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

Abstract

The present disclosure relates to the technical field of computers, in particular, to a word-based video recommendation method and device, medium and electronic equipment. The method comprises: determining a plurality of words to be learned and a word order of the words to be learned according to the words in a word book; determining a target definition of the words to be learned, and determining a learning video corresponding to each word to be learned according to the target definition; and displaying the learning video corresponding to each word to be learned according to the word order. In this way, for each word to be learned, the user can focus on understanding and learning the application of the word to be learned under the target definition, thereby improving the mastery and application of the word to be learned. In addition, through the display of the learning video, the real usage scenario of the word to be learned can be restored, effectively improving the user's attention concentration in learning the word, improving the user's learning pleasure, reducing the boredom of word learning, and further accelerating the speed of mastering the word.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more specifically, to a word-based video recommendation method, apparatus, medium, and electronic device. Background Technology

[0002] Vocabulary learning is the foundation of learning a language. With the continuous development of smart devices, more and more users are learning vocabulary online through these devices. However, existing online vocabulary learning methods mostly rely on word lists, displaying detailed information about each word in the dictionary. This often results in a large amount of content, making it difficult to grasp the key points. Furthermore, list-based learning is relatively tedious, inefficient, and lacks specific application scenarios. Summary of the Invention

[0003] This summary section is provided to briefly introduce the concepts, which will be described in detail in the detailed description section below. This summary section is not intended to identify key or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0004] Firstly, this disclosure provides a word-based video recommendation method, including:

[0005] Based on the words in the vocabulary book, determine multiple words to be learned and their word order;

[0006] Determine the target definition of the word to be learned, and based on the target definition, determine the corresponding learning video for each word to be learned;

[0007] The learning video corresponding to each of the words to be learned is displayed according to the word order.

[0008] Secondly, this disclosure provides a word-based video recommendation device, including:

[0009] The first determining module is used to determine multiple words to be learned and the word order of the words to be learned based on the words in the vocabulary book;

[0010] The second determining module is used to determine the target definition of the word to be learned, and to determine the learning video corresponding to each word to be learned based on the target definition.

[0011] The display module is used to sort the words and display the learning video corresponding to each word to be learned.

[0012] Thirdly, this disclosure provides a computer-readable medium having a computer program stored thereon, which, when executed by a processing device, implements the steps of the above-described word-based video recommendation method.

[0013] Fourthly, this disclosure provides an electronic device, comprising:

[0014] A storage device on which computer programs are stored;

[0015] A processing device is configured to execute the computer program in the storage device to implement the steps of the word-based video recommendation method described above.

[0016] In the above technical solution, multiple words to be learned and their order are determined based on the words in the vocabulary list; the target definition of each word is determined, and a corresponding learning video is selected for each word based on the target definition; the learning video for each word is then displayed according to the word order. In this way, for each word, users can focus on understanding and learning its application under the target definition, improving their mastery and application of the word. Furthermore, by selecting words from the vocabulary list, the time required for learning the entire list at once is avoided, allowing for segmented learning of words within the list. This also reduces the amount of data required for processing words during the learning process, lowering the load on the terminal device. Additionally, the display of learning videos recreates the real-world usage scenarios of the words, effectively improving user concentration and enhancing learning enjoyment, reducing the tedium of vocabulary learning, and further accelerating word mastery.

[0017] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0018] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale. In the drawings:

[0019] Figure 1 This is a flowchart of a word-based video recommendation method provided according to one embodiment of the present disclosure.

[0020] Figure 2 This is a flowchart of a word-based video recommendation method provided according to one embodiment of the present disclosure.

[0021] Figure 3 This is a block diagram of a word-based video recommendation device provided according to one embodiment of the present disclosure.

[0022] Figure 4This is a schematic diagram of the structure of an electronic device provided according to one embodiment of the present disclosure. Detailed Implementation

[0023] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0024] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0025] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based 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". Definitions of other terms will be given in the description below.

[0026] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0027] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0028] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0029] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0030] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0031] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0032] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0033] Meanwhile, it is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0034] Figure 1 This is a flowchart of a word-based video recommendation method provided according to one embodiment of the present disclosure, such as... Figure 1 As shown, the method may include:

[0035] In S101, based on the words in the vocabulary book, multiple words to be learned and their word order are determined.

[0036] For example, a vocabulary notebook can be used to record words that a user needs to master. For instance, while learning a sentence, a user can add unfamiliar words from that sentence to their vocabulary notebook; users can also directly add words they intend to learn by typing them into the notebook. As another example, after taking a vocabulary test, the system can add words that the user failed the test to their vocabulary notebook.

[0037] As the usage time of a vocabulary notebook increases, the number of words in it may also increase. However, users often find it difficult to spend a significant amount of time learning all the words in the notebook completely, and the data processing required for these words is substantial, potentially leading to a high load on the device. Therefore, a selection of words can be chosen from the vocabulary notebook and designated as the learning focus for the current learning phase. For example, if the vocabulary notebook contains too many words, the selection can be based on factors such as the word's addition time and exposure frequency. For instance, if the number of words in the vocabulary notebook exceeds a preset limit, words with fewer exposures than the preset limit can be selected as the learning focus.

[0038] Users have varying levels of mastery over different words. Therefore, words can be sorted based on their level of mastery, ensuring the resulting word ranking aligns with users' actual needs. For instance, the time a word was added can reflect a user's level of mastery; words can be sorted according to their addition time, with more recent additions ranking higher.

