Reader reading interest monitoring method and system, electronic equipment and product

Abstract

The invention belongs to the technical field of computers, and aims to provide a reader reading interest monitoring method and system, electronic equipment and a product. The method comprises the following steps: performing plot analysis processing on a specified text to obtain a plot element set of the specified text; obtaining an emotion score of the text fragment corresponding to each plot element, and collecting user behavior data when the reader user reads the text fragment corresponding to each plot element in the plot element set of the specified text, so as to calculate a reading interest value of the reader user on the text fragment corresponding to each plot element; according to the reading interest values of all the plot elements, key plot elements are recognized from all the plot elements, and the key plot elements are output according to the reading interest values of the key plot elements from large to small. According to the method, the influence of each plot element in the specified text on the interest of the reader user can be deeply analyzed, and the reading interest of the reader user can be detected in real time.

Description

Technical Field

[0001] The present invention belongs to the field of computer technology, and in particular relates to a method, system, electronic equipment and product for monitoring readers' reading interests. Background Art

[0002] With the development of online literature, more and more authors are using writing assistance apps (Applications) to serialize and update their novels. Current writing assistance apps mainly provide basic functions such as text editing, typesetting, and storage, while also analyzing the appeal of works by collecting readers' behavioral data.

[0003] In narrative works such as novels and scripts, factors such as plot twists and turns, the introduction of new characters, key conflicts, and suspense settings have a significant impact on readers' reading interest. For example, when the story reaches its climax, readers tend to pay more attention, while in some foreshadowing or transitional paragraphs, reading interest may decrease. Therefore, accurately analyzing the appeal of different plots to readers can help authors optimize story structure and enhance the readability of their works. However, current writing assistance tools still have the following technical limitations in this regard:

[0004] First, existing apps mainly rely on behavioral statistics of readers to conduct interest analysis, such as chapter click-through rate, reading time, number of likes and comments, etc. Although these data can reflect the overall reading trends of readers, they cannot deeply analyze the impact of specific plots on readers' interests. For example, different paragraphs within the same chapter may contain emotional ups and downs, turning points, or the introduction of new information, but traditional methods cannot identify the degree of appeal of these plots to readers. In addition, existing technologies mainly conduct reading interest analysis based on offline statistical data, which cannot monitor and feedback the changes in readers' interests in real time during the reading process. For example, when readers stay for a long time on a certain plot or frequently reread it, the system cannot immediately determine whether the plot is highly attractive to readers. Therefore, based on existing technologies, it is impossible to effectively guide authors to optimize story structure, which is not conducive to improving the user retention rate of writing assistance apps. Summary of the Invention

[0005] The present invention aims to solve the above technical problems at least to a certain extent, and provides a method, system, electronic device and product for monitoring readers' reading interests.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a method for monitoring a reader's reading interest, comprising:

[0008] Performing plot analysis on a specified text to obtain a set of plot elements of the specified text;

[0009] Obtaining a text segment corresponding to each plot element in the plot element set of the specified text, and performing sentiment analysis on the text segment corresponding to each plot element to obtain a sentiment score for the text segment corresponding to each plot element;

[0010] Real-time collection of user behavior data of readers when reading text segments corresponding to each plot element in the plot element set of the specified text;

[0011] Calculating the reading interest value of the reader user for the text segment corresponding to each plot element based on the sentiment score of the text segment corresponding to each plot element and the user behavior data;

[0012] According to the reading interest values ​​of all plot elements, key plot elements are identified from all plot elements;

[0013] The reading interest value of each key plot element is obtained, and each key plot element is output in descending order according to its reading interest value, so as to assist the author user corresponding to the specified text to perform plot optimization processing on the specified text.

[0014] In one possible design, plot parsing is performed on a specified text to obtain a set of plot elements of the specified text, including:

[0015] Encoding the specified text to obtain a sentence vector for each sentence in the specified text;

[0016] Performing plot element detection on each sentence in the specified text according to the sentence vector of each sentence, so as to obtain initial plot elements of each sentence in the specified text;

[0017] According to the arrangement order of each sentence, the initial plot elements of each sentence are merged to obtain the plot element set of the specified text; wherein, the types of any two adjacent plot elements in the plot element set are different.

