Intelligent monitoring and evaluation system for advertisement delivery acceptance
Through advertising audience analysis and recurrent neural network sentiment analysis, the problems of accuracy and flexibility in advertising delivery are solved, data-driven advertising optimization is achieved, and advertising effectiveness is improved.
Patent Information
- Application Number
- CN202510257399.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-05
- Publication Date
- 2025-07-04
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Advertising delivery in the prior art lacks accuracy and flexibility, and cannot effectively integrate data sources, resulting in low advertising effectiveness, and advertisers rely on empirical judgment rather than data-driven decision-making.
Advertising audience analysis model is used to combine user portraits, and user interaction monitoring and sentiment analysis is performed using recurrent neural network-based sentiment analysis model to calculate user acceptance, and optimize advertising delivery strategies based on results.
It improves the accuracy and flexibility of advertising delivery, improves the interaction rate and conversion rate, ensures that the advertising content matches audience's interests and needs, and achieves data-driven advertising optimization.
Smart Images
Figure CN120258902A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of monitoring and evaluation, and particularly to an intelligent monitoring and evaluation system for the acceptance of advertising placement. Background Art
[0002] With the rapid development of digital marketing, advertising placement has become an important means for enterprises to promote products and services. However, with the diversification of advertising forms and the complexity of channels, advertising faces great challenges in accurately reaching the target audience and evaluating advertising effects. The acceptance of users plays a crucial role in advertising placement, directly affecting the click-through rate, interaction rate, and conversion rate of advertisements.
[0003] In the prior art, there are deficiencies in the audience analysis, sentiment analysis, and acceptance analysis of users: the existing audience analysis methods simply place advertisements on all relevant platforms, ignoring the characteristics of the advertisements themselves and failing to consider the relevance between users and the advertising content. Moreover, the existing analysis methods can only provide basic traffic statistics and simple user feedback analysis, lacking in-depth insight into user sentiment. This makes it difficult for advertisers to understand the true feedback of the audience on the advertising content, resulting in the lack of pertinence and flexibility in advertising placement strategies. In addition, many existing systems fail to effectively integrate data sources and fail to achieve precise matching between advertising content, target audience, and placement channels, leading to low advertising effectiveness. Such limitations make advertisers often rely on empirical judgments rather than data-driven decisions when placing advertisements, thereby reducing the overall efficiency and effectiveness of advertising placement. Summary of the Invention
[0004] In view of the deficiencies of the prior art, the present invention provides an intelligent monitoring and evaluation system for the acceptance of advertising placement to solve the problems raised in the above background art.
[0005] To achieve the above object, the present invention provides the following technical solutions: In a first aspect, an embodiment of the present invention provides an intelligent monitoring and evaluation system for the acceptance of advertising placement, including the following steps: S1. Collect the advertisement to be placed to obtain the advertising content; S2. Conduct audience analysis based on the advertising content to obtain the audience analysis result; S3. Select the advertising placement channel based on the audience analysis result to obtain the recommended placement channel; S4. Conduct advertising placement based on the recommended placement channel to obtain the placement result; S5. Monitor user interaction based on the placement result to obtain the interaction data; S6. Conduct sentiment analysis based on the interaction data to obtain the sentiment analysis result; S7. Calculate the acceptance based on the sentiment analysis result to obtain the user acceptance. S8. Optimize the advertisement placement according to the user acceptance degree to obtain optimization suggestions.
[0006] Further optimize this technical solution. The target audience analysis in S2 includes: According to the collected advertisement content, combine it with the user portrait, use the advertisement audience analysis model, and realize the audience analysis by matching the advertisement features with the user portrait.
[0007] Further optimize this technical solution. The advertisement audience analysis model includes: Model definition: Let the advertisement content feature set be , where each feature represents the quantization value of the advertisement in different dimensions; Model construction: ; Where: : Feature The weight of attribute , obtained according to historical data, and optimized using the gradient descent method; : Logistic function, used to compress the linear combination result to [0,1], representing the matching probability of the audience attribute; : The total number of advertisement content features; : Feature nonlinear amplification coefficient, used to amplify the guiding feature, with a value greater than 1; : Sigmoid adjustment factor, used to suppress noise features, with a value greater than 0; : The matching degree between the jth type of user portrait and the advertisement features.
