CN116796010A - Graphic data recommendation method, device, equipment and storage medium - Google Patents

Abstract

The application discloses a method, a device, equipment and a storage medium for recommending graphic data, wherein the method for recommending the graphic data comprises the following steps: acquiring a first demand text input by a user in an input box of a search interface, wherein the first demand text is an unstructured text; based on the first demand text, displaying first graphic data recommended for the user on a search interface. According to the scheme, only the unstructured first requirement text input by the user in the input frame of the search interface is required to be obtained, namely the first image-text data is recommended to the user, the user does not need to define and even replace keywords used for data retrieval to search, and the efficiency of obtaining the image-text data by the user is improved.

Description

Graphic data recommendation method, device, equipment and storage medium

Technical Field

The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a storage medium for recommending graphic data.

Background

Reading teletext is one of the main ways people today acquire information, for example, users can learn or learn about related information by reading books, newspapers and the like.

However, users often search for and find the desired teletext material by means of a terminal device. For example, a user typically needs to define keywords for material search, such as titles, publishers, authors, etc., and input the keywords in a search box of a terminal device, thereby acquiring corresponding teletext materials. The mode is used for obtaining the graphic data, and the efficiency is low.

Disclosure of Invention

The application mainly solves the technical problem of providing a method, a device, a terminal and a storage medium for recommending graphic data, which can improve the efficiency of acquiring the graphic data for users.

In order to solve the above technical problems, a first aspect of the present application provides a method for recommending graphic data, including: acquiring a first requirement text input by a user in an input box of a search interface; the first demand text is unstructured text; based on the first demand text, displaying first graphic data recommended for the user on a search interface.

In order to solve the above technical problem, a second aspect of the present application provides a teletext recommending device, including: the acquisition module is used for acquiring a first requirement text input by a user in an input box of the search interface; the first demand text is unstructured text; and the recommending module is used for displaying first graphic and text materials recommended for the user on the searching interface based on the first requirement text.

In order to solve the above technical problems, a third aspect of the present application provides an electronic device, which includes a man-machine interaction circuit, a memory and a processor, wherein the man-machine interaction circuit and the memory are respectively coupled to the processor, the memory stores program instructions, and the processor is configured to execute the program instructions to implement the method for recommending graphic and text materials according to the first aspect.

In order to solve the above technical problem, a fourth aspect of the present application provides a computer readable storage medium storing program instructions executable by a processor, the program instructions being configured to implement the method for recommending teletext according to the first aspect.

According to the scheme, the first required text input by the user in the input box of the search interface is obtained, and the first image-text recommended by the user is displayed on the search interface based on the first required text. Wherein the first demand text is unstructured text. By the method, the first graphic data can be recommended to the user only by acquiring the unstructured first demand text input by the user in the input frame of the search interface, the user does not need to define and even replace keywords for data retrieval to search, and the efficiency of acquiring the graphic data by the user is improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application as claimed.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.

FIG. 1 is a flowchart of an embodiment of a method for recommending teletext data according to the application;

FIG. 2 is a flowchart illustrating another embodiment of a method for recommending teletext according to the application;

FIG. 3 is a schematic diagram of a main interface provided by the present application;

FIG. 4 is a schematic diagram of a search interface provided by the present application;

FIG. 5 is another schematic diagram of a search interface provided by the present application;

FIG. 6 is another schematic diagram of a search interface provided by the present application;

FIG. 7 is another schematic diagram of a search interface provided by the present application;

FIG. 8 is a flowchart illustrating another embodiment of a method for recommending teletext according to the application;

FIG. 9 is a flowchart illustrating another embodiment of a method for recommending teletext according to the application;

FIG. 10 is a flowchart illustrating another embodiment of a method for recommending teletext according to the application;

FIG. 11 is a flowchart of an embodiment of a teletext recommending apparatus according to the application;

FIG. 12 is a schematic diagram of a frame of an embodiment of an electronic device provided by the present application;

FIG. 13 is a schematic diagram of a computer-readable storage medium according to an embodiment of the present application.

Detailed Description

The following describes embodiments of the present application in detail with reference to the drawings.

In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, interfaces, techniques, etc., in order to provide a thorough understanding of the present application.

The term "and/or" is herein merely an association relationship describing an associated object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, "a plurality" herein means two or more than two. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C. "several" means at least one. The terms first, second and the like in the description and in the claims and in the above-described figures, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.

Referring to fig. 1, fig. 1 is a flowchart illustrating an embodiment of a method for recommending teletext data according to the application. The method may be performed by a terminal device, which may be, for example, a handwriting book, a mobile phone, a notebook computer, a tablet computer, etc., which is not particularly limited in this embodiment. It should be noted that, if there are substantially the same results, the method of the present application is not limited to the flow sequence shown in fig. 1. As shown in fig. 1, the method comprises the steps of:

s11: the method comprises the steps of obtaining a first requirement text input by a user in an input box of a search interface.

The first requirement text is used for describing the reading requirement of the user.

It should be noted that, the first requirement text in this embodiment is unstructured text. For example, the first demand text is "i am recently learning to cook, please recommend me several books that are suitable for learning", "what books i should read are most recently felt anxious? "and the like. Unlike unstructured text, structured text includes key information for the teletext, such as the name of the teletext, the publisher, the author, etc.

