A text reading control method and device

Abstract

The embodiments of the present application provide a method and device for controlling text reading, which relate to the field of computer technology. The method comprises: a reading application responding to a user's reading operation, displaying a target text, and then determining feature tags of the target text in multiple dimensions. Based on the user's historical behavior data, the user's preference tags are determined. Then, based on the feature tags of the target text in multiple dimensions and the user's preference tags, target audio matching the target text is retrieved from an audio database and played. Therefore, while the user is reading the text, the user can hear audio matching the text content and the user's preferences, thereby enhancing the user's reading immersion and improving the user's reading experience.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of computer technology, and in particular to a method and device for controlling text reading. Background Art

[0002] With the development of e-reading and the fast pace of life, more and more users are choosing mobile phones and other terminals as the medium of reading, replacing the original paper media. Currently, the reading experience of e-reading is a single text experience, which sometimes makes users feel boring. Summary of the Invention

[0003] The embodiments of the present application provide a method and device for controlling text reading, which are used to enhance the user's immersive reading experience and thereby improve the user's reading experience.

[0004] In one aspect, an embodiment of the present application provides a method for controlling text reading, the method comprising:

[0005] Respond to the user's reading operation and display the target text;

[0006] Determining feature labels of the target text in multiple dimensions;

[0007] Based on the feature tags of the target text in multiple dimensions, target audio matching the target text is obtained from an audio database, and the target audio is played.

[0008] In one aspect, an embodiment of the present application provides a device for controlling text reading, the device comprising:

[0009] A display module, used to respond to the user's reading operation and display the target text;

[0010] A processing module, configured to determine feature labels of the target text in multiple dimensions;

[0011] The matching module is used to obtain target audio that matches the target text from an audio database based on feature tags of the target text in multiple dimensions, and play the target audio.

[0012] Optionally, the processing module is specifically configured to:

[0013] For each target dimension among the multiple dimensions, querying a text database for a feature label of the target dimension stored based on the attribute information of the target text;

[0014] When the feature labels of the target dimension stored in the text database include feature labels that match the attribute information of the target text, acquiring the feature labels of the target text in the target dimension from the text database;

[0015] Otherwise, the feature labels of the target text in the target dimension are determined based on the keywords in the target text.

[0016] Optionally, the matching module is specifically configured to:

[0017] Determining the user's preference tags based on the user's historical behavior data;

[0018] Based on the feature tags of the target text in multiple dimensions and the user's preference tags, a target audio that matches the target text is acquired from an audio database.

[0019] Optionally, the matching module is specifically configured to:

[0020] Determining a plurality of audios to be screened that match the target text based on the feature tags of the target text in multiple dimensions and the user's preference tags;

[0021] Determining target audio from the plurality of audios to be screened according to the user's historical audio listening records;

[0022] The target audio is obtained from the audio database.

[0023] On the one hand, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned text reading control method when executing the program.

[0024] On the one hand, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program that can be executed by a computer device. When the program is run on the computer device, the computer device executes the steps of the above-mentioned text reading control method.

[0025] In an embodiment of the present application, based on the feature tags of the text in multiple dimensions and the user's preference tags, target audio matching the text is obtained from an audio database and played. Therefore, while the user is reading the text, he can hear audio matching the text content and the user's preferences, thereby enhancing the user's reading immersion and improving the user's reading experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0027] Figure 1A schematic diagram of a system architecture provided in an embodiment of the present application;

[0028] Figure 2 A schematic diagram of an interface of a reading application provided in an embodiment of the present application;

[0029] Figure 3 A schematic diagram of an interface of a reading application provided in an embodiment of the present application;

[0030] Figure 4 A flowchart of a text reading control method provided in an embodiment of the present application;

[0031] Figure 5 A schematic diagram of an interface of a reading application provided in an embodiment of the present application;

[0032] Figure 6 A schematic diagram of a process for determining a feature tag according to an embodiment of the present application;

[0033] Figure 7 A schematic diagram of a process for determining a feature tag according to an embodiment of the present application;

[0034] Figure 8 A schematic diagram of determining target audio provided in an embodiment of the present application;

[0035] Figure 9 A schematic diagram of determining target audio provided in an embodiment of the present application;

[0036] Figure 10 A schematic diagram of the structure of a text reading system provided in an embodiment of the present application;

[0037] Figure 11 A flowchart of a text reading control method provided in an embodiment of the present application;

[0038] Figure 12 A schematic diagram of determining target audio provided in an embodiment of the present application;

[0039] Figure 13 A schematic diagram of the structure of a text reading control device provided in an embodiment of the present application;

[0040] Figure 14 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and beneficial effects of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0042] For ease of understanding, the terms involved in the embodiments of the present invention are explained below.

[0043] User behavior: User behavior includes two sub-concepts: historical user behavior and current user behavior. Historical user behavior refers to the user's past natural behavior, including but not limited to: the user's text reading behavior and the user's audio listening behavior. Current user behavior refers to the user's current operation behavior, specifically the user's actual text reading behavior.

[0044] It is understandable that in the specific implementation of this application, data related to user behavior is involved. When the embodiments in this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0045] The following is an introduction to the design concept of the embodiments of the present application.

[0046] With the development of e-reading and the fast pace of life, more and more users are choosing mobile phones and other terminals as the medium of reading, replacing the original paper media. Currently, the reading experience of e-reading is a single text experience, which sometimes makes users feel boring.

