Network marketing service intelligent management system and method based on Internet of Things

Abstract

The invention discloses a network marketing service intelligent management system and method based on the Internet of Things, and relates to the technical field of network marketing management, and the method comprises the steps: obtaining visitor information of a network platform, and determining a first acceptance coefficient and a second acceptance coefficient of a visitor for marketing information; the first acceptance coefficient is the acceptance degree of the visitor to the marketing information loading time, and the second acceptance coefficient is the acceptance degree of the visitor to the marketing information content; pushing the marketing information to the visitor according to the first acceptance coefficient and the second acceptance coefficient of the visitor for the marketing information; the network condition of the visitor and the rendering capability of the network platform are analyzed to obtain the loading time of the marketing information, and the loading time demand and section demand of the visitor for the marketing content are analyzed, so that the browsing rate and the loading completion rate of the marketing information are improved, the display effect of the marketing information is improved, and the use experience of the visitor is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of network marketing management, and in particular to an intelligent management system and method for network marketing services based on the Internet of Things. Background Art

[0002] Internet marketing services refer to a series of activities that use Internet technology to promote products or services through various online channels and tools. Internet of Things technology enables companies to collect and analyze massive amounts of data from various devices and sensors in real time, including users' purchase history, browsing habits, etc. Through in-depth mining of these data, companies can more accurately understand consumers' needs and preferences, and then provide more personalized marketing information and services; in the process of pushing marketing services, the user's network status will have an impact on the promotion. If the user is in an environment with slow network speed, the user may not be able to load the promotion information in time or spend more time loading the promotion information, so that the user has no intention to participate in the interaction; in addition, the slow loading of marketing information will also have an adverse impact on the user experience; for this reason, how to push marketing information to users based on their network conditions has become an urgent problem to be solved. Summary of the invention

[0003] The purpose of the present invention is to provide an intelligent management system and method for network marketing services based on the Internet of Things to solve the problems raised in the prior art.

[0004] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an intelligent management system for online marketing services based on the Internet of Things, comprising a network platform information storage module, a network platform information acquisition module, a network platform analysis module, a visitor analysis module and a marketing information push module; the output end of the network platform information storage module is connected to the input end of the network platform analysis module, the visitor analysis module and the marketing information push module, and is used to store marketing information, loading data of marketing information and visitors' browsing data of marketing information; the output end of the network platform information acquisition module is connected to the input end of the network platform information storage module, and is used to obtain the loading data of marketing information on the network platform and visitors' browsing data of marketing information; the output end of the network platform analysis module is connected to the input end of the visitor analysis module, and is used to analyze the time required for the network platform to completely load the marketing information; the output end of the visitor analysis module is connected to the input end of the marketing information push module, and is used to analyze visitors' acceptance of the marketing information loading time and the content of the marketing information section, and determine the marketing information pushed to visitors; the marketing information push module is used to recommend marketing information to visitors on the network platform.

[0005] The network platform analysis module also includes a rendering speed analysis unit, a network speed measurement unit and a loading time determination unit; the rendering speed analysis unit. The visitor analysis module also includes a loading analysis unit, a first acceptance coefficient calculation unit and a second acceptance coefficient calculation unit; the loading analysis unit is used to analyze the complete loading of the historical marketing information pushed by the network platform; the first acceptance coefficient calculation unit is used to calculate the first acceptance coefficient of the visitor to the marketing information; the second acceptance coefficient calculation unit is used to calculate the second acceptance coefficient of the visitor to the marketing information; the first acceptance coefficient is the visitor's acceptance of the marketing information loading time, and the second acceptance coefficient is the visitor's acceptance of the marketing information content. The first acceptance coefficient calculation unit calculates the loading completion rate of the marketing information to be pushed through the neural network classification model; and obtains the browsing completion rate of the information to be pushed through the regression model.