[0008] Further optimize this technical solution. The advertisement placement in S4 includes: Formulate a placement plan according to the recommended placement channels, set up ad campaigns, ad groups, and ad creatives on the advertisement placement platform, and conduct advertisement placement after the settings are completed to obtain the placement results.
[0009] Further optimize this technical solution. The user interaction monitoring in S5 includes: Clarify the user interaction indicators to be monitored, use data monitoring tools to obtain comprehensive and in-depth data analysis results, and obtain the user interaction data, including click-through rate, block rate, dwell time, and conversion rate.
[0010] Further optimize this technical solution. The sentiment analysis in S6 includes: According to the interaction data, a sentiment analysis model based on the recurrent neural network (RNN) is used for sentiment analysis to obtain the sentiment tendency of users towards the advertisement.
[0011] To further optimize this technical solution, the sentiment analysis model based on the recurrent neural network includes: Feature selection and fusion: Construct a feature vector based on the interaction data; ; Among them: : The standardized features of interaction metrics, including click-through rate, interaction rate, conversion rate, and dwell time; : The word vector representation of the text; Model construction: The input layer is used to receive the feature vector, the RNN layer is used to learn the context relationship of time series features, and the output layer uses an activation function to output the sentiment analysis result; ; Among them: : The hidden state vectors at the current time step t and the previous time step t-1; : The input feature vector at the current time step t; : The weight matrices from hidden state to hidden state and from input to hidden state, respectively; : The bias term of the hidden state; : The activation function; ; Among them: : The output vector at the current time step t, representing the prediction of the sentiment category at that moment; : The weight matrix from hidden state to output; : The bias term of the output layer; Model training: Use the cross-entropy loss function to evaluate the performance of the model, and use the stochastic gradient descent algorithm to update the parameters of the model; ; Among them: : The cross-entropy loss, reflecting the difference between the prediction result and the actual result; : The total number of samples; : The actual sentiment of the i-th sample, where 0 represents negative sentiment and 1 represents positive sentiment; : The predicted sentiment category of the i-th sample. The closer it is to 0, the more negative the sentiment; ; Where: : Model parameters, including weights and bias terms; : Learning rate; : The gradient of the loss function with respect to the model parameters.
[0012] Further optimizing this technical solution, the acceptance calculation in S7 includes: Based on the obtained sentiment analysis results, judge the user's sentiment category, calculate the sentiment tendency score, and calculate the user's acceptance of advertisement placement by integrating the sentiment tendency score and interaction data.
[0013] Further optimizing this technical solution, the advertisement placement optimization in S8 includes: Adjust the advertisement placement strategy, collect user feedback, and adjust and optimize the advertisement content.
[0014] Further optimizing this technical solution includes the following functional modules: Advertisement collection module, audience analysis module, channel selection module, advertisement placement module, interaction monitoring module, sentiment analysis module, acceptance calculation module, optimization module.
[0015] In a second aspect, an embodiment of the present invention provides a computer device, including a memory and a processor. The memory stores a computer program, where: when the computer program instructions are executed by the processor, the steps of an intelligent monitoring and evaluation system for advertisement placement acceptance as described in the first aspect of the present invention are implemented.
[0016] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where: when the computer program instructions are executed by the processor, the steps of an intelligent monitoring and evaluation system for advertisement placement acceptance as described in the first aspect of the present invention are implemented.
[0017] Compared with the prior art, the present invention provides an intelligent monitoring and evaluation system for advertisement placement acceptance, having the following beneficial effects: The intelligent monitoring and evaluation system for advertising acceptance conducts sentiment analysis through a sentiment analysis model based on the Recurrent Neural Network (RNN), which can evaluate the sentiment tendency of users towards advertisements in real time, understand the true feedback of users, provide a basis for optimizing the advertising content, and improve the interaction rate and conversion rate of advertisements.
[0018] Through the advertising audience analysis model, according to the characteristics of the advertisement itself, it ensures that the advertising content matches the interests and needs of the audience, thereby effectively improving the accuracy of advertising placement.