[0039] In S102, the target definition of the word to be learned is determined, and based on the target definition, the corresponding learning video for each word to be learned is determined.

[0040] For example, the target definition can be one of all the definitions of the word to be learned. For instance, if a word has only one definition in the Oxford Dictionary, that definition can be identified as the target definition. If a word has multiple definitions in the Oxford Dictionary, any one of those definitions can be identified as the target definition. For each word, if multiple corresponding learning videos are identified based on the target definition, these videos can be considered consistent, meaning the definition of the word is the same across all videos. Thus, even with multiple corresponding learning videos, users can focus on understanding the application of the word under the target definition, enabling them to grasp the key learning points and improve their mastery of the word.

[0041] S103 displays the learning video corresponding to each word to be learned, sorted by word.

[0042] For example, after determining the learning video corresponding to each word to be learned, the learning videos corresponding to each word can be displayed sequentially according to the word order. For instance, if the determined words to be learned include first word A, second word B, and third word C, the word order is first word A, second word B, and third word C. Furthermore, the learning videos corresponding to first word A include first learning video a1, second learning video a2, and third learning video a3; the learning videos corresponding to second word B include fourth learning video b1, fifth learning video b2, and sixth learning video b3; and the learning videos corresponding to third word C include seventh learning video c1 and eighth learning video c2. Therefore, each learning video can be displayed to the user sequentially in the order of first learning video a1, second learning video a2, third learning video a3, fourth learning video b1, fifth learning video b2, sixth learning video b3, seventh learning video c1, and eighth learning video c2.

[0043] In the above technical solution, multiple words to be learned and their order are determined based on the words in the vocabulary list; the target definition of each word is determined, and a corresponding learning video is selected for each word based on the target definition; the learning video for each word is then displayed according to the word order. In this way, for each word, users can focus on understanding and learning its application under the target definition, improving their mastery and application of the word. Furthermore, by selecting words from the vocabulary list, the time required for learning the entire list at once is avoided, allowing for segmented learning of words within the list. This also reduces the amount of data required for processing words during the learning process, lowering the load on the terminal device. Additionally, the display of learning videos recreates the real-world usage scenarios of the words, effectively improving user concentration and enhancing learning enjoyment, reducing the tedium of vocabulary learning, and further accelerating word mastery.

[0044] In an optional embodiment, in S101, determining multiple words to be learned and their word order based on the words in the vocabulary book may include:

[0045] If the number of words in the vocabulary book does not exceed the preset number of words, then all the words in the vocabulary book will be selected as words to be learned.

[0046] For each word to be learned, the word sorting parameters are determined based on the word information, which includes one or more of the following: addition time, word exposure frequency, word mastery level, and word collection method.

[0047] Based on the word sorting parameters, the words to be learned are sorted to determine the word order.

[0048] For example, the preset number of words can be set according to actual needs; for instance, it can be set to 200. If the number of words in the vocabulary list does not exceed 200, it can be determined that the number of words in the current vocabulary list is relatively small. Users can learn all the words in the vocabulary list completely within a certain timeframe, and the amount of data corresponding to processing words at this level is within the allowable load range, which will not cause excessive load on the terminal device. Therefore, all the words in the vocabulary list can be selected as the words to be learned for users to study.

[0049] A word may be added to a vocabulary list repeatedly, and each addition can be interpreted as the user being unfamiliar with the word and not yet having mastered it, thus requiring further study. Therefore, if a word has multiple addition times listed, the most recent addition time can be used as the corresponding addition time for that word. This allows the addition time to more accurately measure whether the user needs to learn the word; the more recent the word's addition time is, the higher the user's need to learn that word.

[0050] The following example uses the word information including the addition time to illustrate how to determine the word sorting parameters. Accordingly, in this embodiment, the word sorting parameters of the word to be learned can be determined based on the addition time of the word to be learned.

[0051] The time weight can be determined by the reciprocal of the time difference between the addition time and the current time of the word to be learned. For example, this time difference can be determined by subtracting the addition time from the current time and rounding up to the nearest day. For instance, if the time difference is 3 days, the time weight can be set to 1 / 3. Thus, the closer the addition time is to the current time, the greater the time weight. In this case, the time weight becomes the word ranking parameter for the word to be learned. The word ranking parameters can be arranged in descending order, so the closer the addition time is to the current time, the higher the word ranks.

[0052] Word exposure count refers to the number of times a learning video corresponding to that word is pushed and displayed. The lower the word exposure count, the greater the user's unfamiliarity with the word and the higher their demand for learning it.

[0053] The following example illustrates how to determine word sorting parameters, using word information including addition time and word exposure count as an example. Accordingly, this embodiment can determine the word sorting parameters based on the addition time and exposure count of the word to be learned. For example, the reciprocal of the number of days between the addition time and the current time can be used as the time weight. If the word exposure count is greater than 0, the reciprocal of the single exposure count can be used as the exposure count weight. If the word exposure count is 0, a preset exposure count weight value can be used as the exposure count weight, where the preset exposure count weight value can be 3. Thus, the fewer the word exposure counts, the greater the exposure count weight. The product of the time weight and the exposure count weight can then be used as the word sorting parameter. The word sorting parameters can be arranged in descending order; thus, the closer the addition time and the current time are, the fewer the word exposure counts, and the higher the word's ranking.

