Intelligent marketing system and method based on user consumption habits

Abstract

The invention discloses an intelligent marketing system and method based on user consumption habits, and the system comprises a data processing module, and belongs to the technical field of intelligent marketing, the data processing module is connected with a user information collection module, a book analysis module, a screening module and a marketing generation system, and the marketing generation system is connected with an intelligent putting module. Through the above mode, personal information data filled by the user is collected, hobbies of the user to books, industries and consumption capabilities are deeply mined, the user tag is generated through integration, consumption habits of the user are analyzed, and a proper book list is screened out through analysis, planning and screening of the user tag and pushed to the user. And marketing content is generated from the book list, and the book information is pushed to the user, so that intelligent marketing of book products and accurate pushing of the products are realized.

Description

Technical Field

[0001] The present invention relates to the field of intelligent marketing technology, and in particular to an intelligent marketing system and method based on user consumption habits. Background Art

[0002] With the development of the Internet, the proportion of online book sales is gradually expanding, indicating that the digital trend of the book market has basically taken shape; however, traditional book marketing has become difficult to adapt, and what is adapting to it is the digitalization of book marketing. Therefore, how to sell books to potential customers and do a good job in online book promotion; how to carry out appropriate promotion based on customer characteristics is crucial.

[0003] For example, Chinese patent CN110111142B discloses an intelligent marketing system based on smart terminals, including a source for outputting multimedia programs, a server, and smart terminals and mobile terminals in the same local area network; the server is used to identify the content of all multimedia programs output by the source and establish an electronic program list; the smart terminal is used to obtain characteristic information of the multimedia programs watched by the user; the smart terminal also receives the electronic program list from the server; the real-time advertising content watched by the user is determined based on the characteristic information and the electronic program list, and the real-time advertising content is synchronized to the mobile terminal; the mobile terminal pushes corresponding mobile advertisements to the user based on the real-time advertising content.

[0004] However, this technology has the following problems: it cannot select appropriate book marketing promotions based on customer characteristics.

[0005] Based on this, the present invention designs an intelligent marketing system and method based on user consumption habits to solve the above problems. Summary of the invention

[0006] In view of the above-mentioned shortcomings of the prior art, the present invention provides an intelligent marketing system and method based on user consumption habits.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0008] An intelligent marketing system based on user consumption habits, comprising a data processing module, the data processing module is connected to a user information collection module, a book analysis module, a screening module and a marketing generation system, the marketing generation system is connected to an intelligent delivery module;

[0009] The user information collection module is used for users to fill in personal preferences, industries, and spending power, and integrates personal preferences, industries, and spending power into user tags and sends them to the data processing module, which then sends them to the screening module;

[0010] The book analysis module is used to analyze the books in the system and generate a ranking list. The book analysis module sends the data information of the book ranking list to the data processing module, which then sends it to the screening module.

[0011] The screening module integrates the collected book ranking lists into a new book ranking list adapted to the user according to the user tag and sends it to the data processing module, which then sends it to the marketing generation system;

[0012] The marketing generation system automatically generates marketing content from the content of the book ranking list;

[0013] The intelligent delivery module automatically pushes the generated content to the user.

[0014] Furthermore, the user information collection module includes a user login unit, a user information filling unit and a user analysis unit, and the user login unit, the user information filling unit and the user analysis unit are all connected to the data processing module.

[0015] Furthermore, the user login unit is used for the user to log into the system, and the user login unit includes a mobile phone number and a password, which can be entered to log into the system;

[0016] The user information filling unit is used to collect the identity information, preferences, industry and consumption capacity data filled in by the user;

[0017] The user's preferences include the books, authors, and characters they like to read;

[0018] The user analysis unit is used to integrate and analyze the information collected in the user information filling unit and generate user tags. The user analysis unit compares and analyzes the time when the user browses the interface and the time when the order is placed, generates and outputs the user's consumption habits;

[0019] The user analysis unit sends the user tags and user consumption habits generated by the user tags to the data processing module, which is then sent to the screening module by the data processing module.

[0020] Furthermore, the book analysis module includes a book classification unit, an author analysis unit, a book analysis unit and a book ranking unit, and the book classification unit, the author analysis unit, the book analysis unit and the book ranking unit are all connected to the data processing module.

[0021] Furthermore, the book classification unit is used to classify the books collected by the system and then transmit the classification results to the data processing module. The book classification includes novels, poems, dramas and essays;

[0022] The author analysis unit is used to analyze the era and background of the author of the book, and then transmit the analysis results to the data processing module.