[0019] Through the optimization of advertising placement, user feedback can be responded to in a timely manner, improving the flexibility and effectiveness of advertising placement, overcoming the deficiency of lacking user interaction analysis in traditional advertising monitoring, and promoting the continuous optimization and upgrading of advertising content. Brief Description of the Drawings
[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.
[0021] Figure 1 It is a schematic flow chart of an intelligent monitoring and evaluation system for advertising acceptance proposed by the present invention; Figure 2 It is a schematic flow chart of an advertising audience analysis model of an intelligent monitoring and evaluation system for advertising acceptance proposed by the present invention; Figure 3 It is a schematic flow chart of a sentiment analysis model based on a recurrent neural network of an intelligent monitoring and evaluation system for advertising acceptance proposed by the present invention; Figure 4 It is a schematic diagram of the modules of an intelligent monitoring and evaluation system for advertising acceptance proposed by the present invention. Detailed Embodiments
[0022] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will make a detailed description of the specific embodiments of the present invention in conjunction with the drawings of the specification.
[0023] In the following description, many specific details are set forth to fully understand the present invention. However, the present invention can also be implemented in other ways different from the description herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.
[0024] Second, the "one embodiment" or "embodiment" mentioned herein refers to specific features, structures, or characteristics that may be included in at least one implementation manner of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or selectively exclusive embodiments from other embodiments. Embodiment 1
[0025] Referring to Figures 1 to 3 , which is the first embodiment of the present invention. This embodiment provides an intelligent monitoring and evaluation system for the acceptance of advertising placement, including the following steps: S1. Collect the advertising to be placed to obtain the advertising content.
[0026] In this embodiment, the collection of the advertising to be placed includes: Clarify the advertising type (including text advertising, image advertising, video advertising, etc.) and the target group to be used, extract the advertising content from the existing advertising creative library, standardize the collected advertising content (including text character set, image resolution, video format, etc.), perform classification management and tagging on the basis of the advertising content for subsequent use, remove low-quality advertisements, and then store them in the database.
[0027] S2. Conduct audience analysis based on the advertising content to obtain the audience analysis result.
[0028] In this embodiment, the audience analysis includes: Based on the collected advertising content, combine it with the user portrait, use the advertising audience analysis model, and achieve audience analysis by matching the advertising features with the user portrait. According to the audience analysis result, obtain the user group type with a high degree of matching with the advertising content features, so as to achieve higher accuracy and effectiveness in advertising placement.
[0029] Furthermore, the advertising audience analysis model includes: Model definition: Let the advertising content feature set be , where each feature represents the quantization value of the advertising in different dimensions; Model construction: ; Where: : The weight of feature for attribute , obtained according to historical data and optimized using the gradient descent method; : Logistic function, used to compress the linear combination result to [0,1], representing the matching probability of the audience attribute; : The total number of advertising content features; : The feature non - linear amplification coefficient, which is used to amplify guiding features and takes a value greater than 1; : The Sigmoid adjustment factor, which is used to suppress noise features and takes a value greater than 0; : The matching degree between the j - th user portrait and the advertising features.
[0030] Model usage: Feature extraction: Use an NLP model (prior art) to extract semantic features. For example, topic features: technology, fashion, mother and baby; sentiment features: positive, neutral, negative; keyword density: the occurrence frequency of keywords such as "discount", "new product", etc. And map the feature values to the interval [0, 1] through Min - Max standardization to obtain the advertising content feature set; Model parameter adjustment: Use historical data for training to obtain the weights, feature non - linear amplification coefficients, and Sigmoid adjustment factors for different user portraits. The weight represents the influence weight of advertising content features on the attributes of the target users. A positive value means enhancement, and a negative value means suppression. The feature non - linear amplification coefficient is used to exponentially amplify features, and the Sigmoid adjustment factor is used to suppress noise features. Features with low values will be quickly suppressed to close to 0; Matching degree calculation: Input the advertising content feature values and the categories of user portraits for calculation to obtain the matching degree between the user portrait category and the input advertising content features. The larger the value, the higher the matching degree. For example, if the matching degree is greater than 0.6, it is a strongly relevant target user; if it is between 0.3 and 0.6, it is a potential target user; if it is less than 0.3, it is an irrelevant group.
[0031] S3. Select the advertising placement channels according to the audience analysis results to obtain the recommended placement channels.