[0054] Vocabulary mastery can be determined by the accuracy rate of relevant practice tests. The lower the accuracy rate, the lower the user's mastery of the word, and the higher the demand for learning it. The lower the vocabulary mastery, the higher its corresponding weight. Taking the determination of word ranking parameters based on the word's addition time, exposure frequency, and mastery level as an example, the product of the time weight, exposure frequency weight, and mastery level weight can be used as the word ranking parameter. The words can be arranged in descending order of their ranking parameters. Thus, the closer the word's addition time is to the current time, the fewer the word's exposure frequency, and the lower its mastery level, the higher the word's ranking.

[0055] Word collection methods can be divided into active collection and passive collection. As mentioned above, words added to the vocabulary list by the user are active collections, while words added to the vocabulary list by the system are passive collections. If the collection method is active collection, it can be determined that the user has a higher initiative to learn the word, that is, a higher demand for learning the word.

[0056] The weight of actively collected words can be higher than that of passively collected words. Taking the determination of word ranking parameters based on the word's addition time, exposure frequency, mastery level, and collection method as an example, the ranking parameter can be determined by the product of the weights of time, exposure frequency, mastery level, and collection method. These ranking parameters can then be arranged in descending order. Thus, the closer the word's addition time is to the current time, the fewer the word's exposure frequency, the lower the mastery level, and the higher the initiative of the collection method, the higher the word's ranking.

[0057] The above explanation focuses on determining word ranking parameters by combining multiple dimensions of word information. For other scenarios involving the combination of multiple dimensions, such as time, word exposure frequency, and word collection methods, the weight of each dimension can be determined, and the word ranking parameters can be finally determined in a similar way, which will not be repeated here.

[0058] In another optional embodiment, if the number of words in the vocabulary book does not exceed a preset number of words, all words in the vocabulary book can be identified as words to be learned. Then, priorities can be set for different dimensions under the word information, such as word exposure count, addition time, word mastery level, and word collection method, from highest to lowest priority. The words to be learned can then be further sorted based on this priority and the word information. For example, words can be sorted according to the word exposure count in the word information, where the fewer the word exposure count, the higher the word ranking. For words with the same word exposure count, they can be sorted according to the addition time in the word information, where the closer the addition time is to the current time, the higher the word ranking. For words with the same word exposure count and the same addition time, they can be sorted according to the word mastery level in the word information, where the lower the word mastery level, the higher the word ranking. For words with the same word exposure count, the same addition time, and the same word mastery level, the higher the initiative corresponding to the word collection method, the higher the word ranking.

[0059] In this way, based on the word information of the words to be learned, the user's demand for learning each word can be determined from multiple dimensions. The words to be learned can be flexibly sorted according to the user's actual needs, so that the word learning video push process fits the user's learning scenario and enhances the user's learning interest.

[0060] In an optional embodiment, in S101, determining multiple words to be learned and their word order based on the words in the vocabulary book may include:

[0061] If the number of words in the vocabulary book exceeds the preset number of words, then for each word, the first word sorting parameter of the word is determined based on the first word information of the word, where the first word information includes the addition time and the number of times the word is exposed;

[0062] Select words according to the first word sorting parameter from largest to smallest, and determine the preset number of words as the words to be learned.

[0063] If the number of words in the vocabulary book exceeds the preset number of words, it can be considered that the current vocabulary book has a large number of words. In this scenario, some words can be selected from all the words in the vocabulary book and used as the words to be learned in this learning process.

[0064] For example, the first word sorting parameter can be determined based on the word's addition time and exposure frequency. Specifically, a time weight can be determined based on the addition time, and an exposure frequency weight can be determined based on the exposure frequency, using the same method described above. The product of the time weight and the exposure frequency weight can be used as the first word sorting parameter. The first word sorting parameter can be arranged in descending order, and the words in the top preset number of the sorted results can be selected as the words to be learned. In this way, words in the entire vocabulary list whose addition time is close to the current time and whose exposure frequency is relatively low can be selected as the words to be learned.

[0065] Furthermore, if the number of words in the vocabulary book exceeds the preset number of words, words in the vocabulary book whose duration since the last exposure has not reached the preset exposure interval can be identified, and their first word sorting parameter can be directly set as a reference value; for other words, the step of determining the first word sorting parameter of the word based on the first word information can be performed.

[0066] The preset exposure interval can be set, for example, to 1 day. The default value can be set to 0. Correspondingly, this reference value can be the smallest value among those words whose corresponding first-word sorting parameters have been determined. That is, the first-word sorting parameter for words in the word list whose exposure time since the last exposure has not reached the preset exposure interval can be set to a smaller value, preventing these recently exposed words from being ranked higher. Thus, after sorting according to the first-word sorting parameter from largest to smallest, recently exposed words are avoided from being identified as words to be learned, preventing users from repeatedly learning the same words in a short period.

[0067] Then, for each word to be learned, the second word sorting parameters of the word to be learned are determined based on the second word information of the word to be learned. The second word information includes one or more of the first word information, word mastery level and word collection method.

[0068] Based on the second word sorting parameter, sort the words to be learned to determine the word order.

[0069] The process of determining the second word ranking parameters for each word to be learned, based on its second word information, is similar to the process described above of determining the word ranking parameters based on the word information of each word to be learned, and will not be repeated here. Thus, based on the second word information of each word to be learned, the user's learning needs for each word can be comprehensively determined from multiple dimensions, allowing for flexible ranking of the words to be learned according to the user's actual needs.

