CN116340567A

CN116340567A - Word-based video recommendation method, device, medium and electronic equipment

Info

Publication number: CN116340567A
Application number: CN202310318951.2A
Authority: CN
Inventors: 杨诗蕾; 陶晋
Original assignee: Beijing Youzhuju Network Technology Co Ltd; Beijing Zitiao Network Technology Co Ltd
Current assignee: Beijing Youzhuju Network Technology Co Ltd; Beijing Zitiao Network Technology Co Ltd
Priority date: 2023-03-28
Filing date: 2023-03-28
Publication date: 2023-06-27

Abstract

The disclosure relates to the field of computer technology, in particular to a word-based video recommendation method, a device, a medium and electronic equipment. The method comprises the following steps: determining a plurality of words to be learned and word sequences of the words to be learned according to the words in the word book; determining target paraphrases of words to be learned, and determining learning videos corresponding to each word to be learned according to the target paraphrases; and displaying the learning video corresponding to each word to be learned according to the word ordering. Thus, for each word to be learned, the user can be focused on understanding learning of the application of the word to be learned under the target paraphrasing, and the mastering degree and the application degree of the word to be learned are improved. In addition, through the display of the learning video, the true use scene of the word to be learned can be restored, the attention concentration of the word to be learned by the user is effectively improved, the learning pleasure of the user is improved, the boring sense of the word learning is reduced, and the word grasping speed is further accelerated.

Description

Word-based video recommendation method, device, medium and electronic equipment

Technical Field

The disclosure relates to the field of computer technology, in particular to a word-based video recommendation method, a device, a medium and electronic equipment.

Background

Word learning is the basis for learning a single language. With the continuous development of intelligent terminals, more and more users learn words online through terminal equipment. However, the existing online word learning is mostly performed through a list of word books, so that detailed information of the word in the dictionary is displayed for a user, the displayed content is more, and the key points are difficult to grasp; and list learning is relatively boring, has low efficiency and lacks specific use scenes.

Disclosure of Invention

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

In a first aspect, the present disclosure provides a word-based video recommendation method, comprising:

determining a plurality of words to be learned and word sequences of the words to be learned according to the words in the word book;

determining target paraphrases of the words to be learned, and determining learning videos corresponding to each word to be learned according to the target paraphrases;

And displaying the learning videos corresponding to each word to be learned according to the word ordering.

In a second aspect, the present disclosure provides a word-based video recommendation apparatus comprising:

the first determining module is used for determining a plurality of words to be learned and word sequences of the words to be learned according to the words in the word book;

the second determining module is used for determining target paraphrases of the words to be learned and determining learning videos corresponding to each word to be learned according to the target paraphrases;

and the display module is used for displaying the learning video corresponding to each word to be learned according to the word ordering.

In a third aspect, the present disclosure provides a computer readable medium having stored thereon a computer program which, when executed by a processing device, performs the steps of the word-based video recommendation method described above.

In a fourth aspect, the present disclosure provides an electronic device comprising:

a storage device having a computer program stored thereon;

processing means for executing said computer program in said storage means to implement the steps of the word-based video recommendation method described above.

In the technical scheme, a plurality of words to be learned and word sequences of the words to be learned are determined according to the words in the word book; determining target paraphrases of words to be learned, and determining learning videos corresponding to each word to be learned according to the target paraphrases; and displaying the learning video corresponding to each word to be learned according to the word ordering. Thus, for each word to be learned, the user can be focused on understanding learning of the application of the word to be learned under the target paraphrasing, and the mastering degree and the application degree of the word to be learned are improved. In addition, the word to be learned can be determined from the word book, so that a great amount of time required for one-time learning of the word of the whole word book is avoided, segmented learning of the word in the word book can be supported, the data volume required for data processing of the word to be learned in the learning process can be reduced, and the operation load occupation of terminal equipment is reduced. In addition, through the display of the learning video, the true use scene of the word to be learned can be restored, the attention concentration of the word to be learned by the user is effectively improved, the learning pleasure of the user is improved, the boring sense of the word learning is reduced, and the word grasping speed is further accelerated.

Additional features and advantages of the present disclosure will be set forth in the detailed description which follows.

Drawings

The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale. In the drawings:

FIG. 1 is a flow chart of a word-based video recommendation method provided in accordance with one embodiment of the present disclosure.

FIG. 2 is a flow chart of a word-based video recommendation method provided in accordance with one embodiment of the present disclosure.

Fig. 3 is a block diagram of a word-based video recommendation device provided in accordance with one embodiment of the present disclosure.

Fig. 4 is a schematic structural view of an electronic device provided according to an embodiment of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure have been shown in the accompanying drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.

It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order and/or performed in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.

The term "including" and variations thereof as used herein are intended to be open-ended, i.e., including, but not limited to. The term "based on" is based at least in part on. The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments. Related definitions of other terms will be given in the description below.

It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.

It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.

The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

It will be appreciated that prior to using the technical solutions disclosed in the embodiments of the present disclosure, the user should be informed and authorized of the type, usage range, usage scenario, etc. of the personal information related to the present disclosure in an appropriate manner according to the relevant legal regulations.

For example, in response to receiving an active request from a user, a prompt is sent to the user to explicitly prompt the user that the operation it is requesting to perform will require personal information to be obtained and used with the user. Thus, the user can autonomously select whether to provide personal information to software or hardware such as an electronic device, an application program, a server or a storage medium for executing the operation of the technical scheme of the present disclosure according to the prompt information.

As an alternative but non-limiting implementation, in response to receiving an active request from a user, the manner in which the prompt information is sent to the user may be, for example, a popup, in which the prompt information may be presented in a text manner. In addition, a selection control for the user to select to provide personal information to the electronic device in a 'consent' or 'disagreement' manner can be carried in the popup window.

It will be appreciated that the above-described notification and user authorization process is merely illustrative and not limiting of the implementations of the present disclosure, and that other ways of satisfying relevant legal regulations may be applied to the implementations of the present disclosure.

Meanwhile, it can be understood that the data (including but not limited to the data itself, the acquisition or the use of the data) related to the technical scheme should conform to the requirements of the corresponding laws and regulations and related regulations.

