Digital management system and method for measuring commodity attention

Abstract

The invention discloses a digital management system and method for measuring commodity attention, and belongs to the technical field of digital management. According to the method, an e-commerce website needing to be crawled and collected data items are input, an HTTP request is sent to obtain webpage content, HTML is analyzed, paging and dynamic content are processed, and a request interval is set; calculating a click rate and a purchase rate of the commodity according to the data item, and generating a popularity index of the commodity according to the click rate and the purchase rate; generating a user evaluation comprehensive score according to the user evaluation, generating a social media evaluation comprehensive score according to the social media evaluation, and generating a user feedback index of the commodity; generating attention indexes of the commodities, obtaining a same-plate commodity data set, a same-category commodity data set and a same-concept commodity data set, and generating attention indexes of the same-plate, same-category and same-concept commodities; and forming an attention index standard of the commodity by using the artificial intelligence model, and generating the commodity attention.

Description

Technical Field

[0001] The present invention relates to the technical field of digital management, and in particular to a digital management system and method for measuring commodity attention. Background Art

[0002] With the rapid development of e-commerce, the types and quantity of goods on e-commerce platforms are increasing. The attention and feedback data of users on goods during shopping have gradually become an important reference for e-commerce platform product management and marketing decisions. In order to improve the platform's operating efficiency and user experience, how to effectively measure the attention of goods has become a key issue.

[0003] Traditional product management methods usually rely on a single data item, such as page views, clicks, or purchases, which fails to fully reflect users' actual interest and feedback on products. In addition, the popularity of social media means that users' evaluation and discussion of products are no longer limited to the e-commerce platform itself, but are widely disseminated on the Internet through various social activities such as likes, comments, and sharing. However, existing technologies often find it difficult to effectively integrate data from e-commerce platforms and social media, and cannot fully evaluate the performance of products in multiple dimensions. Summary of the invention

[0004] The purpose of the present invention is to provide a digital management system and method for measuring product attention, so as to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A digital management method for measuring product attention, the method comprising the following steps:

[0007] S100, input the e-commerce website to be crawled and the collected data items, wherein the data items include the number of views, clicks, purchases, social media reviews and user reviews of the product, use the Requests library to send HTTP requests to obtain web page content, use the BeautifulSoup library to parse HTML, process paging and dynamic content, and set the request interval;

[0008] S200, calculating the click-through rate and purchase rate of the product according to the data items, and generating a popularity index of the product according to the click-through rate and the purchase rate; the user evaluation includes user ratings, user comment texts, sentiment orientation, user identities, user tags, and picture and video feedback, and generating a user evaluation comprehensive score according to the user evaluation; the social media evaluation includes the number of likes, the number of shares, the mention frequency, topic tags, and sentiment orientation, and generating a social media evaluation comprehensive score according to the social media evaluation; and generating a user feedback index of the product according to the user evaluation comprehensive score and the social media evaluation comprehensive score;

[0009] S300, generating a product attention index according to the product popularity index and the product user feedback index, obtaining the product section, product category and product concept of the product, obtaining a product data set of the same section according to the product section, obtaining a product data set of the same category according to the product category, obtaining a product data set of the same concept according to the product concept, generating an attention index of the products of the same section according to the product data set of the same section, generating an attention index of the products of the same category according to the product data set of the same category, and generating an attention index of the products of the same concept according to the product data set of the same concept;

[0010] S400. Use an artificial intelligence model to integrate the attention index of products in the same section, the attention index of products in the same category, and the attention index of products with the same concept to form a product attention index standard, compare the product attention index standard with the product attention index, and generate product attention.

[0011] According to step S100, the user specifies the URL of the target e-commerce website and specifies the data items to be collected, including the number of views, clicks, purchases, social media reviews and user reviews of the product; uses a web crawler to send HTTP requests to obtain web page content from the server, and the request header simulates browser access to avoid being identified as a robot program; the crawler controls the frequency when sending requests and sets the request interval to prevent frequent requests in a short period of time from burdening the target website or causing the IP to be banned; after obtaining the web page content, the HTML page is parsed, and according to the different structures of the e-commerce website, the crawler program uses the HTML parsing tool BeautifulSoup to extract data items, and the data items are embedded in specific tags of the web page. The crawler finds the specific tags according to the page structure and extracts the text content therein;

[0012] E-commerce websites divide product lists into multiple pages for display. Crawler programs can automatically identify paging links and grab data from each page. This is achieved by parsing the URL of the paging button or dynamic request link, and sending requests to each page in turn to obtain its content.

[0013] For e-commerce websites that use JavaScript to asynchronously load and dynamically present product data, the crawler needs to process dynamic content, simulate browser behavior, load JavaScript, or send API requests to the data interface to obtain dynamically generated data; if the e-commerce website integrates user interaction data on social media, the crawler collects social media evaluation data of the product by parsing the embedded social media information; if the e-commerce website does not integrate user interaction data on social media, the crawler accesses the social media platform and grabs social media evaluations related to the product through the corresponding API or page;

[0014] The e-commerce website displays user reviews. The crawler locates the display position of the user review data, extracts the user ratings, user review texts, sentiment tendencies, user identities, user tags, and picture / video feedback provided by users. The crawler program classifies the user review data;

[0015] After each request, the crawler sets a random time interval to simulate the operation behavior of human users and dynamically changes the IP address using an IP proxy pool.

