of the predictions, absent analysis of new retailers and improvements in how marketing is based on the analysis.
Therefore, there is a need for a new AI-based retail intelligent analysis and precision marketing system.
Disclosure of Invention
The invention provides an AI-based new retail intelligent analysis and accurate marketing system, which is characterized in that the acquisition and integration of multi-platform product sales data, the analysis of sales index achievement rate, the prediction of sales index improvement achievement rate according to the analysis result, and the adjustment of initial marketing strategy according to the prediction result are adopted, so that the quality of new retail intelligent analysis can be improved, and targeted scientific decision support is provided for accurate marketing.
The invention provides a new retail intelligent analysis and accurate marketing system based on AI, comprising: the to-be-analyzed sales data acquisition module is used for acquiring, integrating and processing the multi-platform product sales data put on the market to obtain to-be-analyzed sales data;
the to-be-analyzed sales data analysis module is used for correcting the first comparison sales data predicted and obtained by the sales data prediction model to obtain second comparison sales data, analyzing the to-be-analyzed sales data and the second comparison sales data by using a principal component analysis method, and sending an analysis result to the marketing strategy adjustment module;
and the marketing strategy adjustment module is used for predicting the sales index improvement achievement rate by utilizing a neural network prediction model according to the analysis result and adjusting the initial marketing strategy according to the prediction result.
Further, the sales data collection module to be analyzed includes:
Determining corresponding sales data acquisition modes according to a plurality of platforms put on the market, and acquiring multi-platform product sales data according to the sales data acquisition modes;
The sales data acquisition mode comprises the following steps: different acquisition periods and acquisition schemes are applied to different platforms; the acquisition scheme comprises the following steps: randomly designating a sales platform for collection, collecting based on a fixed sales platform and classifying and collecting based on sales platform data;
And classifying and integrating the multi-platform product sales data according to the sales data classifying templates to obtain sales data to be analyzed, and sending the sales data to be analyzed to a sales data analysis module to be analyzed.
Further, the sales data analysis module to be analyzed comprises a first comparison sales data acquisition unit, a sales data correction unit to be analyzed and a sales data analysis unit to be analyzed;
The first comparison sales data acquisition unit is used for predicting and acquiring first comparison sales data based on a preset sales data prediction model according to an initial marketing strategy; the sales data prediction model is generated after training and verification based on the neural network model;
the to-be-analyzed sales data correction unit is used for correcting the first comparison sales data to obtain second comparison sales data;
The to-be-analyzed sales data analysis unit is used for analyzing the sales index achievement rate in the to-be-analyzed sales data according to the second comparison sales data and the to-be-analyzed sales data by utilizing a principal component analysis method, obtaining an analysis result and sending the analysis result to the marketing strategy adjustment module.
Further, the first comparative sales data is subjected to correction processing to obtain second comparative sales data, including:
taking the preset periodic sales in the first comparative sales data as a continuous random variable in a pre-constructed cumulative distribution function, and adopting a quantile deviation correction method to carry out deviation correction on the preset periodic sales in the first comparative sales data on the quantile; wherein, the deviation correction is: calculating a difference value of sales of a preset period and sales in the sales data to be analyzed in terms of the number of the digits, taking the difference value as a target discarding object, discarding the target discarding object in the number of the digits in the first comparison sales data of the subsequent period when the first comparison sales data of the subsequent period is predicted by using the sales data prediction model, and obtaining corrected second comparison sales data of the subsequent period.
Further, according to the second comparative sales data and the sales data to be analyzed, the principal component analysis method is used for analyzing the sales index achievement rate in the sales data to be analyzed, and the method comprises the following steps:
Obtaining sales index achievement data in the second comparison sales data to form an A multiplied by B data matrix, wherein A is the number of samples, B is the number of sales indexes, and the sales index achievement data is subjected to standardized processing to form a standardized sample for representing expected sales index achievement in the second comparison sales data;
Performing control limit calculation corresponding to sales index achievement on the standardized sample; the control limit calculation includes: calculating covariance matrixes among the B sales indexes to obtain eigenvalues and eigenvectors of the covariance matrixes, obtaining the number of principal components by adopting a cumulative contribution percentage method, calculating projection of the eigenvectors on a characteristic space, and obtaining a first control limit of T 2 statistic and a second control limit of Q statistic;
After standardized processing is carried out on sales index achievement data in sales data to be analyzed, a first vector is obtained; and calculating a current T 2 statistic and a current Q statistic corresponding to the first vector, and if the current T 2 statistic is smaller than a first control limit and the current Q statistic is smaller than a second control limit, judging that the sales index achievement data in the sales data to be analyzed does not reach the expected sales index achievement.