[0023] The book analysis unit is used to analyze the cost performance of the book based on the user's evaluation of the book and the price of the book itself and integrate them into a book label;

[0024] The book ranking unit ranks the books according to the book tag information and generates a ranking list;

[0025] The book ranking unit sends the data information of the generated ranking list to the data processing module, which then sends it to the screening module.

[0026] Furthermore, the screening module analyzes the data information of the user's favorite author, industry and consumption capacity one by one;

[0027] The screening module confirms whether there are any books in the user's purchase record;

[0028] If yes, then data on purchased books will be collated and the type and content of the books will be analyzed;

[0029] If you have no history of purchasing books, skip this step;

[0030] The filter module checks whether the user has any favorite authors in the user tags;

[0031] If yes, the screening module performs big data analysis on the favorite author to obtain the author's era and background, and searches for other books of the author to generate a book list;

[0032] If you don't have a favorite author, skip this step;

[0033] If the user's historical purchase records and favorite author data are complete, the screening module will analyze the similarity factors of the favorite author's works and the purchased books one by one;

[0034] Similarity factors include the plot, story background, author, and the era in which the author lived. By comparing and analyzing these factors, we can get the similarity score between the books written by the favorite author and the books in the historical purchase records, and generate and output the top ten books.

[0035] The filter module confirms whether the user's industry is included in the user's tag;

[0036] If yes, the screening module will perform data analysis on the user's industry, which includes finance, e-commerce, computer and online literature, and retrieve the book types suitable for the industry according to the user's industry, and randomly select ten books and output them;

[0037] If there is no industry that the user is in, skip this step;

[0038] The screening module confirms whether the user tag contains the user's spending capacity;

[0039] If yes, the screening module analyzes the user's spending power and generates a price range output;

[0040] Filter out the books that meet the price range from the book list generated by the above steps and output them;

[0041] If there is no user consumption capacity, skip this step;

[0042] When the number of output books is zero, the screening module automatically pushes the book ranking list in the book ranking unit to the data processing module, which then sends it to the marketing generation system;

[0043] When the number of output books is not zero, the screening module generates a recommendation list containing these books, and the screening module sends the recommendation list of books to the data processing module, which then sends it to the marketing generation system.

[0044] Furthermore, the marketing generation system is used to generate marketing content from the books in the book list of the screening module;

[0045] The marketing content includes a brief introduction to the book, the writing background and the author; the marketing generation system then sends the generated content to the intelligent delivery module.

[0046] Furthermore, the intelligent delivery module is used to automatically generate marketing video units, marketing article units and intelligent outbound call units using AI in a style that users like from the content generated in the marketing generation system;

[0047] The marketing video unit and marketing article unit are placed on the system homepage;

[0048] According to the time the user stays on the interface, the system analyzes the user's acceptance of the book.

[0049] If the user has finished viewing, the system will directly jump to the product sales interface;

[0050] If the user stays for a short time, the system will no longer push videos and articles about the book;

[0051] The intelligent outbound call unit uses an AI robot to call users to introduce books. If the user has a clear instruction to buy a book, the call will be transferred to the manual customer service, who will guide the user to place an order.

[0052] The AI ​​robot can intelligently recognize user words. If the user expresses no need or uses harsh words, the AI ​​robot will automatically hang up.

[0053] Furthermore, the marketing video unit, marketing article unit and intelligent outbound call unit intelligently deliver to users according to the user consumption habits analyzed by the user analysis unit;

[0054] For users who are hesitant about purchasing, the system will push relevant books multiple times;

[0055] For users who are more decisive in consumption, the system will only push once.

[0056] In order to better achieve the purpose of the present invention, the present invention also provides a method of an intelligent marketing system based on user consumption habits, comprising the following steps:

[0057] Step 1: The user logs in by entering a mobile phone number and password, and then fills in the identity information, favorite books, authors, characters, industry, and affordable product prices in the user information filling unit. The user analysis unit is used to integrate and analyze the information filled in the user information filling unit and generate a user tag;

[0058] Step 2: The user analysis unit compares and analyzes the time when the user browses the interface and the time when the order is placed, generates and outputs the user's consumption habits; the user analysis unit sends the user tags and user consumption habits generated by the user tags to the data processing module, and then the data processing module sends them to the screening module;

[0059] Step 3: The book classification unit is used to classify the books collected by the system, and then transmit the classification results to the data processing module. The book classification includes novels, poems, dramas and essays;

[0060] The author analysis unit is used to analyze the era and background of the author of the book, and then transmit the analysis results to the data processing module.