[0016] According to step S200, based on the obtained page views, click-through rates, and purchase volumes of the product, the click-through rate and purchase rate are calculated. The click-through rate is the ratio of the click-through volume to the page view volume, and the purchase rate is the ratio of the purchase volume to the click-through volume. The click-through rate reflects the initial interest of users, and the purchase rate measures the effect of converting interest into actual purchases. The popularity index of the product is calculated by weighted calculation based on the click-through rate and purchase rate.

[0017] According to step S200, in the user review, the user rating represents the score given by the user to the product and is presented in the form of a positive integer; the user review text is obtained, and through natural language processing, the sentiment tendency of the review text is analyzed to determine whether the user's comment is positive, neutral, or negative, which is quantified as a score as the sentiment tendency; the user identity is the authentication information of the user on the e-commerce platform; the user tag is the characteristic tag used to evaluate the product attached by the user when evaluating the product; the picture / video feedback shows the usage effect of the product; each element in the user review is weighted and calculated to generate a comprehensive user review score;

[0018] In order to analyze the sentiment tendency of the user review text through natural language processing and determine whether the comment is positive, neutral, or negative, the following steps are taken for detailed processing:

[0019] First, it is necessary to preprocess the user's review text so that subsequent sentiment analysis can be more accurate. It mainly includes the following steps: Remove stop words, punctuation marks, URL links, numbers, and other irrelevant content from the review. Split the review text into individual words or phrases for subsequent sentiment analysis. For example, Chinese reviews can use word segmentation tools such as jieba, and English reviews can use spaCy, etc. Restore the words to their original forms, such as restoring "running" to "run", and remove stop words without practical meaning, such as "de", "shi", etc.

[0020] The sentiment dictionary is a database containing a large number of words or phrases with sentiment tendencies. Each word is associated with a sentiment polarity score. For example, "good" corresponds to a positive score, and "bad" corresponds to a negative score. By matching the words in the review with the entries in the sentiment dictionary, the number and intensity of positive and negative words in the review are counted. Finally, the sentiment score of the review is obtained by weighted summation to determine whether the review is positive, neutral, or negative.

[0021] Based on the analysis results, the reviews are classified as positive, neutral, or negative. For example, if most of the words are positive, the review is classified as positive; if negative words dominate, the review is classified as negative; if positive and negative words are equal, the review is classified as neutral.

[0022] In order to further convert the results of sentiment classification into quantifiable scores, a weight score can be assigned to each sentiment tendency. For example: Positive comments: The score ranges from +1 to +5, depending on the strength of the positive sentiment words in the comment. Neutral comments: The score is 0, indicating that the comment has no strong sentiment tendency. Negative comments: The score ranges from -1 to -5, depending on the strength of the negative sentiment words in the comment. The final sentiment tendency score can be calculated by weighted averaging the proportion of positive, neutral, and negative comments and their corresponding scores to generate an overall sentiment tendency score as a quantified sentiment score.

[0023] In social media evaluation, the number of likes reflects the popularity of the product on social media, the number of shares is used to measure the influence of the product, the frequency of mentions represents the degree to which the product is discussed and paid attention to by users, the topic tags are the tags and topics used by users when discussing products to reflect the positioning and popularity of the product in social media, and the sentiment tendency is obtained through natural language processing; each element in the social media evaluation is weighted and calculated to generate a comprehensive score of the social media evaluation; and a user feedback index for the product is generated based on the comprehensive score of the user evaluation and the comprehensive score of the social media evaluation.

[0024] According to step S300, the comprehensive attention index of the product is calculated according to the popularity index of the product and the user feedback index of the product, and different weights are assigned to the two indexes according to the needs of the platform and the merchant; the calculation is performed using a weighted formula, which is as follows:

[0025] A i =w h *H i +w u *F i ;

[0026] Among them, A i is the attention index of product i, H i is the popularity index of product i,

[0027] F i is the user feedback index of product i, w h and w u They are the heat index weight and the user feedback index weight, satisfying w h +w u =1;

[0028] According to the sector to which the product belongs, a data set of products in the same sector is obtained, and the attention index of products in the same sector is generated; let the set of products in the same sector be S p , the average value of its attention index is calculated by the following formula: Among them, A p is the attention index of products in the same section, |S p | is the total number of products in the section;

[0029] According to the category of the product, a data set of products of the same category is obtained to generate the attention index of products of the same category; let the set of products of the same category be S c , the average value of its attention index is calculated by the following formula: Among them, A c is the attention index of products in the same category.

[0030] |S c | is the total number of items in the category;

[0031] According to the concept labels of the products, we obtain the data set of products with the same concept and generate the attention index of products with the same concept. Let the set of products with the same concept be S g , the average value of its attention index can be calculated by the following formula: Among them, A g is the attention index of products with the same concept, |S g | is the total number of products within the concept.

[0032] It is used to compare the relative performance of products in various dimensions and further calculate the relative attention ranking of products in their respective sections, categories and concepts. The calculation formula for the ranking within a section is as follows:

[0033] Among them, R p (i) represents the relative attention of commodity i in its sector. If R p (i)>1 means that the attention level of product i is higher than the average level of the sector, otherwise it is lower than the average level. The calculation formula for the ranking within the category is as follows: in,

[0034] R c (i) represents the relative attention of product i in its category. If R c (i)>1, indicating that the attention level of product i is higher than the category average level, otherwise it is lower than the category average level. The calculation formula for the intra-concept ranking is as follows: Among them, R g (i) represents the relative attention of product i in its concept. If R g (i)>1, indicating that the attention level of product i is higher than the average level of the concept, otherwise it is lower than the average level.