Further, obtaining the analysis result includes:
determining the unachievable rate of the sales index according to the first difference value of the T 2 statistic and the control limit and the second difference value of the Q statistic and the second control limit;
According to the unachievable rate of the sales index, carrying out subdivision disassembly and reason tracing on the sales index by using a preset sales analysis tracing model, and obtaining an analysis report matched with the unachievable reason of the sales index based on a preset analysis report database according to the unachievable reason of the sales index obtained by the reason tracing;
And (3) carrying out improvement on the content in the analysis report, carrying out operability evaluation to obtain an operability evaluation value, taking the first content with the operability evaluation value larger than a preset value threshold as an analysis result, wherein the first content is the modifiable content.
Further, the marketing strategy adjustment module comprises a prediction unit and a strategy adjustment unit;
The prediction unit is used for improving the modifiable content to obtain improved content, and according to the improved content, predicting the probability of the sales index improvement achievement rate by using a neural network prediction model to obtain a probability value of the sales index improvement achievement rate;
the strategy adjustment unit is used for comparing the probability value with a preset probability threshold value, and adjusting an initial marketing strategy according to the improved content if the probability value is larger than the preset probability threshold value; if the probability value is smaller than the preset probability threshold value, discarding and reformulating the initial marketing strategy.
Further, the predicting of the probability of improving the achievement rate of the sales index by using the neural network prediction model comprises the following steps:
Inputting the improved content into a pre-constructed hybrid neural network model, and outputting the probability of the sales index improvement achievement rate generated by the improved content; the improved content is processed firstly to encode word senses of target words of the improved content; and representing the position of the target word by a position coding layer in the hybrid neural network model, obtaining a vector form corresponding to the improved content, and taking the vector form as the input of the pre-constructed hybrid neural network model.
Further, the system also comprises a sales achievement data analysis module which is used for acquiring user browsing and purchasing data on the new retail platform and analyzing the data, and specifically comprises a sales achievement data acquisition unit and a sales achievement data analysis unit;
The sales achievement data acquisition unit is used for acquiring first browsing data of browsing products of users on the new retail platform and second browsing purchase data of the users from browsing the products to browsing the bid products and purchasing the bid products;
the sales achievement data analysis unit is used for comparing and analyzing the first browsing data and the second browsing purchase data, acquiring a plurality of gap terms of the products and the competing products from the browsing page time length, the product content introduction and the product price, and calculating based on a multiple linear regression model to acquire a comprehensive gap value; and analyzing and evaluating the marketing short plates of the products according to the comprehensive gap value.
Further, the system also comprises a comment information acquisition and analysis module, which is used for acquiring comment information of the product by the user according to after-sales data of the product, carrying out cluster analysis according to the comment information, acquiring the requirement of the user according to the result of the cluster analysis, and improving the marketing strategy according to the requirement of the user; the system specifically comprises a comment information acquisition unit and a comment information use unit;
the comment information acquisition unit is used for acquiring comment information of the product of the user according to the after-sale data of the product, and carrying out cluster analysis on the comment information to obtain a cluster analysis result;
The comment information using unit is used for acquiring the proportion of each category of comment information in the comment information according to the clustering analysis result, inputting comment information content in the category with the largest proportion into a preset user demand extraction model, extracting and obtaining a plurality of demand contents with demand keywords, carrying out product function innovation, simulation production and simulation sales deduction by utilizing an AI algorithm according to the demand contents, and carrying out improvement decision of marketing strategies according to the results of the product function innovation, the simulation production and the simulation sales deduction.
Compared with the prior art, the invention has the following advantages and beneficial effects: by collecting and integrating the sales data of the multi-platform products and analyzing the achievement rate of the sales indexes, and then predicting the improvement achievement rate of the sales indexes according to the analysis result, the quality of new retail intelligent analysis can be improved by adjusting the initial marketing strategy according to the prediction result, and targeted scientific decision support is provided for accurate marketing.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of the novel AI-based retail intelligent analysis and precision marketing system of the present invention;
FIG. 2 is a schematic diagram of a sales data analysis module to be analyzed according to the present invention;
fig. 3 is a schematic diagram of a marketing strategy adjustment module according to the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
The invention provides a new retail intelligent analysis and accurate marketing system based on AI, as shown in figure 1, comprising:
The to-be-analyzed sales data acquisition module is used for acquiring, integrating and processing the multi-platform product sales data put on the market to obtain to-be-analyzed sales data;
the to-be-analyzed sales data analysis module is used for correcting the first comparison sales data predicted and obtained by the sales data prediction model to obtain second comparison sales data, analyzing the to-be-analyzed sales data and the second comparison sales data by using a principal component analysis method, and sending an analysis result to the marketing strategy adjustment module;
and the marketing strategy adjustment module is used for predicting the sales index improvement achievement rate by utilizing a neural network prediction model according to the analysis result and adjusting the initial marketing strategy according to the prediction result.