[0061] The book analysis unit is used to analyze the cost performance of the book based on the user's evaluation of the book and the price of the book itself and integrate them into a book label;

[0062] The book ranking unit ranks the books according to the book tag information and generates a ranking list;

[0063] The book ranking unit sends the data information of the generated ranking list to the data processing module, which then sends it to the screening module;

[0064] Step 4: The screening module confirms whether there are any books in the user's purchase record;

[0065] If yes, then data on purchased books will be collated and the type and content of the books will be analyzed;

[0066] If you have no history of purchasing books, skip this step;

[0067] The filter module checks whether the user has any favorite authors in the user tags;

[0068] If yes, the screening module performs big data analysis on the favorite author to obtain the author's era and background, and searches for other books of the author to generate a book list;

[0069] If you don't have a favorite author, skip this step;

[0070] If the user's historical purchase records and favorite author data are complete, the screening module will analyze the similarity factors of the favorite author's works and the purchased books one by one;

[0071] Similarity factors include the plot, story background, author, and the era in which the author lived. By comparing and analyzing these factors, we can get the similarity score between the books written by the favorite author and the books in the historical purchase records, and generate and output the top ten books.

[0072] Step 5: The screening module confirms whether the user's industry is included in the user tag;

[0073] If yes, the screening module will perform data analysis on the user's industry, which includes finance, e-commerce, computer and online literature, and retrieve the book types suitable for the industry according to the user's industry, and randomly select ten books and output them;

[0074] If there is no industry that the user is in, skip this step;

[0075] The screening module confirms whether the user tag contains the user's spending capacity;

[0076] If yes, the screening module analyzes the user's spending power and generates a price range output;

[0077] Filter out the books that meet the price range from the book list generated by the above steps and output them;

[0078] If there is no user consumption capacity, skip this step;

[0079] When the number of output books is zero, the screening module automatically pushes the book ranking list in the book ranking unit to the data processing module, which then sends it to the marketing generation system;

[0080] When the number of output books is not zero, the screening module generates a recommendation list containing these books, and the screening module sends the recommendation list of books to the data processing module, which then sends it to the marketing generation system;

[0081] Step 6: The marketing generation system is used to generate marketing content from the books in the book list of the screening module;

[0082] The marketing content includes a brief introduction to the book, the writing background, and the author; the marketing generation system then sends the generated content to the smart delivery module;

[0083] Step 7: The intelligent delivery module is used to automatically generate marketing video units, marketing article units and intelligent outbound call units using AI in a style that users like from the content generated in the marketing generation system;

[0084] The marketing video unit and marketing article unit are placed on the system homepage;

[0085] According to the time the user stays on the interface, the system analyzes the user's acceptance of the book.

[0086] If the user has finished viewing, the system will directly jump to the product sales interface;

[0087] If the user stays for a short time, the system will no longer push videos and articles about the book;

[0088] The intelligent outbound call unit uses an AI robot to call users to introduce books. If the user has a clear instruction to buy a book, the call will be transferred to the manual customer service, who will guide the user to place an order.

[0089] The AI ​​robot can intelligently recognize user words. If the user expresses no need or speaks harshly, the AI ​​robot will automatically hang up.

[0090] The marketing video unit, marketing article unit and intelligent outbound call unit intelligently deliver to users according to the user consumption habits analyzed by the user analysis unit;

[0091] For users who are hesitant about purchasing, the system will push relevant books multiple times;

[0092] For users who are more decisive in consumption, the system will only push once.

[0093] The present invention has the following technical effects:

[0094] The present invention collects personal information data filled in by users, deeply mines users' preferences for books, industries they are in and consumption capabilities to generate user tags, analyzes users' consumption habits, screens out suitable book lists through user tag analysis and planning, and pushes them to users. The book list is then generated into marketing content to push book information to users, thereby realizing intelligent marketing of book products and accurate product push. BRIEF DESCRIPTION OF THE DRAWINGS

[0095] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0096] Figure 1 The overall framework of the intelligent marketing system based on user consumption habits of the present invention Figure 1 ;

[0097] Figure 2 The overall framework of the intelligent marketing system based on user consumption habits of the present invention Figure 2 .

[0098] The numbers in the figure represent:

[0099] 1. Data processing module; 2. User information collection module; 21. User login unit; 22. User information filling unit; 23. User analysis unit; 3. Book analysis module; 31. Book classification unit; 32. Author analysis unit; 33. Book analysis unit; 34. Book ranking unit; 4. Screening module; 5. Marketing generation system; 6. Intelligent delivery module; 61. Marketing video unit; 62. Marketing article unit; 63. Intelligent outbound call unit. DETAILED DESCRIPTION

[0100] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0101] The present invention will be further described below in conjunction with the embodiments.

