Insurance propaganda material optimization method and device based on AI enabling, equipment and medium

Abstract

The invention discloses an insurance propaganda material optimization method and device based on AI enabling, equipment and a medium, and the method comprises the steps: determining a target crowd worthy of being delivered with insurance propaganda materials based on historical transaction data, and obtaining the habit data of the target crowd from the delivery channel of each insurance propaganda material; preprocessing the acquired habit data so as to convert the habit data into a form which can be processed by a computer; analyzing the converted habit data by using an analysis model, and extracting an executable result reflecting the habit of the target crowd; according to the executable result, optimizing the appearance position and content quality of the keyword in the insurance propaganda material; and putting the optimized insurance propaganda material into the putting channel.

Description

Technical Field

[0001] The present invention relates to the fields of artificial intelligence technology and promotional material delivery technology, and in particular to an insurance promotional material optimization method, device, equipment and medium based on AI empowerment. Background Art

[0002] Search engine optimization (SEO) is a process of optimizing a website's performance in search results by analyzing search engine ranking algorithms, understanding how different search engines work, and how to determine the search result sorting rules for keywords. By applying SEO techniques, you can increase the chances that a web page will appear in a higher position in a specific keyword query and attract more targeted and organic traffic to your website.

[0003] Applied to the field of insurance promotion, it can be understood as a way to optimize the title, label, quality and other aspects of promotional materials based on the search habits of target users, so as to achieve stronger exposure, thereby acquiring customers more efficiently and promoting sales initiatives.

[0004] Currently, the design of promotional materials in the industry is basically based on manual understanding and output, and there is a lack of research on delivery and channels. This is essentially due to insufficient understanding of the motivations and needs behind users and search habits. In addition, insurance promotion delivery is based on manual understanding and output, and cannot achieve automatic monitoring and analysis of large-scale data, resulting in low work efficiency. Summary of the invention

[0005] The present invention provides an insurance promotional material optimization method, device, equipment and medium based on AI empowerment to solve the technical problems of insufficient understanding of the motivations and needs behind users and search habits, inability to automatically monitor and analyze large-scale data, and low work efficiency.

[0006] First, a method for optimizing insurance promotional materials based on AI empowerment is provided, including:

[0007] Based on historical transaction data, determine the target group that is worthy of being placed with insurance promotional materials, and obtain the habit data of the target group from various insurance promotional material placement channels;

[0008] Preprocessing the acquired habit data to convert the habit data into a form that can be processed by a computer;

[0009] Analyze the converted habit data using an analysis model to extract executable results that reflect the habits of the target population;

[0010] Optimizing the appearance position and content quality of the keywords in the insurance promotional materials according to the executable results;

[0011] The optimized insurance promotional materials are delivered to the delivery channels.

[0012] According to one aspect of the above technical solution, the step of preprocessing the acquired habit data to convert the habit data into a computer-processable form includes:

[0013] removing special characters from the text content in the custom data, and tokenizing and sentence segmenting the corpus;

[0014] Feature engineering is performed on the habit data to represent each word in the text content of the habit data into a vector form that can be understood by a computer.

[0015] According to one aspect of the above technical solution, the use of the analysis model to analyze the converted habit data and extract executable results reflecting the habits of the target population includes:

[0016] Use the analysis model to find popular search terms and long-tail keywords related to the keywords in the text content of the habit data, identify the core intentions behind the search behavior of the target population, analyze the key strategies of industry peers in the placement of the insurance promotional materials, and predict the search behavior trends of the target population;

[0017] The popular search terms, long-tail keywords, core intent, key strategies, and search behavior trends are extracted as executable results.

[0018] According to one aspect of the above technical solution, the identifying the core intention behind the target group's search behavior includes:

[0019] Performing data preprocessing on the search text of the target population, wherein the data preprocessing includes word segmentation, stop word removal, and stem extraction;

[0020] Using a conversion tool to convert the search text after data preprocessing into a vector form so as to capture semantic information;

[0021] A classification model is constructed, and the search text in vector form is input into the classification model for processing to obtain the query intention of the target population.