FIG. 1 is a flow chart of a word-based video recommendation method provided in accordance with one embodiment of the present disclosure, as shown in FIG. 1, the method may include:

in S101, a plurality of words to be learned and word ranks of the words to be learned are determined according to the words in the word book.

For example, a word book may be used to record words that a user needs to grasp. For example, a user may add an unfamiliar word in a sentence to a word book during learning of the sentence; the user can also directly add the words intended for learning in the word book by means of input. For another example, after performing the word test, the system may add words that fail the test to the word book.

With the increasing duration of the word book, the number of words in the word book may increase. However, it is often difficult for the user to spend a great deal of time completely learning all the words in the word book, and the amount of data required for data processing of the words to be learned at this time is large, which may result in a high operation load of the terminal device. Therefore, part of words can be screened from the word book and used as the words to be learned in the learning process. For example, in the case of excessive words in the word book, the word to be learned in the current learning process may be determined based on factors such as the addition time of the word, the number of word exposures, and the like. For example, if the number of words in the word book exceeds the preset number of words, a word in the word book with the number of word exposures less than the preset number of exposures may be determined as the word to be learned.

The user has different mastering degrees of different words to be learned, so that the words to be learned can be ordered based on the mastering degrees of the words, and the determined word ordering result of the words to be learned can be adapted to the actual demands of the user. For example, the adding time of the words may reflect the grasping degree of the user on different words to be learned to a certain extent, the words to be learned may be ordered according to the adding time of the words, and the closer the adding time of the words is to the current time, the earlier the word ordering may be.

In S102, a target paraphrase of the word to be learned is determined, and a learning video corresponding to each word to be learned is determined according to the target paraphrase.

For example, the target paraphrasing may be one of the total paraphrasing of the word to be learned. For example, if a word to be learned corresponds to a paraphrase in the oxford dictionary, the paraphrase may be determined to be the target paraphrase. If one word to be learned corresponds to multiple paraphrases in the oxford dictionary, any of the multiple paraphrases may be determined to be the target paraphrase. For each word to be learned, if a plurality of corresponding learning videos are determined based on the target paraphrasing, the determined plurality of learning videos can be considered to have consistency, namely the paraphrasing of the word to be learned in the plurality of learning videos is the same. Thus, even if a plurality of corresponding learning videos are determined, the user can concentrate on understanding learning of the application of the word to be learned under the target paraphrasing, so that the user can grasp the learning key points of the word to be learned, and the grasping degree of the word to be learned is improved.

S103, according to word sequencing, displaying learning videos corresponding to each word to be learned.

For example, after determining the learning video corresponding to each word to be learned, the learning video corresponding to each word to be learned may be sequentially displayed according to word ordering. For example, if the determined word to be learned includes a first word to be learned a, a second word to be learned B, and a third word to be learned C, the word ordering result is the first word to be learned a, the second word to be learned B, and the third word to be learned C. The learning videos corresponding to the first word to be learned A comprise a first learning video a1, a second learning video a2 and a third learning video a3; the learning videos corresponding to the second word B to be learned comprise a fourth learning video B1, a fifth learning video B2 and a sixth learning video B3; the learning videos corresponding to the third word to be learned C comprise a seventh learning video C1 and an eighth learning video C2; each of the learning videos may be sequentially presented to the user in the order of the first learning video a1, the second learning video a2, the third learning video a3, the fourth learning video b1, the fifth learning video b2, the sixth learning video b3, the seventh learning video c1, and the eighth learning video c 2.

In an alternative embodiment, in S101, determining a plurality of words to be learned and word ranks of the words to be learned according to the words in the word book may include:

if the number of the words in the word book does not exceed the preset number of the words, determining all the words in the word book as the words to be learned;

determining word ordering parameters of the words to be learned according to word information of the words to be learned aiming at each word to be learned, wherein the word information comprises one or more of adding time, word exposure times, word grasping degree and word collecting approaches;

and according to the word sequencing parameters, sequencing the words to be learned, and determining the word sequencing of the words to be learned.

By way of example, the preset number of words may be set according to actual requirements, for example, may be set to 200. If the number of the words in the word book does not exceed 200, it can be determined that the number of the words in the current word book is small, the user can completely learn all the words in the word book within a certain time, and the data volume corresponding to the processing of the words under the level is within the allowable load range, so that the operation load of the terminal equipment is not excessively high. Thus, all words in the word book may be determined as words to be learned for the user to learn.

There is a possibility that a word is repeatedly added to the word book, and each addition can consider that the user is unfamiliar with the word and needs to continue learning. Therefore, if the adding time in the word information of a certain word is multiple, the latest adding time can be used as the adding time corresponding to the word, so that the adding time can more accurately measure whether the user needs to learn the word, and the closer the adding time of the word is to the current time, the higher the requirement of the user on learning the word.

The manner of determining the word ordering parameter will be described below by taking the case that the word information includes the addition time as an example, and accordingly, the word ordering parameter of the word to be learned may be determined according to the addition time of the word to be learned in this embodiment.

As the inverse of the time difference between the addition time of the word to be learned and the current time may be determined as the time weight, the time difference may be determined by subtracting the addition time from the current time and rounding up in days, for example. For example, if the time difference is 3 days, the time weight may be determined to be 1/3. Therefore, the closer the adding time and the current time are, the larger the time weight is, at this time, the time weight is the word ordering parameter of the word to be learned, and the word ordering parameters of the word to be learned can be arranged in the order from big to small, so that the closer the adding time and the current time are, the more the word ordering is.

The number of word exposures may refer to the number of times the learning video corresponding to the word is pushed for display. The lower the number of word exposures, the higher the strangeness of the word to the user, and the higher the need for learning it.

The manner of determining the word ordering parameter will be described below by taking the case where the word information includes the addition time and the number of word exposures as an example, and accordingly, the word ordering parameter of the word to be learned may be determined according to the addition time and the number of word exposures of the word to be learned in this embodiment. For example, the inverse number of days of difference between the addition time of the word to be learned and the current time may be determined as the time weight. If the number of word exposures is greater than 0, the inverse of the number of single exposures may be determined as the number of exposures weight, and if the number of word exposures is 0, a preset number of exposures weight value may be used as the number of exposures weight, where the preset number of exposures weight value may be 3. Thus, the fewer the number of word exposures, the greater the exposure number weight. At this time, the product of the time weight and the exposure time weight may be determined as a word ordering parameter of the word to be learned, and the word ordering parameters of the word to be learned may be arranged in order from large to small, so that the closer the addition time and the current time of the word to be learned are, the smaller the exposure time of the word is, and the earlier the word ordering is.