[0035] According to step S400, a deep neural network is used as an artificial intelligence model to integrate the attention index of different dimensions; the input layer includes three inputs, specifically the attention index of products in the same section, the attention index of products in the same category, and the attention index of products in the same concept; the hidden layer uses multiple levels of neurons to capture the relationship between each dimension, and each layer of neurons gradually integrates and extracts deep features of the data, thereby compressing multi-dimensional information into a more compact representation; the output layer generates a comprehensive attention index standard, which represents the overall market performance of the product under the section, category and concept.

[0036] Input the attention index of products in the same section, the attention index of products in the same category, and the attention index of products in the same concept into the input layer of the deep neural network, collect historical product data, including the attention index of products in different sections, categories, and concepts, for training the model, so that the model can identify the nonlinear relationship between various dimensions; generate the target attention value by annotating the sales performance and market response of historical products; adjust the weight parameters by learning the relationship between the target value and the input data, and make predictions on new product data; through the hidden layer of the neural network, the model can extract the deep features of each dimension, and different hidden layer neurons gradually capture the mutual influence of products in sections, categories, and concepts by weighted combination of attention indexes of different dimensions; finally, the model generates an attention index standard in the output layer;

[0037] If the actual attention index is higher than the attention index standard, it means that the product performs well and exceeds market expectations; if the actual attention index is lower than the attention index standard, it means that the product performs poorly and is lower than market expectations; the product attention is generated based on the difference between the standard value of the model and the actual attention index.

[0038] A digital management system for measuring product attention, comprising:

[0039] Data crawling module: including: data input unit, HTTP request unit, HTML parsing unit, content processing unit and request frequency control unit; wherein the data input unit inputs the e-commerce website to be crawled and the collected data items, the data items include the number of views, clicks, purchases, social media evaluations and user evaluations of the goods, the HTTP request unit uses the Requests library to send HTTP requests to obtain web page content, the HTML parsing unit uses the BeautifulSoup library to parse HTML, the content processing unit processes paging and dynamic content, and the request frequency control unit sets the request interval;

[0040] Index generation module: including: a click-through rate and purchase rate calculation unit, a heat index generation unit, a user evaluation processing unit, a social media evaluation processing unit and a user feedback index generation unit; wherein the click-through rate and purchase rate calculation unit calculates the click-through rate and purchase rate of the product according to the data item, the heat index generation unit generates the heat index of the product according to the click-through rate and the purchase rate, the user evaluation includes the user rating, user comment text, emotional tendency, user identity, user tag and picture and video feedback, the user evaluation processing unit generates a user evaluation comprehensive score according to the user evaluation, the social media evaluation includes the number of likes, the number of shares, the mention frequency, the topic tag and the emotional tendency, the social media evaluation processing unit generates a social media evaluation comprehensive score according to the social media evaluation, and the user feedback index generation unit generates a user feedback index of the product according to the user evaluation comprehensive score and the social media evaluation comprehensive score;

[0041] The commodity attention index generation module includes: a data set generation unit and an attention generation unit; wherein the data set generation unit generates the commodity attention index according to the commodity heat index and the commodity user feedback index, obtains the commodity section, commodity category and commodity concept of the commodity, obtains the commodity data set of the same section according to the commodity section, obtains the commodity data set of the same category according to the commodity category, obtains the commodity data set of the same concept according to the commodity concept, and the attention generation unit generates the attention index of the commodity of the same section according to the commodity data set of the same section, generates the attention index of the commodity of the same category according to the commodity data set of the same category, and generates the attention index of the commodity of the same concept according to the commodity data set of the same concept;

[0042] Artificial intelligence model integration and standardization module: including: artificial intelligence model training unit and attention generation unit; among them, the artificial intelligence model training unit uses the artificial intelligence model to integrate the attention index of products in the same section, the attention index of products in the same category and the attention index of products with the same concept to form the attention index standard of the products, and the attention generation unit compares the attention index standard of the products with the attention index of the products to generate the attention of the products.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] 1. The present invention conducts detailed sentiment analysis and multi-dimensional evaluation processing on user reviews, which not only includes ratings, but also combines information such as the sentiment tendency of the comments, user identity, tags, graphic, text and video feedback, so as to more comprehensively and accurately reflect the user's true feelings and feedback on the products.

[0045] 2. The present invention can not only evaluate the performance of a single commodity by classifying and analyzing the sectors, categories and concepts to which the commodities belong, but also make horizontal comparisons of commodities of the same type, sector and concept to generate respective attention indexes. This method provides merchants with a more comprehensive market analysis and facilitates merchants to formulate more accurate operating strategies.

[0046] 3. The present invention introduces artificial intelligence technology, which integrates the attention index of products in the same sector, category, and concept through a deep learning model to form a standard for product attention, and compares it with the attention of actual products, so as to more accurately evaluate the market performance of products; this dynamic standardization process effectively solves the limitations of the traditional system evaluation process, making the product attention evaluation more intelligent and dynamic. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic diagram of the steps of a digital management method for measuring product attention in the present invention;

[0048] Figure 2 It is a system structure diagram of a digital management system for measuring product attention in the present invention. DETAILED DESCRIPTION

[0049] 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.

[0050] Example: Figure 1-Figure 2 As shown, the present invention provides a technical solution.