[0047] Considering that when reading, playing appropriate background music as the type of content and the development of the plot vary, it can enhance the atmosphere and increase the sense of immersion, thereby improving the user's reading experience.

[0048] In view of this, an embodiment of the present application provides a method for controlling text reading. In this method, a reading application responds to a user's reading operation, displays a target text, and then determines the feature tags of the target text in multiple dimensions. Based on the feature tags of the target text in multiple dimensions, a target audio that matches the target text is retrieved from an audio database and played. Since audio that matches the text features is played while the user is reading the text, the user's immersion in reading is increased, thereby improving the user's reading experience.

[0049] Furthermore, since the audio preferences of different users are different, if the target audio that matches the target text is selected in combination with the characteristics of the target text and the user's preferences, the user's reading experience will be greatly improved. In view of this, the embodiment of the present application provides an implementation method for selecting the target audio, that is, first determining the user's preference tags based on the user's historical behavior data, and then obtaining the target audio that matches the target text from the audio database based on the feature tags of the target text in multiple dimensions and the user's preference tags. Therefore, when the user reads, the audio that matches the text content and the user's preferences is played, thereby improving the user's reading experience.

[0050] refer to Figure 1 , which is a system architecture diagram applicable to an embodiment of the present application, and the system architecture includes at least a user terminal 101 and a server 102.

[0051] The user terminal 101 has a pre-installed reading application, which can be a pre-installed client application, a web application, a mini-program application, etc. The user terminal 101 may include one or more processors 1011, a memory 1012, an I / O interface 1013 for interacting with the server 102, and a display panel 1014. The user terminal 101 may be, but is not limited to, a smartphone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smartwatch, etc.

[0052] The server 102 is a background server of the reading application and provides services for the reading application. The server 102 may include one or more processors 1021, a memory 1022, and an I / O interface 1023 for interacting with the user terminal 101. In addition, the server 102 may also be configured with a database 1024. The server 102 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It may also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. The user terminal 101 and the server 102 may be directly or indirectly connected via wired or wireless communication, which is not limited in this application.

[0053] When a user uses the reading application to read, the reading application responds to the user's reading operation, obtains the target text from the text database of the server 102, and displays the target text. The target text can be a novel, a poem, an instruction manual, a dialogue, a translation, etc.

[0054] In one possible implementation, the reading application determines feature tags of the target text in multiple dimensions, and then obtains target audio that matches the target text from the audio database of the server 102 based on the feature tags of the target text in multiple dimensions, and plays the target audio.

[0055] In another possible implementation, the reading application determines feature tags of the target text in multiple dimensions, then obtains the user's historical behavior data from the user behavior database of server 102, and determines the user's preference tags based on the historical behavior data. Then, based on the feature tags of the target text in multiple dimensions and the user's preference tags, the application retrieves target audio that matches the target text from the audio database of server 102.

[0056] It should be noted that the text database, audio database, and user behavior database can be located within the server 102, within the user terminal 101, or independent of the user terminal 101 and the server 102. Furthermore, the text database, audio database, and user behavior database can be three independent databases, or all three can exist in one database, or two of them can exist in one database. This application does not impose any specific limitations on this.

[0057] For example, when the user starts the reading application, the reading application displays the main interface, such as Figure 2 As shown, the main interface includes a text search box, a navigation bar, and recommended texts, wherein the recommended texts include novel A, novel B, novel C, and novel D. The user clicks on novel A in the main interface of the reading application, and the reading application responds to the user's click operation and obtains the target text of novel A from the text database of server 102 based on the location where the user last finished reading novel A. The reading application first determines the feature tags of the target text of novel A in multiple dimensions, and then obtains the user's historical behavior data from the user behavior database of server 102, and determines the user's preference tags based on the user's historical behavior data. Then, based on the feature tags of the content of novel A in multiple dimensions and the user's preference tags, the target audio X that matches the target text is obtained from the audio database of server 102. The reading application displays the reading interface of novel A and plays the target audio X, as shown in FIG. Figure 3 As shown, the reading interface includes the target text of the novel A currently being read by the user and the relevant information of the target audio X.

[0058] based on Figure 1 The system architecture diagram shown in FIG. 1 shows a flow chart of a text reading control method provided by the present application embodiment. Figure 4 As shown, the process of the method is executed by a computer device, which may be Figure 1 The user terminal 101 or server 102 shown includes the following steps:

[0059] Step S401: responding to the user's reading operation and displaying the target text.

[0060] Specifically, reading operations include, but are not limited to, clicking, sliding, and pausing. The target text may be a novel, poem, instruction manual, dialogue, translation, etc. The target text may be the beginning of an article. For example, when a user clicks on novel A for the first time in a reading app, the reading app displays the beginning of novel A. The target text may also be the middle of an article. For example, if a user has previously read part of novel B, when the user clicks on novel B in the reading app, the reading app displays the content where the user last left off.

[0061] Reading applications respond to user reading operations by retrieving and displaying target text from a text database. The text database is the source of content for reading. Reading applications can access the text database locally, online, locally and online, through third-party online access, and through blockchain technology. Text databases can be updated periodically or on a triggered basis, with updates including additions, modifications, and deletions. In different application scenarios, text databases may employ similar or different content classification and display methods.

[0062] Step S402: determining feature labels of the target text in multiple dimensions.