[0032] In this embodiment, the advertising placement channel selection includes: Identify channel options, including social media (such as QQ), search engines (such as Baidu, Sogou), video platforms (such as Douyin, Bilibili), and mobile application ads, and understand the user attributes of different channels; According to the audience analysis results obtained by the advertising audience analysis model, combined with the user attributes of different channels, select the channels with users having a high matching degree with the advertising content features as the placement channels.
[0033] S4. Conduct advertising placement according to the recommended placement channels to obtain the placement results.
[0034] In this embodiment, the advertising placement includes: Formulate a placement plan according to the recommended placement channels, set up ad campaigns, ad groups, and ad creatives on the ad placement platform. After the setup is completed, conduct ad placement to obtain the placement results. Allocate the ad budget reasonably according to the priorities and expected effects of each channel to ensure that each channel can receive sufficient financial support.
[0035] S5. Monitor user interactions based on the placement results to obtain interaction data.
[0036] In this embodiment, user interaction monitoring includes: Define the user interaction metrics to be monitored, including click-through rate, interaction rate, conversion rate, dwell time, and text feedback. Use data monitoring tools (such as built-in analysis tools in the ad platform, third-party data analysis tools, etc.) to obtain comprehensive and in-depth data analysis results and get the interaction data of users, including click-through rate, block rate, dwell time, and conversion rate.
[0037] S6. Conduct sentiment analysis based on the interaction data to obtain the sentiment analysis results.
[0038] In this embodiment, sentiment analysis includes: Based on the interaction data, use a sentiment analysis model based on the Recurrent Neural Network (RNN) to conduct sentiment analysis and obtain the sentiment tendency of users towards the ad.
[0039] Furthermore, the sentiment analysis model based on the recurrent neural network includes: Feature selection and fusion: Construct feature vectors according to the interaction data ; ; Where: : Standardized features of interaction metrics, including click-through rate, interaction rate, conversion rate, and dwell time; : Word vector representation of the text; Model construction: The input layer is used to receive the feature vectors, the RNN layer is used to learn the context relationship of time series features, and the output layer uses an activation function to output the sentiment analysis results; ; Where: : Hidden state vectors at the current time step t and the previous time step t-1; : Input feature vector at the current time step t; : Weight matrices from hidden state to hidden state and from input to hidden state respectively; : Bias term of the hidden state; : Activation function; ; Where: : Output vector at the current time step t, representing the prediction of the sentiment category at that moment; : Weight matrix from the hidden state to the output; : Bias term of the output layer; Model training: Use the cross - entropy loss function to evaluate the performance of the model, and use the stochastic gradient descent algorithm to update the model's parameters; ; Where: : Cross - entropy loss, reflecting the difference between the prediction result and the actual result; : Total number of samples; : Actual sentiment of the i - th sample, 0 represents negative sentiment, 1 represents positive sentiment; : Predicted sentiment category of the i - th sample, the closer to 0, the more negative the sentiment; ; Where: : Model parameters, including weights and bias terms; : Learning rate; : Gradient of the loss function with respect to the model parameters.
[0040] Model usage: Feature selection and fusion: Construct a feature vector based on the interaction data as the input data of the model; Model construction and training: Determine the architecture of the RNN model, including the input layer, RNN layer, and output layer. After the model is constructed, use the cross - entropy loss function to evaluate the model performance, and use the stochastic gradient descent algorithm to update and optimize the model parameters; Sentiment analysis: Input the obtained user interaction data into the model for sentiment analysis to obtain the sentiment analysis result of the user towards the advertisement.
[0041] S7. Calculate the acceptance based on the sentiment analysis result to obtain the user acceptance.
[0042] In this embodiment, the acceptance calculation includes: Based on the obtained sentiment analysis results, determine the user's sentiment category, including positive, negative, and neutral, calculate the sentiment tendency score, and calculate the user's acceptance of the advertisement placement by integrating the sentiment tendency score and interaction data. The higher the acceptance of the advertisement placement, the higher the degree of acceptance of the advertisement content among the target audience.
[0043] The calculation of the sentiment tendency score includes: ; Wherein: : Sentiment tendency score; : Weight coefficient; : Sentiment category; The calculation of the acceptance of the advertisement placement includes: ; Wherein: : Acceptance; : Weight coefficient; : Interaction metrics, including click-through rate, interaction rate, conversion rate, and dwell time.