In this embodiment, the terminal device may display a search interface, where the search interface is provided with an input box. The terminal device may obtain a first requirement text input by a user in an input box of the search interface. For example, when the user clicks the input box of the search interface, the terminal device may pop up the voice input interface, obtain and recognize the voice about the reading requirement input by the user on the voice input interface, and obtain the recognition text. And then taking the identification text as the first demand text, or normalizing the identification text to obtain the first demand text. For another example, when the user clicks the input box of the search interface, the terminal device may pop up the text input interface, and obtain the text about the reading requirement manually input by the user on the text input interface as the first requirement text.

S12: based on the first demand text, displaying first graphic data recommended for the user on a search interface.

Illustratively, the first teletext may include, but is not limited to, books, news, blogs, public number articles, newspapers, and the like, which are not particularly limited in this embodiment.

In this embodiment, the first requirement text may be specifically input to a large language model, and the large language model is used to obtain the first graphic data related to the reading requirement of the user. Large language models refer to computer models capable of processing and generating natural language. Illustratively, the large language model may include, but is not limited to: a Pre-trained language model such as a GPT (generated Pre-trained Transformer), a series of Pre-trained transformation models (e.g., chatGPT), a MOSS (Multilingual Open-Source Synthesizer, multi-language open source synthesizer), etc. Because the large language model has strong knowledge capability, learning capability, logical reasoning capability and understanding capability, after the first demand text is input into the large language model, the large language model can quickly and accurately understand the reading demand of the user and recommend the first graphic and text data related to the reading demand of the user.

After the first image-text material is obtained, the first image-text material can be displayed on a search interface so that a user can read the related information of the first image-text material.

In this embodiment, the first text required by the user is obtained and input in the input box of the search interface, and based on the first text required, the first text-and-text recommended by the user is displayed on the search interface. Wherein the first demand text is unstructured text. By the method, the first graphic data can be recommended to the user only by acquiring the unstructured first demand text input by the user in the input frame of the search interface, the user does not need to define and even replace keywords for data retrieval to search, and the efficiency of acquiring the graphic data by the user is improved.

Referring to fig. 2, fig. 2 is a flowchart of another embodiment of a method for recommending teletext according to the application. For example, the method may be performed by a terminal device, and the relevant content of the terminal device is referred to the embodiment shown in fig. 1, which is not described herein. As shown in fig. 2, the method comprises the steps of:

s21: and responding to clicking operation of the user on the search box in the main interface, and jumping to the search interface from the main interface.

The terminal device may display a main interface for the teletext recommendation to the user, the main interface comprising a search box. When the user clicks the search box, the main interface jumps to the search interface.

Referring to fig. 3, fig. 3 is a schematic diagram of a main interface provided by the present application. The box numbered 1 in the main interface shown in fig. 3 is the search box. When the user clicks the area where the search box is located, the main interface automatically jumps to the search interface. It should be noted that, fig. 3 is only an example of book recommendation, and the main interface shown in fig. 3 is a main interface applied to book recommendation.

S22: the method comprises the steps of obtaining a first requirement text input by a user in an input box of a search interface.

The related content of the first requirement text may refer to the aforementioned step S11, and will not be described herein. In this embodiment, the search interface is provided with an input box, so that a first requirement text input by the user on the search interface can be obtained. Referring to fig. 4, fig. 4 is a schematic diagram of a search interface provided by the present application. The box numbered 2 in the search interface shown in fig. 4 is the input box.

In one embodiment, the first requirement text is obtained by acquiring and recognizing the voice about the reading requirement of the user, which is input by the user on the voice input interface. Specifically, responding to clicking operation of a user on an input box, and popping up a voice input interface on a search interface; and identifying the language options selected by the user on the voice input interface and the collected user voice to obtain a first required text, and displaying the identified first required text in an input box. The voice input interface is provided with a plurality of language options. Illustratively, the several language options may include mandarin, dialect, ethnic language, along with transliteration (e.g., in english translation, mid-translation), and foreign language, among others.

Referring to fig. 5, fig. 5 is another schematic diagram of a search interface provided by the present application. As shown in fig. 5, the search interface includes an input box 2 and a voice input interface 3. When the user clicks on the input box 2 of the search interface, the voice input interface 3 pops up. The user may select a language option and input speech on the user's reading needs in the speech input interface 3. Illustratively, a language option button and a voice input button (not shown) may be displayed in the voice input interface 3, and the user may start inputting voice regarding the user's reading requirements by clicking the language option button to select a desired language option and clicking the voice input button.

In this embodiment, the step of identifying the first required text based on the language option selected by the user on the voice input interface and the collected user voice includes: recognizing the voice of the user based on the language options selected by the user on the voice input interface to obtain a recognition text; the identified text is taken as the first demand text. Or, the voice of the user can be recognized based on the language options selected by the user on the voice input interface, so as to obtain a recognition text; and performing normalization based on the identification text to obtain a first required text. Illustratively, the normalization of the recognized text may include operations of deleting superfluous text, correcting text phrases, orderings, and orderings. For example, delete an exclamation in the recognition text, correct a flip sentence in the text, etc. In this example, the recognition text after the normalization is used as the first requirement text, so that the large language model can more accurately understand the reading requirement of the user.

In another embodiment, the first requirement text may also be obtained by obtaining text about the reading requirement entered by the user on the text input interface. Specifically, responding to clicking operation of a user on an input box, and popping up a text input interface on a search interface; and obtaining a first required text based on the text input by the user on the text input interface. In this embodiment, the text input by the user on the text input interface may be directly used as the first required text, or the text input by the user on the text input interface may be subjected to the aforementioned normalization, and the normalized text may be used as the first required text.