[0022] According to one aspect of the above technical solution, the key strategies of the analysis industry peers in the placement of the insurance promotional materials include:

[0023] Use analytical tools to analyze the keyword strategies of industry competitors, and extract the content length, keyword density and readability score of the advertising texts of the industry competitors in various delivery channels;

[0024] Calculating the sum of the domain authority values ​​of all the backlinks in the advertisement text, and then evaluating the quality of the backlinks;

[0025] Evaluate the SEO performance score of the industry competitor based on the page load speed, mobile friendliness, and the presence or absence of an XML sitemap of the page containing the ad text;

[0026] The content quality of the ad text is evaluated by comprehensively considering the keyword strategy, ad text, content length of the ad text, keyword density and readability score, quality of backlinks and search engine optimization performance score.

[0027] According to one aspect of the above technical solution, the predicting of the search behavior trend of the target population includes:

[0028] Collect historical search data, click behavior, and page dwell time of the target population;

[0029] Extracting effective features from the historical search data, wherein the effective features include time series features and user behavior patterns;

[0030] Using an autoregressive integrated moving average model to predict the historical search data according to the effective features;

[0031] Using the historical search data to train the autoregressive integrated moving average model;

[0032] Calculating the average of the squares of the differences between the predicted values ​​and the actual values ​​of the historical search data by means of a mean square error to evaluate the accuracy of the autoregressive integrated moving average model;

[0033] The trained autoregressive integrated moving average model is used to predict future user search behavior trends.

[0034] According to one aspect of the above technical solution, before the step of using the autoregressive integrated moving average model to predict the historical search data according to the effective features, the step also includes:

[0035] The behavior indicators of the target population are monitored, and the search engine is trained iteratively based on the collected behavior indicators.

[0036] In the second aspect, an insurance promotion material optimization device based on AI empowerment is provided, including:

[0037] An acquisition module is used to determine the target population worthy of being placed with insurance promotional materials based on historical transaction data, and to obtain the habit data of the target population from various insurance promotional material placement channels;

[0038] a conversion module, used for preprocessing the acquired habit data to convert the habit data into a form processable by a computer;

[0039] An analysis module, used to analyze the converted habit data using an analysis model to extract executable results reflecting the habits of the target population;

[0040] An optimization module, used for optimizing the occurrence position and content quality of keywords in the insurance promotional materials according to the executable results;

[0041] A delivery module delivers the optimized insurance promotional materials to the delivery channel.

[0042] In a third aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the steps of the above-mentioned AI-enabled insurance promotional material optimization method are implemented.

[0043] In a fourth aspect, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps of the above-mentioned AI-enabled insurance promotional material optimization method are implemented.

[0044] In the above-mentioned AI-enabled insurance promotional material optimization method, device, computer equipment and storage medium, a large amount of user data can be collected and analyzed in an AI-enabled manner to understand user search behavior, needs and intentions from multiple dimensions. This data-driven decision allows us to understand the target audience more accurately and adjust the content of promotional materials in a targeted manner to meet their needs; using AI to optimize insurance promotional materials not only saves time and human resources, but also enables automatic monitoring and analysis of large-scale data, and generates executable and accurate valuable management and operation results; in addition, using AI to provide keyword suggestions and other functions to help write high-quality content can effectively improve work efficiency; by adapting to new situations according to specific scenarios (such as product feature updates or market environment changes) and constantly monitoring and improving predetermined results, it helps the marketing team to continuously evaluate performance and continuously improve competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0046] Figure 1This is a schematic diagram of an application environment of an insurance promotional material optimization method based on AI empowerment in one embodiment of the present invention;

[0047] Figure 2 It is a flow chart of an insurance promotion material optimization method based on AI empowerment in one embodiment of the present invention;

[0048] Figure 3 It is a flowchart of an insurance promotion material optimization method based on AI empowerment in one embodiment of the present invention;

[0049] Figure 4 It is a structural block diagram of an insurance promotion material optimization device based on AI empowerment in the second embodiment of the present invention;

[0050] Figure 5 is a schematic diagram of a structure of a computer device in one embodiment of the present invention;

[0051] Figure 6 It is another structural schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0052] 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 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.

