Online reading system and method based on cloud computing

Abstract

The present invention relates to the field of cloud computing, and discloses an online reading system and method based on cloud computing, which is used to solve the problem that when a user performs multi-task reading, the user cannot quickly and effectively find the most needed document according to the document sorting. The method comprises: managing users, providing a registration page for users, and recording the activities of users in the system, managing documents, providing an interface for uploading documents for users, and storing and backing up the uploaded documents, obtaining a document importance index by calculation, sorting the order of documents opened by users when performing multi-task reading according to the document importance index, obtaining a user churn index by calculation, and sending reading information to users according to the user churn index, thereby effectively avoiding the situation that users are inconvenient to browse the most needed content due to opening too many documents, effectively improving user experience and reducing user churn.

Description

Technical Field

[0001] The present invention relates to the field of cloud computing, and more specifically to an online reading system and method based on cloud computing. Background Art

[0002] Online reading refers to the process of browsing, reading and obtaining various text information such as texts, books, articles, news, etc. online using electronic devices through Internet technology. Users can access the required text information through the Internet anytime and anywhere without carrying a large amount of paper materials.

[0003] The existing online reading method arranges the documents in the order in which the user opens them when performing multi-task reading. This online reading method may cause the user to open too many documents and thus cannot conveniently browse and search for the most needed content.

[0004] In view of the above problems, the present invention proposes a solution. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides an online reading system and method based on cloud computing to solve the problems existing in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The online reading method based on cloud computing includes the following steps:

[0008] Manage users, provide registration pages for users, and record user activities in the system;

[0009] Manage documents, provide users with an interface for uploading documents, and store and back up uploaded documents;

[0010] The document importance index is obtained by calculation, and the order of documents opened by the user during multi-tasking reading is sorted according to the document importance index;

[0011] The user churn index is obtained by calculation, and reading information is sent to users according to the user churn index.

[0012] Preferably, the document importance index calculation steps are:

[0013] Preprocess the text and use the Jieba word segmentation tool to segment the document, count the total number of words in the document, traverse each word in the text according to the keywords used by the user's search, record the number of times the keyword appears in the document, and calculate the keyword density coefficient;

[0014] Based on the keywords used by the user in the search, the TF-IDF algorithm is used to calculate the keyword frequency coefficient of the document selected by the user for multi-task reading;

[0015] The click rate, share rate and number of comments of the documents selected by users for multi-task reading are counted, and the document attention coefficient is calculated based on the click rate, share rate and number of comments;

[0016] The document importance index is calculated based on the keyword density coefficient, keyword frequency coefficient and document attention coefficient.

[0017] Preferably, the word segmentation process of the document is performed using the Jieba word segmentation tool, and the specific steps are as follows:

[0018] Install the jieba word segmentation tool, import the jieba library in the Python script, and load the document to be segmented into the program;

[0019] Use the word segmentation function provided by the jieba library to segment the document, traverse the generator object or use the list to obtain the result after word segmentation;

[0020] Filter stop words based on the word segmentation results.

[0021] Preferably, the step of calculating the keyword frequency coefficient of the document selected by the user for multi-task reading is:

[0022] Collect all relevant documents to form a document collection, tokenize the documents, and split the text into individual words;

[0023] For each document, count the number of times each word appears in the document, record it as the word frequency, and calculate the inverse document frequency of each word;

[0024] Multiply the word frequency and the inverse document frequency to get the final TF-IDF value, which is recorded as the keyword frequency coefficient.

[0025] Preferably, the user churn index calculation step is:

[0026] Count the number of user logins during the detection period, calculate the user login frequency, and record it as user activity;

[0027] Count the number of documents opened by the user during the last multi-tasking reading, and record it as the number of multi-tasking documents;

[0028] Count the user's last reading time, and calculate the time from the user's last viewing to the current one, which is recorded as the interval time;

[0029] The user churn index is calculated by weighted summation based on user activity, the number of multi-task documents, and the interval time.