In this embodiment, the text input interface may include an input method keyboard or a handwriting area. For example, when the user clicks the input box, the input method keyboard is popped up at the search interface to support the user to manually enter the first desired text through the input method keyboard. Or when the user clicks the input box, a handwriting area is popped up on the search interface so as to support the user to input the first required text through handwriting.

Optionally, in this embodiment, the obtained first requirement text is input to a large language model, and the large language model is used to obtain the first text data. In order to facilitate the user to quickly enter the first demand text at the search interface and to facilitate the large language model to understand the user's reading needs based on the first demand text, exemplary demand text may be displayed at the search interface. For example, as shown in fig. 4 and 5, the exemplary demand text displayed may include "i want to know about cooking knowledge recently, please recommend me several suitable books", "what books i should read are most often anxious? ".

S23: based on the first demand text, displaying first graphic data recommended for the user on a search interface.

In this embodiment, after a first requirement text input by a user on a search interface is obtained, the first requirement text is input to a large language model, and a first graphic data related to a reading requirement of the user is obtained by using the large language model. Or, after receiving a confirmation operation of the user on the first demand text at the search interface, inputting the first demand text into the large language model. For example, a send button may be displayed on the search interface, such as within an input box, and when it is detected that the user clicks the send button, it is determined that a confirmation operation of the user for the first required text is received, and then the first required text is input to the large language model. For the relevant contents of the large language model, reference is made to the aforementioned step S12, and a detailed description is omitted here. The number of first teletext recommended to the user is at least one.

Optionally, in this embodiment, the search interface is provided with a dialogue area, and the process of recommending the first teletext may be implemented in the dialogue area of the search interface in a form of dialogue interaction.

In one embodiment, after the first required text input by the user at the search interface is acquired, in response to a confirmation operation of the user on the first required text at the search interface, the first required text is displayed as a first dialogue text of the user in the dialogue area, and before the first graphic data recommended to the user is acquired, the first prompt text is displayed as a second dialogue text responding to the first dialogue text in the dialogue area. The first prompt text is used for prompting the user to wait for acquiring the recommended first graphic data, and after acquiring the recommended first graphic data for the user, the recommended first graphic data for the user is displayed as a new second dialogue text in the dialogue area.

Illustratively, a confirm button or a send button is displayed within the input box of the search interface. After a first requirement text input by a user on a search interface is obtained, when a user clicking a confirm button or a send button is detected, confirming that confirmation operation of the user on the first requirement text is received is determined, the first requirement text is displayed in a dialogue area, and then a first prompt text is displayed.

FIG. 6 is another schematic diagram of a search interface provided by the present application, as shown in FIG. 6. As shown in fig. 6, the acquired first demand text is "i am learning cooking recently, please recommend several books suitable for learning for i am", the first demand text is displayed as a first dialog text in the dialog region of the search interface, and the first prompt text is "in mind". . . "within a dialog region of a display search interface".

In one embodiment, after the first teletext recommended to the user is obtained, the introduction text of the first teletext may also be displayed in the dialog region of the search interface. The method specifically comprises the following substeps:

and a first sub-step of extracting abstract text of each first graphic data.

Illustratively, the large language model may summarize the summary text of each first teletext based on the specific content of each first teletext. Alternatively, the abstract text of each first graphic material can be searched and obtained from the internet based on the key information of each first graphic material. Illustratively, the key information of the first teletext comprises a title, an author, a publisher, etc. of the first teletext.

And secondly, selecting abstract texts and attribute texts belonging to the same first graphic data as introduction texts of the corresponding first graphic data.

Illustratively, the attribute text of the first teletext comprises at least one of a title, an author of the first teletext.

And step three, displaying the introduction text of each first graphic data as dialogue text responding to the first requirement text on a search interface.

In an example, the introduction text of each first teletext may be displayed directly in the dialogue area of the search interface, so that the user can quickly learn the key information of each first teletext.

In another example, to further improve the convenience of the user in reading the first teletext, the introduction text and the link button of each first teletext may be displayed on the search interface, and the user may open the detailed introduction interface of a first teletext by clicking on the link button of that first teletext. If the preset database has the first graphic data, the link button corresponding to the first graphic data is displayed in a triggerable state, which indicates that the first graphic data can be found from the preset database. If the first graphic data does not exist in the preset database, the link button corresponding to the first graphic data is displayed in an unactivatable state, which indicates that the first graphic data cannot be found from the preset database.

Further, after displaying the introduction text of each first teletext material as the dialogue text in response to the first demand text on the search interface, further comprising: and responding to clicking operation of the user on the link button in the search interface, and jumping to the introduction interface of the first graphic and text material to which the link button belongs based on the fact that the link button is in a triggerable state. The user may read the first teletext in the switched introduction interface.

Referring to fig. 7, fig. 7 is another schematic diagram of a search interface provided by the present application. As shown in fig. 7, a dialog region is included in the search interface. The first demand text displayed in the dialogue area is "i'm is learning to cook recently, please recommend a few books for i'm that are suitable for learning. The dialogue text responding to the first demand text in the dialogue area comprises the introduction text of three books of "along with garden food list", cooking complete manual "and" cooking manual ", and the introduction text of each book comprises the abstract text, the title, the author and the link button of each book. Illustratively, as shown in fig. 7, when the link button is in the triggerable state, a first link prompt text, for example, "see" is correspondingly displayed on the link button, and the first link prompt text is used for prompting the user to click on the link button to read the corresponding first graphic data. When the link button is in a non-triggerable state, a second link prompt text, such as 'book city temporary not put on shelf', is correspondingly displayed on the link button, and the second link prompt text is used for prompting the user that the first image-text data of the link button cannot be obtained temporarily.