[0053] The AI-enabled insurance promotion material optimization method provided in the embodiment of the present invention can be applied in the following aspects: Figure 1 In an application environment, the client communicates with the server through a network. The marketing department can obtain historical transaction data from the company's server through the network, and obtain the habit data of the target population from the server of the delivery channel. After the result is returned to the client, the habit data is preprocessed and analyzed and optimized, and the optimized insurance promotional materials are returned from the client to the delivery channel server for use. Among them, the client can be but is not limited to various personal computers, laptops, smart phones, tablet computers and portable wearable devices. The server can be implemented with an independent server or a server cluster composed of multiple servers. The present invention is described in detail below through specific embodiments.

[0054] See also Figures 2-3 As shown, Figure 2 A flowchart of an AI-enabled insurance promotional material optimization method provided in an embodiment of the present invention includes the following steps:

[0055] S10: Based on the historical transaction data, determine the target population that is worthy of being delivered insurance promotional materials, and obtain the habit data of the target population from various delivery channels of insurance promotional materials.

[0056] The AI-enabled insurance promotional material optimization method provided by the present invention is mainly used in marketing departments as a delivery strategy for insurance promotional materials. It optimizes the content of insurance promotional materials based on the latest business situation, and places insurance promotional materials that better meet customer requirements at a more forward position on the web page based on customer needs.

[0057] For example, if historical transaction data shows that a user has already purchased insurance, then the user is not included in the target population. If the user has not purchased insurance, then the user can be included in the target population. The habit data of the target population can be obtained from various delivery channels such as web pages and mini-programs. The habit data includes the user's search input, click preferences, scrolling and dwell time on the page, etc. For example, if insurance frequently appears in the user's search input on the web page, or the user actively clicks on insurance advertisements while browsing the web, and stays on the insurance advertisements for a certain period of time.

[0058] S20: pre-processing the acquired habit data to convert the habit data into a form processable by a computer.

[0059] After obtaining the habit data, it is necessary to convert the habit data into a processable form, which includes the following steps:

[0060] S21, removing special characters from the text content in the custom data, and performing tokenization and sentence segmentation processing on the corpus.

[0061] The purpose of clearing special characters and tokenizing and sentence segmenting the corpus is to avoid recognition obstacles in the subsequent processing of custom data text content.

[0062] S22, performing feature engineering processing on the habit data, and representing each word in the text content of the habit data into a vector form that can be understood by a computer.

[0063] Feature engineering can be implemented using Word2Vec software or GloVe software. By representing each word in the habit data text content as a computer-understandable vector form, it is convenient to subsequently classify the habit data text content based on features to obtain information that is helpful for analyzing user intentions. It should be noted that Word2Vec software or GloVe software are both existing technologies and can be used directly by those skilled in the art.

[0064] S30: Analyze the converted habit data using an analysis model to extract executable results that reflect the habits of the target population.

[0065] After the habit data is converted into a vector representation that is understandable to the computer and can obtain meaning, the features of the vector can be analyzed and classified through an analysis model (a Transformer model is used in this embodiment) to obtain different executable results, which specifically includes the following steps:

[0066] S31, finding hot search terms and long-tail keywords related to the keywords in the text content of the habit data;

[0067] The purpose of this step is to extract the keywords of the habit data text and find the popular search terms and long-tail keywords related to the keyword. For example, if the keyword searched by the user is "car", the popular search terms related to it include "car insurance", "vehicle and vessel tax", etc. The long-tail keywords include "how much is the annual loss of the vehicle's vehicle damage insurance", "how much is the vehicle's second year premium", etc., thereby expanding the search strategy.

[0068] S32, identifying the core intention behind the target group's search behavior; specifically including:

[0069] S321, performing data preprocessing on the search text of the target population, wherein the data preprocessing includes word segmentation, stop word removal, and stem extraction;

[0070] The purpose of this step is to avoid subsequent text processing failures and improve search accuracy.

[0071] S322, using a conversion tool to convert the search text after data preprocessing into a vector form so as to capture semantic information;

[0072] Similarly, the purpose of this step is to convert the search text into a vector form and extract the feature information of the search text so as to capture the semantic information more clearly in the future. The conversion tool can use Word2Vec software.

[0073] S323, constructing a classification model, inputting the search text in vector form into the classification model for processing, so as to perform feature classification on the query intention of the target population.

[0074] For example, a support vector machine (SVM) may be used to identify the user's query intent.