[0018] In one possible design, a preset plot element detection model is used to detect plot elements in each sentence in the specified text. Correspondingly, the steps for obtaining the plot element detection model are as follows:

[0019] Obtain sentence vector samples corresponding to each sentence sample in the fragment sample; wherein each sentence vector sample is annotated with plot elements;

[0020] Inputting the sentence vector sample into the initial plot element detection model to obtain a plot element prediction result;

[0021] The loss between the plot element prediction result and the labeled plot element is calculated according to the regression loss function. When the loss meets the convergence condition, the current plot element detection model is used as the trained plot element detection model.

[0022] In a possible design, a VADER-based scoring method is used to perform sentiment analysis on the text fragments corresponding to each plot element.

[0023] In a possible design, the user behavior data includes the length of stay, number of replays, sliding speed, and number of interactions; correspondingly, the reading interest value of the reader user for the text segment t corresponding to any plot element is:

[0024] I(t)=α·T s +β·R f +γ·(1-V s / V avg )+δ·C l +∈·|S|;

[0025] Where, T s is the length of time the reader user stays in the text segment t corresponding to any plot element, R f is the number of times the reader user has reviewed the text segment t corresponding to any plot element, V s is the sliding speed of the reader user when reading the text segment t corresponding to any plot element, V avg is the average sliding speed of the reader user reading the specified text, C l is the number of interactions of the reader user with the text segment t corresponding to any plot element, S is the sentiment score of the text segment t corresponding to any plot element, and α, β, γ, δ and ∈ are preset weight parameters.

[0026] In one possible design, after calculating the reader user's reading interest value for the text segment corresponding to each plot element, the method further includes:

[0027] constructing an interest vector of the reader user according to the reading interest value of the reader user for the text segment corresponding to each plot element;

[0028] Calculating the interest similarity between the reader user and other reader users based on the interest vector of the reader user and the interest vectors of other reader users;

[0029] Obtaining another reader user with the greatest interest similarity to the reader user, and using the other reader user with the greatest interest similarity as a matching reader user;

[0030] According to the reading list of the matching reader user, personalized text recommendations are made to the reader user.

[0031] In a possible design, the interest similarity between the reader user and any other reader user is:

[0032]

[0033] Where, P u is the interest vector of the reader user, P v is the interest vector of any other reader user.

[0034] In a second aspect, the present invention provides a reader's reading interest monitoring system, comprising:

[0035] A plot analysis module, configured to perform plot analysis on a specified text to obtain a set of plot elements of the specified text;

[0036] a sentiment score calculation module, communicatively connected to the plot analysis module, for obtaining a text segment corresponding to each plot element in the plot element set of the specified text, and performing sentiment analysis on the text segment corresponding to each plot element to obtain a sentiment score for the text segment corresponding to each plot element;

[0037] a behavior monitoring module, in communication with the plot analysis module, for collecting in real time user behavior data of a reader user when reading a text segment corresponding to each plot element in the plot element set of the specified text;

[0038] a reading interest value calculation module, which is in communication with the sentiment score calculation module and the behavior monitoring module, and is used to calculate the reading interest value of the reader user for the text segment corresponding to each plot element based on the sentiment score of the text segment corresponding to each plot element and the user behavior data;

[0039] The output module is communicatively connected to the reading interest value calculation module and is used to identify key plot elements from all plot elements based on the reading interest values ​​of all plot elements; it is also used to obtain the reading interest value of each key plot element and output each key plot element in descending order according to its reading interest value, so as to assist the author user corresponding to the specified text to perform plot optimization processing on the specified text.

[0040] In a third aspect, the present invention provides an electronic device, comprising:

[0041] a memory for storing computer program instructions; and

[0042] The processor is used to execute the computer program instructions to complete the operation of a reader's reading interest monitoring method as described in any one of the above.

[0043] In a fourth aspect, the present invention provides a computer program product, comprising a computer program or instructions, which, when executed by a computer, implements a reader's reading interest monitoring method as described in any one of the above.