[0030] Preferably, the sending of reading information to users based on the user churn index is to compare the user churn index with a preset threshold value. If the user churn index is greater than the preset threshold value, it indicates that the possibility of user churn is relatively high, and the document with the highest document importance index when the user last performed a multi-document operation is extracted, and based on the document keywords, a cosine similarity algorithm is used to screen out documents with high similarity, and similar documents are randomly sent to users in the form of advertisements. If the user churn index is less than the preset threshold value, it indicates that the possibility of user churn is relatively low, and no advertisements are sent to the user.

[0031] The online reading system based on cloud computing includes user management module, document management module, reading module and information notification module. The modules are connected through signals:

[0032] The user management module is used to manage documents. It provides users with an interface for uploading documents, allowing users to upload documents, and storing and backing up uploaded documents.

[0033] The document management module manages documents by providing users with an interface for uploading documents, enabling users to upload documents, and storing and backing up uploaded documents;

[0034] The reading module calculates the document importance index and sorts the order of documents opened by users during multi-tasking reading according to the document importance index;

[0035] The information notification module calculates the user churn index and sends reading information to users based on the user churn index.

[0036] Technical effects and advantages of the present invention:

[0037] Manage users, provide users with a registration page, and record user activities in the system; manage documents, provide users with an interface for uploading documents, and store and back up uploaded documents; calculate the document importance index, and sort the order of documents opened by users when performing multi-tasking reading according to the document importance index; calculate the user churn index, and send reading information to users based on the user churn index, effectively avoiding the situation where users are inconvenient to browse the most needed content due to opening too many documents, effectively improving user experience and reducing user churn. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 The document importance index calculation flow chart of the present invention. DETAILED DESCRIPTION

[0039] The technical solutions in the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the present invention. In addition, the forms of the various structures described in the following embodiments are merely illustrative, and the cloud computing-based online reading system and method involved in the present invention are not limited to the various structures described in the following embodiments. All other implementations obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0040] The present invention provides an online reading method based on cloud computing, comprising the following steps:

[0041] S001: Manage users by providing a registration page for users, enabling them to read, evaluate and share by registering and logging in, and record user activities in the system, including reading history, comments, sharing, etc.;

[0042] S002: Manage documents by providing users with an interface for uploading documents, enabling users to upload documents, and storing and backing up uploaded documents to ensure the security of document storage;

[0043] S003: Obtaining a document importance index by calculation, and sorting the order of documents opened by the user during multi-tasking reading according to the document importance index;

[0044] S004: obtaining a user churn index by calculation, and sending reading information to the user according to the user churn index;

[0045] In this embodiment, it should be specifically explained that the steps of managing users are:

[0046] Provide a user registration interface to collect basic information of new users, such as user name, password, email address, etc., and implement form validation to ensure that the information entered by the user complies with the specifications;

[0047] After user registration, users are required to authenticate and log in with a username and password, and a multi-tasking reading function is provided, allowing users to browse multiple documents at the same time;

[0048] Allow users to set up and edit their personal profiles, including uploading avatars, changing usernames, adding contact information, etc., and provide a user-friendly interface to enable them to easily manage their personal profiles;

[0049] Allow users to change their passwords and provide password reset functions, usually through email or mobile phone verification to ensure the security of user accounts;

[0050] Manage users' permissions and roles to ensure they can only access resources and functions for which they have permissions;

[0051] Recording user activities on the platform, such as reading history, comments, likes, etc., helps personalize recommendations and improve user experience;

[0052] Allow users to register and log in using their social media accounts and provide social sharing features to let users share their reading activities.

[0053] Online reading platforms manage users, which helps improve user experience. User management allows the platform to track and analyze users' reading behaviors, interests, and preferences, thereby providing personalized recommendations and services and improving user satisfaction. By tracking and analyzing user activities, the platform can more accurately recommend books and content that users are interested in, increasing the possibility of users discovering new books. The user management module encourages users to register, log in, and participate in platform interactions, such as commenting, liking, etc., to increase user stickiness.