[0075] This step is to understand the intention behind the target population's search behavior. The purpose of some search behaviors is hidden, so feature extraction is needed to get the user's real purpose. For example, the user's search term is "hit a luxury car, take full responsibility", which is actually the user's demand for third-party insurance. Therefore, through feature classification, "hit a luxury car, take full responsibility" can be first classified as a third-party insurance classification item, and then classified into "car insurance" according to the third-party insurance type.

[0076] S33, analyze the key strategies of industry peers in the placement of the insurance promotional materials; the specific steps include:

[0077] S331, use analytical tools to analyze the keyword strategies of industry peers;

[0078] You can use Ahrefs software to analyze the keyword strategies of your industry peers.

[0079] S332, extracting the content length, keyword density and readability score of the advertisement texts of the industry competitors in various delivery channels to evaluate the content quality of the advertisement texts;

[0080] This step is to find the advertising texts of industry peers in distribution channels such as web pages and mini-programs, as well as the priority ranking of advertising texts, extract the content length, keyword density and readability score of the advertising texts for analysis, and then evaluate the content quality of the advertising texts;

[0081] S333, calculating the sum of the domain name authority values ​​of all the backlinks in the advertisement text, and then evaluating the quality of the backlinks;

[0082] This step can be based on collecting the sum of the domain name authority values ​​of all backlinks in the advertising text, the ranking of each advertising text by each delivery channel, and then focusing on analyzing the advertising text with the highest backlink ranking, extracting the content of the advertising text as a method of optimizing one's own search engine (SEO).

[0083] S334, evaluating the search engine optimization performance score of the industry competitor based on the page loading speed, mobile friendliness, and the presence or absence of an XML site map of the page where the advertisement text is located.

[0084] In addition to the quality of the content itself, it is also necessary to learn how the ad text performs in the delivery channel, such as evaluating the SEO performance score of the industry peers through page loading speed, mobile friendliness and the presence or absence of XML sitemaps.

[0085] S34, predicting the search behavior trend of the target population. The steps include:

[0086] S341, collecting historical search data, click behavior, and page dwell time of the target population;

[0087] After determining the target group's search intent and learning about the delivery strategies of industry peers, it is necessary to deliver specific insurance materials to the target group. Therefore, it is necessary to collect the target group's historical search data, click behavior, and page dwell time to determine the target group's preferences.

[0088] S342, extracting effective features from the historical search data, wherein the effective features include time series features and user behavior patterns;

[0089] S343, predicting the historical search data according to the effective features using an autoregressive integrated moving average model;

[0090] This step uses the initial autoregressive integrated moving average model to predict historical search data to evaluate the performance of the model.

[0091] S344, training the autoregressive integrated moving average model using the historical search data;

[0092] By inputting the prediction results of historical search data into the autoregressive integrated moving average model for training, the model's policy accuracy can be improved.

[0093] S345, calculating the average of the squares of the differences between the predicted values ​​and the actual values ​​of the historical search data by means of a mean square error to evaluate the accuracy of the autoregressive integrated moving average model;

[0094] Since the actual value of the historical search data is known, by comparing the predicted value with the actual value of the historical search data, the average of the squares of the differences between the predicted value and the actual value (that is, the gap between the predicted value and the actual value) is obtained, and then the accuracy of the autoregressive integrated moving average model can be evaluated.

[0095] S346, using the trained autoregressive integrated moving average model to predict future user search behavior trends.

[0096] The trained autoregressive integrated moving average model has a high prediction accuracy, so it can be used to predict the future search behavior trends of users.

[0097] S40, optimizing the appearance position and content quality of the keywords in the insurance promotional material according to the executable result;

[0098] It is understandable that by predicting the future search behavior trends of users, we can optimize the content of insurance promotional materials and the search engine's search priority in a targeted manner.

[0099] S50, delivering the optimized insurance promotional materials to the delivery channel.

[0100] According to one aspect of the above technical solution, before the step of using the autoregressive integrated moving average model to predict the historical search data according to the effective features, the step also includes:

[0101] Monitor the behavior indicators of the target population, and iteratively train the search engine based on the collected behavior indicators. Specifically, the following steps are included:

[0102] S51, applying data analysis tools to monitor behavioral indicators of the target population;

[0103] The content of insurance promotional materials is not static and needs to be constantly updated according to market conditions and users' real-time needs. Therefore, it is necessary to monitor the behavioral indicators of the target population in real time through data analysis tools.