[0102] Example 1

[0103] Please refer to the instruction manual Figure 1-2 , an intelligent marketing system based on user consumption habits, comprising a data processing module 1, the data processing module 1 is connected to a user information collection module 2, a book analysis module 3, a screening module 4 and a marketing generation system 5, the marketing generation system 5 is connected to an intelligent delivery module 6;

[0104] The user information collection module 2 is used for users to fill in personal preferences, industries, and consumption capabilities, and integrates personal preferences, industries, and consumption capabilities into user tags and sends them to the data processing module 1, which then sends them to the screening module 4;

[0105] The book analysis module 3 is used to analyze the books in the system and generate a ranking list. The book analysis module 3 sends the data information of the book ranking list to the data processing module 1, and then the data processing module 1 sends it to the screening module 4;

[0106] The screening module 4 integrates the collected book ranking list into a new book ranking list suitable for the user according to the user tag and sends it to the data processing module 1, which then sends it to the marketing generation system 5;

[0107] The marketing generation system 5 automatically generates marketing content from the content of the book ranking list;

[0108] The intelligent delivery module 6 automatically pushes the generated content to the user.

[0109] The present invention collects personal information data filled in by users, deeply mines users' preferences for books, industries they are in and consumption capabilities to generate user tags, analyzes users' consumption habits, screens out suitable book lists through user tag analysis and planning, and pushes them to users. The book list is then generated into marketing content to push book information to users, thereby realizing intelligent marketing of book products and accurate product push.

[0110] Example 2

[0111] like Figure 1-2 As shown, as a preferred embodiment of the present invention, the user information collection module 2 includes a user login unit 21, a user information filling unit 22 and a user analysis unit 23, and the user login unit 21, the user information filling unit 22 and the user analysis unit 23 are all connected to the data processing module 1.

[0112] The user login unit 21 is used for the user to log in to the system. The user login unit 21 includes a mobile phone number and a password, which can be entered to log in to the system;

[0113] The user information filling unit 22 is used to collect the identity information, preferences, industry and consumption capacity data filled in by the user;

[0114] The user's preferences include books, authors, characters, etc. that they like to read;

[0115] The user analysis unit 23 is used to integrate and analyze the information collected by the user information filling unit 22 and generate user tags. The user analysis unit 23 compares and analyzes the time when the user browses the interface and the time when the order is placed, generates and outputs the user's consumption habits;

[0116] The user analysis unit 23 sends the user tags and user consumption habits generated by the user tags to the data processing module 1 , which is then sent to the screening module 4 by the data processing module 1 .

[0117] The book analysis module 3 includes a book classification unit 31 , an author analysis unit 32 , a book analysis unit 33 and a book ranking unit 34 , and the book classification unit 31 , the author analysis unit 32 , the book analysis unit 33 and the book ranking unit 34 are all connected to the data processing module 1 .

[0118] The book classification unit 31 is used to classify the books collected by the system and then transmit the classification results to the data processing module 1. The book classification includes novels, poems, dramas and essays;

[0119] The author analysis unit 32 is used to analyze the era and background of the author of the book, and then transmit the analysis results to the data processing module 1.

[0120] The book analysis unit 33 is used to analyze the cost performance of the book based on the user's evaluation of the book and the price of the book itself and integrate them into a book label;

[0121] The book ranking unit 34 ranks the books according to the book tag information and generates a ranking list;

[0122] The book ranking unit 34 sends the data information of the generated ranking list to the data processing module 1 , which then sends it to the screening module 4 .

[0123] The screening module 4 analyzes the data information of the user's favorite author, industry and consumption capacity one by one;

[0124] The screening module 4 confirms whether there are any books in the user's purchase record;

[0125] If yes, then data on purchased books will be collated and the type and content of the books will be analyzed;

[0126] If you have no history of purchasing books, skip this step;

[0127] The screening module 4 confirms whether there is a favorite author in the user's user tags;

[0128] If yes, the screening module 4 performs big data analysis on the favorite author to obtain the author's era and background, and searches for other books of the author to generate a book list;

[0129] If you don't have a favorite author, skip this step;

[0130] If the user's historical purchase records and favorite author data information are complete, the screening module 4 performs similarity factor analysis on the favorite author's works and the purchased books one by one;

[0131] Similarity factors include the plot, story background, author, and the era in which the author lived. By comparing and analyzing these factors, we can get the similarity score between the books written by the favorite author and the books in the historical purchase records, and generate and output the top ten books.