[0070] In an optional embodiment, in S102, determining the target definition of the word to be learned may include:

[0071] If the word to be learned has a corresponding disambiguation result, the definition represented by the disambiguation result is determined as the target definition. The disambiguation result is used to represent the actual definition of the word to be learned in the sentence.

[0072] If there is no corresponding disambiguation result for the word to be learned, then the first definition of the word in the dictionary will be determined as the target definition.

[0073] For example, if the word to be learned comes from a specific sentence, that is, the user adds the word to the vocabulary book while learning the sentence, then during the word addition process, the disambiguation result can be obtained through a pre-trained word disambiguation model, that is, the actual meaning of the word to be learned in the sentence can be determined, and the disambiguation result can be stored in the form of a label corresponding to the word to be learned.

[0074] Specifically, sentences tagged with specific words can be input into a pre-trained word disambiguation model. The model's output is the disambiguation result for the tagged words. This word disambiguation model can be trained using machine learning. This model can be stored locally for local access each time it's used, or stored on a third-party platform for access each time it's used; no specific limitation is made here. Furthermore, users may add the same word to their vocabulary multiple times while learning different sentences. In this case, the disambiguation result determined when the word was last added can be used. In this way, the determined target definition can be adapted to the user's actual needs, reflecting the user's weak points in understanding the word. Based on this, learning videos determined according to the target definition allow users to focus their learning on understanding the weak points of the word.

[0075] If there is no corresponding disambiguation result for the word to be learned, that is, the word to be learned may have been added directly by the user to the wordbook and there is no corresponding sentence, then the first definition of the word to be learned in the dictionary can be determined as the target definition.

[0076] In an optional embodiment, in S102, based on the target definition, the learning video corresponding to each word to be learned is determined, such as... Figure 2 As shown, this step may include:

[0077] In S1021, multiple candidate videos for the word to be learned are identified based on the target definition.

[0078] For example, multiple candidate videos for a word to be learned can be identified from a video library based on the target definition of the word. As an example, the step of identifying multiple candidate videos for a word to be learned based on its target definition may include:

[0079] Based on the target definition, identify the associated videos for the words to be learned from the video library under the target definition.

[0080] Specifically, a search can be performed in the video library based on the target definition to identify associated videos that include the word to be learned, whose actual definition in the sentences of related videos is the same as the target definition, and whose sentences are grammatically correct. The actual definition of the word in the sentence can be obtained based on the word disambiguation model described above.

[0081] If multiple words to be learned correspond to the same video in the associated videos, then for each group of words to be learned corresponding to the same video, determine the number of associated videos for each word in that group of words to be learned.

[0082] In this group of words to be learned, if the number of associated videos is different, the associated videos of the word with the fewest associated videos are determined as candidate videos for that word. For other words, except for the words with the fewest associated videos, the videos of the associated videos of that word other than the same videos are taken as candidate videos for that word.

[0083] In the group of words to be learned, if the number of associated videos is the same, the associated video of the word with the highest word ranking is determined as the candidate video of that word. For other words other than the word with the highest word ranking, the videos associated with that word other than the same video are taken as the candidate videos of that word.

[0084] For example, if the identified words to be learned include a first word A and a third word C, and the associated videos for the first word A under its target definition include a first associated video a01, a second associated video a02, and a third associated video a03; and the associated videos for the third word C under its target definition include a seventh associated video c01 and an eighth associated video c02, where the second associated video a02 and the eighth associated video c02 are the same video, then the first word A and the third word C correspond to a set of words to be learned. In this case, the first word A corresponds to 3 associated videos, and the third word C corresponds to 2 associated videos. Since the third word C has the fewest associated videos, the first associated video a01 and the third associated video a03 can be identified as candidate videos for the first word A, and the seventh associated video c01 and the eighth associated video c02 can be identified as candidate videos for the third word C, thus achieving video deduplication.

[0085] For example, if the identified words to be learned include a first word A and a second word B, and the associated videos for the first word A under its target definition include a first associated video a01, a second associated video a02, and a third associated video a03; and the associated videos for the second word B under its target definition include a fourth associated video b01, a fifth associated video b02, and a sixth associated video b03; wherein the third associated video a03 and the fourth associated video b01 are the same video, then the first word A and the second word B correspond to a set of words to be learned, and both the first word A and the second word B correspond to 3 associated videos. If the word ranking result is that the first word A precedes the second word B, then the first associated video a01, the second associated video a02, and the third associated video a03 can be determined as candidate videos for the first word A, and the fifth associated video b02 and the sixth associated video b03 can be determined as candidate videos for the second word B, in order to achieve video deduplication.

[0086] In this way, by deleting duplicate videos, the same videos can be avoided from being recommended to users, thus improving the user experience.

[0087] Turn back Figure 2 After the candidate videos are identified, in S1022, the video ranking parameters of the candidate videos are determined based on the video information of the candidate videos. The video information includes one or more of the following: the number of complete sentences in the candidate videos, video duration, speech rate, video source, percentage of words of target difficulty, and richness of video scenes.