[0054] User management helps to improve the security of the platform. It adopts measures such as password management and identity authentication to prevent unauthorized access and hacker attacks and protect the security of user accounts. The user management module collects user behavior data, supports data analysis and statistics, provides the platform with in-depth insights into user behavior, guides operational strategies and decisions, and through user management, forms an active user community where users can communicate with each other, share experiences, and enhance the social nature of the platform.

[0055] In this embodiment, it should be specifically explained that the steps of managing the document are:

[0056] Provide an interface for users to upload documents, support multiple document formats, and implement upload verification to ensure that the document meets the platform's specified format and size;

[0057] Store documents uploaded by users to ensure that they can be stored and retrieved effectively, and back up documents to improve storage capacity and availability;

[0058] Provide document retrieval function, support keyword search, filtering and advanced search, and design a reasonable document classification system so that users can easily find documents of interest;

[0059] Support document version control to ensure that users can view the historical versions of documents and record detailed information about document modifications, such as modification time, modifier, etc.

[0060] Set access rights for documents to ensure that only users with corresponding permissions can access them, and support the management of public and private documents;

[0061] Provide online document editing function, allowing users to edit documents directly in the system, and allow users to add tags, comments, bookmarks and other annotations to better manage and communicate document content;

[0062] Allow users to share documents with other users, support social media sharing, and provide promotion and recommendation mechanisms to make high-quality documents easier for users to discover;

[0063] Provide the option to delete documents, ensure that users can manage their uploaded documents, and consider archiving some inactive documents to maintain a clean system.

[0064] Online reading platforms manage documents, which helps to improve user experience. Users can access the documents they need anytime and anywhere without carrying physical documents, which improves the convenience of reading. Through document management, the platform can provide personalized document recommendations based on users' reading history and interests, increase users' opportunities to discover new content, and provide powerful document retrieval functions. Users can quickly find the required documents through keywords, tags, etc., which improves the efficiency of document search. The platform supports document version control, allowing users to view historical versions of documents. It also provides online editing functions, allowing users to edit documents directly on the platform.

[0065] Users can add comments and tags to documents and share them with other users to promote communication and interaction between users. The platform can count data such as the number of document readings and downloads, providing users with an understanding of the popularity of documents. It also helps the platform to optimize and promote content. Through permission control, the platform ensures that users can only access documents they have permission to, protecting the security and privacy of documents. Online reading platforms reduce the demand for physical documents, help protect the environment, and provide users with a more convenient reading experience.

[0066] In this embodiment, it is necessary to specifically explain that Figure 1 As shown, the steps for calculating the document importance index are:

[0067] Preprocess the text and use the Jieba word segmentation tool to segment the document. Count the total number of words in the document. According to the keywords used by the user's search, traverse each word in the text, record the number of times the keyword appears in the document, and calculate the keyword density coefficient. The calculation formula is: , where DN is the keyword density coefficient, D 总 Denoted as the total number of words in the document, D 关 It is expressed as the number of times a keyword appears in a document. The Jieba word segmentation tool is a Chinese word segmentation tool, which is a word segmentation engine implemented by the Viterbi algorithm. It is a Chinese word segmentation tool based on statistical methods, which is used to segment Chinese text according to the word level. It uses the Viterbi algorithm and has a high word segmentation speed and good word segmentation effect.