[0044] S8. Optimize the advertisement placement according to the user acceptance to obtain optimization suggestions.
[0045] In this embodiment, the advertisement placement optimization includes: Adjust the advertisement placement strategy: According to the user acceptance, increase the budget for advertisements with high acceptance, increase the placement frequency, expand the target audience, reduce the budget for advertisements with low acceptance, adjust the advertisement content, create advertisement content that meets the target audience, and re-analyze the target audience; Collect user feedback for adjustment and optimization: Through various methods such as questionnaires, user comments, and social media interactions, collect user feedback, understand the user's views on the advertisement content, and ensure that the advertisement content is consistent with the user's needs and interests. Embodiment Two
[0046] Refer to Figure 4 , which is the second embodiment of the present invention. This embodiment provides an intelligent monitoring and evaluation system for the acceptance of advertisement placement, including the following functional modules: Advertisement collection module: Used to clarify the advertisement type, extract the advertisement content, and manage, process, and store the advertisement content; Audience analysis module: According to the collected advertisements, combined with the user portrait, conduct audience analysis to obtain the user types that match the advertisement content characteristics; Channel selection module: used to identify channel options and analyze channel attributes, and select the recommended delivery channels; Advertising delivery module: used to deliver advertisements to various channels and reasonably allocate advertising budgets; Interaction monitoring module: used to monitor user interaction metrics of the published advertisements and perform data analysis; Sentiment analysis module: based on the interaction data analysis, analyze the user's sentiment towards the advertisement; Acceptance calculation module: used to calculate the user's acceptance of the advertisement; Optimization module: adjust the advertising delivery strategy according to the user acceptance, and collect user feedback for the adjustment and optimization of the advertisement content. Embodiment III
[0047] This embodiment also provides a computer device, applicable to the situation of an intelligent monitoring and evaluation system for advertising delivery acceptance, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement an intelligent monitoring and evaluation system for advertising delivery acceptance as proposed in the above embodiment.
[0048] This embodiment also provides a storage medium, on which a computer program is stored, and when the program is executed by the processor, it implements an intelligent monitoring and evaluation system for advertising delivery acceptance as proposed in the above embodiment.
[0049] This computer device may be a terminal, and this computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of this computer device is used to provide computing and control capabilities. The memory of this computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of this computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of this computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of this computer device may be a touch layer covered on the display screen, or a button, a trackball, or a touchpad set on the computer device housing, or an external keyboard, touchpad, or mouse, etc.
[0050] If a function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, etc., which can store program codes of various kinds.
[0051] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a predefined sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus, or device and execute the instructions), or used in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
[0052] More specific examples (non-exhaustive list) of computer-readable media include the following: electrical connection parts with one or more wirings (electronic devices), portable computer disk cartridges (magnetic devices), random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), optical fiber devices, and portable compact disc read-only memories (CDROMs). Additionally, a computer-readable medium can even be paper or other suitable media on which a program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or other suitable processing as necessary, and then stored in a computer memory.
[0053] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following techniques known in the art or a combination thereof can be used: discrete logic circuits having logic gate circuits for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.
[0054] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.
Claims
1. An intelligent monitoring and evaluation system for advertising delivery acceptance, characterized in that, It includes the following steps: S1. Collect the advertisements to be launched to obtain the advertisement content; S2. Conduct an audience analysis based on the advertisement content to obtain the audience analysis result; S3. Select the advertisement placement channels according to the audience analysis result to obtain the recommended placement channels; S4. Conduct advertisement placement according to the recommended placement channels to obtain the placement result; S5. Monitor user interactions based on the placement result to obtain interaction data; S6. Conduct sentiment analysis based on the interaction data to obtain the sentiment analysis result; S7. Calculate the acceptance degree according to the sentiment analysis result to obtain the user acceptance degree; S8. Optimize the advertisement placement according to the user acceptance degree to obtain optimization suggestions.
2. The intelligent monitoring and evaluation system for the acceptance degree of advertisement delivery according to claim 1, wherein The target audience analysis in S2 includes: Based on the collected advertisement content, combine it with the user portrait, and use the advertisement audience analysis model to achieve audience analysis by matching the advertisement features with the user portrait.