The working principle of the technical scheme is as follows: in order to realize intelligent analysis and accurate marketing of new retail, the application provides a sales data acquisition module to be analyzed, a sales data analysis module to be analyzed and a marketing strategy adjustment module, wherein the sales data acquisition module to be analyzed, the marketing strategy adjustment module and the marketing strategy adjustment module are used for acquiring, integrating and processing the sales data of a plurality of products on a market to obtain the sales data to be analyzed; correcting the first comparison sales data obtained by the sales data prediction model prediction to obtain second comparison sales data, analyzing the sales data to be analyzed and the second comparison sales data by using a principal component analysis method, analyzing the sales index achievement rate, and sending an analysis result to a marketing strategy adjustment module; and finally, according to the analysis result, predicting the sales index improvement achievement rate by utilizing a neural network prediction model, and according to the prediction result, adjusting the initial marketing strategy, so that the high-efficiency analysis of new retail sales and the accurate adjustment of the marketing strategy can be realized.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the quality of intelligent analysis of new retail sales can be improved by collecting and integrating the sales data of the multi-platform products, analyzing the achievement rate of the sales indexes, predicting the improved achievement rate of the sales indexes according to the analysis result, and adjusting the initial marketing strategy according to the prediction result, so that targeted scientific decision support is provided for accurate marketing.
In one embodiment, the sales data collection module to be analyzed comprises:
Determining corresponding sales data acquisition modes according to a plurality of platforms put on the market, and acquiring multi-platform product sales data according to the sales data acquisition modes;
The sales data acquisition mode comprises the following steps: different acquisition periods and acquisition schemes are applied to different platforms; the acquisition scheme comprises the following steps: randomly designating a sales platform for collection, collecting based on a fixed sales platform and classifying and collecting based on sales platform data;
And classifying and integrating the multi-platform product sales data according to the sales data classifying templates to obtain sales data to be analyzed, and sending the sales data to be analyzed to a sales data analysis module to be analyzed.
The working principle of the technical scheme is as follows: in order to realize the acquisition module of the sales data to be analyzed, the application determines a corresponding sales data acquisition mode according to a plurality of platforms put on the market, and acquires the sales data of the multi-platform products according to the sales data acquisition mode; the sales data acquisition mode comprises the following steps: different acquisition periods and acquisition schemes are applied to different platforms; the acquisition scheme comprises the following steps: randomly designating a sales platform for collection, collecting based on a fixed sales platform and classifying and collecting based on sales platform data; and classifying and integrating the multi-platform product sales data according to the sales data classifying templates to obtain sales data to be analyzed, and sending the sales data to be analyzed to a sales data analysis module to be analyzed.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the comprehensive sales data to be analyzed can be ensured to be obtained by collecting and integrating the sales data of the products on a plurality of platforms.
In one embodiment, as shown in fig. 2, the sales data analysis module to be analyzed includes a first comparative sales data acquisition unit, a sales data correction unit to be analyzed, and a sales data analysis unit to be analyzed;
The first comparison sales data acquisition unit is used for predicting and acquiring first comparison sales data based on a preset sales data prediction model according to an initial marketing strategy; the sales data prediction model is generated after training and verification based on the neural network model;
the to-be-analyzed sales data correction unit is used for correcting the first comparison sales data to obtain second comparison sales data;
The to-be-analyzed sales data analysis unit is used for analyzing the sales index achievement rate in the to-be-analyzed sales data according to the second comparison sales data and the to-be-analyzed sales data by utilizing a principal component analysis method, obtaining an analysis result and sending the analysis result to the marketing strategy adjustment module.
The working principle of the technical scheme is as follows: in order to analyze sales data to be analyzed, the file predicts and obtains first comparison sales data based on a preset sales data prediction model according to an initial marketing strategy; the sales data prediction model is generated after training and verification based on the neural network model; then, the first comparison sales data is subjected to correction processing to obtain second comparison sales data; and finally, analyzing the sales index achievement rate in the sales data to be analyzed according to the second comparison sales data and the sales data to be analyzed by utilizing a principal component analysis method to obtain an analysis result, and sending the analysis result to a marketing strategy adjustment module.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, accurate analysis results can be obtained through the comparative analysis of the sales index achievement rate of the sales data to be analyzed.