[0104] S52, using a gradient descent method to iterate the autoregressive integrated moving average model according to the collected behavior indicators;

[0105]

[0106] Where θ represents the model parameters of the autoregressive integrated moving average model, a represents the learning rate, represents the gradient of the loss function J with respect to the model parameter θ;

[0107] In each iteration, the parameter θ is updated in the direction of gradient descent until convergence conditions are reached, such as the gradient approaches zero or the preset number of iterations is reached. This method can be applied to the training process of machine learning models to optimize model parameters.

[0108] S53, integrating the algorithm of the autoregressive integrated moving average model into the SEO of the insurance promotional material.

[0109] It can be seen that in the above scheme, the SEO optimization method enabled by AI can understand user search behavior, needs and intentions from multiple dimensions by collecting and analyzing a large amount of user data. This data-driven decision allows us to understand the target audience more accurately and adjust the content of promotional materials in a targeted manner to meet their needs; the use of AI for insurance promotional material optimization not only saves time and human resources, but also enables automatic monitoring and analysis of large-scale data, and generates executable and accurate valuable management and operation results; in addition, using AI to provide keyword suggestions and other functions to help write high-quality content can effectively improve work efficiency; AI-enabled SEO insurance promotional material optimization system adapts to new situations according to specific scenarios (such as product feature updates or market environment changes) and continuously monitors and improves predetermined results, helping marketing teams to continuously evaluate performance and continuously improve competitiveness.

[0110] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0111] In the second embodiment, an insurance promotion material optimization device 40 based on AI empowerment is provided, and the insurance promotion material optimization device based on AI empowerment corresponds one-to-one with the insurance promotion material optimization method based on AI empowerment in the above embodiment. Figure 4 As shown, the intelligent question-answering processing device includes an acquisition module 11, a conversion module 12, an analysis module 13, an optimization module 14, and a delivery module 15. The functional modules are described in detail as follows:

[0112] The acquisition module 11 is used to determine the target population worthy of being placed with insurance promotional materials based on the historical transaction data, and to obtain the habit data of the target population from various insurance promotional material placement channels;

[0113] A conversion module 12, used for preprocessing the acquired habit data to convert the habit data into a form processable by a computer;

[0114] An analysis module 13, configured to analyze the converted habit data using an analysis model, and extract executable results reflecting the habits of the target population;

[0115] An optimization module 14, configured to optimize the occurrence position and content quality of keywords in the insurance promotional material according to the executable result;

[0116] The delivery module 15 delivers the optimized insurance promotional materials to the delivery channel.

[0117] In one embodiment, the conversion module 12 is specifically configured to:

[0118] removing special characters from the text content in the custom data, and tokenizing and sentence segmenting the corpus;

[0119] Feature engineering is performed on the habit data to represent each word in the text content of the habit data into a vector form that can be understood by a computer.

[0120] In one embodiment, the analysis module 13 is specifically used for:

[0121] Use the analysis model to find popular search terms and long-tail keywords related to the keywords in the text content of the habit data, identify the core intentions behind the search behavior of the target population, analyze the key strategies of industry peers in the placement of the insurance promotional materials, and predict the search behavior trends of the target population;

[0122] The popular search terms, long-tail keywords, core intent, key strategies, and search behavior trends are extracted as executable results.

[0123] The identification of the core intention behind the target group's search behavior includes:

[0124] Performing data preprocessing on the search text of the target population, wherein the data preprocessing includes word segmentation, stop word removal, and stem extraction;

[0125] Using a conversion tool to convert the search text after data preprocessing into a vector form so as to capture semantic information;

[0126] A classification model is constructed, and the search text in vector form is input into the classification model for processing to obtain the query intention of the target population.