[0088] Specifically, the sentence quantity weight can be determined by the number of complete sentences in the candidate video, the duration weight by the video length, the speech rate weight by the speech rate, the video source weight by the video origin, the difficulty recommendation weight by the number of words of the target difficulty level, and the scene weight by the richness of the video scene. Furthermore, the video ranking parameters for the candidate video can be determined based on one or more of these weights: sentence quantity weight, duration weight, speech rate weight, video source weight, difficulty recommendation weight, and scene weight.

[0089] Among them, the fewer complete sentences in a candidate video, the easier it is for users to understand the content of the candidate video. Therefore, the fewer complete sentences in a candidate video, the greater the weight of the number of sentences in the candidate video.

[0090] For video length, different weights can be pre-set for different video lengths. For example, when the video length is greater than or equal to a first length threshold and less than a second length threshold, the candidate video corresponds to the first length weight; when the video length is greater than or equal to a third length threshold and less than the first length threshold, the candidate video corresponds to the second length weight; and when the video length is greater than or equal to the second length threshold, the candidate video corresponds to the third length weight. Specifically, the first length weight is greater than the second length weight, the second length weight is greater than the third length weight, the second length threshold is greater than the first length threshold, and the first length threshold is greater than the third length threshold. For instance, the first length threshold could be 4 seconds, the second length threshold could be 8 seconds, and the third length threshold could be 2 seconds. This allows for the priority recommendation of videos with more suitable lengths to the user.

[0091] Different speech rates can be pre-set with corresponding speech rate weights. For example, when the speech rate is less than a first speech rate threshold, the candidate video corresponds to the first speech rate weight; when the speech rate is greater than or equal to the first speech rate threshold but less than a second speech rate threshold, the candidate video corresponds to the second speech rate weight; and when the speech rate is greater than or equal to the second speech rate threshold, the candidate video corresponds to the third speech rate weight. Specifically, the first speech rate weight is greater than the second speech rate weight, the second speech rate weight is greater than the third speech rate weight, the first speech rate threshold is less than the second speech rate threshold, and the second speech rate threshold is less than the third speech rate threshold. In other words, the faster the speech rate, the lower the speech rate weight of the candidate video. This allows for the priority recommendation of videos with lower speech rates to users, facilitating their learning and comprehension.

[0092] To obtain a sufficient number of candidate videos, they can be sourced from multiple video sources. Since the video quality varies across different sources, a weight can be pre-set for each source; the higher the video quality from a source, the higher its weight. This allows for the priority recommendation of higher-quality videos to users, facilitating high-quality learning and comprehension.

[0093] The percentage of words at the target difficulty level can be determined based on the number of words in candidate videos that meet the target difficulty. The difficulty value of each word in a candidate video can be pre-set; if a word's difficulty value is greater than the target difficulty value, it can be identified as having reached the target difficulty. A higher percentage of words at the target difficulty level indicates a higher level of comprehension difficulty in the candidate videos, resulting in a lower recommendation weight for those videos. This allows for the priority recommendation of videos with lower comprehension difficulty to users, reducing their learning burden.

[0094] Video scene richness can be determined based on the number of scenes in candidate videos. The higher the scene richness, the higher the scene weight, thus allowing for priority recommendation of videos with richer scenes to users. Therefore, the weight of each dimension can be determined for each video, and the sum of the weights across multiple dimensions can be used as the ranking parameter for that video.

[0095] Thus, for each candidate video, its video ranking parameters can be determined based on the video information. Based on the video information of the candidate videos, the video ranking parameters for each candidate video can be comprehensively determined from multiple dimensions, thereby ensuring that the order in which word learning videos are pushed can adapt to the actual needs of users and improve the user experience.

[0096] In S1023, the candidate videos are sorted according to the video sorting parameters to obtain the target video sorting result.

[0097] For example, for each candidate video under a word to be learned, the candidate videos can be sorted in descending order according to the video sorting parameters to obtain the target video sorting results. When the user is learning the word to be learned, high-quality videos with lower learning difficulty and richer scenarios will be recommended to the user first, thereby improving the user's speed of mastering the word to be learned.

[0098] In S1024, if the number of candidate videos is greater than the preset number of videos, the top N candidate videos in the target video ranking result are determined as learning videos, and the display order of each learning video is determined based on the target video ranking result, where N represents the preset number of videos.

[0099] If the number of candidate videos exceeds the preset number of videos, it can be determined that there are a large number of candidate videos for the word to be learned. To avoid users spending too much time learning this word and being unable to move on to the next word, the top N candidate videos in the target video ranking result can be selected as learning videos, and the display order of each learning video can be determined based on the target video ranking result. Here, N represents the preset number of videos, which can be set to 3. The ranking of the top N candidate videos in the target video ranking result determines the display order of the learning videos for the word to be learned.

[0100] If the number of candidate videos is less than the preset number of videos, it can be determined that there are few candidate videos for the word to be learned. For example, if there are two candidate videos, all candidate videos can be selected as learning videos. When the user is learning the word to be learned, the learning videos for the word to be learned can be shown to the user in a random order to reduce the amount of data processing.

[0101] If the number of candidate videos is less than the preset number of videos, the target video ranking for the word to be learned can be determined using the method described above. All candidate videos can then be selected as learning videos, and the display order of each learning video can be determined based on the target video ranking. This allows for priority recommendations of videos with lower learning difficulty and richer scenarios, improving the user's speed of mastering the vocabulary.