[0132] The screening module 4 confirms whether the user's industry is included in the user tag;

[0133] If yes, the screening module 4 performs data analysis on the industry of the user, which includes finance, e-commerce, computer and online literature, retrieves the book types suitable for the industry according to the user's industry, and randomly selects and outputs ten books;

[0134] If there is no industry that the user is in, skip this step;

[0135] The screening module 4 confirms whether the user tag contains the user's consumption capacity;

[0136] If yes, the screening module 4 analyzes the user's spending power and generates a price range output;

[0137] Filter out the books that meet the price range from the book list generated by the above steps and output them;

[0138] If there is no user consumption capacity, skip this step;

[0139] When the number of output books is zero, the screening module 4 automatically pushes the book ranking list in the book ranking unit 34 to the data processing module 1, which then sends it to the marketing generation system 5;

[0140] When the number of output books is not zero, the screening module 4 generates a recommendation list containing these books, and the screening module 4 sends the recommendation list of books to the data processing module 1, which then sends it to the marketing generation system 5.

[0141] The marketing generation system 5 is used to generate marketing content from the books in the book list of the screening module 4;

[0142] The marketing content includes a brief introduction to the book, the writing background and the author; then the marketing generation system 5 sends the generated content to the intelligent delivery module 6.

[0143] The intelligent delivery module 6 is used to automatically generate a marketing video unit 61, a marketing article unit 62 and an intelligent outbound call unit 63 using AI in a style that the user likes from the content generated in the marketing generation system 5;

[0144] The marketing video unit 61 and the marketing article unit 62 are placed on the system homepage;

[0145] According to the time the user stays on the interface, the system analyzes the user's acceptance of the book.

[0146] If the user has finished viewing, the system will directly jump to the product sales interface;

[0147] If the user stays for a short time, the system will no longer push videos and articles about the book;

[0148] The intelligent outbound call unit 63 uses an AI robot to call users to introduce books. If the user has a clear instruction to buy books, the call is transferred to the manual customer service, who guides the user to place an order.

[0149] The AI ​​robot can intelligently recognize user words. If the user expresses no need or uses harsh words, the AI ​​robot will automatically hang up.

[0150] The marketing video unit 61, marketing article unit 62 and intelligent outbound call unit 63 intelligently deliver to users according to the user consumption habits analyzed by the user analysis unit 23;

[0151] For users who are hesitant about purchasing, the system will push relevant books multiple times;

[0152] For users who are more decisive in consumption, the system will only push once.

[0153] Example 3

[0154] like Figure 1-2 As shown, as a preferred embodiment of the present invention, in order to better achieve the purpose of the present invention, the present invention also provides a method of an intelligent marketing system based on user consumption habits, comprising the following steps:

[0155] Step 1: The user logs in by inputting a mobile phone number and a password, and then fills in the identity information, favorite books, authors, characters, industry, and affordable product prices in the user information filling unit 22. The user analysis unit 23 is used to integrate and analyze the information filled in the user information filling unit 22 and generate a user tag;

[0156] Step 2: The user analysis unit 23 compares and analyzes the time when the user browses the interface and the time when the user places an order, generates and outputs the user's consumption habits; the user analysis unit 23 sends the user tag and the user's consumption habits generated by the user tag to the data processing module 1, and then the data processing module 1 sends them to the screening module 4;

[0157] Step 3: The book classification unit 31 is used to classify the books collected by the system, and then transmit the classification results to the data processing module 1. The book classification includes novels, poems, dramas and essays;

[0158] The author analysis unit 32 is used to analyze the era and background of the author of the book, and then transmit the analysis results to the data processing module 1.

[0159] The book analysis unit 33 is used to analyze the cost performance of the book based on the user's evaluation of the book and the price of the book itself and integrate them into a book label;

[0160] The book ranking unit 34 ranks the books according to the book tag information and generates a ranking list;

[0161] The book ranking unit 34 sends the data information of the generated ranking list to the data processing module 1, and then the data processing module 1 sends it to the screening module 4;

[0162] Step 4: The screening module 4 confirms whether there are any books in the user's purchase record;

[0163] If yes, then data on purchased books will be collated and the type and content of the books will be analyzed;

[0164] If you have no history of purchasing books, skip this step;

[0165] The screening module 4 confirms whether there is a favorite author in the user's user tags;

[0166] If yes, the screening module 4 performs big data analysis on the favorite author to obtain the author's era and background, and searches for other books of the author to generate a book list;

[0167] If you don't have a favorite author, skip this step;

[0168] If the user's historical purchase records and favorite author data information are complete, the screening module 4 performs similarity factor analysis on the favorite author's works and the purchased books one by one;

[0169] Similarity factors include the plot, story background, author, and the era in which the author lived. By comparing and analyzing these factors, we can get the similarity score between the books written by the favorite author and the books in the historical purchase records, and generate and output the top ten books.