In yet another example, to further enhance the recommending effect of the teletext, the user experience may be enhanced by displaying the introduction text and progress buttons of each first teletext on the search interface. If the first graphic data user has read, the progress button corresponding to the first graphic data prompts the reading progress. For example, a progress percentage may be displayed on the progress button of each first teletext to prompt the user for the progress of reading each first teletext. For example, 0% indicates that the user has not read the first teletext and 100% indicates that the user has read the first teletext.

Further, after displaying the introduction text of each first teletext material as the dialogue text in response to the first demand text on the search interface, further comprising: and responding to clicking operation of the user on the progress button on the search interface, representing that the user has read the progress button, and jumping to a reading interface of the first graphic and text data to which the progress button belongs. The display content of the reading interface is matched with the reading progress prompted by the progress button, so that a user can directly read from the unread part of the first image-text data without reading from the beginning, and the use experience of the user is further improved.

Optionally, to further improve the recommending effect of the teletext and enhance the user experience, in this embodiment, after the first teletext recommended to the user is obtained, the reading sequence of each first teletext may be recommended to the user. Illustratively, the large language model may recommend to the user in order of ease of reading the respective first teletext. Alternatively, the large language model may further recommend the large language model to the user according to the reading depth of each of the first teletext data in order of low reading depth. Alternatively, the large language model may also recommend the publishing time of each first graphic data to the user in a front-to-back or back-to-front order according to the publishing time.

In this embodiment, on the one hand, a first requirement text is obtained by interacting with the search interface, and based on the first requirement text, a first graphic data recommended by the user is displayed on the search interface. In the process, only unstructured first demand text input by a user in an input frame of a search interface is required to be obtained, first graphic data can be recommended to the user, the user does not need to define and even replace keywords used for data retrieval to search, and the efficiency of obtaining the graphic data by the user is improved. On the other hand, in the search interface, the process of recommending the first graphic data for the user is realized in a dialogue interaction mode, so that the recommending effect of the graphic data can be improved, and the user experience is enhanced.

Referring to fig. 8, fig. 8 is a flowchart illustrating an embodiment of a method for recommending teletext according to the application. For example, the method may be performed by a terminal device, and the relevant content of the terminal device is referred to the embodiment shown in fig. 1, which is not described herein. As shown in fig. 8, the method includes the steps of:

s81: in response to a profile search operation of the user after the backlog is determined, a reading requirement of the user is determined to be related to the backlog.

In this embodiment, a user may take notes by using a terminal device, for example, taking the terminal device as an office book, the user may carry the office book when in a meeting, and the office book may automatically extract and record backlog mentioned in the meeting. Alternatively, the user may record the backlog directly on the terminal device. Or record backlog on the terminal device. The user may need to do some stock work to complete the backlog, such as searching for data related to the backlog. If the user performs the document searching operation after determining the backlog, the document to be searched is considered to be related to the backlog.

S82: candidate text is generated based on the backlog.

The candidate text is used to describe the user's reading needs with respect to backlog. For example, if the user determines that the backlog is learning neural network related knowledge, then the candidate text generated based on the backlog may be "i want to know the neural network related content, please recommend an appropriate book for i".

In one embodiment, a large language model may be utilized to generate candidate text based on backlog. Specifically, after the reading requirement of the user is determined to be related to the backlog, generating a first indication text for indicating the large language model to generate a candidate text based on the backlog, and inputting the first indication text into the large language model to obtain the candidate text which is output by the large language model and describes the reading requirement of the user.

S83: and obtaining the first required text based on the target operation of the user on the candidate text.

Wherein the target operation includes any one of a confirmation operation and an editing operation. Illustratively, editing operations may include adding text, deleting text, modifying text, and so forth.

In one embodiment, after the candidate text is generated, the candidate text may be displayed within an input box of the search interface, and the displayed candidate text within the input box is in an editable state. When the user determines that the candidate text does not meet the reading requirement of the user or needs to be perfected, the candidate text in the input frame can be edited, so that the edited first requirement text meets the reading requirement of the user, and the first graphic and text materials can be recommended to the user more accurately based on the first requirement text. When the user determines that the candidate text meets the reading requirement of the user, a confirmation operation may be performed, for example, clicking a confirmation button or a send button of the search interface to input the candidate text as the first requirement text into the large language model for first graph document recommendation.

Alternatively, in this embodiment, step S83 is an optional step, and the candidate text generated in step S82 may be directly used as the first requirement text instead of step S83.

S84: based on the first demand text, displaying first graphic data recommended for the user on a search interface.

The relevant content of step S84 may refer to the aforementioned step S23, and will not be described herein.

In this embodiment, after the user determines the backlog and performs the data search operation, it is determined that the reading requirement of the user is related to the backlog, and a candidate text describing the reading requirement may be automatically generated based on the backlog, so that the first graphic data is recommended to the user based on the candidate text. Compared with the embodiment shown in fig. 2, the user does not need to manually input the first requirement text, so that the recommending effect of the graphic data is further improved.