[0063] The multiple dimensions in the embodiments of the present application include but are not limited to text language, text type, text emotion, text theme, text keywords, text IP (Intellectual Property), and text audio keywords.

[0064] Specifically, text language refers to one or more languages ​​that appear frequently in the text, such as Chinese, English, Japanese, etc.

[0065] Text type: refers to the genre of the text content, such as novel, narrative, poetry, instruction manual, dialogue, translation, and others.

[0066] Text sentiment: refers to the text sentiment identified based on text semantics, such as happy, depressed, ordinary, and dull.

[0067] Text theme: refers to the main theme highlighted in the text content, such as basketball skills, violin purchase, English test, etc.

[0068] Text keywords: refers to the core keywords in the text, such as radio, iced tea, panda, etc.

[0069] Text IP: refers to the IP of characters and things that appear in the text, such as tasks in novels, specific game characters, etc.

[0070] Text audio keywords: refers to the audio objects discussed in the text or the audio content that appears repeatedly.

[0071] In a specific implementation, the target text may match one or more feature tags in a dimension, or it may not match any feature tags. When the target text does not match a feature tag in one of the above dimensions, the feature tag of that dimension is set to "default" or "unrecognizable." It should be noted that the dimensions in this application are not limited to the aforementioned examples and can also be other dimensions, which is not specifically limited in this application.

[0072] Step S403: Based on the feature tags of the target text in multiple dimensions, a target audio that matches the target text is obtained from the audio database, and the target audio is played.

[0073] Specifically, the audio database is the content source for audio playback, and reading applications access the audio database in the form of local access, online access, local + online access, third-party online access, blockchain access, etc. The audio database is updated periodically or triggered, and update operations include adding, modifying, deleting, etc. The audio database has basic functions such as storage and reading. In different actual application scenarios, the audio database has the same or different content classification and display methods for its own content. The text database and the audio database can be two independent databases that exist, are maintained, and run independently. The text database and the audio database can also be located in the same entity or address, such as a local database that exists on a user terminal at the same time.

[0074] The mapping rules between feature tags and audio in the audio database are pre-set, and the mapping rules are updated periodically or triggered. After determining the feature tags of the target text in multiple dimensions, the target audio that matches the target text is determined based on the feature tags of the target text in multiple dimensions and the preset mapping rules, and then the target audio is obtained from the audio database and played. In the embodiment of the present application, when the user is reading the text, playing the audio that matches the text features has the effect of strengthening the atmosphere and increasing the sense of immersion, thereby improving the user's reading experience.

[0075] In the above embodiment, playing the audio that matches the target text when the target text is displayed can be a default function or an optional function for the user to select. Figure 5 As shown, the user clicks the Settings button in the reading app, and the reading app displays the settings interface. The settings interface includes an audio function settings button, where the user can choose whether to enable the audio function. When the user chooses to turn off the audio function, the reading app displays the target text without playing the audio. When the user chooses to turn on the audio function, the reading app displays the target text and plays the audio that matches the target text.

[0076] In addition, users can also select audio playback and audio switching methods in the reading application. Audio playback methods include single song loop, random play, sequential play, etc. Audio switching methods include switching based on text content, switching after the current audio playback is completed, etc. In the embodiment of the present application, the reading application provides a variety of optional functions, so users can select the corresponding function according to actual needs, thereby adapting to the preferences of different users and facilitating the promotion of the reading application.

[0077] Optionally, in the above step S402, the present embodiment provides at least the following implementation methods for determining feature labels of the target text in multiple dimensions:

[0078] In the first implementation mode, feature labels of the target text in multiple dimensions are determined based on the target text.

[0079] For each target dimension among the multiple dimensions, a feature label of the target dimension stored in a text database is queried based on the target text. If the feature labels of the target dimension stored in the text database include a feature label that matches the target text, the feature label of the target text in the target dimension is retrieved from the text database. Otherwise, the feature label of the target text in the target dimension is determined based on keywords in the target text.

[0080] Specifically, the text data pre-stores the feature labels of the text in various dimensions. The text database can save the feature labels of each text paragraph in various dimensions on a per-text basis; it can also save the feature labels of each chapter in various dimensions on a per-chapter basis; it can also save the feature labels of the text content in each text display page in various dimensions on a per-text basis. This application does not make any specific restrictions on this.

[0081] Accordingly, when querying the feature labels of the target dimension stored in the text database based on the target text, the embodiment of the present application provides at least the following query methods:

[0082] Query method 1: Query method based on text paragraphs.

[0083] The target text includes multiple text paragraphs. Based on the user's stay time on the target text display page, the text paragraph in the target text currently read by the user is determined. Then, based on the text paragraph, the feature label of the target dimension saved in the text database is queried to obtain the feature label of the target text in the target dimension.

[0084] Query method 2: Chapter-based query method.

[0085] First, the chapter of the target text in the article is determined, and then the feature labels of the target dimension stored in the text database are queried based on the chapter where the target text is located to obtain the feature labels of the target text in the target dimension.

[0086] Query method three: Query method based on text display page.

[0087] Based on the target text displayed on the target text display page, a feature label of the target dimension stored in the text database is queried to obtain the feature label of the target text in the target dimension.

[0088] In specific implementations, the sources of feature labels for each dimension in the text database include, but are not limited to, backend input, previously determined feature labels, user-defined feature labels, and other third-party data sources. In specific implementations, one of these sources can be selected as a benchmark to determine the feature labels for the target text, or a combination of multiple sources can be used to determine the feature labels for the target text. The target text can have one or more feature labels for the target dimension.