[0102] In one possible embodiment, sorting candidate videos according to video sorting parameters to obtain the target video sorting result may include:

[0103] The candidate videos are sorted in descending order of the video sorting parameters to obtain the initial video sorting result;

[0104] If at least two candidate videos belong to different video files, and candidate videos in adjacent positions in the initial video sorting result belong to the same video file, then the candidate video with the later sorting position in the adjacent position will be moved back by a preset number of positions to obtain the target video sorting result, wherein the candidate video is a video slice obtained from the video file.

[0105] For example, a video file can be a long video, such as a movie, containing numerous sentences. To facilitate user learning, the video file can be segmented, for instance, into video clips no longer than 15 seconds. These clips can be used as candidate videos. If adjacent candidate videos in the initial video ranking belong to the same video file, it's highly likely that they express the same theme and are involved in the same context. Recommending these two videos consecutively to the user makes it difficult to recreate multiple usage scenarios for the vocabulary to be learned. Therefore, if at least two candidate videos belong to different video files (i.e., multiple candidate videos are not entirely from the same file), the candidate video ranked later in the adjacent video file can be moved forward a predetermined number of positions to obtain the target video ranking result. For example, if the initial video ranking result for the fourth word to be learned, D, is candidate video d01 (ninth), d02 (tenth), d03 (eleventh), d04 (twelfth), and d05 (thirteenth), and candidate video d02 (tenth) belong to the same video file, while the other candidate videos belong to other video files, then candidate video d02 (tenth) can be moved backward by a preset number of positions (e.g., set to 3). Then the target video ranking result will be candidate video d01 (ninth), d03 (eleventh), d04 (twelfth), d05 (thirteenth), and d02 (tenth).

[0106] In this way, by adjusting the initial video sorting results, videos with lower learning difficulty, richer scenarios, and from different video files can be recommended to users first, so as to restore multiple usage scenarios of the words to be learned and improve the speed at which users master the words.

[0107] In another possible embodiment, sorting the candidate videos according to video sorting parameters to obtain the target video sorting result may include:

[0108] The candidate videos are sorted in descending order of the video sorting parameters to obtain the initial video sorting result;

[0109] If at least two candidate videos represent different themes, and candidate videos in adjacent positions in the initial video ranking result represent the same theme, then the candidate video in the adjacent position that ranks later will be moved back a predetermined number of positions to obtain the target video ranking result.

[0110] For example, different candidate videos represent different themes, such as science fiction, history, and comedy. Candidate videos with the same theme have certain similarities. If candidate videos in adjacent positions in the initial video ranking result represent the same theme, recommending these two videos consecutively to the user may not be able to reproduce multiple usage scenarios of the word to be learned. Therefore, the candidate video ranked later in the adjacent positions can be moved back a predetermined number of positions to obtain the target video ranking result. Taking the initial video ranking result corresponding to the fourth word to be learned, D, as an example, with 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, where the ninth candidate video d01 and the tenth candidate video d02 represent the same theme of science fiction, and the other candidate videos represent the themes of comedy, history, and suspense, respectively, the tenth candidate video d02 can be moved back a predetermined number of positions (for example, set to 3). Then the target video ranking result would be 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.

[0111] In this way, by adjusting the initial video sorting results, videos with lower learning difficulty, richer scenarios, and different themes can be recommended to users to restore multiple usage scenarios of the words to be learned and improve the speed at which users master the words.

[0112] Based on the same inventive concept, this disclosure also provides a word-based video recommendation device. Figure 3 This is a block diagram of a word-based video recommendation apparatus according to one embodiment of the present disclosure. Figure 3 As shown, the video recommendation device 300 for words may include:

[0113] The first determining module 301 is used to determine multiple words to be learned and their word order based on the words in the vocabulary book; the second determining module 302 is used to determine the target definition of the words to be learned and determine the learning video corresponding to each word to be learned based on the target definition; the display module 303 is used to display the learning video corresponding to each word to be learned according to the word order.

[0114] In the above technical solution, multiple words to be learned and their order are determined based on the words in the vocabulary list; the target definition of each word is determined, and a corresponding learning video is selected for each word based on the target definition; the learning video for each word is then displayed according to the word order. In this way, for each word, users can focus on understanding and learning its application under the target definition, improving their mastery and application of the word. Furthermore, by selecting words from the vocabulary list, the time required for learning the entire list at once is avoided, allowing for segmented learning of words within the list. This also reduces the amount of data required for processing words during the learning process, lowering the load on the terminal device. Additionally, the display of learning videos recreates the real-world usage scenarios of the words, effectively improving user concentration and enhancing learning enjoyment, reducing the tedium of vocabulary learning, and further accelerating word mastery.

[0115] Optionally, the first determining module 301 includes:

[0116] The first determining submodule is used to determine all words in the vocabulary book as the words to be learned if the number of words in the vocabulary book does not exceed a preset number of words; the second determining submodule is used to determine the word sorting parameters of each word to be learned based on the word information of the word to be learned, wherein the word information includes one or more of the following: addition time, word exposure frequency, word mastery level, and word collection method; the third determining submodule is used to sort the words to be learned according to the word sorting parameters to determine the word sorting of the words to be learned.