In one embodiment, the correcting the first comparative sales data to obtain second comparative sales data includes:
taking the preset periodic sales in the first comparative sales data as a continuous random variable in a pre-constructed cumulative distribution function, and adopting a quantile deviation correction method to carry out deviation correction on the preset periodic sales in the first comparative sales data on the quantile; wherein, the deviation correction is: calculating a difference value of sales of a preset period and sales in the sales data to be analyzed in terms of the number of the digits, taking the difference value as a target discarding object, discarding the target discarding object in the number of the digits in the first comparison sales data of the subsequent period when the first comparison sales data of the subsequent period is predicted by using the sales data prediction model, and obtaining corrected second comparison sales data of the subsequent period.
The working principle of the technical scheme is as follows: in order to obtain second comparison sales data, adopting a correction processing mode, taking the preset period sales in the first comparison sales data as a continuous random variable in a pre-constructed cumulative distribution function, and adopting a quantile deviation correction method to carry out deviation correction on the preset period sales in the first comparison sales data on the quantile; the fractional deviation correction method is a method for correcting deviation, wherein the deviation correction is as follows: calculating a difference value of sales of a preset period and sales in the sales data to be analyzed in terms of the number of the digits, taking the difference value as a target discarding object, discarding the target discarding object in the number of the digits in the first comparison sales data of the subsequent period when the first comparison sales data of the subsequent period is predicted by using the sales data prediction model, and obtaining corrected second comparison sales data of the subsequent period.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the first comparison sales data is corrected by adopting the quantile deviation correction method, so that the effect of correction can be improved.
In one embodiment, the analysis of the achievement rate of the sales index in the sales data to be analyzed according to the second comparative sales data and the sales data to be analyzed by using the principal component analysis method includes:
Obtaining sales index achievement data in the second comparison sales data to form an A multiplied by B data matrix, wherein A is the number of samples, B is the number of sales indexes, and the sales index achievement data is subjected to standardized processing to form a standardized sample for representing expected sales index achievement in the second comparison sales data;
Performing control limit calculation corresponding to sales index achievement on the standardized sample; the control limit calculation includes: calculating covariance matrixes among the B sales indexes to obtain eigenvalues and eigenvectors of the covariance matrixes, obtaining the number of principal components by adopting a cumulative contribution percentage method, calculating projection of the eigenvectors on a characteristic space, and obtaining a first control limit of T 2 statistic and a second control limit of Q statistic;
After standardized processing is carried out on sales index achievement data in sales data to be analyzed, a first vector is obtained; and calculating a current T 2 statistic and a current Q statistic corresponding to the first vector, and if the current T 2 statistic is smaller than a first control limit and the current Q statistic is smaller than a second control limit, judging that the sales index achievement data in the sales data to be analyzed does not reach the expected sales index achievement.
The working principle of the technical scheme is as follows: the principal component analysis is also called principal component analysis, which converts multiple indexes into a few comprehensive indexes (namely principal components) by using the thought of dimension reduction, wherein each principal component can reflect most of information of an original variable, and the contained information is not repeated; according to the method, multiple variables are introduced, and meanwhile, complex factors are classified into a plurality of main components, so that the problem is simplified, and meanwhile, the obtained result is more scientific and effective data information; the sales index achievement data in the file relate to a plurality of indexes, and for more targeted analysis, according to second comparison sales data and sales data to be analyzed, the sales index achievement rate in the sales data to be analyzed is analyzed by utilizing a principal component analysis method, and the sales index achievement data in the second comparison sales data is specifically obtained first to form an A multiplied by B-dimensional data matrix, wherein A is the number of samples, B is the number of sales indexes, and the sales index achievement data is subjected to standardized processing to form a standardized sample for representing expected sales index achievement in the second comparison sales data; performing control limit calculation corresponding to the sales index achievement on the standardized sample; the control limit calculation includes: calculating covariance matrixes among the B sales indexes to obtain eigenvalues and eigenvectors of the covariance matrixes, obtaining the number of principal components by adopting a cumulative contribution percentage method, calculating projection of the eigenvectors on a characteristic space, and obtaining a first control limit of T 2 statistic and a second control limit of Q statistic; finally, standardized processing is carried out on sales index achievement data in the sales data to be analyzed to obtain a first vector; and calculating a current T 2 statistic and a current Q statistic corresponding to the first vector, and if the current T 2 statistic is smaller than a first control limit and the current Q statistic is smaller than a second control limit, judging that the sales index achievement data in the sales data to be analyzed does not reach the expected sales index achievement.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, whether the sales index achievement data reach the expected sales index achievement is judged by utilizing the principal component analysis method, so that the pertinence and the scientificity of analysis can be improved, and the quality of data analysis can be improved.