[0006] To achieve the above object, the present invention provides the following technical solution: an intelligent management method for network marketing services based on the Internet of Things, comprising the following steps: S11, obtaining visitor information of the network platform, wherein the visitor information includes old users or new users; if the visitor is an old user, proceed to step S12, and if the visitor is a new user, proceed to step S13; S12, obtaining the visitor's historical access information on the network platform, and determining the visitor's first acceptance coefficient and second acceptance coefficient for the marketing information; the first acceptance coefficient is the visitor's acceptance of the marketing information loading time, and the second acceptance coefficient is the visitor's acceptance of the marketing information content; proceed to step S14; S13, obtaining historical visit information on the network platform, and determining a first acceptance coefficient and a second acceptance coefficient of the visitor to the marketing information based on the historical visit information on the network platform; S14, pushing the marketing information to the visitor according to the first acceptance coefficient and the second acceptance coefficient of the visitor to the marketing information.

[0007] In step S12, determining the first acceptance coefficient of the visitor to the marketing information further includes the following steps: S21, obtaining the media content formats and the media content size of each format contained in the marketing information to be pushed; calculating the first time t1 required for the network platform to load the marketing information, t1=x1 / v1+x2 / v2+…+xn / vn; where x1, x2, …, xn are the sizes of media content in different formats, v1, v2, …, vn are the rendering speeds of the network platform for media content in different formats; n is the number of media content formats; obtaining the visitor's network speed through a network speed test tool, obtaining the second time t2 according to the data volume of the marketing information and the visitor's network speed, and taking the maximum value of t1 and t2 to obtain the target time t required for the visitor to receive the marketing information; The rendering speed will be affected by the file type. Different file types have different parsing and rendering methods, which will directly affect the rendering speed of the page. In addition, the rendering speed and performance of different network platforms are also different. Network platforms include but are not limited to game clients, e-commerce platforms, video playback platforms, etc.

[0008] S22, analyzing the visitors' acceptance of marketing information at different target times, obtaining the target time required for the visitors to receive the historical marketing information and the completion status of the historical marketing information from the visitors' historical data, and monitoring whether the historical marketing information is completely loaded through events; taking the completely loaded historical marketing information as a positive example and the incompletely loaded historical marketing information as a negative example, and training a binary classification neural network model; assigning values ​​to the positive examples and negative examples respectively, taking the target time required for the visitors to receive the historical marketing information as input, and the assignment of the positive examples and negative examples as output, and training a binary classification neural network model; inputting the target time required for the visitors to receive the marketing information to be pushed into the binary classification neural network model, and if the classification result is a positive example, setting the loading completion rate of the marketing information to be pushed to 1, and if the classification result is a negative example, setting the loading completion rate of the marketing information to be pushed to 0; S23, in the fully loaded historical marketing information, obtain the residence time of the visitor on the network platform to retain the marketing information page, obtain the browsing time required for the historical marketing information to be completely browsed, calculate the ratio of the residence time to the browsing time to obtain the browsing completion rate, and the maximum value of the browsing completion rate is 1; take the browsing completion rate as output, and the target time required for the visitor to receive the historical marketing information as input, and train the browsing completion rate regression model; input the target time required for the visitor to receive the marketing information to be pushed into the browsing completion rate regression model to obtain the browsing completion rate of the marketing information to be pushed; S24, calculating the product of the browsing completion rate and the loading completion rate of the marketing information to be pushed, and obtaining the first acceptance coefficient of the visitor to the marketing information.

[0009] In the process of visitors using the network platform, the loading speed of marketing information will affect the visitor's experience, and the loading speed is affected by the visitor's network conditions and the rendering speed of the network platform; when the visitor's network condition is poor, the network platform feels stuck, and the marketing information that loads slowly is pushed to the visitor at this time, and it takes a lot of time to complete the loading and occupies the screen at the same time, which will make the visitor's experience on the network platform worse, and the visitor is more likely to directly close the marketing information push interface or even exit the network platform. In addition, visitors have different acceptance levels of loading time on different network platforms. For example, when visitors use a game platform, marketing information is pushed to visitors in the process of entering the game. As long as the marketing information can be loaded before the visitor enters the game, the visitor is very likely to retain the marketing information and browse the marketing information in the process of entering the game. Therefore, the present invention determines the push method of marketing information based on the network platform, and adopts different push methods for different network platforms.