[0051] According to one embodiment of the present invention, Figure 1 A step diagram of a digital management method for measuring product attention is shown in the figure. A digital management method for measuring product attention comprises the following steps:

[0052] S100, input the e-commerce website to be crawled and the collected data items, wherein the data items include the number of views, clicks, purchases, social media reviews and user reviews of the product, use the Requests library to send HTTP requests to obtain web page content, use the BeautifulSoup library to parse HTML, process paging and dynamic content, and set the request interval;

[0053] S200, calculating the click-through rate and purchase rate of the product according to the data items, and generating a popularity index of the product according to the click-through rate and the purchase rate; the user evaluation includes user ratings, user comment texts, sentiment orientation, user identities, user tags, and picture and video feedback, and generating a user evaluation comprehensive score according to the user evaluation; the social media evaluation includes the number of likes, the number of shares, the mention frequency, topic tags, and sentiment orientation, and generating a social media evaluation comprehensive score according to the social media evaluation; and generating a user feedback index of the product according to the user evaluation comprehensive score and the social media evaluation comprehensive score;

[0054] S300, generating a product attention index according to the product popularity index and the product user feedback index, obtaining the product section, product category and product concept of the product, obtaining a product data set of the same section according to the product section, obtaining a product data set of the same category according to the product category, obtaining a product data set of the same concept according to the product concept, generating an attention index of the products of the same section according to the product data set of the same section, generating an attention index of the products of the same category according to the product data set of the same category, and generating an attention index of the products of the same concept according to the product data set of the same concept;

[0055] S400. Use an artificial intelligence model to integrate the attention index of products in the same section, the attention index of products in the same category, and the attention index of products with the same concept to form a product attention index standard, compare the product attention index standard with the product attention index, and generate product attention.

[0056] According to step S100, the user specifies the URL of the target e-commerce website and specifies the data items to be collected, including the number of views, clicks, purchases, social media reviews and user reviews of the product; uses a web crawler to send HTTP requests to obtain web page content from the server, and the request header simulates browser access to avoid being identified as a robot program; the crawler controls the frequency when sending requests and sets the request interval to prevent frequent requests in a short period of time from burdening the target website or causing the IP to be banned; after obtaining the web page content, the HTML page is parsed, and according to the different structures of the e-commerce website, the crawler program uses the HTML parsing tool BeautifulSoup to extract data items, and the data items are embedded in specific tags of the web page. The crawler finds the specific tags according to the page structure and extracts the text content therein;

[0057] E-commerce websites divide product lists into multiple pages for display. Crawler programs can automatically identify paging links and grab data from each page. This is achieved by parsing the URL of the paging button or dynamic request link, and sending requests to each page in turn to obtain its content.

[0058] For e-commerce websites that use JavaScript to asynchronously load and dynamically present product data, the crawler needs to process dynamic content, simulate browser behavior, load JavaScript, or send API requests to the data interface to obtain dynamically generated data; if the e-commerce website integrates user interaction data on social media, the crawler collects social media evaluation data of the product by parsing the embedded social media information; if the e-commerce website does not integrate user interaction data on social media, the crawler accesses the social media platform and grabs social media evaluations related to the product through the corresponding API or page;

[0059] The e-commerce website displays user reviews. The crawler locates the display location of the user review data and extracts the user rating, user comment text, sentiment, user identity, user tags, and image and video feedback provided by the user. The crawler program categorizes the user review data.

[0060] The crawler sets a random time interval after each request to simulate the operation behavior of human users and uses the IP proxy pool to dynamically change the IP address.

[0061] According to step S200, based on the acquired views, clicks and purchases of the product, the click rate and purchase rate are calculated. The click rate is the ratio of the clicks to the views, and the purchase rate is the ratio of the purchases to the clicks. The click rate reflects the user's initial interest, and the purchase rate measures the effect of converting interest into actual purchases. The popularity index of the product is calculated based on the click rate and the purchase rate.

[0062] In this embodiment, a smart watch is being sold on an e-commerce platform. For the purpose of the experiment, we obtained the data on the number of views, clicks, purchases, and user and social media reviews of the product from the platform. The goal is to calculate the popularity index, user review score, and social media review score of the product through these data, and finally generate the user feedback index of the product. The number of views is 10,000, the number of clicks is 2,000, and the number of purchases is 300.

[0063] According to step S200, in the user evaluation, the user rating represents the user's rating for the product, which is presented in the form of a positive integer; the user comment text is obtained, and the emotional tendency of the comment text is analyzed through natural language processing to determine whether the user's comment is positive, neutral or negative, and quantified into a score as the emotional tendency; the user identity is the user's authentication information on the e-commerce platform; the user tag is a characteristic tag used to evaluate the product when the user evaluates the product; the picture and video feedback shows the use effect of the product; each element in the user evaluation is weighted and calculated to generate a comprehensive user evaluation score; user rating: an average of 4.2 / 5 (based on 500 ratings), user comment text: 500 comments were analyzed through NLP processing, and the emotional tendency was: positive comments: 60% (300), neutral comments: 20% (100), negative comments: 20% (100), user identity: 80% of users are authenticated users, user tags: users mentioned "long battery life" and "reasonable price" many times, picture and video feedback: 40% of users uploaded pictures / videos to show the use effect of the product.

