Content identification method, electronic device and storage medium

Abstract

The present invention relates to a content recognition method, an electronic device and a storage medium. The content recognition method includes: obtaining target data of a book to be recognized, the target data includes attribute data and content data of the book to be recognized; determining a content recognition strategy according to the attribute data, the content recognition strategy includes a content recognition algorithm of at least two dimensions; based on the content recognition strategy and the content data, determining a wonderful chapter among multiple chapters in the book to be recognized. The present invention can recognize wonderful chapters in a book according to a content recognition strategy determined by the attribute data of the book. Since the content recognition strategy includes content recognition algorithms of multiple dimensions, multi-dimensional recognition can be achieved, thereby improving the accuracy of identifying the wonderful content of the book, and further enhancing the reading stickiness and interest of the user by prompting the wonderful content, thereby improving the reading experience of the user.

Description

Technical Field

[0001] The present disclosure relates to the technical field of electronic books, and in particular to a content identification method, an electronic device and a storage medium. Background Art

[0002] With the rapid development of Internet technology, electronic books are gaining more and more use and attention.

[0003] Currently, when reading electronic books, users' interest can be stimulated by displaying prompts of wonderful content. However, the accuracy of identifying wonderful content in electronic books in related technologies is low, which affects the experience. Summary of the invention

[0004] In order to solve the technical problem of low accuracy in identifying wonderful content in e-books, the present disclosure provides a content identification method, an electronic device and a storage medium to improve the accuracy of identifying wonderful content in e-books.

[0005] In a first aspect, an embodiment of the present disclosure provides a content identification method, including:

[0006] Acquire target data of the book to be identified, the target data including attribute data and content data of the book to be identified;

[0007] Determine a content identification strategy according to the attribute data, wherein the content identification strategy includes a content identification algorithm of at least two dimensions;

[0008] Based on the content identification strategy and the content data, an excellent chapter among multiple chapters in the book to be identified is determined.

[0009] In a second aspect, an embodiment of the present disclosure provides an electronic device, including:

[0010] processor;

[0011] A memory for storing executable instructions;

[0012] The processor is used to read the executable instructions from the memory and execute the executable instructions to perform the following operations:

[0013] Acquire target data of the book to be identified, the target data including attribute data and content data of the book to be identified;

[0014] Determine a content identification strategy according to the attribute data, wherein the content identification strategy includes a content identification algorithm of at least two dimensions;

[0015] Based on the content identification strategy and the content data, an excellent chapter among multiple chapters in the book to be identified is determined.

[0016] In a third aspect, an embodiment of the present disclosure provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor implements the content recognition method of the first aspect.

[0017] One of the above technical solutions has the following advantages or beneficial effects:

[0018] According to the content recognition method, electronic device and storage medium of the embodiment of the present disclosure, it is possible to obtain target data of the book to be recognized, the target data includes attribute data and content data of the book to be recognized, determine the content recognition strategy according to the attribute data, the content recognition strategy includes at least two-dimensional content recognition algorithms, and determine the wonderful chapters among multiple chapters in the book to be recognized based on the content recognition strategy and the content data. The embodiment of the present disclosure can recognize the wonderful chapters in the book according to the content recognition strategy determined by the attribute data of the book. Since the content recognition strategy includes multiple-dimensional content recognition algorithms, multi-dimensional recognition can be achieved, which improves the accuracy of identifying the wonderful content of the book, and further, by prompting the wonderful content, the user's reading stickiness and interest can be enhanced, thereby improving the user's reading experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0020] Figure 1 A flowchart of a content identification method provided by an embodiment of the present disclosure;

[0021] Figure 2 A flowchart of another content identification method provided by an embodiment of the present disclosure;

[0022] Figure 3 A schematic diagram of prompt information of a wonderful chapter provided by an embodiment of the present disclosure;

[0023] Figure 4 A schematic diagram of another type of prompt information of a wonderful chapter provided by an embodiment of the present disclosure;

[0024] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0026] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0027] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0028] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0029] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0030] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0031] Figure 1 The present invention provides a flow chart of a content recognition method provided by an embodiment of the present invention. The method can be performed by a content recognition device, wherein the device can be implemented by software and / or hardware and can generally be integrated in an electronic device. Figure 1 As shown, the method includes:

[0032] Step 101: Acquire target data of a book to be identified, where the target data includes attribute data and content data of the book to be identified.