[0044] The beneficial effects of the present invention are:

[0045] The present invention discloses a reader reading interest monitoring method, system, electronic device and product, which can deeply analyze the impact of various plot elements in the specified text on the interest of reader users, and can realize real-time detection of reader users' reading interests, which is beneficial to improving the intelligence level of writing auxiliary tools and providing more efficient creative support for author users. Specifically, the present invention includes: performing plot analysis processing on a specified text to obtain a plot element set of the specified text; obtaining a text segment corresponding to each plot element in the plot element set of the specified text, and performing sentiment analysis processing on the text segment corresponding to each plot element, so as to obtain a sentiment score of the text segment corresponding to each plot element; real-time collection of user behavior data of readers when reading the text segment corresponding to each plot element in the plot element set of the specified text; calculating the reading interest value of the reader user for the text segment corresponding to each plot element based on the sentiment score and user behavior data of the text segment corresponding to each plot element; identifying key plot elements from all plot elements based on the reading interest values ​​of all plot elements; obtaining the reading interest value of each key plot element, and outputting each key plot element in descending order according to its reading interest value, so as to assist the author user corresponding to the specified text to perform plot optimization processing on the specified text. During this process, the present invention obtains a set of plot elements of a specified text, and based on this, performs user behavior detection and reading interest value calculation, can deeply analyze the impact of each plot element in the specified text on the interest of reader users, and can realize real-time detection of reader users' reading interests, based on which, provides intelligent creative assistance for author users, facilitates author users to optimize story structure, and thus helps to enhance the attractiveness of their works.

[0046] Other beneficial effects of the present invention will be further described in the specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a flow chart of a method for monitoring reader reading interest in Example 1;

[0048] Figure 2 This is a module block diagram of a reader's reading interest monitoring system in Example 2;

[0049] Figure 3 This is a module block diagram of an electronic device in Example 3. DETAILED DESCRIPTION

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the present invention will be briefly introduced below in conjunction with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structure of the drawings is only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0051] Example 1:

[0052] This embodiment discloses a method for monitoring readers' reading interests, which can be executed by, but is not limited to, a computer device or a virtual machine with certain computing resources, such as a personal computer, a smart phone, a personal digital assistant, or a wearable device, or by a virtual machine.

[0053] like Figure 1 As shown, a method for monitoring a reader's reading interest may include, but is not limited to, the following steps:

[0054] S1. Perform plot analysis on a specified text to obtain a set of plot elements for the specified text. It should be noted that the specified text is text data from an article serially updated by a user and author, and can be set to all text data in the article or only to text data within a specified number of recently updated chapters, without limitation. The plot elements include turning points, new character introductions, and escalating conflicts, also without limitation.

[0055] Specifically, in step S1, a plot analysis process is performed on the specified text to obtain a plot element set of the specified text, including:

[0056] S101. Encode the specified text to obtain sentence vectors for each sentence in the specified text. Specifically, in this embodiment, the specified text is encoded using the BERT (Bidirectional Encoder Representation from Transformers) encoding model, which captures deep bidirectional representations of language through pre-training on large-scale text data and then fine-tunes it for different natural language processing tasks, enabling a better understanding of the context and semantic relationships of the specified text.

[0057] S102. Perform plot element detection on each sentence in the specified text according to the sentence vector of each sentence, so as to obtain the initial plot element of each sentence in the specified text.

[0058] Specifically, in step S102 of this embodiment, a preset plot element detection model is used to detect plot elements for each sentence in the specified text. Correspondingly, the steps for obtaining the plot element detection model are as follows:

[0059] Obtain sentence vector samples corresponding to each sentence sample in the fragment sample; wherein each sentence vector sample is annotated with plot elements;

[0060] Inputting the sentence vector sample into the initial plot element detection model to obtain a plot element prediction result;

[0061] The loss between the plot element prediction result and the labeled plot element is calculated according to the regression loss function. When the loss meets the convergence condition, the current plot element detection model is used as the trained plot element detection model.

[0062] S103. Based on the order of the sentences, the initial plot elements of each sentence are merged to obtain a set of plot elements for the specified text; wherein any two adjacent plot elements in the set of plot elements are of different types. It should be noted that merging the initial plot elements of each sentence means that if any two adjacent sentences have the same plot element, the two sentences are merged, and the same plot element is used to refer to the merged sentence, thereby saving subsequent computational effort.