In one embodiment, obtaining the analysis results includes:
determining the unachievable rate of the sales index according to the first difference value of the T 2 statistic and the control limit and the second difference value of the Q statistic and the second control limit;
According to the unachievable rate of the sales index, carrying out subdivision disassembly and reason tracing on the sales index by using a preset sales analysis tracing model, and obtaining an analysis report matched with the unachievable reason of the sales index based on a preset analysis report database according to the unachievable reason of the sales index obtained by the reason tracing;
And (3) carrying out improvement on the content in the analysis report, carrying out operability evaluation to obtain an operability evaluation value, taking the first content with the operability evaluation value larger than a preset value threshold as an analysis result, wherein the first content is the modifiable content.
The working principle of the technical scheme is as follows: the file of the application firstly determines the unachievable rate of the sales index according to the first difference value of the T 2 statistic and the control limit and the second difference value of the Q statistic and the second control limit; then, a preset sales analysis tracing model is utilized to conduct subdivision disassembly and reason tracing on the sales indexes so as to obtain the unachieved reasons of the sales indexes, and an analysis report is obtained in an analysis report database; and then, carrying out operability evaluation on whether the content in the analysis report can be improved or not so as to carry out improvement evaluation on the improved content in the analysis report, obtaining an operability evaluation value, and taking the first content with the operability evaluation value larger than a preset value threshold as an analysis result, wherein the first content is the improved content.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the analysis result can be better determined by obtaining the reason of the unaccepted sales index according to the unaccepted sales index, obtaining the analysis report, and evaluating the modifiable content in the analysis report.
In one embodiment, as shown in FIG. 3, the marketing strategy adjustment module includes a prediction unit and a strategy adjustment unit;
The prediction unit is used for improving the modifiable content to obtain improved content, and according to the improved content, predicting the probability of the sales index improvement achievement rate by using a neural network prediction model to obtain a probability value of the sales index improvement achievement rate;
the strategy adjustment unit is used for comparing the probability value with a preset probability threshold value, and adjusting an initial marketing strategy according to the improved content if the probability value is larger than the preset probability threshold value; if the probability value is smaller than the preset probability threshold value, discarding and reformulating the initial marketing strategy.
The working principle of the technical scheme is as follows: in order to realize marketing strategy adjustment, firstly improving modifiable content to obtain improved content, and predicting the probability of improving the achievement rate of the sales index by using a neural network prediction model to obtain the probability value of improving the achievement rate of the sales index; comparing the probability value with a preset probability threshold value, and formulating different strategy adjustment schemes according to different comparison results; the method comprises the following steps: if the probability value is larger than a preset probability threshold value, an initial marketing strategy is adjusted according to the improved content; if the probability value is smaller than the preset probability threshold value, discarding and reformulating the initial marketing strategy.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, different strategy adjustment schemes are formulated through the analysis of the probability value of the improved achievement rate according to the sales index obtained through prediction, so that the pertinence and the effectiveness of marketing strategy adjustment can be ensured.
In one embodiment, the predicting of the probability of sales index improvement achievement rate using a neural network prediction model includes:
Inputting the improved content into a pre-constructed hybrid neural network model, and outputting the probability of the sales index improvement achievement rate generated by the improved content; the improved content is processed firstly to encode word senses of target words of the improved content; and representing the position of the target word by a position coding layer in the hybrid neural network model, obtaining a vector form corresponding to the improved content, and taking the vector form as the input of the pre-constructed hybrid neural network model.
The working principle of the technical scheme is as follows: in order to predict the sales index improvement achievement rate by using the neural network prediction model, inputting the improved content into a pre-constructed hybrid neural network model, and outputting the probability of the sales index improvement achievement rate generated by the improved content; the improved content is processed firstly, so that the function exertion and application of the neural network prediction model can be ensured, and the specific processing mode is as follows: encoding word senses of target words of the improved content; and representing the position of the target word by a position coding layer in the hybrid neural network model, obtaining a vector form corresponding to the improved content, and taking the vector form as the input of the pre-constructed hybrid neural network model.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, accurate output results can be ensured to be obtained by utilizing the neural network model to predict the improved contents.
In one embodiment, the system further comprises a sales achievement data analysis module for acquiring and analyzing user browsing and purchasing data on the new retail platform, and specifically comprises a sales achievement data acquisition unit and a sales achievement data analysis unit;
The sales achievement data acquisition unit is used for acquiring first browsing data of browsing products of users on the new retail platform and second browsing purchase data of the users from browsing the products to browsing the bid products and purchasing the bid products;
the sales achievement data analysis unit is used for comparing and analyzing the first browsing data and the second browsing purchase data, acquiring a plurality of gap terms of the products and the competing products from the browsing page time length, the product content introduction and the product price, and calculating based on a multiple linear regression model to acquire a comprehensive gap value; and analyzing and evaluating the marketing short plates of the products according to the comprehensive gap value.