[0033] The book to be identified can be any electronic book that needs to be identified for wonderful content, and the specific source is not limited. For example, the book to be identified can be an electronic book currently uploaded by the user, or an electronic book downloaded from the Internet. The target data can be the relevant data of the electronic book. In the embodiment of the present disclosure, the target data can include attribute data and content data. The attribute data can be understood as the data at the nature level such as the book type, writing time and author of the electronic book, and the content data can include the data at the subject level such as the book content and interaction data of the electronic book.

[0034] In the disclosed embodiment, the content recognition device may send a data acquisition request to a data storage end for the book to be recognized to obtain the attribute data and content data corresponding to the book to be recognized. The data storage end may be a server storing the book to be recognized and its related data.

[0035] Step 102: Determine a content identification strategy based on the attribute data. The content identification strategy includes at least two-dimensional content identification algorithms.

[0036] Among them, the content identification strategy can be a comprehensive solution for identifying excellent content in e-books. The content identification strategy can include content identification algorithms in at least two dimensions. The content identification algorithm can be an algorithm that can identify and judge the excellent content of e-books. It can include multiple types of algorithms. For example, the content identification algorithm can include a statistical algorithm or a deep learning algorithm, etc., without limitation.

[0037] In an embodiment of the present disclosure, the attribute data may include the type of book, and determining the content recognition strategy based on the attribute data may include: when the book type is a female type, the content recognition strategy includes content recognition algorithms in the interaction dimension and the emotion dimension; when the book type is a male type, the content recognition strategy includes a content recognition algorithm in the interaction dimension and at least one content recognition algorithm in the content dimension.

[0038] Book type can be a classification of e-books according to certain standards. The book type in the embodiment of the present disclosure can be divided according to the gender of the user, and specifically can include female type and male type. The female type can be a type with more female users, and the female type can include romance, etc. The male type can be a type with more male users, and the male type can include martial arts, fantasy, etc.

[0039] When the book type of the book to be identified is female type, since female users are more emotional, the content identification strategy can be set to a content identification algorithm that includes two dimensions: interaction dimension and emotional dimension; when the book type of the book to be identified is male type, since male users are more rational, the content identification strategy can be set to a content identification algorithm that includes two dimensions: interaction dimension and content dimension. Since the content identification algorithm of the content dimension can include multiple content identification algorithms, at least one of the content identification algorithms can be added to the content identification strategy for the content dimension.

[0040] The above content identification strategy determined according to the book type in the attribute data is only an example, and it can also be determined according to other data in the attribute data. For example, different content identification strategies can be determined according to different writing times. The specific setting can be based on actual conditions.

[0041] Step 103: Determine the outstanding chapters among the multiple chapters in the book to be identified based on the content identification strategy and the content data.

[0042] The content data may include the main body data such as the book content and interaction data of the e-book. The book content may be the main body text content of the e-book. The book content of a book may include multiple chapters. The wonderful chapter may be a chapter with wonderful content or important plot highlights among multiple chapters of a book. The interaction data may include at least one of the number of books read, the number of likes, and the number of comments by users.

[0043] For example, Figure 2 A flowchart of another content identification method provided by an embodiment of the present disclosure is shown as follows: Figure 2 As shown, based on the content recognition strategy and content data, determining the outstanding chapters among multiple chapters in the book to be recognized may include the following steps:

[0044] Step 201: determine each chapter in the book to be identified as a target chapter in sequence.

[0045] The target chapter may be the chapter currently undergoing content recognition processing. Since the book to be recognized may include multiple chapters, the content recognition device may perform content recognition processing on each chapter in turn, that is, determine each chapter as a target chapter in turn for subsequent processing.

[0046] Step 202: Determine multiple initial recognition results of the target chapter based on the content recognition algorithms in the content recognition strategy and the data corresponding to the content recognition algorithms in the content data.

[0047] The content data may include book content and / or interaction data. Different content recognition algorithms may target different content data. For example, when the content recognition algorithm is a statistical algorithm in the interaction dimension, the corresponding data may be interaction data; when the content recognition algorithm is a named entity recognition algorithm, a part-of-speech tagging algorithm, a classification algorithm, etc. in the content dimension, the corresponding data may be book content. The initial recognition result may be the content recognition result of the target chapter by the content recognition algorithm, that is, an initial judgment result of whether the target chapter is a wonderful chapter.