[0068] According to the keywords used by the user in the search, the TF-IDF algorithm is used to calculate the keyword frequency coefficient of the document selected by the user for multi-task reading. The TF-IDF algorithm is a common algorithm used for information retrieval and text mining, which is used to evaluate the importance of a word to a document in a document collection. The TF-IDF algorithm considers the frequency of a word in a document and its importance in the entire document collection;

[0069] The click-through rate, share rate, and number of comments of the documents selected by users for multi-task reading are counted, and the document attention coefficient is calculated based on the click-through rate, share rate, and number of comments. The calculation formula is: , where AT represents the document attention coefficient, CL represents the click rate of the document, SH represents the sharing rate of the document, and CM represents the number of comments on the document;

[0070] The document importance index is calculated based on the keyword density coefficient, keyword frequency coefficient and document attention coefficient. The calculation formula is: , where SF is the document importance index, DN is the keyword density coefficient, keyword density refers to the frequency of keywords appearing in a document, which is usually expressed as the ratio of the number of times keywords appear in a document to the total number of words in the document. Places with high keyword density are usually the key parts of the document. Moderate keyword density helps to improve the readability and reading experience of the document, and readers can more easily understand the theme of the document. TI is the keyword frequency coefficient of the document. High-frequency keywords usually represent the theme or core content of the document. If a certain word appears frequently in a document, it may have high importance in the document. High-frequency keywords may be the key concepts of the document and play a key role in the overall understanding and expression of the document. AT is the document attention coefficient. High document attention usually means that the document is more well-known. Documents with high attention may be considered to be more credible content. Users are more inclined to read, share and comment on documents recognized and recommended by other users, which further increases the importance of the document. a1, a2, and a3 are weight coefficients of the keyword density coefficient DN, the keyword frequency coefficient TI of the document, and the document attention coefficient AT. In this embodiment, no specific calculation is performed on the specific values ​​of a1, a2, and a3.

[0071] The jieba word segmentation tool is used to segment the document, and the specific steps are as follows:

[0072] Install the jieba word segmentation tool, import the jieba library in the Python script, and load the document to be segmented into the program. The document can be a string or text read from a file;

[0073] Use the word segmentation function provided by the jieba library to segment the document, traverse the generator object or use the list to obtain the result after word segmentation;

[0074] Stop word filtering is performed on the word segmentation results to remove some meaningless high-frequency words to obtain more meaningful keywords. For example, the document content is , the result of using the word segmentation function to segment the document is .

[0075] The steps for calculating the keyword frequency coefficient of the document selected by the user for multi-task reading are as follows:

[0076] Collect all relevant documents to form a document collection, tokenize the documents, and split the text into individual words;

[0077] For each document, calculate the number of times each word appears in the document, which is recorded as the word frequency of the word. The calculation formula is: , where TF stands for word frequency, D 总 Denoted as the total number of words in the document, D 关 It is represented by the number of times the keyword appears in the document. For example, if the user searches for the keyword "online reading", the document selected by the user for multi-task reading is , , , then calculate the word frequency ;

[0078] Calculate the inverse document frequency of each word, that is, the inverse of the number of documents in which the word appears in the document collection. The calculation formula is , where IDF stands for Inverse Document Frequency, where NUM D Represented as the total number of documents in the document collection, NUM t Expressed as the number of documents containing the keyword, for example, the inverse document frequency calculation is performed on the example ;

[0079] Multiply the term frequency and the inverse document frequency to get the final TF-IDF value, which is calculated as follows: , where TF-IDF is the keyword frequency coefficient, TF is the word frequency, IDF is the inverse document frequency, and the keyword frequency coefficient is recorded as TI. For example, the keyword frequency coefficient is calculated for the example .

[0080] Sort the document importance index from high to low, and sort the documents in the user's multi-task bar according to the order of the document importance index, so that the user can read and find the required content more conveniently.

[0081] The user churn index can help companies or platforms evaluate the effectiveness of their user retention strategies. A lower user churn index usually means that users use the platform more stably, while a higher churn index may require further analysis and improvement. High user churn may be a sign of problems with the product, service, or platform. By monitoring the user churn index, you can promptly identify problems that may affect the user experience and take corresponding improvement measures. By understanding the user churn situation, you can specifically improve the quality of products or services, increase user satisfaction, and reduce user churn rates. The changing trend of the user churn index can be used to predict future user churn. This helps companies adjust their strategies in a timely manner and avoid potential user churn risks.