[0089] When the target text has only one feature label in the target dimension, if the feature labels of the target text determined by the above different sources are different, the feature label of one source is selected as the feature label of the target text according to the priority order of the above sources, and the priority order is preset. In addition, the feature label of the text actively calibrated by the user may be one or more. When there are multiple feature labels that match the target text, the preferred feature label is determined from the multiple feature labels according to the number of calibrators of each feature label. Optionally, when there are multiple preferred feature labels with the same number of calibrators, the preferred feature label that was updated last is used as the feature label that matches the target text.

[0090] The following takes the target dimension "text sentiment" as an example to explain the process of determining the feature labels of the target text in multiple dimensions based on the target text. Figure 6 As shown, the following steps are included:

[0091] Step S601 : Based on the text paragraph W in the target text currently read by the user, query the feature labels of the “text sentiment” dimension stored in the text database.

[0092] The text database uses text paragraphs as units and saves the feature labels of each text paragraph in the "text sentiment" dimension.

[0093] Step S602 , determining whether the feature tags of the “text emotion” dimension stored in the text database include feature tags matching the text paragraph W; if so, executing step S603 ; otherwise, executing step S604 .

[0094] Step S603: Obtain the feature label of the text paragraph W in the “text sentiment” dimension from the text database.

[0095] Step S604 , determining whether the text paragraph W includes keywords expressing emotions, if so, executing step S605 , otherwise executing step S606 .

[0096] Step S605 : Determine the feature label of the text paragraph W in the “text sentiment” dimension based on the keywords in the text paragraph W.

[0097] Step S606: Determine that the feature label of the text paragraph W in the “text sentiment” dimension is “empty”.

[0098] For example, when a text paragraph W contains descriptive keywords such as "XX excitedly said," the feature label of the "Text Emotion" dimension of the text paragraph W can be determined to be "happy." Of course, the text paragraph W may not contain keywords that represent emotions. In this case, the feature label of the "Text Emotion" dimension of the text paragraph W is determined to be "empty."

[0099] In the embodiment of the present application, text database query and keyword matching are combined to determine the feature labels of the text in multiple dimensions, thereby ensuring the accuracy of the obtained feature labels and improving the efficiency of determining the feature labels of the text.

[0100] It should be noted that the implementation method of determining the feature labels of the target text in multiple dimensions based on the target text in the embodiment of the present application is not limited to the text database query combined with keyword matching method described above. It can also be to obtain the feature labels of the target text in multiple dimensions only through text database query, or directly determine the feature labels of the target text in multiple dimensions based on the keywords in the target text. This application does not make specific limitations on this.

[0101] In a second implementation mode, feature labels of the target text in multiple dimensions are determined based on the attribute information of the target text.

[0102] Specifically, for each target dimension among multiple dimensions, the feature labels of the target dimension stored in the text database are queried based on the attribute information of the target text; when the feature labels of the target dimension stored in the text database include feature labels that match the attribute information of the target text, the feature labels of the target text in the target dimension are obtained from the text database; otherwise, the feature labels of the target text in the target dimension are determined based on the keywords in the target text.

[0103] The attribute information of the target text is obtained from the text database based on the target text. The attribute information of the target text includes text background, related text, author information, etc. In addition, the text database stores the feature labels corresponding to the attribute information of the text in various dimensions.

[0104] The following takes the target dimension "text type" as an example to explain how to determine the feature labels of the target text in multiple dimensions based on the attribute information of the target text. Figure 7 As shown, the following steps are included:

[0105] Step S701 : querying a text database based on a text paragraph W in a target text currently read by a user, and determining that the text background of the text paragraph W is “martial arts novels”.

[0106] Step S702 , based on the text background “martial arts novel”, query the feature labels of the “text type” dimension stored in the text database.

[0107] Step S703, determining whether the feature tags of the "text type" dimension stored in the text database include feature tags that match the text background "martial arts novels", if so, executing step S704, otherwise executing step S705.

[0108] Step S704: Acquire feature tags matching the text background "martial arts novels" from the text database.

[0109] For example, when the feature tags of the "text type" dimension stored in the text database include the feature tag "novel" that matches the text background "martial arts novel", the feature tag "novel" is used as the feature tag of the text paragraph W in the "text type" dimension.

[0110] Step S705 , determining whether the text paragraph W includes a keyword indicating the text type, if so, executing step S706 , otherwise executing step S707 .

[0111] Step S706: Determine the feature label of the text paragraph W in the “text type” dimension based on the keywords in the text paragraph W.

[0112] Step S707 , determining that the feature label of the text paragraph W in the “text type” dimension is “empty”.

[0113] In the embodiment of the present application, a text database is queried based on the attribute information of the text to determine the feature tags of the text. For the feature tags in the attribute dimension, the efficiency of tag matching can be effectively improved.

[0114] It should be noted that the implementation method of determining the feature labels of the target text in multiple dimensions based on the attribute information of the target text in the embodiment of the present application is not limited to the text database query combined with keyword matching method described above. It can also be to obtain the feature labels of the target text in multiple dimensions only through text database query, or directly determine the feature labels of the target text in multiple dimensions based on the keywords in the target text. This application does not make specific limitations on this.

[0115] In a third implementation mode, feature labels of the target text in multiple dimensions are determined based on the target text and the attribute information of the target text.