[0048] Specifically, the content recognition device can use a content recognition algorithm to recognize the data of the target chapter corresponding to the current content recognition algorithm, and obtain an initial recognition result of the target chapter. Each content recognition algorithm executes the above recognition process once, and finally obtains multiple initial recognition results of the target chapter.

[0049] Exemplarily, assuming that the content recognition algorithm is a named entity recognition algorithm of the content dimension, the corresponding data is the book content, that is, the text content of the target chapter, and the named entity recognition algorithm is used to analyze the text content of the target chapter to identify the named entities therein, such as character names, item names, organization names, etc., and determine the important words in the above named entities based on the pre-set important words. After that, the number of occurrences of the important words in the target chapter can be counted, and the initial recognition result of the target chapter can be determined based on the number of occurrences, that is, whether the target chapter is a wonderful chapter. The above method of determining the initial recognition result of the target chapter based on the number of occurrences can be that if there are important words whose number of occurrences is greater than or equal to the number threshold, then the initial recognition result can be determined as the target chapter is a wonderful chapter, otherwise the initial recognition result is determined as the target chapter is not a wonderful chapter.

[0050] Step 203: Perform weighted calculation on multiple initial recognition results to obtain a recognition result of the wonderful content of the target chapter.

[0051] The wonderful content recognition result indicates whether the target chapter is a wonderful chapter, that is, the wonderful content recognition result can be a final judgment result of whether the target chapter is a wonderful chapter.

[0052] In some embodiments of the present disclosure, after the content recognition device determines multiple initial recognition results, it can count the initial recognition results to obtain the number of different results, compare the number of different results, and determine the result with a larger number as the final wonderful content recognition result; if the number of different results is the same, the result with a larger weight value can be determined as the final wonderful content recognition result, and the weight value of different results can be the sum of the weight values ​​of different content recognition algorithms corresponding to the result.

[0053] Exemplarily, the number of target chapters whose initial recognition results are wonderful chapters is a first number, and the number of target chapters whose initial recognition results are not wonderful chapters is a second number. When the first number is greater than the second number, it can be determined that the wonderful content recognition result is that the target chapter is a wonderful chapter; when the first number is equal to the second number, but the weight value of the initial recognition result that the target chapter is not a wonderful chapter is larger, it can be determined that the wonderful content recognition result is that the target chapter is not a wonderful chapter.

[0054] In some other embodiments of the present disclosure, weighted calculation is performed on multiple initial recognition results to obtain a result of identifying wonderful content of a target chapter, which may include: normalizing the multiple initial recognition results separately to obtain multiple recognition scores; performing weighted calculation based on the multiple recognition scores and their corresponding weight values ​​to obtain a comprehensive score; and determining the result of identifying wonderful content of the target chapter based on the comprehensive score.

[0055] The above recognition score is a value in the range of 0-1. The weight values ​​corresponding to different recognition scores represent the weight values ​​corresponding to different content recognition algorithms. Since different content recognition algorithms have different recognition accuracy rates, different weight values ​​can be set according to actual conditions for weighted calculation. The content recognition device can normalize each initial recognition result to obtain multiple recognition scores, and then sum the product of the recognition score of each initial recognition result and the corresponding weight value to obtain a comprehensive score, and the recognition result of the wonderful content of the target chapter can be determined based on the comprehensive score.

[0056] Optionally, determining the result of identifying the wonderful content of the target chapter according to the comprehensive score includes: if the comprehensive score of the target chapter is greater than or equal to a preset threshold, determining the result of identifying the wonderful content of the target chapter is that the target chapter is a wonderful chapter; otherwise, determining the result of identifying the wonderful content of the target chapter is that the target chapter is not a wonderful chapter. The preset threshold can be set and adjusted according to actual conditions.

[0057] After the content recognition device determines the comprehensive score of the target chapter, it can compare the comprehensive score with a preset threshold. If the comprehensive score is greater than or equal to the preset threshold, the target chapter is determined to be a wonderful chapter; otherwise, the target chapter is determined not to be a wonderful chapter.