3. The intelligent monitoring and evaluation system for advertising delivery acceptance according to claim 2, wherein The advertisement audience analysis model includes: Model definition: Let the set of advertising content features be , where each feature represents the quantified value of the advertisement in different dimensions; Model construction: ； Among them: : Feature The weight of the attribute is obtained according to historical data and optimized using the gradient descent method; : The Logistic function, which is used to compress the result of the linear combination into the range [0, 1], representing the matching probability of the audience attributes; : The total number of advertisement content features; : The characteristic non-linear amplification factor, which is used to amplify the guiding feature and has a value greater than 1; : A sigmoid regulator for suppressing noise features, with a value greater than 0; : The matching degree between the j-th user profile and the advertisement features.
4. The intelligent monitoring and evaluation system for advertising delivery acceptance according to claim 1, characterized in that, The advertisement placement in S4 includes: Formulate a placement plan according to the recommended placement channels, set up ad campaigns, ad groups, and ad materials on the advertisement placement platform, and conduct advertisement placement after the settings are completed to obtain the placement result.
5. The intelligent monitoring and evaluation system for advertising delivery acceptance according to claim 1, characterized in that, The user interaction monitoring in S5 includes: Clarify the user interaction indicators to be monitored, and use data monitoring tools to obtain comprehensive and in-depth data analysis results to obtain the user's interaction data, including click-through rate, blocking rate, dwell time, and conversion rate.
6. The intelligent monitoring and evaluation system for advertisement delivery acceptance degree according to claim 1, characterized in that The sentiment analysis in S6 includes: Based on the interaction data, use the sentiment analysis model based on the recurrent neural network (RNN) to conduct sentiment analysis to obtain the user's sentiment tendency towards the advertisement.
7. The intelligent monitoring and evaluation system for advertising delivery acceptance according to claim 6, wherein The sentiment analysis model based on the recurrent neural network includes: Feature selection and fusion: Construct feature vectors based on interaction data Construct; ； Among them: : Standardized features of interaction metrics, including click-through rate, interaction rate, conversion rate, and dwell time; : Word vector representation of text; Model construction: The input layer is used to receive the feature vector, the RNN layer is used to learn the context relationship of time series features, and the output layer uses an activation function to output the sentiment analysis result; ； Among them: : The hidden state vectors at the current time step t and the previous time step t-1; : The input feature vector at the current time step t; : the weight matrix from hidden state to hidden state and the weight matrix from input to hidden state, respectively; : Bias term of the hidden state; : Activation function; ； Among them: : The output vector at the current time step t, representing the prediction of the sentiment category at that moment; : The weight matrix from the hidden state to the output; : Output layer bias term; Model training: Use the cross-entropy loss function to evaluate the performance of the model, and use the stochastic gradient descent algorithm to update the model parameters; ； Among them: : Cross-entropy loss, which reflects the difference between the predicted result and the actual result; : Total number of samples; : The actual sentiment of the i-th sample, where 0 represents negative sentiment and 1 represents positive sentiment; : The predicted sentiment category of the i-th sample. The closer it is to 0, the more negative the sentiment is; ； Among them: : Model parameters, including weights and bias terms; : Learning rate; : The gradient of the loss function with respect to the model parameters.
8. The intelligent monitoring and evaluation system for advertising delivery acceptance according to claim 1, characterized in that, The acceptance degree calculation in S7 includes: Based on the obtained sentiment analysis result, judge the user's sentiment category, calculate the sentiment tendency score, and comprehensively calculate the user's advertisement placement acceptance degree based on the sentiment tendency score and the interaction data.
9. The intelligent monitoring and evaluation system for advertising delivery acceptance according to claim 1, wherein The advertisement placement optimization in S8 includes: Adjust the advertisement placement strategy, and collect user feedback to adjust and optimize the advertisement content.
10. The intelligent monitoring and evaluation system for the acceptance of advertisement delivery according to claim 1, characterized in that, It includes the following functional modules: Advertisement collection module, audience analysis module, channel selection module, advertisement placement module, interaction monitoring module, sentiment analysis module, acceptance degree calculation module, optimization module.