[0064] Calculate the click-through rate and purchase rate of the product. Click-through rate = clicks / views = 2,000 / 10,000 = 0.2 (20%), purchase rate = purchases / clicks = 300 / 2,000 = 0.15 (15%). The popularity index of the product is calculated based on the weighted click-through rate and purchase rate. The weights of click-through rate and purchase rate are 0.6 and 0.4 respectively: popularity index = (click-through rate * 0.6) + (purchase rate * 0.4) = (0.2 * 0.6) + (0.15 * 0.4) = 0.12 + 0.06 = 0.18. The user rating is 4.2, which directly participates in the comprehensive rating of user evaluation. Emotional tendency: Emotions are divided into positive, neutral, and negative, and the emotional scores are: positive: +1, neutral: 0, negative: -1, emotional score = (300*1+100*0+100*-1) / 500 = (300-100) / 500 = 0.4. User identity: 80% of users are authenticated, the weight of authenticated users is 0.8, the weight of non-authenticated users is 0.2, and the user identity score is: user identity score = 0.8*80%+0.2*20%=0.64+0.04=0.68. Picture / video feedback: 40% of users upload pictures / videos, the picture / video feedback weight is 0.5, and the picture feedback score is: picture feedback score = 0.5*40% = 0.2.

[0065] The final comprehensive user evaluation score = user score * weight + sentiment score * weight + user identity score * weight + picture feedback score * weight. The weights are 0.4, 0.2, 0.2 and 0.2 respectively, so the comprehensive user evaluation score = (4.2*0.4)+(0.4*0.2)+(0.68*0.2)+(0.2*0.2)=1.68+0.08+0.136+0.04=1.936.

[0066] In social media evaluation, the number of likes reflects the popularity of the product on social media, the number of shares is used to measure the influence of the product, the frequency of mentions represents the degree to which the product is discussed and paid attention to by users, the topic tags are the tags and topics used by users when discussing the product to reflect the positioning and popularity of the product in social media, and the sentiment tendency is obtained through natural language processing; the various elements in the social media evaluation are weighted to generate a comprehensive score of the social media evaluation; the user feedback index of the product is generated according to the comprehensive score of the user evaluation and the comprehensive score of the social media evaluation. Number of likes: 3,000, number of shares: 500, frequency of mentions: 2,000 times, topic tags: #smartwatch, #healthmonitoring, #sportstracking, social media sentiment analysis: the sentiment tendency is analyzed by NLP as follows: positive sentiment: 65%, neutral sentiment: 25%, negative sentiment: 10%. Among them, the weight of likes is 0.4, the weight of shares is 0.3, the weight of mention frequency is 0.2, the weight of sentiment tendency is 0.1, and the sentiment tendency score = 65%*1+25%*0+10%*(-1)=0.55.

[0067] The final comprehensive score of social media evaluation = (weight of number of likes + weight of number of shares + weight of mention frequency + weight of sentiment analysis); then the comprehensive score of social media evaluation = (3000*0.4)+(500*0.3)+(2000*0.2)+(0.55*0.1)=1200+150+400+0.055=1750.055.

[0068] User feedback index = comprehensive score of user evaluation + comprehensive score of social media evaluation, then user feedback index = 1.936 + 1750.055 = 1751.991.

[0069] According to step S300, the comprehensive attention index of the product is calculated based on the popularity index of the product and the user feedback index of the product, and different weights are assigned to the two indexes according to the needs of the platform and the merchant; the smart watch belongs to the "electronic products" section, the "smart device" category, and is related to the "health monitoring" concept. In this embodiment, we obtain the popularity index and user feedback index data of the product, as well as the relevant data of other products in the section, category and concept.

[0070] The calculation is done through a weighted formula, as follows:

[0071] A i =w h *H i +w u *F i =0.4*0.18+0.6*1751.991=1051.2666;

[0072] Among them, A i is the attention index of product i, H i is the popularity index of product i,

[0073] F i is the user feedback index of product i, w h and w u They are the heat index weight and the user feedback index weight, satisfying w h +w u =1;

[0074] According to the sector to which the product belongs, a data set of products in the same sector is obtained, and the attention index of products in the same sector is generated; let the set of products in the same sector be S p , the average value of its attention index is calculated by the following formula: Among them, A p is the attention index of products in the same section, |S p | is the total number of products in the section;

[0075] According to the category of the product, a data set of products of the same category is obtained to generate the attention index of products of the same category; let the set of products of the same category be S c , the average value of its attention index is calculated by the following formula: Among them, A c is the attention index of products in the same category, |S c | is the total number of items in the category;

[0076] According to the concept labels of the products, we obtain the data set of products with the same concept and generate the attention index of products with the same concept. Let the set of products with the same concept be S g , the average value of its attention index can be calculated by the following formula: Among them, A g is the attention index of products with the same concept, |S g | is the total number of products within the concept.

[0077] It is used to compare the relative performance of products in various dimensions and further calculate the relative attention ranking of products in their respective sections, categories and concepts. The calculation formula for the ranking within a section is as follows:

[0078] Among them, R p (i) represents the relative attention of commodity i in its sector. If R p (i)>1, indicating that the attention level of product i is higher than the average level of the sector. Otherwise, it is lower than the average level, indicating that the attention index of smart watches is higher than the average level of the sector. The calculation formula for the ranking within the category is as follows: Among them, R c (i) represents the relative attention of product i in its category. If R c (i)>1, indicating that the attention level of product i is higher than the average level of the category. Otherwise, it is lower than the average level, indicating that the attention index of smart watches is higher than the average level of the category. The calculation formula for the ranking within a concept is as follows: Among them, R g (i) represents the relative attention of product i in its concept. If R g (i)>1, indicating that the attention level of product i is higher than the average level of the concept, otherwise it is lower than the average level, indicating that the attention index of smart watches is higher than the average level of the concept.