[0127] The key strategies of the industry partners in the analysis of the insurance promotional materials include:

[0128] Use analytical tools to analyze the keyword strategies of industry competitors, and extract the content length, keyword density and readability score of the advertising texts of the industry competitors in various delivery channels;

[0129] Calculating the sum of the domain authority values ​​of all the backlinks in the advertisement text, and then evaluating the quality of the backlinks;

[0130] Evaluate the SEO performance score of the industry competitor based on the page load speed, mobile friendliness, and the presence or absence of an XML sitemap of the page containing the ad text;

[0131] The content quality of the ad text is evaluated by comprehensively considering the keyword strategy, ad text, content length of the ad text, keyword density and readability score, quality of backlinks and search engine optimization performance score.

[0132] The predicting of the search behavior trend of the target population includes:

[0133] Collect historical search data, click behavior, and page dwell time of the target population;

[0134] Extracting effective features from the historical search data, wherein the effective features include time series features and user behavior patterns;

[0135] Using an autoregressive integrated moving average model to predict the historical search data according to the effective features;

[0136] Using the historical search data to train the autoregressive integrated moving average model;

[0137] Calculating the average of the squares of the differences between the predicted values ​​and the actual values ​​of the historical search data by means of a mean square error to evaluate the accuracy of the autoregressive integrated moving average model;

[0138] The trained autoregressive integrated moving average model is used to predict future user search behavior trends.

[0139] Before the step of using the autoregressive integrated moving average model to predict the historical search data according to the effective features, the step further includes:

[0140] The behavior indicators of the target population are monitored, and the search engine is trained iteratively based on the collected behavior indicators.

[0141] The present invention provides an insurance promotional material optimization device based on AI empowerment, which can understand user search behavior, needs and intentions from multiple dimensions through the AI-enabled SEO optimization system by collecting and analyzing a large amount of user data. This data-driven decision allows us to understand the target audience more accurately and adjust the content of promotional materials in a targeted manner to meet their needs; the use of AI for insurance promotional material optimization not only saves time and human resources, but also can automatically monitor and analyze large-scale data, and generate executable and accurate valuable management and operation results; in addition, using AI to provide keyword suggestions and other functions to help write high-quality content can effectively improve work efficiency; the AI-enabled SEO insurance promotional material optimization system adapts to new situation needs according to specific scenarios (such as product feature updates or market environment changes) and continuously monitors and improves predetermined results, helping the marketing team to continuously evaluate performance, thereby continuously improving competitiveness.

[0142] For the specific limitations of the insurance promotional material optimization device based on AI empowerment, please refer to the limitations of the insurance promotional material optimization method based on AI empowerment above, which will not be repeated here. Each module in the above-mentioned insurance promotional material optimization device based on AI empowerment can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0143] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client through a network connection. When the computer program is executed by the processor, it realizes a function or step on the service side of an insurance promotional material optimization device based on AI empowerment.

[0144] In one embodiment, a computer device is provided. The computer device may be a client, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the 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 network interface of the computer device is used to communicate with an external server via a network connection. When the computer program is executed by the processor, it realizes the functions or steps on the client side of a method for optimizing insurance promotional materials based on AI empowerment

[0145] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0146] Based on historical transaction data, determine the target group that is worthy of being placed with insurance promotional materials, and obtain the habit data of the target group from various insurance promotional material placement channels;

[0147] Preprocessing the acquired habit data to convert the habit data into a form that can be processed by a computer;

[0148] Analyze the converted habit data using an analysis model to extract executable results that reflect the habits of the target population;

[0149] Optimizing the appearance position and content quality of the keywords in the insurance promotional materials according to the executable results;

[0150] The optimized insurance promotional materials are delivered to the delivery channels.

[0151] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0152] Based on historical transaction data, determine the target group that is worthy of being placed with insurance promotional materials, and obtain the habit data of the target group from various insurance promotional material placement channels;

[0153] Preprocessing the acquired habit data to convert the habit data into a form that can be processed by a computer;

[0154] Analyze the converted habit data using an analysis model to extract executable results that reflect the habits of the target population;

[0155] Optimizing the appearance position and content quality of the keywords in the insurance promotional materials according to the executable results;

[0156] The optimized insurance promotional materials are delivered to the delivery channels.