[0058] According to the content recognition method of the embodiment of the present disclosure, it is possible to obtain target data of the book to be recognized, the target data includes attribute data and content data of the book to be recognized, determine the content recognition strategy according to the attribute data, the content recognition strategy includes at least two-dimensional content recognition algorithms, and determine the wonderful chapters among multiple chapters in the book to be recognized based on the content recognition strategy and the content data. The embodiment of the present disclosure can recognize the wonderful chapters in the book according to the content recognition strategy determined by the attribute data of the book. Since the content recognition strategy includes multiple-dimensional content recognition algorithms, multi-dimensional recognition can be achieved, which improves the accuracy of identifying the wonderful content of the book, and further, by prompting the wonderful content, the user's reading stickiness and interest can be enhanced, thereby improving the user's reading experience.

[0059] In some embodiments, the content identification algorithm may include at least one of the following: a statistical algorithm of the interaction dimension, an analysis algorithm of the sentiment dimension, and a named entity recognition algorithm, a part-of-speech tagging algorithm, and a classification algorithm of the content dimension.

[0060] Among them, the statistical algorithm of the interaction dimension and the analysis algorithm of the sentiment dimension perform content recognition based on the user's interaction data, while the named entity algorithm, part-of-speech tagging algorithm, and classification algorithm of the content dimension perform content recognition based on the book content.

[0061] For the statistical algorithm of the interactive dimension, the initial content recognition result can be determined based on the number of readings, the number of likes, the number of comments, and the retention rate trend chart. The above reading number is the number of unique visitors (UV), and the retention rate trend chart can be a UV trend chart corresponding to each chapter of a book. For the analysis algorithm of the emotional dimension, sentiment analysis can be performed on user-generated content (UGC): Specifically, sentiment analysis can be performed on user comments and published "ideas", etc., to distinguish between positive and negative sentiments. Positive sentiments indicate that users think the writing is good and attractive, while negative sentiments indicate that users think the writing is poor and not very interesting. In terms of specific implementation, a text binary classification model can be used to calculate the percentage of positive and negative sentiments to determine whether each chapter in the book is an exciting chapter.

[0062] For the named entity algorithm of the content dimension, a named entity recognition algorithm is used to analyze the text content of each chapter of the book, identify the named entities therein, such as character names, item names, organization names, etc., and determine the important words in the above named entities based on the pre-set important words. After that, the number of occurrences of the important words in the chapter can be counted, and the initial recognition result of the chapter can be determined based on the number of occurrences, that is, whether the chapter is a wonderful chapter. The above method of determining the initial recognition result of a chapter based on the number of occurrences of important words in a chapter can be that if there are important words with a number of occurrences greater than or equal to the number threshold, the chapter can be determined to be a wonderful chapter, otherwise the chapter is determined to be not a wonderful chapter. This is only an example.

[0063] For the part-of-speech tagging algorithm of the content dimension, a segmentation algorithm can be used to identify words of different parts of speech in each chapter of the book, such as adjectives, adverbs, verbs, and onomatopoeia, etc., and then it can be matched with the pre-set feature vocabulary to determine the feature vocabulary that is successfully matched. Then, the number of occurrences of the successfully matched feature vocabulary in the chapter can be counted, and the initial recognition result of the chapter can be determined according to the number of occurrences, that is, whether the chapter is a wonderful chapter. The above-mentioned method of determining the initial recognition result of the chapter according to the number of occurrences of the successfully matched feature vocabulary in the chapter can be that if there is a feature vocabulary with a number of occurrences greater than or equal to the number threshold, the chapter can be determined to be a wonderful chapter, otherwise it is determined that the chapter is not a wonderful chapter, which is only an example. The above-mentioned feature vocabulary can be set according to the type of book, and the feature vocabulary corresponding to different book types is different. For the classification algorithm of the content dimension, the chapter name of each chapter of the book or a whole paragraph of content can be classified using a pre-trained classification model to determine whether the chapter is a wonderful chapter. The above-mentioned classification model can be set according to the actual situation. For example, the classification model can be a Fasttext classifier, a Bert classification model, etc.

[0064] The content recognition algorithm in the disclosed embodiment may include algorithms of multiple dimensions to achieve multi-dimensional recognition during content recognition, thereby improving the accuracy of identifying the wonderful content of the book.

[0065] In some embodiments, the content recognition method in the disclosed embodiments may further include: displaying prompt information of the wonderful chapters on a preset page of the book to be recognized. Optionally, the preset page may include a first page of target content associated with the wonderful chapter, a second page before the wonderful chapter and whose distance to the wonderful chapter meets a threshold, and / or a cover page of the book to be recognized. Optionally, the prompt information includes at least one of a preset prompt text, the number of wonderful chapters, and the distance to the wonderful chapters.