[0063] S2. Obtaining a text segment corresponding to each plot element in the plot element set of the specified text, and performing sentiment analysis on the text segment corresponding to each plot element to obtain a sentiment score for the text segment corresponding to each plot element.

[0064] In step S2, sentiment analysis is performed on the text segments corresponding to each plot element using a scoring method based on VADER (Valence Aware Dictionary and sEntiment Reasoner), a Python-based sentiment analysis tool focused on analyzing social media text. It should be noted that the VADER-based scoring method performs sentiment analysis on the text segments corresponding to each plot element. It is easy to use, highly adaptable, and highly real-time, making it easy to provide results and suitable for real-time analysis.

[0065] Specifically, in this embodiment, the sentiment score S of a text segment corresponding to any plot element ranges from -1 to 1, such as S>0.5 indicates positive sentiment, and S<-0.5 indicates strong negative sentiment.

[0066] S3. Real-time collection of user behavior data of readers as they read the text segments corresponding to each plot element in the plot element set of the specified text. It should be understood that any plot element corresponding to a text segment includes a single sentence or multiple adjacent sentences with the same plot element in the specified text; wherein the user behavior data includes data such as dwell time, number of replays, scrolling speed, and number of interactions (likes, comments, etc.), which are not limited here.

[0067] S4. Calculate the reader user's reading interest value for the text segment corresponding to each plot element based on the sentiment score of the text segment corresponding to each plot element and the user behavior data.

[0068] In step S3, the user behavior data includes the length of stay, number of replays, sliding speed, and number of interactions; correspondingly, in step S4, the reading interest value of the reader user for the text segment t corresponding to any plot element is:

[0069] I(t)=α·T s +β·R f +γ·(1-V s / V avg )+δ·C l +∈·|S|;

[0070] Where, T s is the length of time the reader user stays in the text segment t corresponding to any plot element, R f is the number of times the reader user has reviewed the text segment t corresponding to any plot element, V s is the sliding speed of the reader user when reading the text segment t corresponding to any plot element, V avg is the average sliding speed of the reader user reading the specified text, C l is the number of interactions of the reader user with the text segment t corresponding to any plot element, S is the sentiment score of the text segment t corresponding to any plot element, and α, β, γ, δ and ∈ are preset weight parameters.

[0071] For example, the reader user stays for a certain length of time T in the text segment t corresponding to any plot element. s is 8.5 seconds, and the number of times the reader user replays the text segment t corresponding to any plot element is R f is 3 times, the sliding speed V of the reader user reading the text segment t corresponding to any plot element s is 120px / s, and the average sliding speed of the reader user reading the specified text is V avg300px / s, the number of interactions C of the reader user on the text segment t corresponding to any plot element l For 5 times, the sentiment score S of the text segment t corresponding to any plot element is -0.7. Assuming that the weight parameters are α=1.2, β=2, γ=3, δ=1.5 and ∈=2.5, the reading interest value of the reader user for the text segment t corresponding to any plot element is:

[0072] I(t)=(1.2×8.5)+(2.0×3)+(3.0×(1-120 / 300))+(1.5×5)+(2.5×0.7)

[0073] =10.2+6+(3.0×0.6)+7.5+1.75=28.35.

[0074] The reading interest value indicates that this paragraph is more attractive to readers, and the higher the value, the stronger the reading interest of the readers.

[0075] In step S4, after calculating the reading interest value of the reader user for the text segment corresponding to each plot element, the method further includes:

[0076] A1. Constructing an interest vector of the reader user based on the reading interest value of the reader user for the text segment corresponding to each plot element.

[0077] A2. Calculate the interest similarity between the reader user and other reader users based on the interest vector of the reader user and the interest vectors of other reader users.

[0078] In step A2, the interest similarity between the reader user and any other reader user is:

[0079]

[0080] Where, P u is the interest vector of the reader user, P v is the interest vector of any other reader user. Specifically, the interest vector P of the reader user u =[I1,I2,...,I n ],I1,I2,...,I n is the reading interest value of the reader user for the text segments corresponding to the first to nth plot elements in the specified text, where n is a natural number greater than 1; the interest vector P of any other reader user v =[I1',I2',...,I n '],I1',I2',...,I n' is the reading interest value of any other reader user for the text segments corresponding to the first to nth plot elements in the specified text.