The working principle of the technical scheme is as follows: in order to analyze sales achievement data, user browsing and purchasing data on a new retail platform can be obtained, and analysis and evaluation can be performed to analyze the sales process of the product from the user's perspective; firstly, first browsing data of a user browsing products on a new retail platform are obtained, and the user jumps to browse the bid products from the browsing products and purchases second browsing purchase data of the bid products; comparing and analyzing the first browsing data and the second browsing purchase data, acquiring a plurality of gap terms of the product and the bid product from the browsing page time length, the product content introduction and the product price, and calculating based on a multiple linear regression model to acquire a comprehensive gap value; and analyzing and evaluating the marketing short plates of the products according to the comprehensive gap value.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the difference between the product and the bid can be obtained through the acquisition and analysis of the sales achievement data and the purchase process of the user on the new retail platform, so that the reference opinion is provided for the marketing short board of the product.
In one embodiment, the system further comprises a comment information acquisition and analysis module, wherein the comment information acquisition and analysis module is used for acquiring comment information of a user on a product according to after-sales data of the product, performing cluster analysis according to the comment information, acquiring requirements of the user according to a cluster analysis result, and improving a marketing strategy according to the requirements of the user; the system specifically comprises a comment information acquisition unit and a comment information use unit;
the comment information acquisition unit is used for acquiring comment information of the product of the user according to the after-sale data of the product, and carrying out cluster analysis on the comment information to obtain a cluster analysis result;
The comment information using unit is used for acquiring the proportion of each category of comment information in the comment information according to the clustering analysis result, inputting comment information content in the category with the largest proportion into a preset user demand extraction model, extracting and obtaining a plurality of demand contents with demand keywords, carrying out product function innovation, simulation production and simulation sales deduction by utilizing an AI algorithm according to the demand contents, and carrying out improvement decision of marketing strategies according to the results of the product function innovation, the simulation production and the simulation sales deduction.
The working principle of the technical scheme is as follows: in order to fully know the feedback comments of the clients, comment information of the users on the products is obtained according to after-sales data of the products, cluster analysis is carried out according to the comment information, the demands of the users are obtained according to the result of the cluster analysis, and marketing strategies can be improved according to the demands of the users; firstly, according to after-sales data of a product, comment information of the product of a user is obtained, and cluster analysis is carried out on the comment information to obtain a cluster analysis result; and obtaining the proportion of each category of comment information in the comment information according to the clustering analysis result, inputting comment information content in the category with the largest proportion into a preset user demand extraction model, extracting and obtaining a plurality of demand contents with demand keywords, carrying out product function innovation, simulated production and simulated sales deduction according to the demand contents by using an AI algorithm, and carrying out improvement decision of marketing strategies according to the results of the product function innovation, the simulated production and the simulated sales deduction.
The beneficial effects of the technical scheme are as follows: by adopting the scheme provided by the embodiment, the marketing condition of the product can be obtained from the after-sale angle by obtaining the comment information of the user, and the simulation realization of the user demand can be carried out according to the AI algorithm, so that the marketing strategy can be used for providing reference for the improvement of the marketing strategy.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. An AI-based new retail intelligent analysis and precision marketing system, comprising:
The to-be-analyzed sales data acquisition module is used for acquiring, integrating and processing the multi-platform product sales data put on the market to obtain to-be-analyzed sales data;
the to-be-analyzed sales data analysis module is used for correcting the first comparison sales data predicted and obtained by the sales data prediction model to obtain second comparison sales data, analyzing the to-be-analyzed sales data and the second comparison sales data by using a principal component analysis method, and sending an analysis result to the marketing strategy adjustment module;
and the marketing strategy adjustment module is used for predicting the sales index improvement achievement rate by utilizing a neural network prediction model according to the analysis result and adjusting the initial marketing strategy according to the prediction result.
2. The AI-based new retail intelligent analysis and precision marketing system of claim 1, wherein the sales data collection module to be analyzed comprises:
Determining corresponding sales data acquisition modes according to a plurality of platforms put on the market, and acquiring multi-platform product sales data according to the sales data acquisition modes;
The sales data acquisition mode comprises the following steps: different acquisition periods and acquisition schemes are applied to different platforms; the acquisition scheme comprises the following steps: randomly designating a sales platform for collection, collecting based on a fixed sales platform and classifying and collecting based on sales platform data;
And classifying and integrating the multi-platform product sales data according to the sales data classifying templates to obtain sales data to be analyzed, and sending the sales data to be analyzed to a sales data analysis module to be analyzed.