[0066] Among them, the preset page can be a page for displaying prompt information of the book to be identified, which can be set according to actual conditions. The preset page in the embodiment of the present disclosure can be a first page including target content associated with the wonderful chapter, and the target content can be associated with the wonderful chapter in plot or content, for example, the target content can be the foreshadowing content of the wonderful chapter; the preset page can also be a second page before the wonderful chapter and the distance between the wonderful chapter and the preset page meets the threshold, the distance can be understood as page distance or text distance, the threshold can be set to be smaller, that is, the preset page can be a page closer to the wonderful chapter, for example, the preset page can be the second to last page before the wonderful chapter; the preset page can also be the cover page of the book to be identified, and the cover page can be a page outside the book to be identified.

[0067] The prompt information may be information for prompting the wonderful chapters of the book to be identified, and may include at least one of preset prompt text, the number of wonderful chapters, and the distance between the wonderful chapters. For example, the preset prompt text may be "High energy ahead".

[0068] For example, Figure 3 A schematic diagram of prompt information of a wonderful chapter provided by an embodiment of the present disclosure, Figure 4 A schematic diagram of another type of prompt information of a wonderful chapter provided by an embodiment of the present disclosure, Figure 3 and Figure 4 Two different tips for wonderful chapters are shown. Figure 3 As shown in the figure, a preset page 300 is shown, and the preset page 300 displays prompt information 301 of the wonderful chapter. The prompt information 301 includes a prompt text "High energy ahead", which prompts that the wonderful chapter is about to arrive. Figure 4 As shown, another preset page 400 is shown in the figure, which displays the prompt information 401 of the wonderful chapter and the target content 402 associated with the wonderful chapter. The target content 402 is "a key is lost", and the prompt information 401 includes the text "pay special attention here, high-energy preview", which is used to prompt to pay special attention to the target content 402, and the target content 402 is a foreshadowing content and is associated with a subsequent wonderful chapter.

[0069] In the above scheme, after determining the wonderful chapters of the book, the wonderful chapters can be prompted while the user is reading the book, so that the user knows the distribution of the wonderful content in advance, stimulates the user's interest in the book, and thus improves the reading stickiness and retention rate of the book.

[0070] The disclosed embodiment also provides an electronic device, which may include a processor and a memory, wherein the memory may be used to store executable instructions. The processor may be used to read the executable instructions from the memory, and execute the executable instructions to perform the following operations: obtaining target data of a book to be identified, wherein the target data includes attribute data and content data of the book to be identified; determining a content identification strategy based on the attribute data, wherein the content identification strategy includes a content identification algorithm of at least two dimensions; and determining a wonderful chapter among multiple chapters in the book to be identified based on the content identification strategy and the content data.

[0071] Figure 5 The electronic device 500 in the embodiment of the present disclosure may be the electronic device described above. It should also be noted that: Figure 5 The electronic device 500 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0072] The electronic device 500 conventionally includes a processor 510 and a computer program product or computer-readable medium in the form of a memory 520. The memory 520 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk or a ROM. The memory 520 has a storage space 521 for executable instructions (or program codes) 5211 for executing any method steps in the above-mentioned content identification method. For example, the storage space 521 for executable instructions may include individual executable instructions 5211 respectively used to implement various steps in the above-mentioned content identification method. These executable instructions may be read from or written to one or more computer program products. These computer program products include program code carriers such as a hard disk, a compact disk (CD), a memory card or a floppy disk. Such a computer program product is typically a portable or fixed storage unit. The storage unit may have a storage device 5211 having a storage device 5212 configured to store and store the executable instructions. Figure 5 The memory 520 in the electronic device of the present invention is similarly arranged as a storage segment or storage space. The executable instructions can be compressed, for example, in an appropriate form. Generally, the storage unit includes executable instructions for executing the steps of the content identification method according to the present invention, that is, codes that can be read by a processor such as the processor 510, and when these codes are executed by the electronic device, the electronic device executes the various steps in the content identification method described above.

[0073] An embodiment of the present invention further provides a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the content identification method provided by each embodiment of the present invention.