[0081] A3. Obtain another reader user whose interests are most similar to those of the reader user, and use the other reader user with the most similar interests as a matching reader user.

[0082] A4. Based on the reading list of the matching reader user, personalized text recommendations are made to the reader user.

[0083] It should be noted that, in this embodiment, the following steps may also be used to implement personalized text recommendations for the reader user:

[0084] B1. According to the reading interest value of each plot element corresponding to the text segment, the plot elements are sorted in descending order according to the reading interest value, and the interest tags of the reader user are determined according to the plot element sorting;

[0085] B2. Perform personalized text recommendations for the reader user based on the interest tags.

[0086] It should be noted that this embodiment helps understand readers' interests and preferences so as to recommend books of interest to them. Specifically, during implementation, this embodiment obtains the reader's interest tags based on the reader's reading interest values ​​for the text segments corresponding to each plot element. Based on these tags, personalized text recommendations are made to the reader, thereby improving the reader's retention rate.

[0087] S5. Identify key plot elements from all plot elements based on the reading interest values ​​of all plot elements. The key plot elements may include, but are not limited to, climax, turning point, and / or suspense.

[0088] S6. Obtain the reading interest value of each key plot element, and output each key plot element in descending order according to its reading interest value, so as to assist the author user corresponding to the specified text to perform plot optimization processing on the specified text.

[0089] This embodiment can deeply analyze the impact of each plot element in the specified text on the interest of the reader user, and can realize real-time detection of the reading interest of the reader user, which is conducive to improving the intelligence level of the writing assistance tool and providing more efficient creative support for the author user. Specifically, this embodiment includes: performing plot parsing processing on the specified text to obtain a plot element set of the specified text; obtaining a text segment corresponding to each plot element in the plot element set of the specified text, and performing sentiment analysis processing on the text segment corresponding to each plot element to obtain a sentiment score for the text segment corresponding to each plot element; real-time collection of user behavior data of the reader user when reading the text segment corresponding to each plot element in the plot element set of the specified text; calculating the reading interest value of the reader user for the text segment corresponding to each plot element based on the sentiment score and user behavior data of the text segment corresponding to each plot element; identifying key plot elements from all plot elements based on the reading interest values ​​of all plot elements; obtaining the reading interest value of each key plot element, and outputting each key plot element in descending order according to its reading interest value, so as to assist the author user corresponding to the specified text in performing plot optimization processing on the specified text. During this process, this embodiment obtains a set of plot elements of a specified text, and based on this, performs user behavior detection and reading interest value calculation, which can deeply analyze the impact of each plot element in the specified text on the interest of the reader user, and can realize real-time detection of the reading interest of the reader user. Based on this, it provides intelligent creative assistance for the author user, facilitates the author user to optimize the story structure, and thus helps to enhance the attractiveness of their work.

[0090] Example 2:

[0091] This embodiment discloses a reader reading interest monitoring system for implementing the reader reading interest monitoring method in embodiment 1; Figure 2 As shown, the reader reading interest monitoring system includes:

[0092] A plot analysis module, configured to perform plot analysis on a specified text to obtain a set of plot elements of the specified text;

[0093] a sentiment score calculation module, communicatively connected to the plot analysis module, for obtaining a text segment corresponding to each plot element in the plot element set of the specified text, and performing sentiment analysis on the text segment corresponding to each plot element to obtain a sentiment score for the text segment corresponding to each plot element;

[0094] a behavior monitoring module, in communication with the plot analysis module, for collecting in real time user behavior data of a reader user when reading a text segment corresponding to each plot element in the plot element set of the specified text;

[0095] a reading interest value calculation module, which is in communication with the sentiment score calculation module and the behavior monitoring module, and is used to calculate the reading interest value of the reader user for the text segment corresponding to each plot element based on the sentiment score of the text segment corresponding to each plot element and the user behavior data;

[0096] The output module is communicatively connected to the reading interest value calculation module and is used to identify key plot elements from all plot elements based on the reading interest values ​​of all plot elements; it is also used to obtain the reading interest value of each key plot element and output each key plot element in descending order according to its reading interest value, so as to assist the author user corresponding to the specified text to perform plot optimization processing on the specified text.