[0010] In step S21, the rendering speed of the media content by the network platform is determined by the following steps: From the historical data of marketing information pushed by the network platform, obtain the time t when the network platform completes rendering of the marketing information and the sizes y1, y2, ..., yn of the media content in different formats included in the marketing information; establish the equation t=y1 / v1+y2 / v2+yn / vn; and establish a group of equations through the historical data of marketing information pushed by n network platforms, and combine them to obtain the rendering speed of the marketing information by the network platform.

[0011] In step S12, determining the second acceptance coefficient of the visitor to the marketing information further includes the following steps: S41, obtaining browsing data information of visitors on the network platform, wherein the browsing data information includes the total browsing time T of visitors on the network platform, the total number of times marketing information is fully loaded D, the browsing time t of media content in various formats i , the number of times each format of media content is fully loaded d i , the browsing time of marketing information in each section j The number of times the marketing information of each section is fully loaded d j ; S42, calculate the visitor's acceptance coefficient C of each section on the network platform according to the formula j , C j =e1×t j / T+e2×d j / D; e1 and e2 are preset weights; the visitor's acceptance coefficient C for each format on the network platform is calculated according to the formula i , C i =e1×t i / T+e2×d i / D; S43, record the marketing information to be pushed whose first acceptance coefficient is not zero as the alternative marketing information, obtain the section to which the alternative marketing information belongs and the size of the media content in each format z1, z2, ..., zn; obtain the acceptance coefficient L1 of the section according to the section to which the alternative marketing information belongs, and calculate the acceptance coefficient L2 of the format according to the formula, L2=C1×z1 / (z1+z2+…+zn)+C2×z2 / (z1+z2+…+zn)+…+C n ×zn / (z1+z2+…+zn).

[0012] In step S13, the following steps are also included: S51, obtaining the first acceptance coefficient of the old user visitors on the network platform to the marketing information, calculating the average value of the first acceptance coefficient of the old user visitors to the marketing information, and adding the marketing information with the average value not less than the set threshold to the candidate marketing information for the new user visitors; S52, obtaining the acceptance coefficients of old users and visitors on the network platform for each section and each format, and calculating the average values ​​to obtain the acceptance coefficients of new users and visitors for each section and each format; S53, substituting the acceptance coefficient of the new user visitor to each section and the acceptance coefficient of each format into step S43 to obtain the second acceptance coefficient of the new user visitor to the alternative marketing information.

[0013] In step S14, the following steps are specifically included: The first acceptance coefficient and the second acceptance coefficient of the visitor for the alternative marketing information are obtained, the estimated value of the alternative marketing information is calculated by a weighted method, and the alternative marketing information is pushed to the visitor according to the estimated value of the alternative marketing information.

[0014] Compared with the prior art, the beneficial effects of the present invention are: analyzing the visitor's network conditions and the rendering capabilities of the network platform to obtain the loading time of marketing information, analyzing the visitor's loading time requirements and section requirements for marketing content, which helps to improve the browsing rate and loading completion rate of marketing information, improve the display effect of marketing information and improve the visitor's user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a structural schematic diagram of the network marketing service intelligent management system based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0017] Example: Figure 1 As shown, the present invention provides a technical solution, an intelligent management system for network marketing services based on the Internet of Things, including a network platform information storage module, a network platform information acquisition module, a network platform analysis module, a visitor analysis module and a marketing information push module; the output end of the network platform information storage module is connected to the input end of the network platform analysis module, the visitor analysis module and the marketing information push module, and is used to store marketing information, loading data of marketing information and visitor browsing data of marketing information; the output end of the network platform information acquisition module is connected to the input end of the network platform information storage module, and is used to obtain the loading data of marketing information on the network platform and the browsing data of marketing information by visitors; the output end of the network platform analysis module is connected to the input end of the visitor analysis module, and is used to analyze the time required for the network platform to completely load the marketing information; the output end of the visitor analysis module is connected to the input end of the marketing information push module, and is used to analyze the visitor's acceptance of the marketing information loading time and the content of the marketing information section, and determine the marketing information pushed by the visitor; the marketing information push module is used to recommend marketing information to visitors on the network platform.