The word grasping degree can be determined by the accuracy of the related problem test, and the lower the accuracy is, the lower the grasping degree of the word by the user is, and the higher the requirement for learning the word is. The lower the word mastery, the higher the corresponding mastery weight. Taking the word ordering parameter of the word to be learned as an example according to the adding time of the word to be learned, the word exposure times and the word grasping degree. The product of the time weight, the exposure frequency weight and the mastery degree weight can be determined as the word ordering parameter of the word to be learned, and the word ordering parameter of the word to be learned can be arranged in the order from big to small, so that the closer the addition time and the current time of the word to be learned are, the lower the exposure frequency of the word is, the lower the mastery degree of the word is, and the word ordering is the earlier.

The word collection approach can be divided into active collection and passive collection, as described above, the words added to the word book by the user are active collections, the words added to the word book by the system are passive collections, and if the collection approach is active collection, it can be determined that the user has higher initiative to learn the word, i.e., the need to learn the word is higher.

The collection path weight of the active collection may be higher than the collection path weight of the passive collection. Taking the word ordering parameters of the words to be learned as an example according to the addition time of the words to be learned, the number of word exposure times, the word grasping degree and the word collection way. The product of the time weight, the exposure frequency weight, the mastery degree weight and the collection path weight can be determined as the word ordering parameter of the word to be learned, and the word ordering parameter of the word to be learned can be arranged in the order from big to small, so that the closer the addition time and the current time of the word to be learned are, the lower the exposure frequency of the word is, the lower the mastery degree of the word is, the higher the initiative corresponding to the word collection path is, and the word ordering is the earlier.

The above method for determining word ordering parameters by combining multiple dimensions in word information is aimed at the description, and for combining multiple dimensions in other scenes, adding time, word exposure times and word collection ways, determining corresponding weights in each dimension, and finally determining the word ordering parameters, wherein the determination method is similar to the above method and is not repeated here.

In another alternative embodiment, if the number of words in the word book does not exceed the preset number of words, all the words in the word book may be determined as the words to be learned. Then, priorities among different dimensions under the word information can be set, and if the priorities are word exposure times, addition time, word grasping degree and word collection ways in sequence from high to low, the words to be learned can be further ordered based on the priorities and the word information. The word to be learned can be ordered according to the word exposure times in the word information of the word to be learned, wherein the word to be learned is ordered earlier the lower the word exposure times of the word to be learned are. For the words to be learned with the same word exposure times, word ordering can be performed according to the adding time in the word information, and the closer the adding time is to the current time, the earlier the word ordering is. For the words to be learned, which have the same word exposure times and the same adding time, the words can be ordered according to the word grasping degree in the word information, and the lower the word grasping degree is, the earlier the word ordering is. Aiming at the words to be learned, which have the same word exposure times, the same adding time and the same word grasping degree, the higher the initiative corresponding to the word collection approach is, the higher the word ordering is.

Therefore, based on word information of the words to be learned, the requirement of the user for learning each word to be learned can be comprehensively determined from a plurality of dimensions, so that the words to be learned are flexibly ordered according to the actual requirement of the user, the pushing process of the word learning video is attached to the learning scene of the user, and the learning interest of the user is improved.

if the number of words in the word book exceeds the preset number of words, determining a first word ordering parameter of the words according to first word information of the words for each word, wherein the first word information comprises addition time and word exposure times;

and selecting the words with the preset word number according to the sequence of the first word ordering parameters from large to small, and determining the words as the words to be learned.

If the number of the words in the word book exceeds the preset number of the words, the number of the words in the current word book can be considered to be more, and partial words can be screened out from all the words in the word book under the scene and used as the words to be learned in the learning process.

For example, a first word ordering parameter for a word may be determined based on the time of addition of the word and the number of word exposures. Specifically, the time weight may be determined based on the addition time, and the exposure time weight may be determined according to the number of word exposures, in the same manner as described above. The product of the time weight and the exposure time weight can be determined as a first word ordering parameter of the words, the first word ordering parameter can be arranged in the order from big to small, and the words with the number of the preset words in the ordering result are selected and determined as the words to be learned. Thus, the addition time is close to the current time in all words of the word book, and the word with the smaller number of word exposure times is determined as the word to be learned.

Further, after the number of words in the word book exceeds the number of preset words, determining the words in the word book, the duration of which is not up to the preset exposure interval duration from the last word exposure, and directly setting the first word ordering parameter as a reference value; the step of determining a first word ordering parameter of the word from the first word information of the word is performed for the other words.

The preset exposure interval period may be set, for example, to 1 day. The default value may be set to 0, and accordingly, the reference value may be the smallest value among the words after other words determine the corresponding first word ordering parameter, i.e., the first word ordering parameter corresponding to a word in the word book whose duration since the last word exposure has not reached the preset exposure interval duration may be set to a smaller value, such that such recently exposed words are not ordered to the previous position. Thus, after the first word ordering parameters are ordered from the big to the small, the word exposed in the near period can be prevented from being determined as the word to be learned, so that the user can repeatedly learn the same word in a short time.

Then, for each word to be learned, determining second word ordering parameters of the word to be learned according to second word information of the word to be learned, wherein the second word information comprises one or more of the first word information, the word grasping degree and the word collecting way;

and according to the second word sequencing parameters, word sequencing is carried out on the words to be learned, and the word sequencing of the words to be learned is determined.

The process of determining the second word ordering parameter of the word to be learned according to the second word information of the word to be learned is similar to the process of determining the word ordering parameter of the word to be learned according to the word information of the word to be learned for each word to be learned, which is described above, and is not repeated here. Therefore, based on the second word information of the words to be learned, the requirement of the user for learning each word to be learned can be comprehensively determined from a plurality of dimensions, so that the words to be learned are flexibly ordered according to the actual requirement of the user.