Referring to fig. 9, fig. 9 is a flowchart of another embodiment of a method for recommending teletext according to the application. For example, the method may be performed by a terminal device, and the relevant content of the terminal device is referred to the embodiment shown in fig. 1, which is not described herein. As shown in fig. 9, the method includes the steps of:

s91: the method comprises the steps of obtaining a first requirement text input by a user in an input box of a search interface.

The relevant content can refer to the foregoing steps S21 and S22, and will not be described herein.

S92: recording data of a user is obtained.

By way of example, the user's recorded data may include, but is not limited to, meeting notes, backlog, and the like. The user's recorded data may be retrieved from a local storage unit. Or the cloud end is backed up with the recorded data of the user, and the recorded data of the user can be obtained from the cloud end.

Optionally, before performing step S92, the method further includes: requesting the user for the acquisition right to acquire the recorded data. Illustratively, the permission options are displayed on a display interface of the terminal device, and the permission options include an agreeing to acquire option and a disagreeing to acquire option. When the user clicks the consent acquisition option, the acquisition permission for acquiring the record data is determined, and then the record data of the user is acquired. When it is detected that the user does not click on the consent acquisition option or the user does not click on the consent acquisition option, it is determined that the acquisition right for acquiring the record data is not possessed, and the record data of the user is not acquired, at this time, only the step S93 is executed, that is, only the first teletext is recommended to the user based on the first demand text.

In this embodiment, in order to increase the possibility of acquiring the recorded data, it is also possible to prompt the user at the colleague requesting the acquisition right "the right helps to more accurately implement the teletext recommendation".

S93: based on the first demand text, a first teletext recommended to the user is obtained.

The related content can refer to the aforementioned step S23, and will not be described herein.

S94: and obtaining the correlation degree between each first graphic data and the recorded data.

For example, a large language model may be used to analyze the correlation between each of the first teletext data and the recorded data. Alternatively, the neural network model may be used to predict the correlation between each of the first teletext data and the recorded data.

S95: and recommending the first graphic data to the user according to the sequence of the correlation degree from high to low.

For example, the first teletext having a high correlation with the recorded data may be recommended before and the first teletext having a low correlation with the recorded data may be recommended after.

Optionally, step S95 may be replaced by: and recommending the first graphic data with the highest correlation degree with the recorded data to the user. Alternatively, step S95 may be replaced with: and recommending the first image-text data with the relatedness larger than a preset threshold value to the user. The preset threshold value can be set according to actual needs. Alternatively, step S95 may be replaced with: and recommending the first image-text data with the relevance ranking rank larger than the preset ranking to the user, for example, recommending the first image-text data with the relevance ranking rank in the first three to the user. The preset ranking can be set according to actual needs.

In this embodiment, after the first teletext recommended to the user is obtained based on the first demand text, the first teletext may be recommended to the user according to the correlation between each first teletext and the recorded data of the user. Therefore, the first image-text data with higher correlation degree with the recorded data of the user can be recommended to the user preferentially, and the recommending effect of the image-text data is further improved.

Referring to fig. 10, fig. 10 is a flowchart illustrating another embodiment of a method for recommending teletext according to the application. The method may be performed by the terminal device as described above and the method may be performed after recommending the first teletext for the user, e.g. after having performed the method shown in fig. 2, 8 or 9. As shown in fig. 10, the method includes the steps of:

s101: and acquiring browsing data of the user for each first graphic data.

In this embodiment, the browsing data may include, but is not limited to, a browsing duration of the user on the first teletext, a number of times of clicking on the first teletext, a number of times of exiting the first teletext, a browsing mark, etc. Wherein, the longer the browsing time of the user to the first image-text material, the more times of clicking or exiting the first image-text material, and the more browsing marks indicate the higher the reference value of the first image-text material. The navigation mark may be a mark, such as a key mark, for example, that is made when the first textual material is read.

S102: and displaying second graphic data recommended for the user on the search interface based on the first demand text and the browsing data.

Specifically, step S102 includes: generating a second demand text finer than the first demand text based on the first demand text and the browsing data; and displaying second graphic data recommended for the user on the search interface based on the second requirement text.

For example, a first teletext a, a first teletext B and a first teletext C are obtained based on the first demand text, wherein the first teletext C corresponds to the longest browsing duration. The second demand text generated may be "recommending me a teletext more similar to the first teletext C". For another example, the first graphic data a, the first graphic data B and the first graphic data C are obtained based on the first required text, wherein the first graphic data B corresponds to the longest browsing time, and the first graphic data B includes the key mark made by the user. The second demand text generated may be "recommending me a teletext more similar to the first teletext B". Alternatively, the first teletext B is further analyzed to obtain the topic D and the emphasis E, and "the teletext specifically related to the topic D and the emphasis E" can be added as the second requirement text on the basis of the first requirement text. It can be seen that in this embodiment, the second demand text description is more accurate and detailed than the first demand text.

In one embodiment, the second demand text may be generated using a large language model. Specifically, second instruction information for instructing the large language model to generate the second required text can be generated based on the first required text and the browsing data, and the second instruction text is input into the large language model to obtain the second required text output by the large language model.

Further, after generating the second desired text, the second desired text may be displayed in an input box of the search interface. The displayed candidate text within the input box is in an editable state. When the user determines that the second demand text does not meet the reading demand of the user or needs to be perfected, the second demand text in the input frame can be edited, so that the edited second demand text meets the reading demand of the user, and the second image-text data can be recommended to the user more accurately based on the second demand text. When the user determines that the second requirement text meets the reading requirement of the user, a confirmation operation may be performed, for example, clicking a confirmation button or a send button of the search interface to input the second requirement text into the large language model for first-drawing recommendation.