[0079] According to step S400, a deep neural network is used as an artificial intelligence model to integrate the attention index of different dimensions; the input layer includes three inputs, specifically the attention index of products in the same section, the attention index of products in the same category, and the attention index of products in the same concept; the hidden layer uses multiple levels of neurons to capture the relationship between each dimension, and each layer of neurons gradually integrates and extracts deep features of the data, thereby compressing multi-dimensional information into a more compact representation; the output layer generates a comprehensive attention index standard, which represents the overall market performance of the product under the section, category and concept.

[0080] Input the attention index of products in the same section, the attention index of products in the same category, and the attention index of products in the same concept into the input layer of the deep neural network, collect historical product data, including the attention index of products in different sections, categories, and concepts, for training the model, so that the model can identify the nonlinear relationship between various dimensions; generate the target attention value by annotating the sales performance and market response of historical products; adjust the weight parameters by learning the relationship between the target value and the input data, and make predictions on new product data; through the hidden layer of the neural network, the model can extract the deep features of each dimension, and different hidden layer neurons gradually capture the mutual influence of products in sections, categories, and concepts by weighted combination of attention indexes of different dimensions; finally, the model generates an attention index standard in the output layer;

[0081] If the actual attention index is higher than the attention index standard, it means that the product performs well and exceeds market expectations; if the actual attention index is lower than the attention index standard, it means that the product performs poorly and is lower than market expectations; the product attention is generated based on the difference between the standard value of the model and the actual attention index.

[0082] A digital management system for measuring product attention, comprising:

[0083] Data crawling module: including: data input unit, HTTP request unit, HTML parsing unit, content processing unit and request frequency control unit; wherein the data input unit inputs the e-commerce website to be crawled and the collected data items, the data items include the number of views, clicks, purchases, social media evaluations and user evaluations of the goods, the HTTP request unit uses the Requests library to send HTTP requests to obtain web page content, the HTML parsing unit uses the BeautifulSoup library to parse HTML, the content processing unit processes paging and dynamic content, and the request frequency control unit sets the request interval;

[0084] Index generation module: including: a click-through rate and purchase rate calculation unit, a heat index generation unit, a user evaluation processing unit, a social media evaluation processing unit and a user feedback index generation unit; wherein the click-through rate and purchase rate calculation unit calculates the click-through rate and purchase rate of the product according to the data item, the heat index generation unit generates the heat index of the product according to the click-through rate and the purchase rate, the user evaluation includes the user rating, user comment text, emotional tendency, user identity, user tag and picture and video feedback, the user evaluation processing unit generates a user evaluation comprehensive score according to the user evaluation, the social media evaluation includes the number of likes, the number of shares, the mention frequency, the topic tag and the emotional tendency, the social media evaluation processing unit generates a social media evaluation comprehensive score according to the social media evaluation, and the user feedback index generation unit generates a user feedback index of the product according to the user evaluation comprehensive score and the social media evaluation comprehensive score;

[0085] The commodity attention index generation module includes: a data set generation unit and an attention generation unit; wherein the data set generation unit generates the commodity attention index according to the commodity heat index and the commodity user feedback index, obtains the commodity section, commodity category and commodity concept of the commodity, obtains the commodity data set of the same section according to the commodity section, obtains the commodity data set of the same category according to the commodity category, obtains the commodity data set of the same concept according to the commodity concept, and the attention generation unit generates the attention index of the commodity of the same section according to the commodity data set of the same section, generates the attention index of the commodity of the same category according to the commodity data set of the same category, and generates the attention index of the commodity of the same concept according to the commodity data set of the same concept;

[0086] Artificial intelligence model integration and standardization module: including: artificial intelligence model training unit and attention generation unit; among them, the artificial intelligence model training unit uses the artificial intelligence model to integrate the attention index of products in the same section, the attention index of products in the same category and the attention index of products with the same concept to form the attention index standard of the products, and the attention generation unit compares the attention index standard of the products with the attention index of the products to generate the attention of the products.

[0087] In this embodiment, the model training unit aggregates all attention indexes into a training data set, including the attention index of smart watches and products in the same section, category, and concept. The attention index of each product is extracted as a feature for training, and the target variable is the attention ranking of each product. The training data set is input into the model for training to generate a standard model of the attention index.

[0088] The attention generation unit uses the trained model to predict all products and form an attention standard. The attention index of the smart watch is compared with the generated attention standard to generate the product attention. The calculated product attention = 1051.27 / 1100 = 0.956, indicating that the attention of the smart watch is slightly lower than the standard generated by the model.