In an alternative embodiment, in S102, determining the target paraphrasing of the word to be learned may include:

if the word to be learned has a corresponding disambiguation result, determining the paraphrasing represented by the disambiguation result as a target paraphrasing, wherein the disambiguation result is used for representing the actual paraphrasing of the word to be learned of the source and the sentence in the sentence;

if the word to be learned does not have the corresponding disambiguation result, determining the first paraphrasing of the word to be learned in the dictionary as the target paraphrasing.

For example, if the word to be learned comes from a specific sentence, that is, the user adds the word to be learned to the word book during the process of learning the sentence, the disambiguation result can be obtained by training the word disambiguation model in advance during the process of adding the word, that is, the actual paraphrasing of the word in the sentence is determined, and the disambiguation result can be stored in a label form corresponding to the word to be learned.

Specifically, sentences marked with specific words can be input into a pre-trained word disambiguation model, and the obtained model output result is the disambiguation result of the marked specific words, wherein the word disambiguation model can be trained by adopting a machine learning mode. The word disambiguation model may be stored locally, for example, with local invocations made per use, or may be stored on a third party platform with invocations from a third party per use, without limitation. In addition, the user may add the same word to the word book multiple times during learning of different sentences, in which case the disambiguation result determined when the word was last added may be in order. Therefore, the determined target paraphrasing can be adapted to the actual demands of the users, and the weak points of the knowledge points of the users when learning the word to be learned are reflected. Based on the learning video determined according to the target definition, the user can concentrate on understanding learning at the weak part of the word to be learned.

If the word to be learned has no corresponding disambiguation result, i.e. the word to be learned may be directly added by the user in the word book and no corresponding sentence exists, the first paraphrasing of the word to be learned in the dictionary may be determined as the target paraphrasing.

In an alternative embodiment, in S102, according to the target paraphrasing, determining a learning video corresponding to each word to be learned, as shown in fig. 2, the steps may include:

in S1021, a plurality of candidate videos of the word to be learned are determined from the target paraphrasing.

For example, a plurality of candidate videos of the word to be learned may be determined from a video library based on target paraphrasing of the word to be learned. As an example, the step of determining a plurality of candidate videos of the word to be learned from the target paraphrasing may include:

and according to the target paraphrasing, determining the associated video of the word to be learned under the target paraphrasing from the video library.

Wherein a search can be conducted in the video library based on the target paraphrasing to determine an associated video that includes the word to be learned, and the actual paraphrasing of the word to be learned in the sentence of the associated video is the same as the target paraphrasing, and no grammar errors in the sentence. The actual paraphrasing of the word in the sentence may be obtained based on the word disambiguation model as described above.

If the associated videos corresponding to the plurality of words to be learned comprise the same videos, determining the number of the associated videos of each word in the group of words to be learned according to the group of words to be learned corresponding to each same video;

In the group of words to be learned, if the number of the associated videos is different, determining the associated video of the word with the least number of the associated videos as a candidate video of the word, and regarding other words except the word with the least number, taking the videos except the same video in the associated video of the word as the candidate video of the word;

and if the number of the associated videos is the same in the group of words to be learned, determining the associated video of the word with the highest word rank as the candidate video of the word, and regarding the other words except the word with the highest word rank, taking the videos except the same video in the associated video of the word as the candidate video of the word.

For example, if the determined word to be learned includes a first word to be learned a and a third word to be learned C, the associated video of the first word to be learned a under the target paraphrasing thereof includes a first associated video a01, a second associated video a02 and a third associated video a03; the associated video of the third word C to be learned under its target paraphrasing includes a seventh associated video C01 and an eighth associated video C02. Wherein, the second associated video a02 and the eighth associated video C02 are the same video, and the first word to be learned a and the third word to be learned C correspond to a group of words to be learned. The first word to be learned a corresponds to 3 associated videos, the third word to be learned C corresponds to 2 associated videos, in this case, the data of the associated videos of the third word to be learned C is the least, the first associated video a01 and the third associated video a03 may be determined as candidate videos of the first word to be learned a, and the seventh associated video C01 and the eighth associated video C02 may be determined as candidate videos of the third word to be learned C, so as to implement video deduplication.

For example, if the determined word to be learned includes a first word to be learned a and a second word to be learned B. The associated video of the first word A to be learned under the target paraphrasing comprises a first associated video a01, a second associated video a02 and a third associated video a03; the associated video of the second word B to be learned under the target paraphrasing thereof comprises a fourth associated video B01, a fifth associated video B02 and a sixth associated video B03; the third association video a03 and the fourth association video B01 are the same video, the first word to be learned a and the second word to be learned B correspond to a group of words to be learned, the first word to be learned a and the second word to be learned B both correspond to 3 association videos, the word ordering result is that the first word to be learned a is before the second word to be learned B, the first association video a01, the second association video a02 and the third association video a03 can be determined as candidate videos of the first word to be learned a, and the fifth association video B02 and the sixth association video B03 can be determined as candidate videos of the second word to be learned B, so as to realize video deduplication.

Therefore, the repeated videos can be deleted, the same videos are prevented from being recommended to the user, and the use experience of the user is improved.

Turning back to fig. 2, after determining the candidate video, in S1022, video ranking parameters of the candidate video are determined according to video information of the candidate video, where the video information includes one or more of a number of complete sentences in the candidate video, a video duration, a speech rate, a video source, a word number duty of a target difficulty, and a video scene richness.

The sentence number weight can be determined by the number of complete sentences in the candidate video, the duration weight can be determined by the video duration of the candidate video, the speech rate weight can be determined by the speech rate of the candidate video, the video source weight can be determined by the video source of the candidate video, the difficulty recommendation weight can be determined by the number of words of the target difficulty of the candidate video, and the scene weight can be determined by the video scene richness of the candidate video. Further, the video ranking parameters of the candidate video may be determined based on one or more of sentence number weights, duration weights, pace weights, video source weights, difficulty recommendation weights, and scene weights.

The fewer the number of complete sentences in the candidate video, the easier the user can understand the content in the candidate video, so that the fewer the number of complete sentences in the candidate video, the larger the number of sentences corresponding to the candidate video is weighted.