Alternatively, in this embodiment, the process of recommending the second teletext may be implemented in the dialog region of the search interface in the form of a dialog interaction.

In one embodiment, after the second required text is acquired, in response to a confirmation operation of the user on the second required text at the search interface, the second required text is displayed as a third dialog text of the user in the dialog region, and before the second teletext recommended to the user is acquired, the second prompt text is displayed as a fourth dialog text of the third dialog text in the dialog region. The second prompt text is used for prompting the user to wait for acquiring the recommended second graphic data, and after acquiring the recommended second graphic data for the user, the recommended second graphic data for the user is displayed as a new fourth dialogue text in the dialogue area.

Illustratively, a confirm button or a send button is displayed within the input box of the search interface. After the generated second demand text is acquired, when the fact that the user clicks the confirm button or the send button is detected, the fact that the user confirms the second demand text is received is determined, the second demand text is displayed in the dialogue area, and then the second prompt text is displayed.

In one embodiment, after the second teletext is obtained based on the first desired text and the browsing data, an introduction text of the second teletext may also be displayed in the dialog region of the search interface. The method specifically comprises the following steps: extracting abstract text of each second image-text material; selecting abstract text and attribute text belonging to the same second image-text material as introduction text of the corresponding second image-text material; and displaying the introduction text of each second graphic data as dialogue text responding to the second requirement text on the search interface. Illustratively, the attribute text of the second teletext comprises at least one of a title, an author of the second teletext.

In an example, the introduction text of each second teletext may be displayed directly in the dialogue area of the search interface, so that the user can quickly learn the key information of each second teletext.

In another example, to further improve the convenience of the user in reading the second teletext, the introduction text and the link button of each second teletext may be displayed on the search interface, and the user may open the detailed introduction interface of a second teletext by clicking on the link button of that second teletext. If the preset database has the second graphic data, the link button corresponding to the second graphic data is displayed in a triggerable state, which indicates that the second graphic data can be found from the preset database. If the second graphic data does not exist in the preset database, the link button corresponding to the second graphic data is displayed in an unactivatable state, which indicates that the second graphic data cannot be found from the preset database.

Further, after displaying the introduction text of each of the second teletext material as the dialogue text in response to the second demand text on the search interface, further comprising: and responding to clicking operation of the user on the link button in the search interface, and jumping to the introduction interface of the second graphic and text material to which the link button belongs based on the fact that the link button is in a triggerable state. The user can read the second teletext in the presentation interface after the jump.

In yet another example, to further enhance the recommending effect of the teletext, the user experience may be enhanced by displaying the introduction text and progress buttons of each second teletext on the search interface. If the second graphic data user has read, the progress button corresponding to the second graphic data prompts the reading progress. For example, a progress percentage may be displayed on the progress button of each second teletext to prompt the user for the progress of reading each second teletext.

Further, after displaying the introduction text of each of the second teletext material as the dialogue text in response to the second demand text on the search interface, further comprising: and responding to clicking operation of the user on the progress button in the search interface, representing that the user has read the progress button, and jumping to a reading interface of the second graphic and text data to which the progress button belongs. The display content of the reading interface is matched with the reading progress prompted by the progress button, so that a user can directly read from the unread part of the second image-text data without reading from the beginning, and the use experience of the user is further improved.

Optionally, to further improve the recommending effect of the graphic data and enhance the user experience, in this embodiment, after the second graphic data is obtained based on the second requirement text, the reading sequence of each second graphic data may be recommended to the user. Illustratively, the large language model may recommend to the user in order of ease of reading the respective second teletext. Alternatively, the large language model may also recommend the user according to the reading depth of each second teletext material in order of low reading depth to high reading depth. Alternatively, the large language model may also recommend the publishing time of each second teletext to the user in a front-to-back or back-to-front order of the publishing time.

In this embodiment, after the first teletext is obtained based on the first demand text, a second demand text is further generated based on the first demand text and the browsing data of the user for each first teletext, and the second teletext is recommended to the user based on the second demand text. Because the second demand text description is more accurate and finer than the first demand text, the second image-text data recommended based on the second demand text is more accurate, and the recommending effect of the image-text data is further improved.

Referring to fig. 11, fig. 11 is a schematic diagram of a frame of an embodiment of a teletext recommending apparatus according to the application. As shown in fig. 11, the teletext recommending means 110 includes: an acquisition module 111 and a recommendation module 112. The obtaining module 111 is configured to obtain a first required text input by a user in an input box of a search interface, where the first required text is unstructured text. The recommending module 112 is configured to display a first teletext recommended for the user on the search interface based on the first requirement text.

Optionally, the obtaining module 111 is configured to jump from the main interface to the search interface in response to a clicking operation of the user on the search box in the main interface, and perform a step of obtaining a first requirement text input by the user in an input box of the search interface; the first requirement text and the first graphic data recommended to the user are displayed in a dialogue mode in a dialogue area of the search interface.

Optionally, the obtaining module 111 is configured to pop up a voice input interface on the search interface in response to a click operation of the user on the input box; the voice input interface is provided with a plurality of language options; and identifying the language options selected by the user on the voice input interface and the collected user voice, and displaying the first requirement text obtained by identification on the input box.