[0074] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0075] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0076] In an embodiment of the present invention, computer program code for performing the operation of the present invention may be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as a separate software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0077] The various component embodiments of the present invention may be implemented in hardware in all or part of the steps, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in the content recognition device according to an embodiment of the present invention. The present invention may also be implemented as a device or device program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program for implementing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0078] According to one or more embodiments of the present disclosure, the present disclosure provides a content identification method, including:

[0079] Acquire target data of the book to be identified, the target data including attribute data and content data of the book to be identified;

[0080] Determine a content identification strategy according to the attribute data, wherein the content identification strategy includes a content identification algorithm of at least two dimensions;

[0081] Based on the content identification strategy and the content data, an excellent chapter among multiple chapters in the book to be identified is determined.

[0082] Optionally, the attribute data includes a book type, and a content identification strategy is determined based on the attribute data, including:

[0083] When the book type is female type, the content identification strategy includes content identification algorithms in the interactive dimension and the emotional dimension;

[0084] When the book genre is male genre, the content identification strategy includes a content identification algorithm in the interaction dimension and at least one content identification algorithm in the content dimension.

[0085] Optionally, based on the content identification strategy and the content data, the outstanding chapters among the multiple chapters in the book to be identified are determined, including:

[0086] Determine each chapter in the book to be identified as a target chapter in turn;

[0087] Determine multiple initial recognition results of the target chapter according to each content recognition algorithm in the content recognition strategy and data corresponding to the content recognition algorithm in the content data;

[0088] A weighted calculation is performed on the multiple initial recognition results to obtain a wonderful content recognition result of the target chapter, and the wonderful content recognition result indicates whether the target chapter is a wonderful chapter.

[0089] Optionally, multiple initial recognition results are weighted to obtain a recognition result of the wonderful content of the target chapter, including:

[0090] Normalizing and calculating the multiple initial recognition results respectively to obtain multiple recognition scores;

[0091] Perform weighted calculation based on multiple recognition scores and their corresponding weight values ​​to obtain a comprehensive score;

[0092] The highlight content recognition result of the target chapter is determined according to the comprehensive score.

[0093] Optionally, the highlight content recognition result of the target chapter is determined based on the comprehensive score, including:

[0094] If the comprehensive score of the target chapter is greater than or equal to the preset threshold, the wonderful content recognition result of the target chapter is determined to be that the target chapter is a wonderful chapter; otherwise, the wonderful content recognition result of the target chapter is determined to be that the target chapter is not a wonderful chapter.

[0095] Optionally, the content identification algorithm includes at least one of the following: a statistical algorithm of the interaction dimension, an analysis algorithm of the sentiment dimension, and a named entity recognition algorithm, a part-of-speech tagging algorithm, and a classification algorithm of the content dimension, and the content data includes book content and / or interaction data.

[0096] Optionally, the method further includes:

[0097] Display prompt information of wonderful chapters on the preset page of the book to be identified.

[0098] Optionally, the preset pages include a first page of target content associated with a wonderful chapter, a second page before the wonderful chapter and whose distance to the wonderful chapter meets a threshold, and / or a cover page of the book to be identified.

[0099] Optionally, the prompt information includes at least one of a preset prompt text, the number of wonderful chapters, and the distance between the wonderful chapters.

[0100] According to one or more embodiments of the present disclosure, the present disclosure provides an electronic device, including:

[0101] processor;

[0102] a memory for storing processor-executable instructions;

[0103] A processor that reads executable instructions from memory and executes the instructions to:

[0104] Acquire target data of the book to be identified, the target data including attribute data and content data of the book to be identified;

[0105] Determine a content identification strategy according to the attribute data, wherein the content identification strategy includes a content identification algorithm of at least two dimensions;

[0106] Based on the content identification strategy and the content data, an excellent chapter among multiple chapters in the book to be identified is determined.

[0107] Optionally, the attribute data includes a book type, and the executable instructions further cause the processor to perform the following operations:

[0108] The content identification strategy is determined according to the attribute data, including:

[0109] When the book type is female type, the content identification strategy includes content identification algorithms in the interactive dimension and the emotional dimension;

[0110] When the book genre is male genre, the content identification strategy includes a content identification algorithm in the interaction dimension and at least one content identification algorithm in the content dimension.

[0111] Optionally, the executable instructions further cause the processor to perform the following operations:

[0112] Among them, based on the content recognition strategy and content data, the wonderful chapters among multiple chapters in the book to be recognized are determined, including:

[0113] Determine each chapter in the book to be identified as a target chapter in turn;

[0114] Determine multiple initial recognition results of the target chapter according to each content recognition algorithm in the content recognition strategy and data corresponding to the content recognition algorithm in the content data;

[0115] A weighted calculation is performed on the multiple initial recognition results to obtain a wonderful content recognition result of the target chapter, and the wonderful content recognition result indicates whether the target chapter is a wonderful chapter.