[0117] Optionally, the first determining module 301 includes:

[0118] The fourth determining submodule is used to determine a first word sorting parameter for each word based on its first word information if the number of words in the vocabulary book exceeds a preset number of words. The first word information includes the addition time and the number of times the word is exposed. The fifth determining submodule is used to select a preset number of words according to the first word sorting parameter in descending order, and determine them as the words to be learned. The sixth determining submodule is used to determine a second word sorting parameter for each word to be learned based on its second word information. The second word information includes one or more of the first word information, word mastery level, and word collection methods. The seventh determining submodule is used to sort the words to be learned according to the second word sorting parameter, and determine the word order of the words to be learned.

[0119] Optionally, the second determining module 302 includes:

[0120] The eighth determining submodule is used to determine the definition represented by the disambiguation result as the target definition if the word to be learned has a corresponding disambiguation result, wherein the disambiguation result is used to represent the actual definition of the word to be learned from the sentence in the sentence; the ninth determining submodule is used to determine the first definition of the word to be learned in the dictionary as the target definition if the word to be learned does not have a corresponding disambiguation result.

[0121] Optionally, the second determining module 302 includes:

[0122] The tenth determining submodule is used to determine multiple candidate videos for the word to be learned based on the target definition; the eleventh determining submodule is used to determine the video sorting parameters of the candidate videos based on the video information of the candidate videos, wherein the video information includes one or more of the following: the number of complete sentences in the candidate videos, video duration, speech rate, video source, the proportion of words of target difficulty, and video scene richness; the obtaining submodule is used to sort the candidate videos according to the video sorting parameters to obtain the target video sorting result; the twelfth determining submodule is used to determine the top N candidate videos in the target video sorting result as the learning videos if the number of candidate videos is greater than the preset number of videos, and to determine the display order of each learning video based on the target video sorting result, wherein N is used to represent the preset number of videos.

[0123] Optionally, obtaining submodules includes:

[0124] The sorting submodule is used to sort the candidate videos in descending order according to the video sorting parameters to obtain an initial video sorting result; the first moving submodule is used to move the candidate video with the later sorting position in the adjacent positions backward by a preset number of positions to obtain the target video sorting result if at least two of the candidate videos belong to different video files and the candidate videos in adjacent positions in the initial video sorting result belong to the same video file, wherein the candidate videos are video slices obtained from the video files.

[0125] Optionally, the acquisition submodule also includes:

[0126] The second moving submodule is used to move the candidate video that is ranked later in the adjacent positions backward by a predetermined number of positions if at least two candidate videos represent different themes and the candidate videos in adjacent positions in the initial video ranking result represent the same theme, so as to obtain the target video ranking result.

[0127] Optionally, the tenth determining submodule includes:

[0128] The thirteenth determining submodule is used to determine the associated videos of the word to be learned under the target definition from the video library; the fourteenth determining submodule is used to determine the number of associated videos of each word in a group of words to be learned if the associated videos of multiple words to be learned include the same video; the first deduplication submodule is used to determine the associated video of the word with the fewest associated videos as the candidate video of the word if the number of associated videos of the words to be learned is different, and for other words other than the word with the fewest associated videos, the videos of the associated videos of the word other than the same video are used as the candidate videos of the word; the second deduplication submodule is used to determine the associated video of the word with the highest word ranking as the candidate video of the word if the number of associated videos of the words to be learned is the same, and for other words other than the word with the highest word ranking, the videos of the associated videos of the word other than the same video are used as the candidate videos of the word.

[0129] The following is for reference. Figure 4 This diagram illustrates a structural schematic of an electronic device 600 suitable for implementing embodiments of the present disclosure. The terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0130] like Figure 4 As shown, electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 601, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 602 or a program loaded from storage device 608 into random access memory (RAM) 603. RAM 603 also stores various programs and data required for the operation of electronic device 600. Processing device 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0131] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic device 600 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 4 An electronic device 600 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0132] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a storage device 608, or installed from a ROM 602. When the computer program is executed by the processing device 601, it performs the functions defined in the methods of embodiments of this disclosure.

[0133] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0134] In some implementations, the client can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0135] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0136] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to:

[0137] Based on the words in the vocabulary list, determine multiple words to be learned and their word order; determine the target definition of each word to be learned, and based on the target definition, determine the corresponding learning video for each word to be learned; display the corresponding learning video for each word to be learned according to the word order.

[0138] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0139] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0140] The modules described in the embodiments of this disclosure can be implemented in software or hardware. The names of the modules are not necessarily limiting in certain circumstances; for example, the third determining submodule can also be described as a word sorting module.

[0141] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0142] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0143] According to one or more embodiments of this disclosure, Example 1 provides a word-based video recommendation method, including:

[0144] Based on the words in the vocabulary list, determine multiple words to be learned and their word order; determine the target definition of each word to be learned, and based on the target definition, determine the corresponding learning video for each word to be learned; display the corresponding learning video for each word to be learned according to the word order.

[0145] According to one or more embodiments of this disclosure, Example 2 provides the method of Example 1, wherein determining a plurality of words to be learned and a word order of the words to be learned based on words in a wordbook includes:

[0146] If the number of words in the vocabulary book does not exceed the preset number of words, then all words in the vocabulary book are identified as the words to be learned; for each word to be learned, the word sorting parameters of the word to be learned are determined according to the word information of the word to be learned, wherein the word information includes one or more of the following: addition time, word exposure frequency, word mastery level, and word collection method; according to the word sorting parameters, the words to be learned are sorted to determine the word order of the words to be learned.