Optionally, the teletext recommending means 110 further comprises a dialog text display module 113. The dialogue text display module 113 is used for respectively extracting abstract text of each first graphic data; selecting abstract text and attribute text belonging to the same first image-text material as introduction text of the corresponding first image-text material; wherein the attribute text includes at least one of a title and an author of the first teletext; the introduction text of each first teletext is displayed on the search interface as dialog text in response to the first demand text.

Optionally, the dialogue text display module 113 is configured to display the introduction text and the link buttons of the respective first teletext materials on the search interface; and if the preset database does not have the first graphic data, the link button corresponding to the first graphic data is displayed in an unclonable state. The teletext recommending device 110 further comprises a first teletext display module 114 for, in response to a clicking operation of the link button by a user at the search interface, jumping to an introduction interface of the first teletext to which the link button belongs, based on the link button being in a triggerable state.

Optionally, the dialogue text display module 113 is configured to display the introduction text and the progress button of each first teletext on the search interface; if the first graphic data user has read, the progress button corresponding to the first graphic data prompts the reading progress. The first graphic data display module 114 is configured to respond to a click operation of the progress button by the user on the search interface, indicate that the user has read based on the progress button, and skip to a reading interface of the first graphic data to which the progress button belongs; the display content of the reading interface is matched with the reading progress prompted by the progress button.

Optionally, the acquiring module 111 is further configured to acquire browsing data of the user on each of the first teletext materials; wherein the browsing data comprises at least a browsing duration. The recommending module 112 is further configured to display a second teletext recommended for the user on the search interface based on the first requirement text and the browsing data.

Optionally, the recommendation module 112 is configured to generate, based on the first demand text and the browsing data, a second demand text that is finer than the first demand text; and displaying second graphic data recommended for the user on the search interface based on the second requirement text.

Optionally, the teletext recommending means 110 further comprises a demand text display module 115. After the recommending module 112 generates a second required text which is finer than the first required text based on the first required text and the browsing data, and before the searching interface displays a second graphic material recommended by the user based on the second required text, the required text displaying module 115 is configured to display the second required text in an input box of the searching interface; the second requirement text and the second graphic data recommended to the user are displayed in a dialogue mode on a search interface.

Optionally, the obtaining module 111 is further configured to obtain record data of the user. The recommending module 112 is further configured to obtain a first teletext recommended for the user based on the first demand text; acquiring the correlation degree between each first graphic data and the recorded data; and recommending the first graphic data to the user according to the sequence of the correlation degree from high to low.

Optionally, the obtaining module 111 is configured to determine that the reading requirement of the user is related to the backlog in response to the data searching operation of the user after the backlog is determined, and generate the candidate text based on the backlog; obtaining a first demand text based on target operation of a user on the candidate text; wherein the target operation includes any one of a confirmation operation and an editing operation.

It should be noted that, the apparatus of this embodiment may perform the steps in the above method, and details of the related content refer to the above method section, which is not described herein again.

Referring to fig. 12, fig. 12 is a schematic frame diagram of an embodiment of an electronic device according to the present application. The electronic device 120 includes a man-machine interaction circuit 123, a memory 121 and a processor 122, wherein the man-machine interaction circuit 123 and the memory 121 are respectively coupled to the processor 122, the memory 121 stores program instructions, and the processor 122 is configured to execute the program instructions to implement the steps of any of the above-mentioned embodiments of the method for recommending graphic data.

Specifically, the processor 122 is configured to control itself, the memory 121, and the man-machine interaction circuit 123 to implement the steps of any of the above-described embodiments of the method for recommending teletext. The processor 122 may also be referred to as a CPU (Central Processing Unit ). The processor 122 may be an integrated circuit chip having signal processing capabilities. The processor 122 may also be a general purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a Field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. In addition, the processor 122 may be commonly implemented by an integrated circuit chip.

Referring to fig. 13, fig. 13 is a schematic diagram of a frame of an embodiment of a computer readable storage medium according to the present application. The computer readable storage medium 130 of the embodiment of the present application stores a program instruction 131, and the program instruction 131 implements the method for recommending teletext provided by the present application when executed. Wherein the program instructions 131 may form a program file stored in the computer readable storage medium 130 as a software product, so that a computer device (which may be a personal computer, a server, or a network device, etc.) performs all or part of the steps of the methods according to the embodiments of the present application. And the aforementioned computer-readable storage medium 130 includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, an optical disk, or other various media capable of storing program codes, or a terminal device such as a computer, a server, a mobile phone, a tablet, or the like.

According to the scheme, the first required text input by the user in the input box of the search interface is obtained, and the first image-text recommended by the user is displayed on the search interface based on the first required text. Wherein the first demand text is unstructured text. By the method, the first graphic data can be recommended to the user only by acquiring the unstructured first demand text, the user does not need to define and even replace keywords for data retrieval to search, and the efficiency of acquiring the graphic data by the user is improved.

In some embodiments, functions or modules included in an apparatus provided by the embodiments of the present disclosure may be used to perform a method described in the foregoing method embodiments, and specific implementations thereof may refer to descriptions of the foregoing method embodiments, which are not repeated herein for brevity.

The foregoing description of various embodiments is intended to highlight differences between the various embodiments, which may be the same or similar to each other by reference, and is not repeated herein for the sake of brevity.