[0018] The network platform analysis module also includes a rendering speed analysis unit, a network speed measurement unit and a loading time determination unit; the rendering speed analysis unit. The visitor analysis module also includes a loading analysis unit, a first acceptance coefficient calculation unit and a second acceptance coefficient calculation unit; the loading analysis unit is used to analyze the complete loading of the historical marketing information pushed by the network platform; the first acceptance coefficient calculation unit is used to calculate the first acceptance coefficient of the visitor to the marketing information; the second acceptance coefficient calculation unit is used to calculate the second acceptance coefficient of the visitor to the marketing information; the first acceptance coefficient is the visitor's acceptance of the marketing information loading time, and the second acceptance coefficient is the visitor's acceptance of the marketing information content. The first acceptance coefficient calculation unit calculates the loading completion rate of the marketing information to be pushed through the neural network classification model; and obtains the browsing completion rate of the information to be pushed through the regression model.

[0019] Embodiment: The present invention provides a technical solution, a network marketing service intelligent management method based on the Internet of Things, comprising the following steps: S11, obtaining visitor information of the network platform, wherein the visitor information includes old users or new users; if the visitor is an old user, proceed to step S12, and if the visitor is a new user, proceed to step S13; S12, obtaining the visitor's historical access information on the network platform, and determining the visitor's first acceptance coefficient and second acceptance coefficient for the marketing information; the first acceptance coefficient is the visitor's acceptance of the marketing information loading time, and the second acceptance coefficient is the visitor's acceptance of the marketing information content; proceed to step S14; Determining the first acceptance coefficient of the visitor to the marketing information also includes the following steps: S21, obtaining the media content formats and the media content size of each format contained in the marketing information to be pushed; calculating the first time t1 required for the network platform to load the marketing information, t1=x1 / v1+x2 / v2+…+xn / vn; where x1, x2, …, xn are the sizes of media content in different formats, v1, v2, …, vn are the rendering speeds of the network platform for media content in different formats; n is the number of media content formats; obtaining the visitor's network speed through a network speed test tool, obtaining the second time t2 according to the data volume of the marketing information and the visitor's network speed, and taking the maximum value of t1 and t2 to obtain the target time t required for the visitor to receive the marketing information; The speed at which a network platform renders media content is determined by the following steps: From the historical data of marketing information pushed by the network platform, the time t when the network platform renders the marketing information and the sizes y1, y2, ..., yn of the media content in different formats contained in the marketing information are obtained; the equation t=y1 / v1+y2 / v2+yn / vn is established; the equation group is established through the historical data of marketing information pushed by n network platforms, and the rendering speed of the marketing information by the network platform is obtained by combining them; For example, when the media content format is text, video and picture, three historical data in the marketing information pushed through the network platform can establish a system of equations. At the same time, through the solution method of linear equations, 1 / v1, 1 / v2, 1 / v3 are solved, and then the reciprocal is taken to obtain v1, v2 and v3; a set of solutions can be obtained for every 3 historical data. In order to eliminate randomness, multiple sampling can be performed to calculate the average value as the final result.

[0020] S22, analyzing the visitors' acceptance of marketing information at different target times, obtaining the target time required for the visitors to receive the historical marketing information and the completion status of the historical marketing information from the visitors' historical data, and monitoring whether the historical marketing information is completely loaded through events; taking the completely loaded historical marketing information as a positive example, and the incompletely loaded historical marketing information as a negative example, and training a binary classification neural network model; assigning values ​​to the positive examples and negative examples respectively, taking the target time required for the visitors to receive the historical marketing information as input, and the assignment of positive examples and negative examples as output, and training a binary classification neural network model; inputting the target time required for the visitors to receive the marketing information to be pushed into the binary classification neural network model, if the classification result is a positive example, the loading completion rate of the marketing information to be pushed is set to 1, if the classification result is a negative example, the loading completion rate of the marketing information to be pushed is set to 0; models such as feedforward neural networks, convolutional neural networks, and recurrent neural networks can be used for classification; S23, in the fully loaded historical marketing information, obtain the residence time of the visitor on the network platform to retain the marketing information page, obtain the browsing time required for the historical marketing information to be completely browsed, calculate the ratio of the residence time to the browsing time to obtain the browsing completion rate, and the maximum value of the browsing completion rate is 1; take the browsing completion rate as output, and the target time required for the visitor to receive the historical marketing information as input, and train the browsing completion rate regression model; input the target time required for the visitor to receive the marketing information to be pushed into the browsing completion rate regression model to obtain the browsing completion rate of the marketing information to be pushed; the completion rate regression model can use multiple linear regression, support vector machine regression, neural network regression, etc. S24, calculating the product of the browsing completion rate and the loading completion rate of the marketing information to be pushed, and obtaining the first acceptance coefficient of the visitor to the marketing information.