[0170] Step 5: The screening module 4 confirms whether the user's industry is included in the user tag;

[0171] If yes, the screening module 4 performs data analysis on the industry of the user, which includes finance, e-commerce, computer and online literature, retrieves the book types suitable for the industry according to the user's industry, and randomly selects and outputs ten books;

[0172] If there is no industry that the user is in, skip this step;

[0173] The screening module 4 confirms whether the user tag contains the user's consumption capacity;

[0174] If yes, the screening module 4 analyzes the user's spending power and generates a price range output;

[0175] Filter out the books that meet the price range from the book list generated by the above steps and output them;

[0176] If there is no user consumption capacity, skip this step;

[0177] When the number of output books is zero, the screening module 4 automatically pushes the book ranking list in the book ranking unit 34 to the data processing module 1, which then sends it to the marketing generation system 5;

[0178] When the number of output books is not zero, the screening module 4 generates a recommendation list containing these books, and the screening module 4 sends the recommendation list of books to the data processing module 1, which then sends it to the marketing generation system 5;

[0179] Step 6: the marketing generation system 5 is used to generate marketing content from the books in the book list of the screening module 4;

[0180] The marketing content includes a brief introduction to the book, the writing background and the author; then the marketing generation system 5 sends the generated content to the intelligent delivery module 6;

[0181] Step 7: The intelligent delivery module 6 is used to automatically generate a marketing video unit 61, a marketing article unit 62 and an intelligent outbound call unit 63 using the AI ​​in a style that the user likes from the content generated in the marketing generation system 5;

[0182] The marketing video unit 61 and the marketing article unit 62 are placed on the system homepage;

[0183] According to the time the user stays on the interface, the system analyzes the user's acceptance of the book.

[0184] If the user has finished viewing, the system will directly jump to the product sales interface;

[0185] If the user stays for a short time, the system will no longer push videos and articles about the book;

[0186] The intelligent outbound call unit 63 uses an AI robot to call users to introduce books. If the user has a clear instruction to buy books, the call is transferred to the manual customer service, who guides the user to place an order.

[0187] The AI ​​robot can intelligently recognize user words. If the user expresses no need or speaks harshly, the AI ​​robot will automatically hang up.

[0188] The marketing video unit 61, marketing article unit 62 and intelligent outbound call unit 63 intelligently deliver to users according to the user consumption habits analyzed by the user analysis unit 23;

[0189] For users who are hesitant about purchasing, the system will push relevant books multiple times;

[0190] For users who are more decisive in consumption, the system will only push once.

[0191] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent marketing system based on user consumption habits, comprising a data processing module (1), characterized in that: The data processing module (1) is connected to a user information collection module (2), a book analysis module (3), a screening module (4) and a marketing generation system (5), and the marketing generation system (5) is connected to an intelligent delivery module (6); The user information collection module (2) is used for the user to fill in personal preferences, industry, and consumption capacity, and integrates the personal preferences, industry, and consumption capacity into user tags and sends them to the data processing module (1), which then sends them to the screening module (4); The book analysis module (3) is used to analyze the books in the system and generate a ranking list. The book analysis module (3) sends the data information of the book ranking list to the data processing module (1), and then the data processing module (1) sends it to the screening module (4); The screening module (4) integrates the collected book ranking lists into a new book ranking list suitable for the user according to the user tags and sends it to the data processing module (1), which then sends it to the marketing generation system (5); The marketing generation system (5) automatically generates marketing content from the content of the book ranking list; The intelligent delivery module (6) automatically pushes the generated content to the user.

2. The intelligent marketing system based on user consumption habits according to claim 1 is characterized in that: The user information collection module (2) comprises a user login unit (21), a user information filling unit (22) and a user analysis unit (23); the user login unit (21), the user information filling unit (22) and the user analysis unit (23) are all connected to the data processing module (1).

3. The intelligent marketing system based on user consumption habits according to claim 2 is characterized in that: The user login unit (21) is used for a user to log into the system. The user login unit (21) includes a mobile phone number and a password, which can be input to log into the system; The user information filling unit (22) is used to collect the identity information, preferences, industry and consumption capacity data filled in by the user; The user's preferences include the books, authors, and characters they like to read; The user analysis unit (23) is used to integrate and analyze the information collected in the user information filling unit (22) and generate a user tag. The user analysis unit (23) compares and analyzes the time when the user browses the interface and the time when the user places an order, generates the user's consumption habits, and outputs them; The user analysis unit (23) sends the user tags and user consumption habits generated by the user tags to the data processing module (1), and then the data processing module (1) sends them to the screening module (4).