For video duration, duration weights corresponding to different video durations can be preset. For example, when the video time period is greater than or equal to a first time period threshold and less than a second time period threshold, the candidate video corresponds to a first time period weight; when the video time length is greater than or equal to a third time length threshold value and is smaller than a first time length threshold value, the candidate video corresponds to a second time length weight; and when the video time length is greater than or equal to the second time length threshold value, the candidate video corresponds to the third time length weight. The first time length weight is greater than the second time length weight, the second time length weight is greater than the third time length weight, the second time length threshold is greater than the first time length threshold, the first time length threshold is greater than the third time length threshold, specifically, the first time length threshold can be 4s, the second time length threshold can be 8s, and the third time length threshold can be 2s. Thus, the user can be preferentially recommended with the video with more proper video duration.

The speech speed weight corresponding to different speech speeds can be preset for the speech speeds. For example, when the speech rate is less than a first speech rate threshold, the candidate video corresponds to a first speech rate weight; when the speech speed is greater than or equal to the first speech speed threshold and is smaller than the second speech speed threshold, the candidate video corresponds to the second speech speed weight; and when the speech speed is greater than or equal to the second speech speed threshold value, the candidate video corresponds to a third speech speed weight. The first speech speed weight is greater than the second speech speed weight, the second speech speed weight is greater than the third speech speed weight, the first speech speed threshold value is smaller than the second speech speed threshold value, and the second speech speed threshold value is smaller than the third speech speed threshold value. I.e., the faster the speech rate, the less the speech rate weight the candidate video corresponds to. Therefore, the video with lower speech speed can be recommended to the user preferentially, so that the user can learn and understand conveniently.

To obtain enough candidate videos, candidate videos may be obtained from multiple video sources. Because the video quality in different video sources is different, the video source weight of each video source can be preset, wherein the higher the video quality under the video source is, the higher the video weight corresponding to the video source is. Therefore, the video with higher quality can be recommended to the user preferentially, so that the user can learn and understand with high quality.

The word number ratio of the target difficulty may be determined based on the number of words in the candidate video that reach the target difficulty, the difficulty value of each word in the candidate video may be preset, and if the difficulty value of the word is greater than the target difficulty value, the word may be determined to be a word that has reached the target difficulty. The higher the word number of the target difficulty is, the higher the understanding difficulty of the candidate video is, and the smaller the difficulty recommendation weight corresponding to the candidate video is, so that the video with lower understanding difficulty can be recommended preferentially to the user, and the learning difficulty of the user is reduced.

The video scene richness can be determined based on the scene number of candidate videos, and the higher the video scene richness is, the higher the corresponding scene weight is, so that the video with richer scenes can be recommended for the user preferentially. Thus, the corresponding weight of each video can be determined for each dimension, and then the sum of the weights of the plurality of dimensions can be determined as the video ordering parameter under the plurality of dimensions.

As such, for each candidate video, its video ordering parameters may be determined from the video information of the candidate video. Based on the video information of the candidate videos, the video ordering parameters of each candidate video can be comprehensively determined from multiple dimensions, so that the pushing sequence of the word learning videos can be adapted to the actual demands of users, and the use experience of the users is improved.

In S1023, the candidate videos are ranked according to the video ranking parameter, and a target video ranking result is obtained.

For example, for the candidate video under each word to be learned, the candidate videos can be ranked according to the order of the video ranking parameters from large to small, so as to obtain a target video ranking result, so that when the user learns the word to be learned, high-quality videos with smaller learning difficulty and rich scenes are recommended preferentially to the user, and the mastering speed of the user on the word to be learned is improved.

In S1024, if the number of candidate videos is greater than the preset number of videos, determining N candidate videos before the target video ranking result is ranked as learning videos, and determining a display sequence of each learning video based on the target video ranking result, where N is used to represent the preset number of videos.

If the number of the candidate videos is greater than the preset number of videos, it can be determined that the number of the candidate videos of the word to be learned is greater, and in order to avoid that a user spends too much time learning the word to be learned and cannot enter the learning of the next word to be learned later, the candidate videos of N before the target video ordering result is ordered can be determined to be learning videos, and the display sequence of each learning video is determined based on the target video ordering result. Where N is used to represent the preset number of videos, and may be set to 3. And sequencing the first N candidate videos in the target video sequencing result, namely, the learning video display sequence of the word to be learned.

If the number of candidate videos is smaller than the preset number of videos, it may be determined that the number of candidate videos of the word to be learned is smaller, for example, there are two candidate videos in total, all candidate videos may be determined as learning videos, and when the user learns the word to be learned, the learning videos of the word to be learned may be displayed to the user according to a random sequence, so as to reduce the data processing amount.

If the number of candidate videos is smaller than the preset number of videos, determining a target video ordering result of the word to be learned based on the method, determining all candidate videos as learning videos, and determining the display sequence of each learning video based on the target video ordering result. Therefore, the video with smaller learning difficulty and rich scenes can be recommended to the user preferentially, and the mastering speed of the user to the word to be learned is improved.

In one possible embodiment, ranking the candidate videos according to the video ranking parameter to obtain the target video ranking result may include:

sequencing candidate videos according to the sequence of the video sequencing parameters from big to small to obtain an initial video sequencing result;

if the video files to which at least two candidate videos belong are different, and the candidate videos at adjacent positions in the initial video ordering result belong to the same video file, the candidate videos at the positions, which are positioned at the positions behind the adjacent positions in the ordering position, are moved backwards by a preset number of positions so as to obtain a target video ordering result, wherein the candidate videos are obtained from video slices of the video files.

For example, the video file may be a long video, such as a movie video, in which a large number of sentences are included, and for convenience of learning by a user, the video file may be subjected to slicing processing, for example, by slicing to obtain video clips having a length of not more than 15s on the video, and the video clips may be used as candidate videos. If the candidate videos at adjacent positions in the initial video sequencing result belong to the same video file, the possibility that the topics expressed by the candidate videos at the adjacent positions are consistent is extremely high, the possibility that occasions are consistent is also high, the two videos are continuously recommended to a user, and a plurality of use occasions of the word to be learned are difficult to restore. Therefore, on the premise that the video files to which at least two candidate videos belong are different, namely when a plurality of candidate videos do not completely belong to the same video file, the candidate videos with the rear ordering positions in the adjacent positions can be moved backwards by a preset number of positions so as to obtain the ordering result of the target videos. For example, the initial video ranking result corresponding to the fourth word to be learned D is a ninth candidate video D01, a tenth candidate video D02, an eleventh candidate video D03, a twelfth candidate video D04, and a thirteenth candidate video D05, where the ninth candidate video D01, the tenth candidate video D02 belong to the same video file, the other candidate videos belong to other video files, the tenth candidate video D02 may be moved backward by a preset number (e.g., set to 3) of positions, and the target video ranking result is the ninth candidate video D01, the eleventh candidate video D03, the twelfth candidate video D04, the thirteenth candidate video D05, and the tenth candidate video D02.