[0116] Specifically, for each target dimension among the multiple dimensions, based on the target text and the target text's attribute information, a query is performed on the feature tags of the target dimension stored in the text database. If the feature tags of the target dimension stored in the text database include a feature tag that matches the target text or its attribute information, the feature tag of the target text in the target dimension is retrieved from the text database. Otherwise, the feature tag of the target text in the target dimension is determined based on keywords in the target text.

[0117] The target text's attribute information is retrieved from a text database based on the target text. This includes text context, related text, and author information. The text database stores both feature tags corresponding to the specific text content and feature tags corresponding to the text's attribute information. The text database has been described in detail in Implementations 1 and 2 and will not be further elaborated here.

[0118] When querying the feature labels of the target dimension stored in the text database based on the target text and the attribute information of the target text, you can first query the feature labels of the target dimension stored in the text database based on the target text. If the feature labels of the target dimension stored in the text database do not include feature labels that match the target text, then query the feature labels of the target dimension stored in the text database based on the attribute information of the target text. You can also first query the feature labels of the target dimension stored in the text database based on the attribute information of the target text. If the feature labels of the target dimension stored in the text database do not include feature labels that match the attribute information of the target text, then query the feature labels of the target dimension stored in the text database based on the target text. You can also pre-set the feature labels of some dimensions and obtain them by querying the text database based on the target text, and obtain the feature labels of another part of the dimensions by querying the text database based on the attribute information of the target text. This application does not make any specific restrictions on this.

[0119] In the embodiment of the present application, the text database is queried in combination with the text content and the attribute information of the text to determine the feature labels of the text in multiple dimensions, so that the feature labels obtained in each dimension are more comprehensive.

[0120] It should be noted that the implementation method of determining the feature labels of the target text in multiple dimensions based on the target text and the attribute information of the target text in the embodiment of the present application is not limited to the text database query combined with keyword matching method described above. It can also be to obtain the feature labels of the target text in multiple dimensions only through text database query, or directly determine the feature labels of the target text in multiple dimensions based on the keywords in the target text. This application does not make specific limitations on this.

[0121] Optionally, in the above step S403, since the audio preferences of different users are different, if the target audio matching the target text is selected in combination with the characteristics of the target text and the user's preferences, the user's reading experience will be greatly improved. In view of this, an embodiment of the present application provides an implementation method for selecting the target audio, that is, first determining the user's preference tags based on the user's historical behavior data, and then obtaining the target audio matching the target text from the audio database based on the feature tags of the target text in multiple dimensions and the user's preference tags.

[0122] In specific implementations, the user's historical behavior data is obtained from the user behavior database, wherein the user behavior database stores the user behavior data actively uploaded by the user and the user behavior data actively collected by the user terminal with authorization. After the user terminal collects the user behavior, it can trigger or periodically write batches into the user behavior database. The user's historical behavior includes text reading behavior and audio playback behavior, specifically including clicks, reading, staying, jumping out, subscription, unsubscription, payment, refund, complaint, consultation, opening, closing, setting changes, and preference tags actively uploaded by the user. The reading application accesses the user behavior database in the form of online access, third-party online access, blockchain access, etc. The user behavior database is updated based on the actual behavior of the user, including triggered updates and periodic batch updates. Existing behaviors in the user behavior database will not be changed and can be deleted. The user behavior database has storage, access and other functions.

[0123] Preset mapping rules between feature tags, preference tags, and audio in the audio database are used to determine initial audio that matches the target text based on the target text's feature tags in multiple dimensions and the pre-set mapping rules. The user's preference tags are determined based on historical user behavior data. Based on the user's preference tags and the pre-set mapping rules, target audio that matches the user's preference tags is determined from each initial audio.

[0124] For example, Figure 8 As shown in the example, assume that the user is currently reading a joyful romantic story set in France. Based on the text they are currently reading, the user's feature tags across multiple dimensions are determined to be "joyful_France_love." Based on their historical behavior data, the user's preference tag is determined to be "piano music." Based on the preset mapping rules, the target audio is determined to be romantic piano music. The romantic piano music is then retrieved from the audio database and played.

[0125] In an embodiment of the present application, target audio is obtained from an audio database and played based on the feature tags of the text in multiple dimensions and the user's preference tags. Therefore, while the user is reading, audio that matches the text content and the user's preferences is played, thereby enhancing the user's reading immersion and improving the user's reading experience.

[0126] Furthermore, there may be one or more audio tracks that match the text's feature tags in multiple dimensions and the user's preference tags. When there are multiple matching audio tracks, the multiple audio tracks can be sorted and then played according to the playback method set by the user. Alternatively, one audio track can be selected from the multiple audio tracks. The specific method is as follows: based on the target text's feature tags in multiple dimensions and the user's preference tags, multiple audio tracks to be screened that match the target text are determined. Then, based on the user's historical audio listening history, the target audio track is determined from the multiple audio tracks to be screened, and the target audio track is retrieved from the audio database.

[0127] In a specific implementation, the audio to be filtered that matches the historical audio listening record among multiple audios to be filtered can be determined as the target audio. If there are multiple audios to be filtered that match the historical audio listening record, the audio to be filtered that the user has listened to the most times among the multiple matching audios to be filtered can be used as the target audio, or the audio to be filtered that the user has listened to most recently among the multiple matching audios to be filtered can be used as the target audio. This application does not make specific restrictions on this.