[0082] In this embodiment, it should be specifically explained that the steps of calculating the user churn index are:

[0083] Count the number of user logins during the detection period and calculate the user login frequency, which is recorded as user activity. The calculation formula is: , where LG represents user activity, NUM L It is represented by the number of user logins during the detection period, and T is the detection time;

[0084] Count the number of documents opened by the user during the last multi-tasking reading, and record it as the number of multi-tasking documents;

[0085] Count the user's last reading time and calculate the time from the user's last viewing to the current time, which is recorded as the interval time. The calculation formula is: , where IT represents the interval time, DT represents the current time, and T' represents the user's last reading time;

[0086] The user churn index is calculated based on user activity, the number of multi-task documents, and the interval time. The calculation formula is: , where CR represents the user churn index, LG represents user activity, which has a direct impact on the user churn index, because high user activity may mean that users are more interested in the platform. High user activity is usually associated with a lower user churn rate. Active users are more likely to participate in social interactions, comments, sharing and other activities on the platform, which can promote interaction between users, increase user stickiness to the platform, and reduce the risk of churn. MD represents the number of multi-task documents. The number of documents opened by the user last time can reflect the user's interest in the platform content. If the number of documents opened by the user is large, it may mean that the user is more interested in the platform content and has browsed and interacted with these contents. The number of documents opened by the user last time can indirectly reflect the user's satisfaction with the platform. Users with higher satisfaction may be more willing to browse more content, while low satisfaction may lead to user loss. IT represents the interval time. If the user's last login time is long from the current time, it means that the user has not used the platform or application for a long time, which may indicate an increased risk of user loss. b1, b2, and b3 represent the weight coefficients of user activity AT, the number of multi-task documents MD, and the interval time IT. In this embodiment, the specific values ​​of b1, b2, and b3 are not specifically calculated;

[0087] The user churn index is compared with the preset threshold. If the user churn index is greater than the preset threshold, it means that the possibility of user churn is high. The document with the highest document importance index when the user last performed multi-document operations is extracted, and based on the document keywords, the cosine similarity algorithm is used to screen out documents with high similarity, and similar documents are randomly sent to users. If the user churn index is less than the preset threshold, it means that the possibility of user churn is low.

[0088] In this embodiment, it should be specifically explained that the online reading system based on cloud computing includes:

[0089] The user management module is used to manage documents. It provides users with an interface for uploading documents, allowing them to upload documents, store and back up uploaded documents, and ensure the security of document storage.

[0090] The document management module manages documents by providing users with an interface for uploading documents, allowing users to upload documents, and storing and backing up uploaded documents to ensure the security of document storage;

[0091] The reading module calculates the document importance index and sorts the order of documents opened by users during multi-tasking reading according to the document importance index;

[0092] The information notification module calculates the user churn index and sends reading information to users based on the user churn index.