Therefore, through adjusting the initial video sequencing result, videos with smaller learning difficulty, rich scenes and from different video files can be recommended to the user preferentially, so that a plurality of use occasions of the word to be learned can be restored, and the grasping speed of the user on the word to be learned can be improved.

In another possible embodiment, ranking the candidate videos according to the video ranking parameter to obtain the target video ranking result may include:

if the subjects represented by at least two candidate videos are different and the subjects represented by the candidate videos at adjacent positions in the initial video ordering result are the same, moving the candidate videos at the rear ordering position in the adjacent positions backwards by a preset number of positions so as to obtain a target video ordering result.

For example, the topics represented by different candidate videos are different, the topics may include science fiction, history, comedy, and the like, the candidate videos of the same topic have a certain similarity, if the topics represented by the candidate videos of adjacent positions in the initial video ranking result are the same, the two videos are continuously recommended to the user, and it may be difficult to restore a plurality of use occasions of the word to be learned, so that the candidate videos of the adjacent positions with the rear ranking position can be moved backwards by a preset number of positions, so as to obtain the target video ranking result. Taking the ninth candidate video D01, the tenth candidate video D02, the eleventh candidate video D03, the twelfth candidate video D04 and the thirteenth candidate video D05 as examples of the initial video ranking result corresponding to the fourth word D to be learned. The subject represented by the ninth candidate video d01 and the tenth candidate video d02 is the same as the subject represented by the science fiction, and the subjects represented by the other candidate videos are comedy, history and suspicion, respectively, so that the tenth candidate video d02 can be moved backward by a preset number (for example, set to 3) of positions, and then the target video ranking result is the ninth candidate video d01, the eleventh candidate video d03, the twelfth candidate video d04, the thirteenth candidate video d05 and the tenth candidate video d02.

Therefore, through adjusting the initial video sequencing result, videos with smaller learning difficulty, rich scenes and different characterization subjects can be recommended to the user preferentially, so that a plurality of use occasions of the word to be learned are restored, and the grasping speed of the user on the word to be learned is improved.

Based on the same inventive concept, the present disclosure also provides a word-based video recommendation apparatus. Fig. 3 is a block diagram of a word-based video recommendation device provided in accordance with one embodiment of the present disclosure. As shown in fig. 3, the video recommendation device 300 for words may include:

a first determining module 301, configured to determine a plurality of words to be learned and word ranks of the words to be learned according to words in a word book; a second determining module 302, configured to determine a target paraphrase of the word to be learned, and determine a learning video corresponding to each word to be learned according to the target paraphrase; and the display module 303 is configured to display the learning video corresponding to each word to be learned according to the word ordering.

Optionally, the first determining module 301 includes:

a first determining submodule, configured to determine all words in the word book as the words to be learned if the number of words in the word book does not exceed a preset number of words; a second determining submodule, configured to determine, for each word to be learned, a word ordering parameter of the word to be learned according to word information of the word to be learned, where the word information includes one or more of an addition time, a word exposure number, a word grasping degree, and a word collection way; and the third determining submodule is used for carrying out word sequencing on the words to be learned according to the word sequencing parameters and determining the word sequencing of the words to be learned.

Optionally, the first determining module 301 includes:

a fourth determining submodule, configured to determine, for each word, a first word ordering parameter of the word according to first word information of the word if the number of words in the word book exceeds a preset number of words, where the first word information includes an addition time and a number of word exposure times; a fifth determining submodule, configured to select, according to the order of the first word ordering parameters from big to small, the words of a preset number of words, and determine the words as the words to be learned; a sixth determining submodule, configured to determine, for each word to be learned, a second word ordering parameter of the word to be learned according to second word information of the word to be learned, where the second word information includes one or more of the first word information, word grasping level, and word collection way; and a seventh determining submodule, configured to perform word ranking on the word to be learned according to the second word ranking parameter, and determine word ranking of the word to be learned.

Optionally, the second determining module 302 includes:

an eighth determining submodule, configured to determine, if the word to be learned has a corresponding disambiguation result, a paraphrasing represented by the disambiguation result as the target paraphrasing, where the disambiguation result is used to represent an actual paraphrasing of the word to be learned of the source and the sentence in the sentence; and a ninth determining submodule, configured to determine, as the target paraphrasing, a first paraphrasing of the word to be learned in the dictionary if the word to be learned has no corresponding disambiguation result.

Optionally, the second determining module 302 includes:

a tenth determination submodule, configured to determine a plurality of candidate videos of the word to be learned according to the target paraphrasing; an eleventh determination submodule, configured to determine a video ranking parameter of the candidate video according to video information of the candidate video, where the video information includes one or more of a number of complete sentences in the candidate video, a video duration, a speech speed, a video source, a word number ratio of a target difficulty, and a video scene richness; the acquisition sub-module is used for sequencing the candidate videos according to the video sequencing parameters to obtain a target video sequencing result; and a twelfth determining sub-module, configured to determine, if the number of candidate videos is greater than a preset number of videos, N candidate videos before the target video ranking result is ranked as the learning videos, and determine a display order of each learning video based on the target video ranking result, where N is used to represent the preset number of videos.

Optionally, the obtaining submodule includes:

the sequencing sub-module is used for sequencing the candidate videos according to the sequence of the video sequencing parameters from big to small to obtain an initial video sequencing result; and the first moving submodule is used for moving the candidate videos with the rear sorting positions in the adjacent positions backwards by a preset number of positions if the video files to which at least two candidate videos belong are different and the candidate videos in the adjacent positions in the initial video sorting result belong to the same video file so as to obtain the target video sorting result, wherein the candidate videos are obtained from video slices of the video files.