3. The AI-based new retail intelligent analysis and precision marketing system of claim 1, wherein the sales data to be analyzed analysis module comprises a first comparative sales data acquisition unit, a sales data to be analyzed correction unit, and a sales data to be analyzed analysis unit;
The first comparison sales data acquisition unit is used for predicting and acquiring first comparison sales data based on a preset sales data prediction model according to an initial marketing strategy; the sales data prediction model is generated after training and verification based on the neural network model;
the to-be-analyzed sales data correction unit is used for correcting the first comparison sales data to obtain second comparison sales data;
The to-be-analyzed sales data analysis unit is used for analyzing the sales index achievement rate in the to-be-analyzed sales data according to the second comparison sales data and the to-be-analyzed sales data by utilizing a principal component analysis method, obtaining an analysis result and sending the analysis result to the marketing strategy adjustment module.
4. The AI-based new retail intelligent analysis and precision marketing system of claim 3, wherein the modifying the first comparative marketing data to obtain the second comparative marketing data comprises:
Taking the preset periodic sales in the first comparative sales data as a continuous random variable in a pre-constructed cumulative distribution function, and adopting a quantile deviation correction method to carry out deviation correction on the preset periodic sales in the first comparative sales data on the quantile;
Wherein, the deviation correction is: calculating a difference value of sales of a preset period and sales in the sales data to be analyzed in terms of the number of the digits, taking the difference value as a target discarding object, discarding the target discarding object in the number of the digits in the first comparison sales data of the subsequent period when the first comparison sales data of the subsequent period is predicted by using the sales data prediction model, and obtaining corrected second comparison sales data of the subsequent period.
5. The AI-based new retail intelligent analysis and precision marketing system of claim 3, wherein the analysis of the achievement rate of the sales index in the sales data to be analyzed based on the second comparative sales data and the sales data to be analyzed using the principal component analysis method comprises:
Obtaining sales index achievement data in the second comparison sales data to form an A multiplied by B data matrix, wherein A is the number of samples, B is the number of sales indexes, and the sales index achievement data is subjected to standardized processing to form a standardized sample for representing expected sales index achievement in the second comparison sales data;
Performing control limit calculation corresponding to sales index achievement on the standardized sample; the control limit calculation includes: calculating covariance matrixes among the B sales indexes to obtain eigenvalues and eigenvectors of the covariance matrixes, obtaining the number of principal components by adopting a cumulative contribution percentage method, calculating projection of the eigenvectors on a characteristic space, and obtaining a first control limit of T 2 statistic and a second control limit of Q statistic;
After standardized processing is carried out on sales index achievement data in sales data to be analyzed, a first vector is obtained; and calculating a current T 2 statistic and a current Q statistic corresponding to the first vector, and if the current T 2 statistic is smaller than a first control limit and the current Q statistic is smaller than a second control limit, judging that the sales index achievement data in the sales data to be analyzed does not reach the expected sales index achievement.
6. The AI-based new retail intelligent analysis and precision marketing system of claim 5, wherein obtaining analysis results comprises:
determining the unachievable rate of the sales index according to the first difference value of the T 2 statistic and the control limit and the second difference value of the Q statistic and the second control limit;
According to the unachievable rate of the sales index, carrying out subdivision disassembly and reason tracing on the sales index by using a preset sales analysis tracing model, and obtaining an analysis report matched with the unachievable reason of the sales index based on a preset analysis report database according to the unachievable reason of the sales index obtained by the reason tracing;
And (3) carrying out improvement on the content in the analysis report, carrying out operability evaluation to obtain an operability evaluation value, taking the first content with the operability evaluation value larger than a preset value threshold as an analysis result, wherein the first content is the modifiable content.
7. The AI-based new retail intelligent analysis and precision marketing system of claim 6, wherein the marketing strategy adjustment module comprises a prediction unit and a strategy adjustment unit;
The prediction unit is used for improving the modifiable content to obtain improved content, and according to the improved content, predicting the probability of the sales index improvement achievement rate by using a neural network prediction model to obtain a probability value of the sales index improvement achievement rate;
the strategy adjustment unit is used for comparing the probability value with a preset probability threshold value, and adjusting an initial marketing strategy according to the improved content if the probability value is larger than the preset probability threshold value; if the probability value is smaller than the preset probability threshold value, discarding and reformulating the initial marketing strategy.
8. The AI-based new retail intelligent analysis and precision marketing system of claim 7, wherein the predicting of the probability of sales index improvement achievement rate using a neural network prediction model comprises:
Inputting the improved content into a pre-constructed hybrid neural network model, and outputting the probability of the sales index improvement achievement rate generated by the improved content; wherein, the improved content is processed firstly, and the processing is as follows: encoding word senses of target words of the improved content; and representing the position of the target word by a position coding layer in the hybrid neural network model, obtaining a vector form corresponding to the improved content, and taking the vector form as the input of the pre-constructed hybrid neural network model.