[0116] Optionally, the executable instructions further cause the processor to perform the following operations:

[0117] Among them, multiple initial recognition results are weighted and calculated to obtain the wonderful content recognition results of the target chapter, including:

[0118] Normalizing and calculating the multiple initial recognition results respectively to obtain multiple recognition scores;

[0119] Perform weighted calculation based on multiple recognition scores and their corresponding weight values ​​to obtain a comprehensive score;

[0120] The highlight content recognition result of the target chapter is determined according to the comprehensive score.

[0121] Optionally, the executable instructions further cause the processor to perform the following operations:

[0122] Among them, the wonderful content recognition results of the target chapter are determined according to the comprehensive score, including:

[0123] If the comprehensive score of the target chapter is greater than or equal to the preset threshold, the wonderful content recognition result of the target chapter is determined to be that the target chapter is a wonderful chapter; otherwise, the wonderful content recognition result of the target chapter is determined to be that the target chapter is not a wonderful chapter.

[0124] Optionally, the content identification algorithm includes at least one of the following: a statistical algorithm of the interaction dimension, an analysis algorithm of the sentiment dimension, and a named entity recognition algorithm, a part-of-speech tagging algorithm, and a classification algorithm of the content dimension, and the content data includes book content and / or interaction data.

[0125] Optionally, the executable instructions further cause the processor to perform the following operations:

[0126] Display prompt information of wonderful chapters on the preset page of the book to be identified.

[0127] Optionally, the preset pages include a first page of target content associated with a wonderful chapter, a second page before the wonderful chapter and whose distance to the wonderful chapter meets a threshold, and / or a cover page of the book to be identified.

[0128] Optionally, the prompt information includes at least one of a preset prompt text, the number of wonderful chapters, and the distance between the wonderful chapters.

[0129] According to one or more embodiments of the present disclosure, the present disclosure provides a computer-readable storage medium, the storage medium storing a computer program, and the computer program is used to execute any content identification method provided by the present disclosure.

[0130] The above description is only a preferred embodiment of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the disclosure scope involved in the present invention is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present invention (but not limited to) by each other.

[0131] In addition, although each operation is described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present invention. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0132] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A content identification method, characterized in that: include: Acquire target data of a book to be identified, wherein the target data includes attribute data and content data of the book to be identified, wherein the content data includes book content and / or interaction data; Determine a content identification strategy according to the attribute data, wherein the content identification strategy includes a content identification algorithm of at least two dimensions; Based on the content identification strategy and the content data, determining a wonderful chapter among a plurality of chapters in the to-be-identified book; The attribute data includes a book type, and determining a content identification strategy according to the attribute data includes: When the book type is female type, the content identification strategy includes content identification algorithms in the interaction dimension and the emotion dimension; When the book type is male type, the content identification strategy includes the content identification algorithm in the interaction dimension and at least one content identification algorithm in the content dimension.

2. The method according to claim 1, characterized in that Determining, based on the content identification strategy and the content data, a wonderful chapter among a plurality of chapters in the to-be-identified book, comprising: Determine each chapter in the book to be identified as a target chapter in sequence; Determining a plurality of initial recognition results of the target chapter according to each content recognition algorithm in the content recognition strategy and data corresponding to the content recognition algorithm in the content data; A weighted calculation is performed on the multiple initial recognition results to obtain a wonderful content recognition result of the target chapter, wherein the wonderful content recognition result indicates whether the target chapter is a wonderful chapter.

3. The method according to claim 2, characterized in that The multiple initial recognition results are weighted and calculated to obtain the wonderful content recognition result of the target chapter, including: Normalizing and calculating the multiple initial recognition results respectively to obtain multiple recognition scores; Performing weighted calculation according to the multiple recognition scores and their corresponding weight values ​​to obtain a comprehensive score; The result of identifying the wonderful content of the target chapter is determined according to the comprehensive score.

4. The method according to claim 3, characterized in that Determining the wonderful content recognition result of the target chapter according to the comprehensive score includes: If the comprehensive score of the target chapter is greater than or equal to a preset threshold, the wonderful content recognition result of the target chapter is determined to be that the target chapter is a wonderful chapter; otherwise, the wonderful content recognition result of the target chapter is determined to be that the target chapter is not a wonderful chapter.