Optionally, the acquiring sub-module further includes:

and the second moving submodule is used for moving the candidate videos with the rear sorting positions in the adjacent positions backwards by a preset number of positions if the topics represented by at least two candidate videos are different and the topics represented by the candidate videos in the adjacent positions in the initial video sorting result are the same, so as to obtain the target video sorting result.

Optionally, the tenth determination submodule includes:

a thirteenth determining submodule, configured to determine, from a video library, an associated video of the word to be learned under the target paraphrasing according to the target paraphrasing; a fourteenth determination submodule, configured to determine, for a group of words to be learned corresponding to each identical video, a number of associated videos of each word in the group of words to be learned if the associated videos corresponding to the plurality of words to be learned include identical videos; the first de-duplication sub-module is used for determining the associated video of the word with the least number of associated videos as the candidate video of the word in the group of words to be learned if the number of the associated videos is different, and taking the videos except the same video in the associated video of the word as the candidate video of the word aiming at the other words except the word with the least number; and the second de-duplication sub-module is used for determining the associated video of the word with the forefront word sequence as the candidate video of the word if the number of the associated videos is the same in the group of words to be learned, and taking the videos except the same video in the associated video of the word as the candidate video of the word aiming at the other words except the word with the forefront word sequence.

Referring now to fig. 4, a schematic diagram of an electronic device 600 suitable for use in implementing embodiments of the present disclosure is shown. The terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 4 is merely an example and should not be construed to limit the functionality and scope of use of the disclosed embodiments.

As shown in fig. 4, the electronic device 600 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 601, which may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic apparatus 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

In general, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, and the like; an output device 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, magnetic tape, hard disk, etc.; and a communication device 609. The communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While fig. 4 shows an electronic device 600 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead.

In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a non-transitory computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via communication means 609, or from storage means 608, or from ROM 602. The above-described functions defined in the methods of the embodiments of the present disclosure are performed when the computer program is executed by the processing device 601.

It should be noted that the computer readable medium described in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.

In some implementations, the clients may communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.

The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device.

The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to:

determining a plurality of words to be learned and word sequences of the words to be learned according to the words in the word book; determining target paraphrases of the words to be learned, and determining learning videos corresponding to each word to be learned according to the target paraphrases; and displaying the learning videos corresponding to each word to be learned according to the word ordering.

Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including, but not limited to, an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The modules described in the embodiments of the present disclosure may be implemented in software or hardware. Wherein the name of the module does not in some case constitute a limitation of the module itself, e.g. the third determination submodule may also be described as a word ordering module.

The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

In accordance with one or more embodiments of the present disclosure, example 1 provides a word-based video recommendation method, comprising:

Example 2 provides the method of example 1, according to one or more embodiments of the present disclosure, the determining a plurality of words to be learned and word ordering of the words to be learned from words in a word book, comprising:

if the number of the words in the word book does not exceed the preset number of the words, determining all the words in the word book as the words to be learned; determining word ordering parameters of the words to be learned according to word information of the words to be learned, wherein the word information comprises one or more of adding time, word exposure times, word grasping degree and word collection ways; and according to the word sequencing parameters, sequencing the words to be learned, and determining the word sequencing of the words to be learned.

According to one or more embodiments of the present disclosure, example 3 provides the method of example 1, the determining a plurality of words to be learned and word ordering of the words to be learned according to words in a word book, comprising:

if the number of words in the word book exceeds the preset number of words, determining a first word ordering parameter of each word according to first word information of the word, wherein the first word information comprises addition time and word exposure times; selecting the words with preset word numbers according to the sequence of the first word ordering parameters from big to small, and determining the words to be learned; determining, for each word to be learned, a second word ordering parameter of the word to be learned according to second word information of the word to be learned, wherein the second word information includes one or more of the first word information, word grasping degree, and word collection approach; and according to the second word sequencing parameters, word sequencing is carried out on the words to be learned, and the word sequencing of the words to be learned is determined.

In accordance with one or more embodiments of the present disclosure, example 4 provides the method of example 1, the determining the target paraphrasing of the word to be learned, comprising:

If the word to be learned has a corresponding disambiguation result, determining the paraphrasing represented by the disambiguation result as the target paraphrasing, wherein the disambiguation result is used for representing the actual paraphrasing of the word to be learned of the source and the sentence in the sentence; and if the word to be learned does not have a corresponding disambiguation result, determining the first paraphrasing of the word to be learned in the dictionary as the target paraphrasing.

According to one or more embodiments of the present disclosure, example 5 provides the method of example 1, the determining, according to the target paraphrasing, a learning video corresponding to each word to be learned, including:

determining a plurality of candidate videos of the word to be learned according to the target paraphrasing; determining video ordering parameters of the candidate videos according to the video information of the candidate videos, wherein the video information comprises one or more of the number of complete sentences in the candidate videos, video duration, speech speed, video sources, word number duty ratio of target difficulty and video scene richness; sorting the candidate videos according to the video sorting parameters to obtain a target video sorting result; and if the number of the candidate videos is larger than the preset number of videos, determining N candidate videos before the target video ordering result is ordered as the learning videos, and determining the display sequence of each learning video based on the target video ordering result, wherein N is used for representing the preset number of videos.

According to one or more embodiments of the present disclosure, example 6 provides the method of example 5, the ranking the candidate videos according to the video ranking parameter to obtain a target video ranking result, including:

sequencing the candidate videos according to the sequence of the video sequencing parameters from big to small to obtain an initial video sequencing result; if the video files to which at least two candidate videos belong are different, and the candidate videos in adjacent positions in the initial video ordering result belong to the same video file, moving the candidate videos in the adjacent positions with the subsequent ordering positions backwards by a preset number of positions to obtain the target video ordering result, wherein the candidate videos are obtained from video slices of the video files.

According to one or more embodiments of the present disclosure, example 7 provides the method of example 5, the ranking the candidate videos according to the video ranking parameter to obtain a target video ranking result, comprising:

sequencing the candidate videos according to the sequence of the video sequencing parameters from big to small to obtain an initial video sequencing result; and if the subjects represented by at least two candidate videos are different and the subjects represented by the candidate videos at adjacent positions in the initial video ordering result are the same, moving the candidate videos at the rear ordering positions in the adjacent positions backwards by a preset number of positions so as to obtain the target video ordering result.