4. The intelligent marketing system based on user consumption habits according to claim 3 is characterized in that: The book analysis module (3) comprises a book classification unit (31), an author analysis unit (32), a book analysis unit (33) and a book ranking unit (34); the book classification unit (31), the author analysis unit (32), the book analysis unit (33) and the book ranking unit (34) are all connected to the data processing module (1).

5. The intelligent marketing system based on user consumption habits according to claim 4 is characterized in that: The book classification unit (31) is used to classify the books collected by the system and then transmit the classification results to the data processing module (1). The book classification includes novels, poems, dramas and essays. The author analysis unit (32) is used to analyze the era and background of the author of the book, and then transmit the analysis results to the data processing module (1). The book analysis unit (33) is used to analyze the cost performance of the book based on the user's evaluation of the book and the price of the book itself and integrate them into a book label; The book ranking unit (34) ranks the books according to the book tag information and generates a ranking list; The book ranking unit (34) sends the data information for generating the ranking list to the data processing module (1), which then sends the data information to the screening module (4).

6. The intelligent marketing system based on user consumption habits according to claim 5 is characterized in that: The screening module (4) analyzes the data information of the user's favorite author, industry and consumption capacity one by one; The screening module (4) confirms whether there are any books in the user's purchase record; If yes, then data on purchased books will be collated and the type and content of the books will be analyzed; If you have no history of purchasing books, skip this step; The screening module (4) confirms whether the user has a favorite author in the user tag; If yes, the screening module (4) performs big data analysis on the favorite author to obtain the author's era and background, and searches for other books of the author to generate a book list; If you don't have a favorite author, skip this step; If the user's historical purchase records and data information of favorite authors are complete, the screening module (4) performs similarity factor analysis on the favorite author's works and purchased books one by one; Similarity factors include the plot, story background, author, and the era in which the author lived. By comparing and analyzing these factors, we can get the similarity score between the books written by the favorite author and the books in the historical purchase records, and generate and output the top ten books. The screening module (4) confirms whether the user's industry is included in the user tag; If yes, the screening module (4) performs data analysis on the industry in which the user is located, which includes finance, e-commerce, computer and online literature, retrieves the book types suitable for the industry according to the user's industry, and randomly selects ten books and outputs them; If there is no industry that the user is in, skip this step; The screening module (4) confirms whether the user tag contains the user's consumption capacity; If yes, the screening module (4) analyzes the user's spending power and generates a price range output; Filter out the books that meet the price range from the book list generated by the above steps and output them; If there is no user consumption capacity, skip this step; When the number of books outputted is zero, the screening module (4) automatically pushes the book ranking list in the book ranking unit (34) to the data processing module (1), and then the data processing module (1) sends it to the marketing generation system (5); When the number of output books is not zero, the screening module (4) generates a recommendation list containing these books, and the screening module (4) sends the recommendation list of books to the data processing module (1), which then sends it to the marketing generation system (5).

7. The intelligent marketing system based on user consumption habits according to claim 6 is characterized in that: The marketing generation system (5) is used to generate marketing content from the books in the book list of the screening module (4); The marketing content includes a brief introduction to the book, the writing background and the author; then the marketing generation system (5) sends the generated content to the intelligent delivery module (6).

8. The intelligent marketing system based on user consumption habits according to claim 7 is characterized in that: The intelligent delivery module (6) is used to automatically generate a marketing video unit (61), a marketing article unit (62) and an intelligent outbound call unit (63) using AI in a style that is preferred by the user from the content generated in the marketing generation system (5); The marketing video unit (61) and the marketing article unit (62) are placed on the system homepage; According to the time the user stays on the interface, the system analyzes the user's acceptance of the book. If the user has finished viewing, the system will directly jump to the product sales interface; If the user stays for a short time, the system will no longer push videos and articles about the book; The intelligent outbound call unit (63) uses an AI robot to call users to introduce books. If the user has a clear instruction to buy books, the call is transferred to the manual customer service, who guides the user to place an order. The AI ​​robot can intelligently recognize user words. If the user expresses no need or uses harsh words, the AI ​​robot will automatically hang up.