[0021] Determining the second acceptance coefficient of the visitor to the marketing information also includes the following steps: S41, obtaining browsing data information of visitors on the network platform, wherein the browsing data information includes the total browsing time T of visitors on the network platform, the total number of times marketing information is fully loaded D, the browsing time t of media content in various formats i , the number of times each format of media content is fully loaded d i , the browsing time of marketing information in each section j The number of times the marketing information of each section is fully loaded d j ; Each marketing message consists of multiple formats and belongs to a fixed section. For example, a marketing message under the entertainment section can include media content in both text and image formats. When the marketing message is loaded, the number of times the media content in all formats contained in the marketing message is fully loaded is allocated to one according to the proportion of each format of the media content in the marketing message, and the number of times the section to which the marketing message belongs is fully loaded is also increased by one; when the marketing message is loaded, if the visitor spends Y time browsing the marketing message, the visitor is allocated a Y amount of browsing time for the marketing message according to the proportion of each format of the media content in the marketing message, and the visitor's browsing time for the section to which the marketing message belongs is also increased by Y; S42, calculate the visitor's acceptance coefficient C of each section on the network platform according to the formula j , C j =e1×t j / T+e2×d j / D; e1 and e2 are preset weights; the visitor's acceptance coefficient C for each format on the network platform is calculated according to the formula i , C i =e1×t i / T+e2×d i / D; S43, record the marketing information to be pushed whose first acceptance coefficient is not zero as the alternative marketing information, obtain the section to which the alternative marketing information belongs and the size of the media content in each format z1, z2, ..., zn; obtain the acceptance coefficient L1 of the section according to the section to which the alternative marketing information belongs, and calculate the acceptance coefficient L2 of the format according to the formula, L2=C1×z1 / (z1+z2+…+zn)+C2×z2 / (z1+z2+…+zn)+…+C n ×zn / (z1+z2+…+zn).

[0022] S13, obtaining historical visit information on the network platform, and determining a first acceptance coefficient and a second acceptance coefficient of the visitor to the marketing information based on the historical visit information on the network platform: Obtain the first acceptance coefficient of marketing information for old user visitors on the network platform, calculate the average value of the first acceptance coefficient of marketing information for old user visitors, and add the marketing information with an average value not less than a set threshold to the alternative marketing information for new user visitors; specifically, the threshold can be set to 50%, that is, the marketing information is fully loaded at more than half of the visitors; the threshold can be adjusted after determining the network situation of the new user visitor. When the network situation of the new user visitor is poor, the threshold can be increased, and when the network situation of the new user visitor is good, the threshold can be reduced.

[0023] Obtain the acceptance coefficients of old users and visitors on the network platform for each section and each format, and calculate the average values ​​to obtain the acceptance coefficients of new users and visitors for each section and each format; Substitute the acceptance coefficients of the new user visitor to each section and the acceptance coefficients of each format into step S43 to obtain the second acceptance coefficient of the new user visitor to the alternative marketing information.

[0024] S14, obtaining the first acceptance coefficient and the second acceptance coefficient of the visitor for the alternative marketing information, calculating the estimated value of the alternative marketing information by a weighted method, and pushing the alternative marketing information to the visitor according to the estimated value of the alternative marketing information.