According to one or more embodiments of the present disclosure, example 8 provides the method of example 5, the determining a plurality of candidate videos of the word to be learned according to the target paraphrasing, comprising:

according to the target paraphrasing, determining an associated video of the word to be learned under the target paraphrasing from a video library; if the associated videos corresponding to the plurality of words to be learned comprise the same videos, determining the number of the associated videos of each word in the group of words to be learned according to the group of words to be learned corresponding to each same video; in the group of words to be learned, if the number of the associated videos is different, determining the associated video of the word with the least number of the associated videos as the candidate video of the word, and regarding the other words except the word with the least number, taking the video except the same video in the associated video of the word as the candidate video of the word; and if the number of the associated videos is the same in the group of words to be learned, determining the associated videos of the word with the top word sequence as candidate videos of the word, and regarding other words except the word with the top word sequence as candidate videos of the word, wherein videos except the same videos in the associated videos of the word are used as candidate videos of the word.

Example 9 provides a word-based video recommendation apparatus according to one or more embodiments of the present disclosure, comprising:

the first determining module is used for determining a plurality of words to be learned and word sequences of the words to be learned according to the words in the word book; the second determining module is used for determining target paraphrases of the words to be learned and determining learning videos corresponding to each word to be learned according to the target paraphrases; and the display module is used for displaying the learning video corresponding to each word to be learned according to the word ordering.

According to one or more embodiments of the present disclosure, example 10 provides a computer-readable medium having stored thereon a computer program which, when executed by a processing device, implements the steps of the method of any one of examples 1 to 8.

Example 11 provides an electronic device according to one or more embodiments of the present disclosure, comprising: a storage device having a computer program stored thereon; processing means for executing the computer program in the storage means to implement the steps of the method of any one of examples 1 to 8.

The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by persons skilled in the art that the scope of the disclosure referred to in this disclosure is not limited to the specific combinations of features described above, but also covers other embodiments which may be formed by any combination of features described above or equivalents thereof without departing from the spirit of the disclosure. Such as those described above, are mutually substituted with the technical features having similar functions disclosed in the present disclosure (but not limited thereto).

Moreover, although operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.

Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are example forms of implementing the claims. The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.

Claims

1. A method of word-based video recommendation, comprising:

2. The method of claim 1, wherein the determining a plurality of words to be learned and word ordering of the words to be learned based on words in a word book comprises:

determining word ordering parameters of the words to be learned according to word information of the words to be learned, wherein the word information comprises one or more of adding time, word exposure times, word grasping degree and word collection ways;

3. The method of claim 1, wherein the determining a plurality of words to be learned and word ordering of the words to be learned based on words in a word book comprises:

if the number of words in the word book exceeds the preset number of words, determining a first word ordering parameter of each word according to first word information of the word, wherein the first word information comprises addition time and word exposure times;

selecting the words with preset word numbers according to the sequence of the first word ordering parameters from big to small, and determining the words to be learned;

determining, for each word to be learned, a second word ordering parameter of the word to be learned according to second word information of the word to be learned, wherein the second word information includes one or more of the first word information, word grasping degree, and word collection approach;

4. The method of claim 1, wherein the determining the target paraphrasing of the word to be learned comprises:

If the word to be learned has a corresponding disambiguation result, determining the paraphrasing represented by the disambiguation result as the target paraphrasing, wherein the disambiguation result is used for representing the actual paraphrasing of the word to be learned of the source and the sentence in the sentence;

and if the word to be learned does not have a corresponding disambiguation result, determining the first paraphrasing of the word to be learned in the dictionary as the target paraphrasing.

5. The method of claim 1, wherein determining a learning video corresponding to each word to be learned based on the target paraphrasing comprises:

determining a plurality of candidate videos of the word to be learned according to the target paraphrasing;

determining video ordering parameters of the candidate videos according to the video information of the candidate videos, wherein the video information comprises one or more of the number of complete sentences in the candidate videos, video duration, speech speed, video sources, word number duty ratio of target difficulty and video scene richness;

sorting the candidate videos according to the video sorting parameters to obtain a target video sorting result;

and if the number of the candidate videos is larger than the preset number of videos, determining N candidate videos before the target video ordering result is ordered as the learning videos, and determining the display sequence of each learning video based on the target video ordering result, wherein N is used for representing the preset number of videos.

6. The method of claim 5, wherein ranking the candidate videos according to the video ranking parameter to obtain a target video ranking result comprises:

sequencing the candidate videos according to the sequence of the video sequencing parameters from big to small to obtain an initial video sequencing result;

if the video files to which at least two candidate videos belong are different, and the candidate videos in adjacent positions in the initial video ordering result belong to the same video file, moving the candidate videos in the adjacent positions with the subsequent ordering positions backwards by a preset number of positions to obtain the target video ordering result, wherein the candidate videos are obtained from video slices of the video files.

7. The method of claim 5, wherein ranking the candidate videos according to the video ranking parameter to obtain a target video ranking result comprises:

and if the subjects represented by at least two candidate videos are different and the subjects represented by the candidate videos at adjacent positions in the initial video ordering result are the same, moving the candidate videos at the rear ordering positions in the adjacent positions backwards by a preset number of positions so as to obtain the target video ordering result.

8. The method of claim 5, wherein the determining a plurality of candidate videos for the word to be learned based on the target paraphrasing comprises:

according to the target paraphrasing, determining an associated video of the word to be learned under the target paraphrasing from a video library;

in the group of words to be learned, if the number of the associated videos is different, determining the associated video of the word with the least number of the associated videos as the candidate video of the word, and regarding the other words except the word with the least number, taking the video except the same video in the associated video of the word as the candidate video of the word;

and if the number of the associated videos is the same in the group of words to be learned, determining the associated videos of the word with the top word sequence as candidate videos of the word, and regarding other words except the word with the top word sequence as candidate videos of the word, wherein videos except the same videos in the associated videos of the word are used as candidate videos of the word.

9. A word-based video recommendation device, comprising:

10. A computer readable medium on which a computer program is stored, characterized in that the program, when being executed by a processing device, carries out the steps of the method according to any one of claims 1-8.

11. An electronic device, comprising:

a storage device having a computer program stored thereon;

processing means for executing said computer program in said storage means to carry out the steps of the method according to any one of claims 1-8.