[0093] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0094] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An online reading method based on cloud computing, characterized in that: The following steps are involved: Manage users, provide registration pages for users, and record user activities in the system; Manage documents, provide users with an interface for uploading documents, and store and back up uploaded documents; The document importance index is obtained by calculation, and the order of documents opened by the user during multi-tasking reading is sorted according to the document importance index; The steps for calculating the document importance index are as follows: Preprocess the text and use the Jieba word segmentation tool to segment the document, count the total number of words in the document, traverse each word in the text according to the keywords used by the user's search, record the number of times the keyword appears in the document, and calculate the keyword density coefficient; The calculation formula is: , where DN is the keyword density coefficient, D 总 Denoted as the total number of words in the document, D 关 It is expressed as the number of times the keyword appears in the document; Based on the keywords used by the user in the search, the TF-IDF algorithm is used to calculate the keyword frequency coefficient of the document selected by the user for multi-task reading; The click rate, share rate and number of comments of the documents selected by users for multi-task reading are counted, and the document attention coefficient is calculated based on the click rate, share rate and number of comments; The calculation formula is: , where AT represents the document attention coefficient, CL represents the click rate of the document, SH represents the sharing rate of the document, and CM represents the number of comments on the document; The document importance index is calculated based on the keyword density coefficient, keyword frequency coefficient and document attention coefficient; its calculation formula is: , where SF represents the document importance index, a1, a2, a3 represent the weight coefficients of the keyword density coefficient DN, the keyword frequency coefficient TI of the document, and the document attention coefficient AT; The steps for calculating the keyword frequency coefficient of the document selected by the user for multi-task reading are as follows: Collect all relevant documents to form a document collection, tokenize the documents, and split the text into individual words; For each document, calculate the number of times each word appears in the document, which is recorded as the word frequency of the word. The calculation formula is: , where TF stands for word frequency, D 总 Denoted as the total number of words in the document, D 关 It is expressed as the number of times the keyword appears in the document, and the inverse document frequency of each word is calculated; the inverse document frequency of each word is calculated, that is, the inverse of the number of documents in which the word appears in the document collection, and the calculation formula is , where IDF stands for Inverse Document Frequency, where NUM D Represented as the total number of documents in the document collection, NUM t Expressed as the number of documents containing the keyword; Multiply the term frequency and the inverse document frequency to get the final TF-IDF value, which is calculated as follows: , where TF-IDF is the keyword frequency coefficient, TF is the word frequency, IDF is the inverse document frequency, and the keyword frequency coefficient is recorded as TI; The user churn index is obtained by calculation, and reading information is sent to users according to the user churn index; The steps for calculating the user churn index are as follows: Count the number of user logins during the detection period, calculate the user login frequency, and record it as user activity; The calculation formula is: , where LG represents user activity, NUM L It is represented by the number of user logins during the detection period, and T is the detection time; Count the number of documents opened by the user during the last multi-tasking reading, and record it as the number of multi-tasking documents; Count the user's last reading time, and calculate the time from the user's last viewing to the current one, which is recorded as the interval time; The calculation formula is: , where IT represents the interval time, DT represents the current time, and T' represents the user's last reading time; The user churn index is calculated by weighted summation based on user activity, the number of multi-task documents, and the interval time; its calculation formula is: , where CR represents the user churn index, MD represents the number of multi-task documents, b1, b2, and b3 represent the weight coefficients of user activity AT, the number of multi-task documents MD, and the interval time IT.

2. The online reading method based on cloud computing according to claim 1, characterized in that: The jieba word segmentation tool is used to segment the document, and the specific steps are as follows: Install the jieba word segmentation tool, import the jieba library in the Python script, and load the document to be segmented into the program; Use the word segmentation function provided by the jieba library to segment the document, traverse the generator object or use the list to obtain the result after word segmentation; Filter stop words based on the word segmentation results.

3. The online reading method based on cloud computing according to claim 1, characterized in that: The method sends reading information to users based on the user churn index, compares the user churn index with a preset threshold, and if the user churn index is greater than the preset threshold, it means that the possibility of user churn is high, then the document with the highest document importance index when the user last performed a multi-document operation is extracted, and based on the document keywords, the cosine similarity algorithm is used to screen out documents with high similarity, and similar documents are randomly sent to users in the form of advertisements. If the user churn index is less than the preset threshold, it means that the possibility of user churn is low, then no advertisements are sent to the user.

4. An online reading system based on cloud computing, used to implement the method described in any one of claims 1 to 3, characterized in that: It includes user management module, document management module, reading module and information notification module, and each module is connected through signals: The user management module is used to manage documents. It provides users with an interface for uploading documents, allowing users to upload documents, and storing and backing up uploaded documents. The document management module manages documents by providing users with an interface for uploading documents, enabling users to upload documents, and storing and backing up uploaded documents; The reading module calculates the document importance index and sorts the order of documents opened by users during multi-tasking reading according to the document importance index; The information notification module calculates the user churn index and sends reading information to users based on the user churn index.

Images