[0025] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. An intelligent management method for network marketing services based on the Internet of Things, characterized in that: The following steps are involved: S11, obtaining visitor information of the network platform, wherein the visitor information includes old users or new users; if the visitor is an old user, proceed to step S12, and if the visitor is a new user, proceed to step S13; S12, obtaining the visitor's historical access information on the network platform, and determining the visitor's first acceptance coefficient and second acceptance coefficient for the marketing information; the first acceptance coefficient is the visitor's acceptance of the marketing information loading time, and the second acceptance coefficient is the visitor's acceptance of the marketing information content; proceed to step S14; S13, obtaining historical visit information on the network platform, and determining a first acceptance coefficient and a second acceptance coefficient of the visitor to the marketing information based on the historical visit information on the network platform; S14, pushing the marketing information to the visitor according to the first acceptance coefficient and the second acceptance coefficient of the visitor to the marketing information.

2. The method for intelligent management of Internet marketing services based on the Internet of Things according to claim 1 is characterized in that: In step S12, determining the first acceptance coefficient of the visitor to the marketing information further includes the following steps: S21, obtaining the media content formats and the media content size of each format contained in the marketing information to be pushed; calculating the first time t1 required for the network platform to load the marketing information, t1=x1 / v1+x2 / v2+…+xn / vn; where x1, x2, …, xn are the sizes of media content in different formats, v1, v2, …, vn are the rendering speeds of the network platform for media content in different formats; n is the number of media content formats; obtaining the visitor's network speed through a network speed test tool, obtaining the second time t2 according to the data volume of the marketing information and the visitor's network speed, and taking the maximum value of t1 and t2 to obtain the target time t required for the visitor to receive the marketing information; S22, analyzing the visitors' acceptance of marketing information at different target times, obtaining the target time required for the visitors to receive the historical marketing information and the completion status of the historical marketing information from the visitors' historical data, and monitoring whether the historical marketing information is completely loaded through events; taking the completely loaded historical marketing information as a positive example and the incompletely loaded historical marketing information as a negative example, and training a binary classification neural network model; assigning values ​​to the positive examples and negative examples respectively, taking the target time required for the visitors to receive the historical marketing information as input, and the assignment of the positive examples and negative examples as output, and training a binary classification neural network model; inputting the target time required for the visitors to receive the marketing information to be pushed into the binary classification neural network model, and if the classification result is a positive example, setting the loading completion rate of the marketing information to be pushed to 1, and if the classification result is a negative example, setting the loading completion rate of the marketing information to be pushed to 0; S23, in the fully loaded historical marketing information, obtain the residence time of the visitor on the network platform to retain the marketing information page, obtain the browsing time required for the historical marketing information to be completely browsed, calculate the ratio of the residence time to the browsing time to obtain the browsing completion rate, and the maximum value of the browsing completion rate is 1; take the browsing completion rate as output, and the target time required for the visitor to receive the historical marketing information as input, and train the browsing completion rate regression model; input the target time required for the visitor to receive the marketing information to be pushed into the browsing completion rate regression model to obtain the browsing completion rate of the marketing information to be pushed; S24, calculating the product of the browsing completion rate and the loading completion rate of the marketing information to be pushed, and obtaining the first acceptance coefficient of the visitor to the marketing information.

3. The method for intelligent management of network marketing services based on the Internet of Things according to claim 2 is characterized in that: In step S21, the rendering speed of the media content by the network platform is determined by the following steps: From the historical data of marketing information pushed by the network platform, obtain the time t when the network platform completes rendering of the marketing information and the sizes y1, y2, ..., yn of the media content in different formats included in the marketing information; establish the equation t=y1 / v1+y2 / v2+yn / vn; and establish a group of equations through the historical data of marketing information pushed by n network platforms, and combine them to obtain the rendering speed of the marketing information by the network platform.