[0089] 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. A digital management method for measuring product attention, characterized in that: The method comprises the following steps: S100, input the e-commerce website to be crawled and the collected data items, wherein the data items include the number of views, clicks, purchases, social media reviews and user reviews of the product, use the Requests library to send HTTP requests to obtain web page content, use the BeautifulSoup library to parse HTML, process paging and dynamic content, and set the request interval; S200, calculating the click-through rate and purchase rate of the product according to the data items, and generating a popularity index of the product according to the click-through rate and the purchase rate; the user evaluation includes user ratings, user comment texts, sentiment orientation, user identities, user tags, and picture and video feedback, and generating a user evaluation comprehensive score according to the user evaluation; the social media evaluation includes the number of likes, the number of shares, the mention frequency, topic tags, and sentiment orientation, and generating a social media evaluation comprehensive score according to the social media evaluation; and generating a user feedback index of the product according to the user evaluation comprehensive score and the social media evaluation comprehensive score; S300, generating a product attention index according to the product popularity index and the product user feedback index, obtaining the product section, product category and product concept of the product, obtaining a product data set of the same section according to the product section, obtaining a product data set of the same category according to the product category, obtaining a product data set of the same concept according to the product concept, generating an attention index of the products of the same section according to the product data set of the same section, generating an attention index of the products of the same category according to the product data set of the same category, and generating an attention index of the products of the same concept according to the product data set of the same concept; S400. Use an artificial intelligence model to integrate the attention index of products in the same section, the attention index of products in the same category, and the attention index of products with the same concept to form a product attention index standard, compare the product attention index standard with the product attention index, and generate product attention.

2. A digital management method for measuring product attention according to claim 1, characterized in that: According to step S100, the user specifies the URL of the target e-commerce website and specifies the data items to be collected, wherein the data items include the number of views, clicks, purchases, social media reviews, and user reviews of the product; Use a web crawler to send HTTP requests to obtain web page content from the server. The request header will simulate browser access to avoid being identified as a robot program. The crawler controls the frequency when sending requests and sets the request interval to prevent frequent requests in a short period of time from burdening the target website or causing the IP to be blocked. After obtaining the web page content, the HTML page is parsed. According to the different structures of e-commerce websites, the crawler program uses the HTML parsing tool BeautifulSoup to extract data items. The data items are embedded in specific tags on the web page. The crawler finds specific tags based on the page structure and extracts the text content therein. E-commerce websites divide product lists into multiple pages for display. Crawler programs can automatically identify paging links and grab data from each page. This is achieved by parsing the URL of the paging button or dynamic request link, and sending requests to each page in turn to obtain its content.

3. A digital management method for measuring product attention according to claim 2, characterized in that: For e-commerce websites that use JavaScript to asynchronously load and dynamically present product data, the crawler needs to process dynamic content, simulate browser behavior, load JavaScript, or send API requests to the data interface to obtain dynamically generated data; if the e-commerce website integrates user interaction data on social media, the crawler collects social media evaluation data of the product by parsing the embedded social media information; if the e-commerce website does not integrate user interaction data on social media, the crawler accesses the social media platform and grabs social media evaluations related to the product through the corresponding API or page; The e-commerce website displays user reviews. The crawler locates the display location of the user review data and extracts the user rating, user comment text, sentiment, user identity, user tags, and image and video feedback provided by the user. The crawler program categorizes the user review data. The crawler sets a random time interval after each request to simulate the operation behavior of human users and uses the IP proxy pool to dynamically change the IP address.

4. A digital management method for measuring product attention according to claim 1, characterized in that: According to step S200, based on the acquired views, clicks and purchases of the product, the click rate and purchase rate are calculated. The click rate is the ratio of the clicks to the views, and the purchase rate is the ratio of the purchases to the clicks. The click rate reflects the user's initial interest, and the purchase rate measures the effect of converting interest into actual purchases. The popularity index of the product is calculated based on the click rate and the purchase rate.

5. A digital management method for measuring product attention according to claim 4, characterized in that: According to step S200, in the user evaluation, the user rating represents the score given by the user to the product, which is presented in the form of a positive integer; the user comment text is obtained, and the sentiment tendency of the comment text is analyzed through natural language processing to determine whether the user's comment is positive, neutral or negative, and quantified into a score as the sentiment tendency; the user identity is the authentication information of the user on the e-commerce platform; The user tag is a characteristic tag used to evaluate the product when the user evaluates the product; the picture and video feedback show the use effect of the product; each element in the user evaluation is weighted and calculated to generate a comprehensive score of the user evaluation; In social media evaluation, the number of likes reflects the popularity of the product on social media, the number of shares is used to measure the influence of the product, the frequency of mentions represents the degree to which the product is discussed and paid attention to by users, the topic tags are the tags and topics used by users when discussing products to reflect the positioning and popularity of the product in social media, and the sentiment tendency is obtained through natural language processing; each element in the social media evaluation is weighted and calculated to generate a comprehensive score of the social media evaluation; and a user feedback index for the product is generated based on the comprehensive score of the user evaluation and the comprehensive score of the social media evaluation.

6. A digital management method for measuring product attention according to claim 1, characterized in that: According to step S300, the comprehensive attention index of the product is calculated according to the popularity index of the product and the user feedback index of the product, and different weights are assigned to the two indexes according to the needs of the platform and the merchant; the calculation is performed using a weighted formula, which is as follows: A i =w h *H i +w u *F i ; Among them, A i is the attention index of product i, H i is the popularity index of product i, F i is the user feedback index of product i, w h and w u They are the heat index weight and the user feedback index weight, satisfying w h +w u =1; According to the sector to which the product belongs, a data set of products in the same sector is obtained, and the attention index of products in the same sector is generated; let the set of products in the same sector be S p , the average value of its attention index is calculated by the following formula: Among them, A p is the attention index of products in the same section, |S p | is the total number of products in the section; According to the category of the product, a data set of products of the same category is obtained to generate the attention index of products of the same category; let the set of products of the same category be S c , the average value of its attention index is calculated by the following formula: Among them, A c is the attention index of products in the same category, |S c | is the total number of items in the category; According to the concept labels of the products, we obtain the data set of products with the same concept and generate the attention index of products with the same concept. Let the set of products with the same concept be S g , the average value of its attention index can be calculated by the following formula: Among them, A g is the attention index of products with the same concept, |S g | is the total number of products within the concept.