5. The method according to any one of claims 1 to 4, characterized in that: The content identification algorithm includes at least one of the following: a statistical algorithm in the interaction dimension, an analysis algorithm in the sentiment dimension, and a named entity recognition algorithm, a part-of-speech tagging algorithm, and a classification algorithm in the content dimension.

6. The method according to claim 1, characterized in that The method further comprises: The prompt information of the wonderful chapter is displayed on a preset page of the book to be identified.

7. The method according to claim 6, characterized in that The preset pages include a first page of target content associated with the wonderful chapter, a second page before the wonderful chapter and whose distance from the wonderful chapter meets a threshold, and / or a cover page of the book to be identified.

8. The method according to claim 6, characterized in that The prompt information includes at least one of a preset prompt text, the number of the wonderful chapters, and the distance between the wonderful chapters.

9. An electronic device, characterized in that: include: processor; A memory for storing executable instructions; The processor is used to read the executable instructions from the memory and execute the executable instructions to perform the following operations: Acquire target data of a book to be identified, wherein the target data includes attribute data and content data of the book to be identified, wherein the content data includes book content and / or interaction data; Determine a content identification strategy according to the attribute data, wherein the content identification strategy includes a content identification algorithm of at least two dimensions; Based on the content identification strategy and the content data, determining a wonderful chapter among a plurality of chapters in the to-be-identified book; The attribute data includes a book type, and the executable instructions further cause the processor to perform the following operations: Determining the content identification strategy according to the attribute data includes: When the book type is female type, the content identification strategy includes content identification algorithms in the interaction dimension and the emotion dimension; When the book type is male type, the content identification strategy includes the content identification algorithm in the interaction dimension and at least one content identification algorithm in the content dimension.

10. The electronic device according to claim 9, characterized in that: The executable instructions further cause the processor to perform the following operations: Wherein, based on the content identification strategy and the content data, determining the wonderful chapters among the multiple chapters in the book to be identified includes: Determine each chapter in the book to be identified as a target chapter in sequence; Determining a plurality of initial recognition results of the target chapter according to each content recognition algorithm in the content recognition strategy and data corresponding to the content recognition algorithm in the content data; A weighted calculation is performed on the multiple initial recognition results to obtain a wonderful content recognition result of the target chapter, wherein the wonderful content recognition result indicates whether the target chapter is a wonderful chapter.

11. The electronic device according to claim 10, characterized in that: The executable instructions further cause the processor to perform the following operations: The multiple initial recognition results are weighted and calculated to obtain the wonderful content recognition result of the target chapter, including: Normalizing and calculating the multiple initial recognition results respectively to obtain multiple recognition scores; Performing weighted calculation according to the multiple recognition scores and their corresponding weight values ​​to obtain a comprehensive score; The result of identifying the wonderful content of the target chapter is determined according to the comprehensive score.

12. The electronic device according to claim 11, characterized in that: The executable instructions further cause the processor to perform the following operations: The step of determining the wonderful content recognition result of the target chapter according to the comprehensive score includes: If the comprehensive score of the target chapter is greater than or equal to a preset threshold, the wonderful content recognition result of the target chapter is determined to be that the target chapter is a wonderful chapter; otherwise, the wonderful content recognition result of the target chapter is determined to be that the target chapter is not a wonderful chapter.

13. The electronic device according to any one of claims 9 to 12, characterized in that: The content identification algorithm includes at least one of the following: a statistical algorithm in the interaction dimension, an analysis algorithm in the sentiment dimension, and a named entity recognition algorithm, a part-of-speech tagging algorithm, and a classification algorithm in the content dimension.

14. The electronic device according to claim 9, characterized in that: The executable instructions further cause the processor to perform the following operations: The prompt information of the wonderful chapter is displayed on a preset page of the book to be identified.

15. The electronic device according to claim 14, characterized in that: The preset pages include a first page of target content associated with the wonderful chapter, a second page before the wonderful chapter and whose distance from the wonderful chapter meets a threshold, and / or a cover page of the book to be identified.

16. The electronic device according to claim 14, characterized in that: The prompt information includes at least one of a preset prompt text, the number of the wonderful chapters, and the distance between the wonderful chapters.

17. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the content identification method described in any one of claims 1 to 8.

Images