[0097] It should be noted that the working process, working details and technical effects of the reader reading interest monitoring system provided in this embodiment 2 can be found in embodiment 1 and will not be described in detail here.

[0098] Example 3:

[0099] Based on the embodiment 1 or 2, this embodiment discloses an electronic device, which may be a smart phone, a tablet computer, a laptop computer or a desktop computer. The electronic device may be called a user terminal, a portable terminal, a desktop terminal, etc. Figure 3 As shown, the electronic equipment includes:

[0100] a memory for storing computer program instructions; and

[0101] The processor is used to execute the computer program instructions to complete the operation of a reader's reading interest monitoring method as described in any one of Example 1.

[0102] Specifically, the processor 301 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 301 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 301 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 301 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen.

[0103] The memory 302 may include one or more computer-readable storage media, which may be non-transitory. The memory 302 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 302 is used to store at least one instruction, which is executed by the processor 301 to implement the reader's reading interest monitoring method provided in Example 1 of the present application.

[0104] In some embodiments, the terminal may optionally include a communication interface 303 and at least one peripheral device. The processor 301, memory 302, and communication interface 303 may be connected via a bus or signal lines. Each peripheral device may be connected to the communication interface 303 via a bus, signal lines, or circuit boards. Specifically, the peripheral device may include at least one of a radio frequency circuit 304, a display screen 305, and a power supply 306.

[0105] The communication interface 303 can be used to connect at least one I / O (Input / Output)-related peripheral device to the processor 301 and the memory 302. In some embodiments, the processor 301, the memory 302, and the communication interface 303 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 301, the memory 302, and the communication interface 303 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0106] The radio frequency circuit 304 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 304 communicates with a communication network and other communication devices via electromagnetic signals.

[0107] The display screen 305 is used to display a UI (User Interface). The UI may include any combination of graphics, text, icons, and videos.

[0108] The power supply 306 is used to supply power to various components in the electronic device.

[0109] Example 4:

[0110] Based on any one of Examples 1 to 3, this embodiment discloses a computer program product, including a computer program or instructions. When executed by a computer, the computer program or instructions implement a reader's reading interest monitoring method as described in any one of Example 1. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.

[0111] Obviously, those skilled in the art will appreciate that the modules or steps of the present invention described above can be implemented using a general-purpose computing device. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Alternatively, they can be implemented using program code executable by a computing device, which can then be stored in a storage device and executed by the computing device. Alternatively, they can be fabricated into separate integrated circuit modules, or multiple modules or steps can be fabricated into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0112] Finally, it should be noted that the above embodiments are intended only to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art will appreciate that modifications may be made to the technical solutions described in the above embodiments, or that some of the technical features may be replaced with equivalents. Such modifications or replacements do not deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for monitoring readers' reading interests, characterized in that: include: Performing plot analysis on a specified text to obtain a plot element set of the specified text; Obtaining a text segment corresponding to each plot element in the plot element set of the specified text, and performing sentiment analysis on the text segment corresponding to each plot element to obtain a sentiment score for the text segment corresponding to each plot element; Real-time collection of user behavior data of readers when reading text segments corresponding to each plot element in the plot element set of the specified text; Calculating the reading interest value of the reader user for the text segment corresponding to each plot element based on the sentiment score of the text segment corresponding to each plot element and the user behavior data; According to the reading interest values ​​of all plot elements, key plot elements are identified from all plot elements; The reading interest value of each key plot element is obtained, and each key plot element is output in descending order according to its reading interest value, so as to assist the author user corresponding to the specified text to perform plot optimization processing on the specified text.

2. A method for monitoring readers' reading interests according to claim 1, characterized in that: Perform plot analysis on the specified text to obtain a set of plot elements of the specified text, including: Encoding the specified text to obtain a sentence vector for each sentence in the specified text; Performing plot element detection on each sentence in the specified text according to the sentence vector of each sentence, so as to obtain initial plot elements of each sentence in the specified text; According to the arrangement order of each sentence, the initial plot elements of each sentence are merged to obtain the plot element set of the specified text; wherein, the types of any two adjacent plot elements in the plot element set are different.