[0128] For example, Figure 9 As shown, assume that the user is currently reading a joyful romantic love story set in France. Based on the text currently being read, the user's feature tags across multiple dimensions are determined to be "joyful_France_love." Based on the user's historical behavioral data, the user's preference tag is determined to be "piano music." Based on the feature tags "joyful_France_love," the preference tag "piano music," and a pre-set mapping rule, the audio matching the target text is determined to be a romantic piano piece. The romantic piano pieces in the audio database include Audio A, Audio B, Audio C, and Audio D. The multiple romantic piano pieces are then compared with the user's historical audio listening history. If Audio B is an audio the user has previously listened to, Audio B is selected as the target audio, retrieved from the audio database, and played.

[0129] In an embodiment of the present application, based on the feature tags of the text in multiple dimensions, the user's preference tags and historical audio listening records, the target audio matching the text is determined and played. Therefore, while the user is reading, the audio matching the text content and the user's preferences is played, thereby enhancing the user's reading immersion and improving the user's reading experience.

[0130] In order to more clearly describe the technical solution of the embodiment of the present application, the following describes a text reading control method provided by the embodiment of the present application in combination with a specific system architecture. The method is interactively executed by various units in the text reading system. The structure of the text reading system is as follows: Figure 10As shown, it includes a text database, an audio database, a user behavior database, a user behavior collection unit, a text content determination unit, a feedback decision unit, a text reading unit and an audio playback unit.

[0131] Text databases are the source of text reading content. Access to text databases includes local access, online access, local and online access, third-party online access, and blockchain access. Text databases can be updated periodically or on a triggered basis, with update operations including addition, modification, and deletion. In different practical application scenarios, text databases may employ similar or different content classification and display methods.

[0132] The audio database is the source of audio content for playback. Access to the audio database includes local, online, local and online, third-party online, and blockchain-based access. The audio database is updated periodically or triggered, with operations such as addition, modification, and deletion. The audio database has basic functions such as storage and retrieval. In different practical application scenarios, audio databases may use the same or different content classification and display methods.

[0133] The user behavior database stores user behavior data actively uploaded by users and user behavior data actively collected by user terminals with authorization. After collecting user behavior, the user terminal can trigger or periodically write user behavior data in batches. User historical behavior includes text reading behavior and audio playback behavior, including clicks, reading, staying, jumping out, subscription, unsubscription, payment, refund, complaint, consultation, opening, closing, setting changes, and user-uploaded preference tags. Access to the user behavior database includes online access, third-party online access, and blockchain access. The user behavior database is updated based on the actual user behavior, including triggered updates and periodic batch updates. Existing behaviors in the user behavior database will not be changed and can be deleted. The user behavior database has storage and access functions.

[0134] The user behavior collection unit is used to collect the user's text reading behavior and audio playback behavior. After collecting the user behavior, the user behavior collection unit can trigger or periodically write it into the user behavior database in batches.

[0135] The text content determination unit is used to determine the feature labels of the target text in multiple dimensions, including but not limited to text language, text type, text emotion, text theme, text keywords, text IP, and text audio keywords.

[0136] The feedback decision unit stores mapping rules between feature tags, preference tags, and audio in the audio database. These mapping rules are updated periodically or on a trigger basis. Based on the target text's feature tags across multiple dimensions, the user's preference tags, and the mapping rules, it determines the target audio that matches the target text.

[0137] The text reading unit is used to display the target text that the user is currently reading.

[0138] The audio playback unit is used to play target audio that matches the target text.

[0139] Based on the structure of the above text reading system, the following describes the flow of the text reading control method. Figure 11 As shown, the following steps are included:

[0140] Step S1101: The user starts the audio function.

[0141] In step S1102 , the user generates a reading behavior in the text reading unit, and the text reading unit displays the target text.

[0142] Step S1103: The user behavior collection unit collects reading behavior and target text.

[0143] Step S1104: The user behavior collection unit sends the target text to the text content determination unit.

[0144] Step S1105: The text content determination unit submits an attribute information retrieval request to the text data based on the target text.

[0145] Step S1106: The text database returns the attribute information of the target text.

[0146] Step S1107 : The text content determination unit determines feature labels of the target text in multiple dimensions based on the target text and the attribute information of the target text.

[0147] In step S1108 , the text content determination unit sends the feature labels of the target text in multiple dimensions to the feedback decision unit.

[0148] In step S1109 , the user behavior collection unit feeds back the collected reading behavior to the feedback decision unit.

[0149] It should be noted that there is no particular order in which step S1108 and step S1109 are performed. In addition, the execution of step S1109 does not depend on the completion of steps S1104 to S1108, that is, the content corresponding to step S1109 can be executed immediately after the completion of step S1103.

[0150] Step S1110: The feedback decision unit submits a retrieval request for the user's historical behavior data to the user behavior database.

[0151] Step S1111: The user behavior database returns the user's historical behavior data.

[0152] In step S1112, the feedback decision unit determines the target audio that matches the target text by combining the user's reading behavior, the feature labels of the target text in multiple dimensions, and the user's historical behavior data.

[0153] Step S1113: The feedback decision unit submits a retrieval request for the target audio to the audio database.

[0154] Step S1114: The audio database returns the target audio.

[0155] Specifically, when there are multiple target audios, the audio database returns the multiple audios and also returns the playback order of the multiple target audios.

[0156] Step S1115: The feedback decision unit sends the target audio to the audio playback unit.

[0157] Step S1116: the audio playback unit plays the target audio.

[0158] In the above step S1112, the feedback decision unit combines the user's reading behavior, the feature labels of the target text in multiple dimensions, and the user's historical behavior data to determine the target audio that matches the target text. Figure 12 As shown, the following steps are included:

[0159] The feedback decision unit receives the feature labels of the target text in multiple dimensions sent by the text content determination unit, receives the user's reading behavior collected by the user behavior collection unit, and obtains the user's historical behavior data from the user behavior database.

[0160] The feedback decision unit calls the mapping processing logic of this unit to determine one or more initial audios that match the target text based on the user's reading behavior and the feature labels of the target text currently being read by the user in multiple dimensions.

[0161] The feedback decision unit calls this unit to determine the user's preference tags based on the user's historical behavior data, and then based on the user's preference tags, determines one or more target audios that match the user's preference tags from each initial audio.

[0162] When users read text, audio that matches the text features and user preferences is played, which increases the immersiveness of reading and improves the user's reading experience.

[0163] Based on the same technical concept, the embodiment of the present application provides a control device for text reading, such as Figure 13 As shown, the apparatus 1300 includes:

[0164] Display module 1301, for responding to the user's reading operation and displaying the target text;

[0165] Processing module 1302, used to determine feature labels of target text in multiple dimensions;

[0166] The matching module 1303 is used to obtain target audio that matches the target text from the audio database based on the feature tags of the target text in multiple dimensions, and play the target audio.

[0167] Optionally, the processing module 1302 is specifically configured to:

[0168] Determine the feature labels of the target text in multiple dimensions based on the target text; or

[0169] Determine the feature labels of the target text in multiple dimensions based on the target text and the attribute information of the target text; or

[0170] According to the attribute information of the target text, the feature labels of the target text in multiple dimensions are determined.

[0171] Optionally, the attribute information of the target text is obtained by querying a text database based on the target text.

[0172] Optionally, the processing module 1302 is specifically configured to:

[0173] For each target dimension among the multiple dimensions, query the feature label of the target dimension stored in the text database based on the target text;

[0174] When the feature labels of the target dimension stored in the text database include feature labels that match the target text, obtaining the feature labels of the target text in the target dimension from the text database;

[0175] Otherwise, the feature labels of the target text in the target dimension are determined based on the keywords in the target text.

[0176] Optionally, the processing module 1302 is specifically configured to:

[0177] For each target dimension among the multiple dimensions, based on the target text and the attribute information of the target text, query the feature label of the target dimension stored in the text database;

[0178] When the feature labels of the target dimension stored in the text database include feature labels that match the target text or attribute information of the target text, obtaining the feature labels of the target text in the target dimension from the text database;

[0179] Otherwise, the feature labels of the target text in the target dimension are determined based on the keywords in the target text.

[0180] Optionally, the processing module 1302 is specifically configured to:

[0181] For each target dimension among the multiple dimensions, query the feature label of the target dimension stored in the text database based on the attribute information of the target text;

[0182] When the feature labels of the target dimension stored in the text database include feature labels that match the attribute information of the target text, obtaining the feature labels of the target text in the target dimension from the text database;

[0183] Otherwise, the feature labels of the target text in the target dimension are determined based on the keywords in the target text.

[0184] Optionally, the matching module 1303 is specifically configured to:

[0185] Determine the user's preference tags based on the user's historical behavior data;

[0186] Based on the feature labels of the target text in multiple dimensions and the user's preference labels, the target audio matching the target text is obtained from the audio database.

[0187] Optionally, the matching module 1303 is specifically configured to:

[0188] Based on the feature tags of the target text in multiple dimensions and the user's preference tags, multiple audios to be screened that match the target text are determined;

[0189] Determine target audio from multiple audios to be screened based on the user's historical audio listening records;

[0190] Get the target audio from the audio database.

[0191] Based on the same technical concept, the embodiment of the present application provides a computer device, such as Figure 14 As shown, it includes at least one processor 1401 and a memory 1402 connected to the at least one processor. The specific connection medium between the processor 1401 and the memory 1402 is not limited in the embodiment of the present application. Figure 14 For example, the processor 1401 and the memory 1402 are connected via a bus. The bus can be divided into an address bus, a data bus, a control bus, and the like.

[0192] In the embodiment of the present application, the memory 1402 stores instructions that can be executed by at least one processor 1401. The at least one processor 1401 can execute the steps included in the above-mentioned text reading control method by executing the instructions stored in the memory 1402.

[0193] Among them, the processor 1401 is the control center of the computer device. It can use various interfaces and lines to connect various parts of the computer device. By running or executing instructions stored in the memory 1402 and calling data stored in the memory 1402, it matches audio for the text currently read by the user and plays it. Optionally, the processor 1401 may include one or more processing units. The processor 1401 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 1401. In some embodiments, the processor 1401 and the memory 1402 may be implemented on the same chip. In some embodiments, they may also be implemented separately on independent chips.

[0194] The processor 1401 can be a general-purpose processor, such as a central processing unit (CPU), a digital signal processor, an application-specific integrated circuit (ASIC), a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor.

[0195] Memory 1402 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules. Memory 1402 may include at least one type of storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory, a random access memory (Random Access Memory, RAM), a static random access memory (Static Random Access Memory, SRAM), a programmable read-only memory (Programmable Read Only Memory, PROM), a read-only memory (Read Only Memory, ROM), an electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), a magnetic memory, a disk, an optical disk, etc. Memory 1402 is any other medium that can be used to carry or store a desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 1402 in the embodiment of the present application can also be a circuit or any other device that can realize a storage function, for storing program instructions and / or data.

[0196] Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program that can be executed by a computer device. When the program runs on the computer device, the computer device executes the steps of the above-mentioned text reading control method.

[0197] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0198] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0199] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0200] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0201] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0202] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for controlling text reading, characterized in that: include: Respond to the user's reading operation and display the target text on the reading interface; For each target dimension in the multiple dimensions, determining a text paragraph in the target text currently read by the user based on the user's stay time on the reading interface; Querying a text database for feature labels of a target dimension based on the text paragraph, where the feature labels of each dimension in the text database come from multiple sources; When the feature label of the text paragraph in the target dimension is one, if the feature labels of the text paragraph determined by multiple sources are different, then according to the priority order of the multiple sources, a feature label from one source is selected as the feature label of the text paragraph; When the one source is user-initiated calibration and multiple feature tags matching the text paragraph appear, determining the feature tag of the text paragraph from the multiple feature tags according to the number of calibrated users of each feature tag; When there are multiple feature tags with the same number of calibrated persons, the feature tag updated last is used as the feature tag of the text paragraph; Determining the user's preference tags based on the user's historical behavior data; Presetting mapping rules between feature tags, preference tags and audio in the audio database; Based on the feature labels of the text paragraph in multiple dimensions and a preset mapping rule, obtaining an initial audio matching the text paragraph from the audio database; Based on the user's preference tags and a preset mapping rule, determining target audio that matches the user's preference tags from each initial audio; The target audio is played when the target text is displayed on the reading interface.

2. The method according to claim 1, wherein Also includes: When the saved feature tags of the target dimension do not include a feature tag matching the text paragraph, the feature tags of the target text in multiple dimensions are determined according to the attribute information of the target text.

3. The method according to claim 2, wherein The attribute information of the target text is obtained by querying the target text from a text database.

4. The method according to claim 1, wherein Also includes: The saved feature tags of the target dimension do not include feature tags matching the text paragraph, and the feature tags of the target text in the target dimension are determined based on keywords in the target text.

5. The method according to claim 2, wherein Determining the feature labels of the target text in multiple dimensions based on the attribute information of the target text includes: For each target dimension among the multiple dimensions, based on the attribute information of the target text, query the feature label of the target dimension stored in the text database; When the feature labels of the target dimension stored in the text database include feature labels that match the attribute information of the target text, acquiring the feature labels of the target text in the target dimension from the text database; Otherwise, the feature labels of the target text in the target dimension are determined based on the keywords in the target text.

6. A text reading control device, characterized in that: include: The display module is used to respond to the user's reading operation and display the target text on the reading interface; A processing module is used to determine, for each target dimension in a plurality of dimensions, a text paragraph in the target text currently being read by the user according to the dwell time of the user on the reading interface; query the feature label of the target dimension stored in a text database based on the text paragraph, wherein the feature labels of each dimension in the text database come from multiple sources; when the text paragraph has only one feature label in the target dimension, if the feature labels of the text paragraph determined using multiple sources are different, then according to the priority order of the multiple sources, a feature label from one source is selected as the feature label of the text paragraph; when the one source is actively calibrated by the user and there are multiple feature labels matching the text paragraph, the feature label of the text paragraph is determined from the multiple feature labels according to the number of calibrated people for each feature label; when there are multiple feature labels with the same number of calibrated people, the feature label with the latest update is used as the feature label of the text paragraph; A matching module is used to determine the user's preference tags based on the user's historical behavior data; and pre-set mapping rules between feature tags, preference tags and audio in the audio database; Based on the feature labels of the text paragraph in multiple dimensions and a preset mapping rule, obtaining an initial audio matching the text paragraph from the audio database; Based on the user's favorite tags and preset mapping rules, target audio that matches the user's favorite tags is determined from each initial audio, and the target audio is played when the target text is displayed on the reading interface.

7. The device according to claim 6, characterized in that The processing module is further configured to: When the saved feature tags of the target dimension do not include a feature tag matching the text paragraph, the feature tags of the target text in multiple dimensions are determined according to the attribute information of the target text.

8. The device according to claim 7, wherein The attribute information of the target text is obtained by querying the target text from a text database.

9. The device according to claim 6, wherein The processing module is further configured to: When the saved feature tags of the target dimension do not include a feature tag matching the text paragraph, the feature tag of the target text in the target dimension is determined based on keywords in the target text.

10. The device according to claim 7, wherein The processing module is specifically used for: For each target dimension among the multiple dimensions, based on the attribute information of the target text, query the feature label of the target dimension stored in the text database; When the feature labels of the target dimension stored in the text database include feature labels that match the attribute information of the target text, acquiring the feature labels of the target text in the target dimension from the text database; Otherwise, the feature labels of the target text in the target dimension are determined based on the keywords in the target text.

11. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of any one of the methods of claims 1 to 5 are implemented.

12. A computer-readable storage medium, characterized in that It stores a computer program that can be executed by a computer device. When the program is run on the computer device, the computer device executes the steps of any one of the methods described in claims 1 to 5.

Images