[0157] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant descriptions on the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0158] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0159] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0160] The embodiments described above 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 do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. An insurance promotion material optimization method based on AI empowerment, characterized in that: include: Based on historical transaction data, determine the target group that is worthy of being placed with insurance promotional materials, and obtain the habit data of the target group from various insurance promotional material placement channels; Preprocessing the acquired habit data to convert the habit data into a form that can be processed by a computer; Analyze the converted habit data using an analysis model to extract executable results that reflect the habits of the target population; Optimizing the appearance position and content quality of the keywords in the insurance promotional materials according to the executable results; The optimized insurance promotional materials are delivered to the delivery channels.

2. The AI-enabled insurance promotion material optimization method according to claim 1, characterized in that: The preprocessing of the acquired habit data to convert the habit data into a computer-processable form includes: removing special characters from the text content in the custom data, and tokenizing and sentence segmenting the corpus; Feature engineering is performed on the habit data to represent each word in the text content of the habit data into a vector form that can be understood by a computer.

3. The AI-enabled insurance promotion material optimization method according to claim 2, characterized in that: The use of the analysis model to analyze the converted habit data and extract executable results reflecting the habits of the target population includes: Use the analysis model to find popular search terms and long-tail keywords related to the keywords in the text content of the habit data, identify the core intentions behind the search behavior of the target population, analyze the key strategies of industry peers in the placement of the insurance promotional materials, and predict the search behavior trends of the target population; The popular search terms, long-tail keywords, core intent, key strategies, and search behavior trends are extracted as executable results.

4. The AI-enabled insurance promotion material optimization method according to claim 3, characterized in that: The identification of the core intention behind the target group's search behavior includes: Performing data preprocessing on the search text of the target population, wherein the data preprocessing includes word segmentation, stop word removal, and stem extraction; Using a conversion tool to convert the search text after data preprocessing into a vector form so as to capture semantic information; A classification model is constructed, and the search text in vector form is input into the classification model for processing to obtain the query intention of the target population.

5. The AI-enabled insurance promotion material optimization method according to claim 3, characterized in that: The key strategies of the industry partners in the analysis of the insurance promotional materials include: Use analytical tools to analyze the keyword strategies of industry competitors, and extract the content length, keyword density and readability score of the advertising texts of the industry competitors in various delivery channels; Calculating the sum of the domain authority values ​​of all the backlinks in the advertisement text, and then evaluating the quality of the backlinks; Evaluate the SEO performance score of the industry competitor based on the page load speed, mobile friendliness, and the presence or absence of an XML sitemap of the page containing the ad text; The content quality of the ad text is evaluated by comprehensively considering the keyword strategy, ad text, content length of the ad text, keyword density and readability score, quality of backlinks and search engine optimization performance score.

6. The AI-enabled insurance promotion material optimization method according to claim 3, characterized in that: The predicting of the search behavior trend of the target population includes: Collect historical search data, click behavior, and page dwell time of the target population; Extracting effective features from the historical search data, wherein the effective features include time series features and user behavior patterns; Using an autoregressive integrated moving average model to predict the historical search data according to the effective features; Using the historical search data to train the autoregressive integrated moving average model; Calculating the average of the squares of the differences between the predicted values ​​and the actual values ​​of the historical search data by means of a mean square error to evaluate the accuracy of the autoregressive integrated moving average model; The trained autoregressive integrated moving average model is used to predict future user search behavior trends.

7. The AI-enabled insurance promotion material optimization method according to claim 6, characterized in that: Before the step of using the autoregressive integrated moving average model to predict the historical search data according to the effective features, the following steps are also included: The behavior indicators of the target population are monitored, and the search engine is trained iteratively based on the collected behavior indicators.

8. An insurance promotion material optimization device based on AI empowerment, characterized in that: include: An acquisition module is used to determine the target population worthy of being placed with insurance promotional materials based on historical transaction data, and to obtain the habit data of the target population from various insurance promotional material placement channels; a conversion module, used for preprocessing the acquired habit data to convert the habit data into a form processable by a computer; An analysis module, used to analyze the converted habit data using an analysis model to extract executable results reflecting the habits of the target population; An optimization module, used for optimizing the occurrence position and content quality of keywords in the insurance promotional materials according to the executable results; A delivery module delivers the optimized insurance promotional materials to the delivery channel.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the insurance promotional material optimization method based on AI empowerment as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the insurance promotional material optimization method based on AI empowerment as described in any one of claims 1 to 7 are implemented.

Images