9. The intelligent marketing system based on user consumption habits according to claim 8, characterized in that: The marketing video unit (61), the marketing article unit (62) and the intelligent outbound call unit (63) intelligently deliver to users according to the user consumption habits analyzed by the user analysis unit (23); For users who are hesitant about purchasing, the system will push relevant books multiple times; For users who are more decisive in consumption, the system will only push once.

10. A method of an intelligent marketing system based on user consumption habits as claimed in claim 9, characterized in that: The following steps are involved: Step 1: The user logs in by inputting a mobile phone number and a password, and then fills in the identity information, favorite books, authors, characters, industry, and affordable product prices in the user information filling unit (22). The user analysis unit (23) is used to integrate and analyze the information filled in the user information filling unit (22) and generate a user tag; Step 2: The user analysis unit (23) compares and analyzes the time when the user browses the interface and the time when the user places an order, generates and outputs the user's consumption habits; the user analysis unit (23) sends the user tag and the user's consumption habits generated by the user tag to the data processing module (1), and the data processing module (1) sends them to the screening module (4); Step 3: The book classification unit (31) is used to classify the books collected by the system and then transmit the classification results to the data processing module (1). The book classification includes novels, poems, dramas and essays. The author analysis unit (32) is used to analyze the era and background of the author of the book, and then transmit the analysis results to the data processing module (1). The book analysis unit (33) is used to analyze the cost performance of the book based on the user's evaluation of the book and the price of the book itself and integrate them into a book label; The book ranking unit (34) ranks the books according to the book tag information and generates a ranking list; The book ranking unit (34) sends the data information of the generated ranking list to the data processing module (1), and then the data processing module (1) sends it to the screening module (4); Step 4: the screening module (4) confirms whether there are any books in the user's purchase record; If yes, then data on purchased books will be collated and the type and content of the books will be analyzed; If you have no history of purchasing books, skip this step; The screening module (4) confirms whether the user has a favorite author in the user tag; If yes, the screening module (4) performs big data analysis on the favorite author to obtain the author's era and background, and searches for other books of the author to generate a book list; If you don't have a favorite author, skip this step; If the user's historical purchase records and data information of favorite authors are complete, the screening module (4) performs similarity factor analysis on the favorite author's works and purchased books one by one; Similarity factors include the plot, story background, author, and the era in which the author lived. By comparing and analyzing these factors, we can get the similarity score between the books written by the favorite author and the books in the historical purchase records, and generate and output the top ten books. Step 5: The screening module (4) confirms whether the user's industry is included in the user tag; If yes, the screening module (4) performs data analysis on the industry in which the user is located, which includes finance, e-commerce, computer and online literature, retrieves the book types suitable for the industry according to the user's industry, and randomly selects ten books and outputs them; If there is no industry that the user is in, skip this step; The screening module (4) confirms whether the user tag contains the user's consumption capacity; If yes, the screening module (4) analyzes the user's spending power and generates a price range output; Filter out the books that meet the price range from the book list generated by the above steps and output them; If there is no user consumption capacity, skip this step; When the number of books outputted is zero, the screening module (4) automatically pushes the book ranking list in the book ranking unit (34) to the data processing module (1), and then the data processing module (1) sends it to the marketing generation system (5); When the number of output books is not zero, the screening module (4) generates a recommendation list containing these books, and the screening module (4) sends the recommendation list of books to the data processing module (1), which then sends it to the marketing generation system (5); Step 6: the marketing generation system (5) is used to generate marketing content from the books in the book list of the screening module (4); The marketing content includes a brief introduction to the book, the writing background and the author; then the marketing generation system (5) sends the generated content to the intelligent delivery module (6); Step 7: The intelligent delivery module (6) is used to automatically generate a marketing video unit (61), a marketing article unit (62) and an intelligent outbound call unit (63) using AI in a style that the user likes from the content generated in the marketing generation system (5); The marketing video unit (61) and the marketing article unit (62) are placed on the system homepage; According to the time the user stays on the interface, the system analyzes the user's acceptance of the book. If the user has finished viewing, the system will directly jump to the product sales interface; If the user stays for a short time, the system will no longer push videos and articles about the book; The intelligent outbound call unit (63) uses an AI robot to call users to introduce books. If the user has a clear instruction to buy books, the call is transferred to the manual customer service, who guides the user to place an order. The AI ​​robot can intelligently recognize user words. If the user expresses no need or speaks harshly, the AI ​​robot will automatically hang up. The marketing video unit (61), the marketing article unit (62) and the intelligent outbound call unit (63) intelligently deliver to users according to the user consumption habits analyzed by the user analysis unit (23); For users who are hesitant about purchasing, the system will push relevant books multiple times; For users who are more decisive in consumption, the system will only push once.

Images