3. A method for monitoring readers' reading interests according to claim 1, characterized in that: A preset plot element detection model is used to detect plot elements for each sentence in the specified text. Correspondingly, the steps for obtaining the plot element detection model are as follows: Obtain sentence vector samples corresponding to each sentence sample in the fragment sample; wherein each sentence vector sample is annotated with plot elements; Inputting the sentence vector sample into the initial plot element detection model to obtain a plot element prediction result; The loss between the plot element prediction result and the labeled plot element is calculated according to the regression loss function. When the loss meets the convergence condition, the current plot element detection model is used as the trained plot element detection model.

4. A method for monitoring readers' reading interests according to claim 1, characterized in that: When performing sentiment analysis on the text fragments corresponding to each plot element, a scoring method based on VADER is used.

5. The method for monitoring readers' reading interests according to claim 1, characterized in that: The user behavior data includes the length of stay, number of replays, sliding speed and number of interactions; correspondingly, the reading interest value of the reader user for the text segment t corresponding to any plot element is: I(t)=α·T s +β·R f +γ·(1-V s / V avg )+δ·C l +∈·|S|; Where, T s is the length of time the reader user stays in the text segment t corresponding to any plot element, R f is the number of times the reader user has reviewed the text segment t corresponding to any plot element, V s is the sliding speed of the reader user when reading the text segment t corresponding to any plot element, V avg is the average sliding speed of the reader user reading the specified text, C l is the number of interactions of the reader user with the text segment t corresponding to any plot element, S is the sentiment score of the text segment t corresponding to any plot element, and α, β, γ, δ and ∈ are preset weight parameters.

6. A method for monitoring readers' reading interests according to claim 1, characterized in that: After calculating the reading interest value of the reader user for the text segment corresponding to each plot element, the method further includes: constructing an interest vector of the reader user according to the reading interest value of the reader user for the text segment corresponding to each plot element; Calculating the interest similarity between the reader user and other reader users based on the interest vector of the reader user and the interest vectors of other reader users; Obtaining another reader user with the greatest interest similarity to the reader user, and using the other reader user with the greatest interest similarity as a matching reader user; According to the reading list of the matching reader user, personalized text recommendations are made to the reader user.

7. A method for monitoring readers' reading interests according to claim 6, characterized in that: The interest similarity between the reader user and any other reader user is: Where, P u is the interest vector of the reader user, P v is the interest vector of any other reader user.

8. A reader's reading interest monitoring system, characterized in that: include: A plot analysis module, configured to perform plot analysis on a specified text to obtain a set of plot elements of the specified text; a sentiment score calculation module, communicatively connected to the plot analysis module, for obtaining a text segment corresponding to each plot element in the plot element set of the specified text, and performing sentiment analysis on the text segment corresponding to each plot element to obtain a sentiment score for the text segment corresponding to each plot element; a behavior monitoring module, in communication with the plot analysis module, for collecting in real time user behavior data of a reader user when reading a text segment corresponding to each plot element in the plot element set of the specified text; a reading interest value calculation module, which is in communication with the sentiment score calculation module and the behavior monitoring module, and is used to calculate the reading interest value of the reader user for the text segment corresponding to each plot element based on the sentiment score of the text segment corresponding to each plot element and the user behavior data; The output module is communicatively connected to the reading interest value calculation module and is used to identify key plot elements from all plot elements based on the reading interest values ​​of all plot elements; it is also used to obtain the reading interest value of each key plot element and output each key plot element in descending order according to its reading interest value, so as to assist the author user corresponding to the specified text to perform plot optimization processing on the specified text.

9. An electronic device, characterized in that: include: a memory for storing computer program instructions; as well as, A processor is used to execute the computer program instructions to complete the operation of a reader's reading interest monitoring method as described in any one of claims 1 to 7.

10. A computer program product comprising a computer program or instructions, characterized in that When the computer program or the instruction is executed by a computer, the method for monitoring a reader's reading interest as described in any one of claims 1 to 7 is implemented.

Images