4. The method for intelligent management of network marketing services based on the Internet of Things according to claim 3 is characterized in that: In step S12, determining the second acceptance coefficient of the visitor to the marketing information further includes the following steps: S41, obtaining browsing data information of visitors on the network platform, wherein the browsing data information includes the total browsing time T of visitors on the network platform, the total number of times marketing information is fully loaded D, the browsing time t of media content in various formats i , the number of times each format of media content is fully loaded d i , the browsing time of marketing information in each section j The number of times the marketing information of each section is fully loaded d j ; S42, calculate the visitor's acceptance coefficient C of each section on the network platform according to the formula j , C j =e1×t j / T+e2×d j / D; e1 and e2 are preset weights; the visitor's acceptance coefficient C for each format on the network platform is calculated according to the formula i , C i =e1×t i / T+e2×d i / D; S43, record the marketing information to be pushed whose first acceptance coefficient is not zero as the alternative marketing information, obtain the section to which the alternative marketing information belongs and the size of the media content in each format z1, z2, ..., zn; obtain the acceptance coefficient L1 of the section according to the section to which the alternative marketing information belongs, and calculate the acceptance coefficient L2 of the format according to the formula, L2=C1×z1 / (z1+z2+…+zn)+C2×z2 / (z1+z2+…+zn)+…+C n ×zn / (z1+z2+…+zn).

5. The method for intelligent management of network marketing services based on the Internet of Things according to claim 4 is characterized in that: In step S13, the following steps are also included: S51, obtaining the first acceptance coefficient of the old user visitors on the network platform to the marketing information, calculating the average value of the first acceptance coefficient of the old user visitors to the marketing information, and adding the marketing information with the average value not less than the set threshold to the candidate marketing information of the new user visitors; S52, obtaining the acceptance coefficients of old users and visitors on the network platform for each section and each format, and calculating the average values ​​to obtain the acceptance coefficients of new users and visitors for each section and each format; S53, substituting the acceptance coefficient of the new user visitor to each section and the acceptance coefficient of each format into step S43 to obtain the second acceptance coefficient of the new user visitor to the alternative marketing information.

6. The method for intelligent management of network marketing services based on the Internet of Things according to claim 4 is characterized in that: In step S14, the following steps are specifically included: The first acceptance coefficient and the second acceptance coefficient of the visitor for the alternative marketing information are obtained, the estimated value of the alternative marketing information is calculated by a weighted method, and the alternative marketing information is pushed to the visitor according to the estimated value of the alternative marketing information.

7. The intelligent management system for Internet marketing services based on the Internet of Things is characterized by: It includes a network platform information storage module, a network platform information acquisition module, a network platform analysis module, a visitor analysis module and a marketing information push module; the output end of the network platform information storage module is connected to the input end of the network platform analysis module, the visitor analysis module and the marketing information push module, and is used to store marketing information, loading data of marketing information and visitors' browsing data of marketing information; the output end of the network platform information acquisition module is connected to the input end of the network platform information storage module, and is used to obtain the loading data of marketing information on the network platform and visitors' browsing data of marketing information; the output end of the network platform analysis module is connected to the input end of the visitor analysis module, and is used to analyze the time required for the network platform to completely load the marketing information; The output end of the visitor analysis module is connected to the input end of the marketing information push module, and is used to analyze visitors' acceptance of marketing information loading time and marketing information section content, and determine the marketing information pushed to visitors; the marketing information push module is used to recommend marketing information to visitors on the network platform.

8. The intelligent management system for Internet marketing services based on the Internet of Things according to claim 7 is characterized in that: The network platform analysis module also includes a rendering speed analysis unit, a network speed measurement unit and a loading time determination unit; the rendering speed analysis unit.

9. The intelligent management system for network marketing services based on the Internet of Things according to claim 7 is characterized in that: The visitor analysis module also includes a loading analysis unit, a first acceptance coefficient calculation unit and a second acceptance coefficient calculation unit; the loading analysis unit is used to analyze the complete loading status of the historical marketing information pushed by the network platform; the first acceptance coefficient calculation unit is used to calculate the visitor's first acceptance coefficient for the marketing information; the second acceptance coefficient calculation unit is used to calculate the visitor's second acceptance coefficient for the marketing information; the first acceptance coefficient is the visitor's acceptance of the marketing information loading time, and the second acceptance coefficient is the visitor's acceptance of the marketing information content.

10. The intelligent management system for network marketing services based on the Internet of Things according to claim 9 is characterized in that: The first acceptance coefficient calculation unit obtains the loading completion rate of the marketing information to be pushed through a neural network classification model; and obtains the browsing completion rate of the information to be pushed through a regression model.

Images