7. A digital management method for measuring product attention according to claim 6, characterized in that: It is used to compare the relative performance of products in various dimensions and further calculate the relative attention ranking of products in their respective sections, categories and concepts. The calculation formula for the ranking within a section is as follows: Among them, R p (i) represents the relative attention of commodity i in its sector. If R p (i)>1 means that the attention level of product i is higher than the average level of the sector, otherwise it is lower than the average level. The calculation formula for the ranking within the category is as follows: Among them, R c (i) represents the relative attention of product i in its category. If R c (i)>1 means that the attention level of product i is higher than the average level of the category, otherwise it is lower than the average level. The calculation formula for the ranking within a concept is as follows: Among them, R g (i) represents the relative attention of product i in its concept. If R g (i)>1, indicating that the attention level of product i is higher than the average level of the concept, otherwise it is lower than the average level.

8. A digital management method for measuring product attention according to claim 1, characterized in that: According to step S400, a deep neural network is used as an artificial intelligence model to integrate the attention index of different dimensions; the input layer includes three inputs, specifically the attention index of products in the same section, the attention index of products in the same category, and the attention index of products in the same concept; the hidden layer uses multiple layers of neurons to capture the relationship between the dimensions, and the neurons in each layer gradually integrate and extract the deep features of the data, thereby compressing the multi-dimensional information into a more compact representation; The output layer generates a comprehensive attention index standard, which represents the overall market performance of the product under the sector, category and concept.

9. A digital management method for measuring product attention according to claim 8, characterized in that: Input the attention index of products in the same section, the attention index of products in the same category, and the attention index of products in the same concept into the input layer of the deep neural network, collect historical product data, including the attention index of products in different sections, categories, and concepts, for training the model, so that the model can identify the nonlinear relationship between various dimensions; generate the target attention value by annotating the sales performance and market response of historical products; adjust the weight parameters by learning the relationship between the target value and the input data, and make predictions on new product data; through the hidden layer of the neural network, the model can extract the deep features of each dimension, and different hidden layer neurons gradually capture the mutual influence of products in sections, categories, and concepts by weighted combination of attention indexes of different dimensions; finally, the model generates an attention index standard in the output layer; If the actual attention index is higher than the attention index standard, it means that the product performs well and exceeds market expectations; if the actual attention index is lower than the attention index standard, it means that the product performs poorly and is lower than market expectations; the product attention is generated based on the difference between the standard value of the model and the actual attention index.

10. A digital management system for measuring product attention, using a digital management method for measuring product attention according to any one of claims 1 to 9, characterized in that: include: Data crawling module: including: data input unit, HTTP request unit, HTML parsing unit, content processing unit and request frequency control unit; wherein the data input unit inputs the e-commerce website to be crawled and the collected data items, the data items include the number of views, clicks, purchases, social media evaluations and user evaluations of the goods, the HTTP request unit uses the Requests library to send HTTP requests to obtain web page content, the HTML parsing unit uses the BeautifulSoup library to parse HTML, the content processing unit processes paging and dynamic content, and the request frequency control unit sets the request interval; Index generation module: including: a click-through rate and purchase rate calculation unit, a heat index generation unit, a user evaluation processing unit, a social media evaluation processing unit and a user feedback index generation unit; wherein the click-through rate and purchase rate calculation unit calculates the click-through rate and purchase rate of the product according to the data item, the heat index generation unit generates the heat index of the product according to the click-through rate and the purchase rate, the user evaluation includes the user rating, user comment text, emotional tendency, user identity, user tag and picture and video feedback, the user evaluation processing unit generates a user evaluation comprehensive score according to the user evaluation, the social media evaluation includes the number of likes, the number of shares, the mention frequency, the topic tag and the emotional tendency, the social media evaluation processing unit generates a social media evaluation comprehensive score according to the social media evaluation, and the user feedback index generation unit generates a user feedback index of the product according to the user evaluation comprehensive score and the social media evaluation comprehensive score; The commodity attention index generation module includes: a data set generation unit and an attention generation unit; wherein the data set generation unit generates the commodity attention index according to the commodity heat index and the commodity user feedback index, obtains the commodity section, commodity category and commodity concept of the commodity, obtains the commodity data set of the same section according to the commodity section, obtains the commodity data set of the same category according to the commodity category, obtains the commodity data set of the same concept according to the commodity concept, and the attention generation unit generates the attention index of the commodity of the same section according to the commodity data set of the same section, generates the attention index of the commodity of the same category according to the commodity data set of the same category, and generates the attention index of the commodity of the same concept according to the commodity data set of the same concept; Artificial intelligence model integration and standardization module: including: artificial intelligence model training unit and attention generation unit; among them, the artificial intelligence model training unit uses the artificial intelligence model to integrate the attention index of products in the same section, the attention index of products in the same category and the attention index of products with the same concept to form the attention index standard of the products, and the attention generation unit compares the attention index standard of the products with the attention index of the products to generate the attention of the products.

Images