9. The AI-based new retail intelligent analysis and precision marketing system of claim 1, further comprising a sales achievement data analysis module for acquiring and analyzing user browsing and purchasing data on the new retail platform, in particular comprising a sales achievement data acquisition unit and a sales achievement data analysis unit;
The sales achievement data acquisition unit is used for acquiring first browsing data of browsing products of users on the new retail platform and second browsing purchase data of the users from browsing the products to browsing the bid products and purchasing the bid products;
the sales achievement data analysis unit is used for comparing and analyzing the first browsing data and the second browsing purchase data, acquiring a plurality of gap terms of the products and the competing products from the browsing page time length, the product content introduction and the product price, and calculating based on a multiple linear regression model to acquire a comprehensive gap value; and analyzing and evaluating the marketing short plates of the products according to the comprehensive gap value.
10. The novel AI-based retail intelligent analysis and accurate marketing system of claim 1, further comprising a comment information acquisition analysis module for acquiring comment information of a product by a user according to after-sales data of the product, performing cluster analysis according to the comment information, acquiring a user demand according to a result of the cluster analysis, and improving a marketing strategy according to the user demand; the system specifically comprises a comment information acquisition unit and a comment information use unit;
the comment information acquisition unit is used for acquiring comment information of the product of the user according to the after-sale data of the product, and carrying out cluster analysis on the comment information to obtain a cluster analysis result;
The comment information using unit is used for acquiring the proportion of each category of comment information in the comment information according to the clustering analysis result, inputting comment information content in the category with the largest proportion into a preset user demand extraction model, extracting and obtaining a plurality of demand contents with demand keywords, carrying out product function innovation, simulation production and simulation sales deduction by utilizing an AI algorithm according to the demand contents, and carrying out improvement decision of marketing strategies according to the results of the product function innovation, the simulation production and the simulation sales deduction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410497492.3A CN118350848A (en) | 2024-04-24 | 2024-04-24 | Novel retail intelligent analysis and accurate marketing system based on AI |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410497492.3A CN118350848A (en) | 2024-04-24 | 2024-04-24 | Novel retail intelligent analysis and accurate marketing system based on AI |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118350848A true CN118350848A (en) | 2024-07-16 |
Family
ID=91822347
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410497492.3A Pending CN118350848A (en) | 2024-04-24 | 2024-04-24 | Novel retail intelligent analysis and accurate marketing system based on AI |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118350848A (en) |
-
2024
- 2024-04-24 CN CN202410497492.3A patent/CN118350848A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110162693B (en) | Information recommendation method and server | |
| CN107423442B (en) | Application recommendation method and system based on user portrait behavior analysis, storage medium and computer equipment | |
| CN111797321B (en) | Personalized knowledge recommendation method and system for different scenes | |
| TWI591556B (en) | Search engine results sorting method and system | |
| CN110781409B (en) | Article recommendation method based on collaborative filtering | |
| CN105184618A (en) | Commodity individual recommendation method for new users and system | |
| CN113469730A (en) | Customer repurchase prediction method and device based on RF-LightGBM fusion model under non-contract scene | |
| CN103886486A (en) | Electronic commerce recommending method based on support vector machine (SVM) | |
| CN112488507B (en) | Expert classification portrait method and device based on clustering and storage medium | |
| CN111797320A (en) | Data processing method, device, equipment and storage medium | |
| CN116681490A (en) | Information recommendation method based on identity authentication | |
| CN117196787B (en) | Intelligent decision optimization method and system based on artificial intelligence | |
| CN112464106B (en) | Object recommendation method and device | |
| Krishnan et al. | Social influence bias in recommender systems: a methodology for learning, analyzing, and mitigating bias in ratings | |
| CN118014652A (en) | Advertisement creative design method and system based on artificial intelligence and big data analysis technology | |
| CN117333262A (en) | Big data demand prediction method and system based on artificial intelligence for electronic commerce platform | |
| CN116703533A (en) | Business management data optimized storage analysis method | |
| CN117131261A (en) | E-commerce content recommendation system based on AI and big data analysis | |
| CN118350848A (en) | Novel retail intelligent analysis and accurate marketing system based on AI | |
| CN112767085B (en) | Commodity similarity analysis and commodity recommendation method and device and computer storage medium | |
| CN115222177A (en) | Service data processing method and device, computer equipment and storage medium | |
| CN115344701A (en) | E-commerce recommendation method based on knowledge graph | |
| CN111400567A (en) | AI-based user data processing method, device and system | |
| Jadon et al. | A Comprehensive Survey of Evaluation Techniques for Recommendation Systems | |
| CN111738790A (en) | Business pushing method and pushing system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication |