CN111523289B

CN111523289B - Text format generation method, device, equipment and readable medium

Info

Publication number: CN111523289B
Application number: CN202010334143.1A
Authority: CN
Inventors: 钟明洁; 郑培祥; 蔡明宸
Original assignee: Alipay Hangzhou Information Technology Co Ltd
Current assignee: Alipay Hangzhou Information Technology Co Ltd
Priority date: 2020-04-24
Filing date: 2020-04-24
Publication date: 2023-05-09
Anticipated expiration: 2040-04-24
Also published as: CN111523289A

Abstract

The embodiment of the specification discloses a text format generation method, a device, equipment and a computer readable medium. The scheme comprises the following steps: acquiring a target text; extracting keywords in the target text; determining a label of the target text based on the extracted keywords; and determining the text format of the target text according to the label of the target text based on a mapping relation library of the preset label and the preset text format.

Description

Text format generation method, device, equipment and readable medium

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a computer readable medium for generating a text format.

Background

At present, internet technology is vigorously developed, and users can receive various information through terminals such as smart phones, computers and the like. When an information provider pushes information to a user, the specific display mode of the pushed information can greatly influence the acceptance condition of the user on the information.

For example, in a scene of recommending marketing, a good document display form can effectively highlight the key points of document contents, attract eyeballs of users, and obtain better user conversion efficiency. However, in most of the recommended scenes at present, the format of the document is unchanged, the content of the document cannot be highlighted well, and the document presentation effect is poor.

Disclosure of Invention

In view of this, the embodiments of the present application provide a text format generating method, apparatus, device, and computer readable medium for highlighting text content for display, so that the display effect of the text is better.

In order to solve the above technical problems, the embodiments of the present specification are implemented as follows:

the text format generation method provided by the embodiment of the specification comprises the following steps: acquiring a target text; extracting keywords in the target text; determining a label of the target text based on the extracted keywords; and determining the text format of the target text according to the label of the target text based on a mapping relation library of the preset label and the preset text format.

The text format generating device provided in the embodiment of the present specification includes: the target text acquisition module is used for acquiring a target text; the keyword extraction module is used for extracting keywords in the target text; the label determining module is used for determining labels of the target text based on the extracted keywords; the text format determining module is used for determining the text format of the target text according to the label of the target text based on a mapping relation library of the preset label and the preset text format.

The text format generating device provided in the embodiment of the present specification includes:

at least one processor; the method comprises the steps of,

a memory communicatively coupled to the at least one processor; wherein,,

the memory stores instructions executable by the at least one processor to enable the at least one processor to:

acquiring a target text; extracting keywords in the target text; determining a label of the target text based on the extracted keywords; and determining the text format of the target text according to the label of the target text based on a mapping relation library of the preset label and the preset text format.

The embodiments of the present disclosure provide a computer readable medium having computer readable instructions stored thereon, the computer readable instructions being executable by a processor to implement the text format generating method according to any of the foregoing embodiments.

The above-mentioned at least one technical scheme that this description embodiment adopted can reach following beneficial effect: the method comprises the steps of firstly obtaining a target text to be displayed, then extracting keywords in the target text, determining a label corresponding to the target text based on the extracted keywords, and then determining a proper text format of the target text according to a preset mapping relation between preset labels and preset text formats. According to the scheme, the text content of the target text is analyzed, so that the text content is displayed in a mode corresponding to the text content, the display format of the text is more matched with the text content, the text content can be better highlighted, further, the text display effect is better, and the understanding and the interest of a user on the text can be better promoted.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:

fig. 1 is a flow chart of a text format generating method according to an embodiment of the present disclosure;

fig. 2 is a schematic diagram of a specific application scenario of a text format generating method according to an embodiment of the present disclosure;

fig. 3 is a schematic structural diagram of a text format generating device corresponding to fig. 1 according to an embodiment of the present disclosure;

fig. 4 is a schematic structural diagram of a text format generating apparatus corresponding to fig. 1 provided in an embodiment of the present disclosure.

Detailed Description

In, for example, a recommended marketing scenario, the placement of a document is an important means. The good document display form can effectively highlight the key points of the document content, attract the eyeballs of users and obtain better conversion efficiency. In most of the recommended scenes at present, the presentation forms of the texts are constant, namely, the presentation forms of the texts are the same for different text contents and different users. The existing text formats for showing the texts cannot effectively highlight the contents of different texts, and it is difficult to promote the understanding and interest of users to the contents of the texts. To better highlight text content of a document, and to facilitate user understanding and interest in the document, the present application provides a method for generating a document text format based on text content mining.

For the purposes, technical solutions and advantages of the present application, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.

In the description of the present application, the terms first, second, etc. are used to describe various information, parameters, fields, instructions, terminals, etc., but these information, parameters, fields, instructions, terminals should not be limited by these terms. These terms are used to distinguish one information, parameter, field, instruction, terminal from another information, parameter, field, instruction, terminal. Thus, a first information, parameter, field, instruction, terminal discussed below may also be referred to as a second information, parameter, field, instruction, terminal without departing from the teachings of the present disclosure.

The following describes in detail the technical solutions provided by the embodiments of the present application with reference to the accompanying drawings.

Fig. 1 is a flow chart of a text format generating method according to an embodiment of the present disclosure. From the program perspective, the execution subject of the flow may be a program installed on an application server or an application terminal.

As shown in fig. 1, the process may include the steps of:

step 102: and acquiring the target text.

The target text may be a text intended to be presented to the user, wherein the text is text used for content recommendation. For example, the text may be a recommended word, a recommended title, or the like. In some cases, the document may also be a paragraph, etc.

The target text may be a word, a sentence, etc. For example, a word-form target text may be "ant forest", "car insurance", "red package", or the like. For example, a sentence form of target text may be "hungry: share peripheral food "," spare gold: your emergency wallet ", etc.

Step 104: and extracting keywords in the target text.

In an embodiment, specifically, the extracting the keywords in the target text may specifically include: word segmentation is carried out on the target text, and a word segmentation set corresponding to the target text is obtained; extracting keywords from the word segmentation set to obtain a keyword set corresponding to the target text, wherein the keyword set comprises at least one keyword.

Specifically, the target text may be segmented using existing segmentation techniques. The word segmentation technique refers to a process of recombining continuous word sequences into word sequences according to a certain specification. As an example, natural language processing (Natural Language Processing, NLP) algorithmic word segmentation techniques may be employed to segment target text, and accordingly, word segmentation packages common in NLP may be employed during word segmentation. The technique of word segmentation of the target text is not limited to this example, and embodiments of the present application may be implemented using any word segmentation technique known in the art.

For the target text in the word form, the word segmentation set obtained after word segmentation may include the original word. For example, for the target text of word form, "ant forest," "car insurance," "red package," the corresponding word segmentation set obtained after word segmentation includes "ant forest," "car insurance," "red package," respectively.

For a target text in a sentence form, the sentence can be divided into a plurality of understandable words by a word segmentation technology, and the split-out understandable words in the sentence can be contained in a word segmentation set obtained after word segmentation. For example, for target text in sentence form, "starve: the surrounding food is shared, and the word segmentation set obtained after word segmentation can contain hungry, full, shared, surrounding food; for "spare gold: your emergency wallet ", the word segmentation collection obtained after word segmentation can contain 'spare gold, your, emergency, wallet'.

In the word segmentation set obtained by the word segmentation technology, keywords with attribute characteristics such as "hungry", "spare gold" and the like, and non-keywords without obvious attribute characteristics such as "your", "full", "shared" and the like may be included.

In order to improve recognition efficiency and recognition accuracy of recognizing the text attribute features in the subsequent steps, a keyword set may be further screened from the partitioned word set, that is, keywords in the word set may be extracted. More specifically, important words related to the purpose can be extracted based on the word segmentation result. In an embodiment, a keyword set may be extracted from a segmentation set using, for example, a keyword extraction algorithm in NLP.

For example, for the word segmentation set "hungry, full, shared, peripheral, delicacy", the corresponding keyword set may include "hungry, delicacy"; for the word segmentation set of 'spare gold, your, emergency and small wallet', the corresponding keyword set can comprise 'spare gold, small wallet'.

Step 106: and determining the label of the target text based on the extracted keywords.

In an embodiment, the determining, based on the extracted keyword, a tag of the target text may specifically include: a set of labels of the target text is determined based on the set of keywords corresponding to the target text, wherein each keyword in the set of keywords corresponds to at least one label in the set of labels.

Alternatively, multiple tags in a keyword set may correspond to the same tag, and as an example, if the keyword set contains "hungry, food", both keywords may correspond to the tag "food". Alternatively, one keyword in the keyword set may correspond to a plurality of tags, and as an example, if the keyword set includes "car insurance", the keyword may correspond to the tags "car has" and "finance" at the same time.

In an embodiment, the determining, based on the extracted keyword, a tag of the target text may specifically include: and inputting the keywords into a pre-trained label determination model to obtain a label set corresponding to the target text.

Specifically, the tag determination model may be various, and for example, may be a model for determining a scene attribute, a model for determining an audience group attribute, a model for determining an emotion attribute, a model for determining an event degree attribute, a model for determining a region attribute, or the like.

The tag determination model may include one or more.

Optionally, when the tag determination model is multiple, the determining the tag of the target text based on the extracted keyword may specifically include: inputting the keyword into a pre-trained first tag determination model to obtain a first tag subset; inputting the keyword into a pre-trained second tag determination model to obtain a second tag subset; and taking the labels in the first label subset and the second label subset as the labels in the label set corresponding to the target text.

The above is only taken as an example, alternatively, the keyword may be input into a pre-trained third tag determination model, to obtain a third tag subset, and the tags in the third tag subset are also used as the tags in the tag set corresponding to the target text. It is to be understood that the number of tag determination models is not limited thereto, and may be set as needed.

The first tag model, the second tag model, the third tag model, and the like may be selected from, for example, a scene attribute tag model, an audience attribute tag model, an emotion attribute tag model, an event level attribute tag model, a region attribute tag model, and the like, and are not limited thereto.

For the scene attribute tag model, the tags determined thereof may be, for example, "public welfare", "education", "mother and infant", "activity", "holiday", "delicacy", "fitness", "health", "finance", "life", "sleep", "shopping", "reading", "home", and the like, without being limited thereto. For the audience attribute tag model, the determined tags may be, for example, but not limited to, "mother and infant", "having car", "male", "female", "child", "Libra", and the like. For the emotion attribute tag model, the determined tags may be, for example, "positive", "negative", "neutral", etc., without being limited thereto. For the event extent attribute tag model, the determined tags may be, for example, "serious", "urgent", "normal", etc., without being limited thereto. For the regional attribute tag model, the determined tags may be, for example, "northeast", "west", "coastal", "beijing", etc., without being limited thereto.

Any of the above sub-sets of tags may contain one or more tags. For example, for the keyword set "hungry, food, five-one", it is input into the scene attribute tag model, and the resulting corresponding tag subset may contain "food, holiday". In some cases, any subset of tags may be an empty set. When the keywords in the target text do not have the event degree attribute, if the keywords in the target text are input into the event degree attribute tag model, the obtained corresponding tag subset can be an empty set. For example, for a keyword set "hungry, food, five-one," which is input into the event-level attribute tag model, the resulting corresponding subset of tags may be an empty set.

Although the label models correspond to different attributes, labels corresponding to different models may overlap, for example, a label such as "mother and infant" belongs to a scene attribute label and a label such as a group of people attribute label.

In practical application, the above process of determining the label of the target text based on the extracted keywords may be optionally specifically divided into two stages: firstly, mining contents of a target text based on keywords; and then marking the mining result by utilizing the labels in the pre-built label library.

Specifically, content mining of target text may include, but is not limited to, emotion analysis, regional analysis, business attribute analysis, audience segment analysis, and the like. The emotion analysis is to analyze, process, generalize and infer subjective texts with emotion colors; audience segment analysis refers to analysis of a population of information recipients; the business attribute analysis refers to a partitioning analysis of business types.

Specifically, the above-mentioned pre-built tag library may be a library containing tags with different attributes, for example, may contain tags "positive", "negative" of emotion type, and may contain tags "mother and infant", "car", "male", "female", "child", "Libra", and the like of crowd type; tags "positive", "negative" of the event severity class may be included.

In practical application, a content mining technology is adopted first, mining analysis of various aspects of scenes, emotions, audience groups and the like is carried out on a target text based on keywords, and then corresponding scene labels, emotion labels, audience group labels and the like in a pre-established label library are correspondingly used for marking the target text according to analysis results.

For ease of understanding, some examples of labels obtained based on keywords are given below: the ant forest contains scene attribute labels of public welfare, car insurance contains oriented crowd labels of cars, red packet contains scene labels of activities and emotion labels of active, hungry, food containing scene labels of food, standby gold and wallet containing scene labels of finance, epidemic situation fighting containing emotion labels of passive and emergency.

Step 108: and determining the text format of the target text according to the label of the target text based on a mapping relation library of the preset label and the preset text format.

Wherein, the mapping relation library stores the mapping relation between the preset label and the preset text format. The preset tag may be a tag in a pre-built tag library as mentioned above. The preset text format may be predetermined according to user history behavior information.

Specifically, before determining the text format of the target text according to the label of the target text, the mapping relation library based on the preset label and the preset text format may further include: determining at least one preset label and constructing a preset label set; determining a corresponding preset text format for each preset tag in the preset tag set; and constructing a mapping relation library of the preset labels and the preset text formats according to each preset label and the corresponding preset text format.

The determining, for each preset tag in the preset tag set, a corresponding preset text format may specifically be determined by a developer according to experience or according to user historical behavior information. When determining based on user historical behavioral information, a particular determination method may include: acquiring user historical behavior information, wherein the user historical behavior information reflects the acceptance degree of a user on a text which is displayed in a preset text format and corresponds to the preset label; and determining at least one preset text format corresponding to each preset label based on the user historical behavior information. The acceptance degree may correspond to, for example, a ratio of a counted number of users to a user amount of effective feedback on a target text in a preset text format, where the effective feedback may include clicking operation on the target text, and the like.

Alternatively, in embodiments of the present application, the text format may include text color, text effect, text font, and the like. The text color can be simple red, yellow, green, etc., or RGB color. The text effects may include bolded, underlined, italics, etc. The text fonts may include Song Ti, regular script, etc. The text format is not limited to the examples given herein, for example, the text effect may also have a dynamic effect (e.g., blinking, becoming larger), and so on.

For example, the "ant forest" contains a "public welfare" label, and in the mapping relation library of the preset label and the preset text format, the corresponding color of the "public welfare" label is "green", and then the "ant forest" may correspond to the "green" text format. For another example, the "red package" contains an "active" tag and a "finance" tag, and in the mapping relation library of the preset tag and the preset text format, the corresponding relation is "active-red/orange" and "finance-red", and the "red package" may correspond to the "red" text format. For another example, the "anti-epidemic situation" contains an "urgent" tag, and in the mapping relation library of the preset tag and the preset text format, the corresponding relation is "urgent-black/red" and "urgent-bold", and then the "anti-epidemic situation" may correspond to the "black/red and bold" text format.

The method in fig. 1 determines the text format corresponding to the text content for displaying the text content by analyzing the text content of the target text, so that the display format of the text is more matched with the text content, the text content can be better highlighted, namely, the text display effect is better, and the understanding and the interest of the user on the text can be better promoted.

The examples of the present specification also provide some specific embodiments of the method based on the method of fig. 1, which is described below.

After determining the text format of the target text in the step 108, the method may further include: step 110, displaying the target text based on the text format.

Specifically, the execution subject of step 110 may be a program loaded on the application terminal. If steps 102 to 108 are performed on the server, then before step 110, the server may further include sending information including the text format to the application terminal.

The method may further include, before the presenting the target text (step 110) based on the text format: and selecting a target text format for displaying the target text from a text format set corresponding to the label set of the target text according to a preset rule.

For example, the mapping relation library may store, for example, the following mappings of labels to text formats, "public welfare-green/blue", "education-blue", "activity-red/orange", "delicacy-red/orange", "health-blue/green", "finance-red", "sleep-dark", "shopping-red/orange", "reading-dark", "negative-black", "serious-black/red", "urgent-black/red"; "severely-bolded", "urgently-bolded", etc.

In the mapping relation library, one preset label may correspond to one or more preset text formats, for example, the label "public welfare" may correspond to blue or green, and at this time, blue and green may be determined as the text formats corresponding to the label at the same time. When the target text is displayed later, the target text can be displayed by selecting any one of the target text and the target text, or can be selected by combining with other preset rules.

Optionally, the selecting, according to the preset rule, a target text format from a text format set corresponding to the label set of the target text may specifically include: acquiring a page background color of a page to be displayed of a target text and/or a screen color system of a user terminal; and selecting a target text format for displaying the target text from the text format set based on the page background color of the page to be displayed and/or the screen color system of the user terminal.

In practical applications, there may be different background colors for different APPs, or in different pages in the same APP; in addition, in actual use, the user may adjust the screen color system according to the change of the external light, for example, white screen background is used in daytime and black screen background is used at night. In order to make the display effect of the target text better, a text format for final display can be selected from the alternative text formats according to the background color of the page to be displayed of the target text and/or the screen color system of the user terminal. For example, the alternative text color with high contrast may be selected as the color that is ultimately used to present the target text by calculating the contrast of the alternative text color with the page background color and/or screen color system.

Optionally, the selecting, according to the preset rule, a target text format from a text format set corresponding to the label set of the target text may specifically include: acquiring user preference information of a user; and selecting a target text format for displaying the target text from the text format set according to the user use preference information.

The user preference information may be obtained by analyzing historical behavior data of the user. For example, the preference of the user for different colors may be inferred from the setting information of the user for the page, the usage information of the user for the text and the picture of different colors, and the like, and from the feedback rate of the user for the text of various colors, and the like, and the color finally used for displaying the target text may be selected from the alternative color formats based on the color preference of the user.

How to select a text format for presentation from among the alternative text formats based on the preset rule is described above only from the viewpoint of text color, and in fact, for a text effect, a text font, etc., the selection of the final text format may also be performed based on the preset rule (e.g., according to the quality of the final presentation effect and the preference of the user), which will not be described herein.

In the scheme of the embodiment of the application, firstly, the target text is segmented, the keywords in the target text are extracted, the text content of the keywords is obtained, deeper content mining analysis is carried out, and corresponding labels are marked. Then, by associating the content with the tag, and then associating the tag with the text format (color, font, etc.), the correspondence of the text content and the text format is obtained. Further, the text format set of the target text content is combined with the background color of the text control and/or the screen color of the mobile phone, the text format of the target text is dynamically generated, and the target text is dynamically displayed. The dynamic state can include, for example, presenting the target text in different forms for different users and user terminals; for the same user terminal, the target text can be presented in different forms according to the current setting of the user terminal.

The scheme of the embodiment of the application combines the text content of the text to generate the text format (color, font form and the like) of the text, fully considers the influence of the text format on the effect of the text, and promotes the interest and understanding of the user on the text. In addition, dynamic release is realized, namely, after the text format library is generated, the final text format of the text can be dynamically generated by combining the background color of the text control, the mobile phone environment and the like, and in practical application, the same text is realized, and different display forms of different users are realized.

In order to make the solution of the present application clearer, a specific application scenario is provided below. Fig. 2 is a schematic diagram of a specific application scenario of a text format generating method according to an embodiment of the present disclosure.

As shown in fig. 2, the word is segmented by using an NLP algorithm, and a word segmentation package commonly used in NLP can be used in particular; then extracting keywords by using NLP, wherein a keyword extraction algorithm common in NLP can be used; content mining including, but not limited to, emotion mining, region mining, business attribute mining, audience group mining, etc.; meanwhile, preparing a set of content tag libraries, such as emotion tags of "positive", "negative", crowd tags of "mother and infant", "having car", "male", "female", "child", "Libra", etc., event degree tags of "positive", "negative", etc.; meanwhile, a set of color libraries are prepared, which can be simple red, yellow, green and the like, or RGB and the like; meanwhile, a set of tag-font color matching libraries, such as "public welfare-green/blue", "education-blue", "activity-red/orange", "food-red/orange", "health-blue/green", "finance-red", "sleep-dark", "shopping-red/orange", "reading-dark", "negative-black", "serious-black/red", "urgent-black/red", "serious-bolded", "urgent-bolded", etc., is prepared corresponding to the content tag library and the color library; then, tag attributes such as emotion tags like positive tags and negative tags are added to the mined content, and the emotion tags can be crowd tags like mother and infant tags and train tags, or event degree tags like serious tags and emergency tags; the mapping relation of the content-font color can be generated through the mapping relation of the content-label and the mapping relation of the label and the color font; further, based on the mapping relation of the content and the font color, the color and the font of the text can be dynamically generated by combining the text control and the screen color.

Based on the same thought, the embodiment of the specification also provides a device corresponding to the method. Fig. 3 is a schematic structural diagram of a text format generating device corresponding to fig. 1 according to an embodiment of the present disclosure.

As shown in fig. 3, the apparatus may include:

a target text acquisition module 302, configured to acquire a target text;

a keyword extraction module 304, configured to extract keywords in the target text;

a tag determining module 306, configured to determine a tag of the target text based on the extracted keyword;

the text format determining module 308 is configured to determine a text format of the target text according to the tag of the target text based on a mapping relation library of the preset tag and the preset text format.

According to an embodiment, the keyword extraction module 304 may specifically include: the word segmentation set generation unit is used for segmenting the target text to obtain a word segmentation set corresponding to the target text; and the keyword set generating unit is used for extracting keywords from the word segmentation set to obtain a keyword set corresponding to the target text, wherein the keyword set comprises at least one keyword.

Accordingly, the tag determination module 306 may be specifically configured to: a set of labels of the target text is determined based on the set of keywords corresponding to the target text, wherein each keyword in the set of keywords corresponds to at least one label in the set of labels.

Optionally, the tag determination module 306 may specifically be configured to: and inputting the keywords into a pre-trained label determination model to obtain a label set corresponding to the target text.

According to an embodiment, the apparatus may further include a mapping relation library construction module, configured to construct a mapping relation library before determining a text format of the target text according to the tag of the target text based on the mapping relation library of the preset tag and the preset text format. Specifically, the mapping relation library construction module comprises: the preset label set construction unit is used for determining at least one preset label and constructing a preset label set; a preset text format determining unit, configured to determine, for each preset tag in the preset tag set, a corresponding preset text format; the mapping relation library construction unit is used for constructing a mapping relation library of the preset labels and the preset text formats according to each preset label and the corresponding preset text format.

Optionally, the preset text format determining unit may be specifically configured to: acquiring user historical behavior information, wherein the user historical behavior information reflects the acceptance degree of a user on a text which is displayed in a preset text format and corresponds to the preset label; and determining at least one preset text format corresponding to each preset label based on the user historical behavior information.

Alternatively, the text format may include text colors, text effects including bolded, underlined, italics, and text fonts.

According to an embodiment, the apparatus may further comprise: a target text display module 310, configured to display the target text based on the text format.

Optionally, the apparatus may further include: and the target text format selection module is used for selecting a target text format for displaying the target text from a text format set corresponding to the label set of the target text according to a preset rule.

Optionally, the target text format selection module may specifically include: the background color acquisition unit is used for acquiring the page background color of the page to be displayed of the target text and/or the screen color system of the user terminal; and the target text format determining unit is used for selecting a target text format for displaying the target text from the text format set based on the page background color of the page to be displayed and/or the screen color system of the user terminal.

Optionally, the target text format selection module may specifically include: a user use preference information acquisition unit configured to acquire user use preference information; and the target text format determining unit is used for selecting a target text format for displaying the target text from the text format set according to the user preference information.

It will be appreciated that each of the modules described above refers to a computer program or program segment for performing one or more particular functions. Furthermore, the distinction of the above-described modules does not represent that the actual program code must also be separate.

Based on the same thought, the embodiment of the specification also provides equipment corresponding to the method.

Fig. 4 is a schematic structural diagram of a text format generating apparatus corresponding to fig. 1 provided in an embodiment of the present disclosure. As shown in fig. 4, the apparatus 400 may include:

at least one processor 410; the method comprises the steps of,

a memory 430 communicatively coupled to the at least one processor; wherein,,

the memory 430 stores instructions 420 executable by the at least one processor 410, the instructions being executable by the at least one processor 410 to enable the at least one processor 410 to:

acquiring a target text;

extracting keywords in the target text;

determining a label of the target text based on the extracted keywords;

and determining the text format of the target text according to the label of the target text based on a mapping relation library of the preset label and the preset text format.

Based on the same idea, the embodiments of the present disclosure further provide a computer readable medium corresponding to the above method, where computer readable instructions are stored, and the computer readable instructions are executable by a processor to implement the text format generating method described in any one of the embodiments above.

The foregoing describes particular embodiments of the present disclosure, and in some cases, acts or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for the apparatus, device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, as relevant to see the section description of the method embodiments.

The apparatus, the device, and the method provided in the embodiments of the present disclosure correspond to each other, and therefore, the apparatus, the device, and the method also have similar beneficial technical effects as those of the corresponding method, and since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding apparatus, device are not described here again.

In the 90 s of the 20 th century, improvements to one technology could clearly be distinguished as improvements in hardware (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software (improvements to the process flow). However, with the development of technology, many improvements of the current method flows can be regarded as direct improvements of hardware circuit structures. Designers almost always obtain corresponding hardware circuit structures by programming improved method flows into hardware circuits. Therefore, an improvement of a method flow cannot be said to be realized by a hardware entity module. For example, a programmable logic device (Programmable Logic Device, PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose logic function is determined by the user programming the device. A designer programs to "integrate" a digital system onto a PLD without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Moreover, nowadays, instead of manually manufacturing integrated circuit chips, such programming is mostly implemented by using "logic compiler" software, which is similar to the software compiler used in program development and writing, and the original code before the compiling is also written in a specific programming language, which is called hardware description language (Hardware Description Language, HDL), but not just one of the hdds, but a plurality of kinds, such as ABEL (Advanced BooleanExpression Language), AHDL (Altera Hardware Description Language), confluence, CUPL (Cornell UniversityProgramming Language), HDCal, JHDL (Java Hardware Description Language), lava, lola, myHDL, PALASM, RHDL (Ruby Hardware DescriptionLanguage), etc., VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog are currently most commonly used. It will also be apparent to those skilled in the art that a hardware circuit implementing the logic method flow can be readily obtained by merely slightly programming the method flow into an integrated circuit using several of the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable logic controllers, and embedded microcontrollers, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, atmelAT91SAM, microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic of the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller in a pure computer readable program code, it is well possible to implement the same functionality by logically programming the method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Such a controller may thus be regarded as a kind of hardware component, and means for performing various functions included therein may also be regarded as structures within the hardware component. Or even means for achieving the various functions may be regarded as either software modules implementing the methods or structures within hardware components.

The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in one or more software and/or hardware elements when implemented in the present application.

It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, 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 embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transshipment) such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.

The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims

1. A text format generation method, comprising:

acquiring a target text;

extracting keywords in the target text;

determining a label of the target text based on the extracted keywords;

determining the text format of the target text according to the label of the target text based on a mapping relation library of the preset label and the preset text format; the mapping relation between the preset label and the preset text format is determined based on user history behavior information, and the user history behavior information reflects the acceptance degree of a user on the text which is displayed in the preset text format and corresponds to the preset label.

2. The method of claim 1, wherein the extracting keywords in the target text specifically comprises:

word segmentation is carried out on the target text, and a word segmentation set corresponding to the target text is obtained;

extracting keywords from the word segmentation set to obtain a keyword set corresponding to the target text, wherein the keyword set comprises at least one keyword.

3. The method according to claim 2, wherein determining the tag of the target text based on the extracted keyword, specifically comprises:

a set of labels of the target text is determined based on the set of keywords corresponding to the target text, wherein each keyword in the set of keywords corresponds to at least one label in the set of labels.

4. The method according to claim 1, wherein the determining the tag of the target text based on the extracted keyword, specifically comprises:

and inputting the keywords into a pre-trained label determination model to obtain a label set corresponding to the target text.

5. The method according to claim 1, wherein the determining the text format of the target text based on the mapping relation library of the preset label and the preset text format according to the label of the target text further comprises:

Determining at least one preset label and constructing a preset label set;

determining a corresponding preset text format for each preset tag in the preset tag set;

and constructing a mapping relation library of the preset labels and the preset text formats according to each preset label and the corresponding preset text format.

6. The method according to claim 5, wherein the determining, for each preset tag in the set of preset tags, a corresponding preset text format specifically comprises:

acquiring user historical behavior information, wherein the user historical behavior information reflects the acceptance degree of a user on a text which is displayed in a preset text format and corresponds to the preset label;

and determining at least one preset text format corresponding to each preset label based on the user historical behavior information.

7. The method of claim 1, wherein the text format includes text color, text effect, and text font, the text effect including bold, underline, italics.

8. The method of claim 1, further comprising, after determining the text format of the target text:

based on the text format, the target text is presented _。

9. The method of claim 8, wherein prior to presenting the target text based on the text format, further comprising:

and selecting a target text format for displaying the target text from a text format set corresponding to the label set of the target text according to a preset rule.

10. The method according to claim 9, wherein the selecting, according to a preset rule, a target text format from a set of text formats corresponding to the set of tags of the target text, specifically includes:

acquiring a page background color of a page to be displayed of a target text and/or a screen color system of a user terminal;

and selecting a target text format for displaying the target text from the text format set based on the page background color of the page to be displayed and/or the screen color system of the user terminal.

11. The method according to claim 9, wherein the selecting, according to a preset rule, a target text format from a set of text formats corresponding to the set of tags of the target text, specifically includes:

acquiring user preference information of a user;

and selecting a target text format for displaying the target text from the text format set according to the user use preference information.

12. A text format generating apparatus comprising:

the target text acquisition module is used for acquiring a target text;

the keyword extraction module is used for extracting keywords in the target text;

the label determining module is used for determining labels of the target text based on the extracted keywords;

the text format determining module is used for determining the text format of the target text according to the label of the target text based on a mapping relation library of the preset label and the preset text format; the mapping relation between the preset label and the preset text format is determined based on user history behavior information, and the user history behavior information reflects the acceptance degree of a user on the text which is displayed in the preset text format and corresponds to the preset label.

13. The device of claim 12, wherein the keyword extraction module specifically comprises:

the word segmentation set generation unit is used for segmenting the target text to obtain a word segmentation set corresponding to the target text;

and the keyword set generating unit is used for extracting keywords from the word segmentation set to obtain a keyword set corresponding to the target text, wherein the keyword set comprises at least one keyword.

14. The apparatus of claim 13, wherein the tag determination module is specifically configured to:

15. The apparatus of claim 12, wherein the tag determination module is specifically configured to:

16. The apparatus according to claim 12, further comprising a mapping relation library construction module for constructing a mapping relation library before determining a text format of the target text from the tags of the target text based on a mapping relation library of preset tags and preset text formats, in particular, the mapping relation library construction module comprises:

the preset label set construction unit is used for determining at least one preset label and constructing a preset label set;

a preset text format determining unit, configured to determine, for each preset tag in the preset tag set, a corresponding preset text format;

The mapping relation library construction unit is used for constructing a mapping relation library of the preset labels and the preset text formats according to each preset label and the corresponding preset text format.

17. The apparatus of claim 16, wherein the preset text format determining unit is specifically configured to: acquiring user historical behavior information, wherein the user historical behavior information reflects the acceptance degree of a user on a text which is displayed in a preset text format and corresponds to the preset label; and determining at least one preset text format corresponding to each preset label based on the user historical behavior information.

18. The apparatus of claim 12, wherein the text format comprises text color, text effect, and text font, the text effect comprising bold, underline, italics.

19. The apparatus of claim 12, the apparatus further comprising: a target text display module for displaying the target text based on the text format _。

20. The apparatus of claim 19, the apparatus further comprising: and the target text format selection module is used for selecting a target text format for displaying the target text from a text format set corresponding to the label set of the target text according to a preset rule before displaying the target text.

21. The apparatus of claim 20, the target text format selection module specifically comprising:

the background color acquisition unit is used for acquiring the page background color of the page to be displayed of the target text and/or the screen color system of the user terminal;

and the target text format determining unit is used for selecting a target text format for displaying the target text from the text format set based on the page background color of the page to be displayed and/or the screen color system of the user terminal.

22. The apparatus of claim 20, the target text format selection module specifically comprising:

a user use preference information acquisition unit configured to acquire user use preference information;

and the target text format determining unit is used for selecting a target text format for displaying the target text from the text format set according to the user preference information.

23. A text format generating apparatus comprising:

at least one processor; the method comprises the steps of,

a memory communicatively coupled to the at least one processor; wherein,,

Acquiring a target text;

extracting keywords in the target text;

determining a label of the target text based on the extracted keywords;

24. A computer readable medium having stored thereon computer readable instructions executable by a processor to implement the text format generation method of any of claims 1 to 11.