In the several embodiments provided in the present application, it should be understood that the disclosed method, apparatus and system may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of modules or units is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical, or other forms.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The foregoing description is only of embodiments of the present application, and is not intended to limit the scope of the application, and all equivalent structures or equivalent processes using the descriptions and the drawings of the present application or directly or indirectly applied to other related technical fields are included in the scope of the present application.

Claims (14)

1. A method for recommending teletext, comprising:

acquiring a first requirement text input by a user in an input box of a search interface; the first demand text is unstructured text;

and displaying a first image-text material recommended for the user on the search interface based on the first requirement text.

2. The method of claim 1, wherein the obtaining the first requirement text entered by the user in the input box of the search interface comprises:

responding to clicking operation of a user on a search box in a main interface, jumping to the search interface from the main interface, and executing the step of acquiring a first requirement text input by the user in an input box of the search interface;

and displaying the first requirement text and the first graphic data recommended to the user in a dialogue mode in a dialogue area of the search interface.

3. The method according to claim 1 or 2, wherein the obtaining the first requirement text input by the user in the input box of the search interface includes:

responding to clicking operation of a user on the input box, and popping up a voice input interface on the search interface; wherein, the voice input interface is provided with a plurality of language options;

and identifying based on the language options selected by the user on the voice input interface and the collected user voice, and displaying the first requirement text obtained by identification on the input box.

4. The method according to claim 1, wherein the method further comprises:

extracting abstract text of each first image-text material;

selecting abstract text and attribute text belonging to the same first graphic data as introduction text corresponding to the first graphic data; wherein the attribute text comprises at least one of a title and an author of the first teletext;

and displaying the introduction text of each first graphic data as dialogue text responding to the first requirement text on the search interface.

5. The method of claim 4, wherein displaying the introduction text of each of the first teletext as a dialog text in response to the first demand text on the search interface comprises:

Displaying introduction text and a link button of each first graphic data on the search interface; if the preset database is in the first graphic data, the link button corresponding to the first graphic data is displayed in a triggerable state, and if the preset database is not in the first graphic data, the link button corresponding to the first graphic data is displayed in a non-triggerable state;

after displaying the introduction text of each of the first teletext material as a dialog text in response to the first demand text on the search interface, the method further comprises:

and responding to clicking operation of a user on the link button in the search interface, and jumping to an introduction interface of the first graphic and text material to which the link button belongs based on the fact that the link button is in a triggerable state.

6. The method of claim 4, wherein displaying the introduction text of each of the first teletext as a dialog text in response to the first demand text on the search interface comprises:

displaying introduction text and progress buttons of each first graphic data on the search interface; if the first graphic data user has read, prompting the reading progress on a progress button corresponding to the first graphic data;

After displaying the introduction text of each of the first teletext material as a dialog text in response to the first demand text on the search interface, the method further comprises:

responding to clicking operation of a user on the progress button on the search interface, representing that the user has read the progress button, and jumping to a reading interface of a first image-text material to which the progress button belongs; and the display content of the reading interface is matched with the reading progress prompted by the progress button.

7. The method of claim 1, wherein after the displaying of the first teletext based on the first demand text as recommended by the user on the search interface, the method further comprises:

acquiring browsing data of a user for each first image-text material; wherein, the browsing data at least comprises browsing duration;

and displaying second graphic data recommended for the user on the search interface based on the first demand text and the browsing data.

8. The method of claim 7, wherein displaying the second teletext based on the first demand text and the browsing data as a user recommendation on the search interface comprises:

Generating a second demand text that is finer than the first demand text description based on the first demand text and the browsing data;

and displaying second graphic data recommended for the user on the search interface based on the second requirement text.

9. The method of claim 8, wherein after generating a second demand text that is finer than the first demand text description based on the first demand text and the browsing data, and before displaying a second teletext material recommended as a user on the search interface based on the second demand text, the method further comprises:

displaying the second required text in an input box of a search interface;

and displaying the second required text and the second graphic data recommended to the user in a dialogue form on the search interface.

10. The method of claim 1, wherein after the obtaining the first desired text entered by the user in the input box of the search interface and before the displaying the first teletext recommended by the user on the search interface based on the first desired text, the method further comprises:

Acquiring record data of a user;

the displaying, based on the first requirement text, a first teletext recommended for the user on the search interface, including:

acquiring a first image-text material recommended for a user based on the first demand text;

acquiring the correlation degree between each first image-text material and the recorded data;

and recommending the first graphic data to the user according to the sequence of the correlation degree from high to low.

11. The method of claim 1, wherein the obtaining the first requirement text entered by the user in the input box of the search interface comprises:

in response to a data search operation of a user after determining a backlog, determining that a reading requirement of the user is related to the backlog, and generating candidate text based on the backlog;

obtaining the first required text based on target operation of the user on the candidate text; wherein the target operation includes any one of a confirmation operation and an editing operation.

12. A teletext recommending apparatus, comprising:

the acquisition module is used for acquiring a first requirement text input by a user in an input box of the search interface; the first demand text is unstructured text;

And the recommending module is used for displaying first graphic and text materials recommended for the user on the searching interface based on the first requirement text.

13. An electronic device, comprising a man-machine interaction circuit, a memory and a processor, wherein the man-machine interaction circuit and the memory are respectively coupled to the processor, the memory stores program instructions, and the processor is configured to execute the program instructions to implement the method for recommending graphic data according to any one of claims 1 to 11.

14. A computer readable storage medium, characterized in that program instructions executable by a processor are stored, said program instructions being for implementing a teletext recommending method according to any one of claims 1 to 11.