[0147] According to one or more embodiments of this disclosure, Example 3 provides the method of Example 1, wherein determining a plurality of words to be learned and a word order of the words to be learned based on words in a wordbook includes:

[0148] If the number of words in the vocabulary book exceeds a preset number of words, then for each word, a first word sorting parameter is determined based on the word's first word information, wherein the first word information includes the addition time and the number of times the word has been exposed; words of a preset number are selected in descending order of the first word sorting parameter and determined as the words to be learned; for each word to be learned, a second word sorting parameter is determined based on the word's second word information, wherein the second word information includes one or more of the first word information, word mastery level, and word collection methods; the words to be learned are sorted according to the second word sorting parameter to determine the word order of the words to be learned.

[0149] According to one or more embodiments of this disclosure, Example 4 provides the method of Example 1, wherein determining the target definition of the word to be learned includes:

[0150] If the word to be learned has a corresponding disambiguation result, the definition represented by the disambiguation result is determined as the target definition, wherein the disambiguation result is used to represent the actual definition of the word to be learned from the sentence in that sentence; if the word to be learned does not have a corresponding disambiguation result, the first definition of the word to be learned in the dictionary is determined as the target definition.

[0151] According to one or more embodiments of this disclosure, Example 5 provides the method of Example 1, wherein determining the learning video corresponding to each word to be learned based on the target definition includes:

[0152] Based on the target definition, multiple candidate videos for the word to be learned are determined; based on the video information of the candidate videos, video sorting parameters for the candidate videos are determined, wherein the video information includes one or more of the following: the number of complete sentences in the candidate videos, video duration, speaking speed, video source, the proportion of words of target difficulty, and video scene richness; based on the video sorting parameters, the candidate videos are sorted to obtain a target video sorting result; if the number of candidate videos is greater than a preset number of videos, the top N candidate videos in the target video sorting result are determined as the learning videos, and the display order of each learning video is determined based on the target video sorting result, where N represents the preset number of videos.

[0153] According to one or more embodiments of this disclosure, Example 6 provides the method of Example 5, wherein sorting the candidate videos according to the video sorting parameters to obtain a target video sorting result includes:

[0154] The candidate videos are sorted in descending order according to the video sorting parameters to obtain an initial video sorting result. If at least two candidate videos belong to different video files, and the candidate videos in adjacent positions in the initial video sorting result belong to the same video file, then the candidate video in the adjacent position that is later in the sorting is moved back by a preset number of positions to obtain the target video sorting result. The candidate videos are video slices obtained from the video files.

[0155] According to one or more embodiments of this disclosure, Example 7 provides the method of Example 5, wherein sorting the candidate videos according to the video sorting parameters to obtain a target video sorting result includes:

[0156] The candidate videos are sorted in descending order according to the video sorting parameters to obtain an initial video sorting result. If at least two candidate videos represent different themes, and the candidate videos in adjacent positions in the initial video sorting result represent the same theme, the candidate video in the adjacent position that is later in the sorting is moved back by a preset number of positions to obtain the target video sorting result.

[0157] According to one or more embodiments of this disclosure, Example 8 provides the method of Example 5, wherein determining a plurality of candidate videos for the word to be learned based on the target definition includes:

[0158] Based on the target definition, the associated videos of the words to be learned under the target definition are determined from the video library. If the associated videos of multiple words to be learned include the same video, then for each group of words to be learned corresponding to the same video, the number of associated videos for each word in the group of words to be learned is determined. If the number of associated videos is different in the group of words to be learned, the associated video of the word with the fewest associated videos is determined as the candidate video of that word. For other words, except for the word with the fewest associated videos, the videos in the associated videos of that word other than the same video are taken as candidate videos of that word. If the number of associated videos is the same in the group of words to be learned, the associated video of the word ranked first is determined as the candidate video of that word. For other words, except for the word ranked first, the videos in the associated videos of that word other than the same video are taken as candidate videos of that word.

[0159] According to one or more embodiments of this disclosure, Example 9 provides a word-based video recommendation apparatus, comprising:

[0160] The first determining module is used to determine multiple words to be learned and their word order based on the words in the vocabulary book; the second determining module is used to determine the target definition of the words to be learned and, based on the target definition, determine the learning video corresponding to each word to be learned; the display module is used to display the learning video corresponding to each word to be learned according to the word order.

[0161] According to one or more embodiments of the present disclosure, Example 10 provides a computer-readable medium having a computer program stored thereon that, when executed by a processing device, implements the steps of the method described in any of Examples 1 to 8.

[0162] According to one or more embodiments of this disclosure, Example 11 provides an electronic device, including: a storage device having a computer program stored thereon; and a processing device for executing the computer program in the storage device to implement the steps of the method described in any of Examples 1 to 8.

[0163] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0164] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0165] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative forms of implementing the claims. Regarding the apparatus in the above embodiments, the specific manner in which the various modules perform their operations has been described in detail in the embodiments relating to the method, and will not be elaborated upon here.

Claims

1. A word-based video recommendation method, characterized in that, include: Based on the words in the vocabulary book, determine multiple words to be learned and their word order; Determine the target definition of the word to be learned, and based on the target definition, determine the corresponding learning video for each word to be learned; The learning video corresponding to each of the words to be learned is displayed according to the word order. The step of determining the learning video corresponding to each word to be learned based on the target definition includes: Based on the target definition, multiple candidate videos for the word to be learned are determined; Based on the video information of the candidate videos, the video ranking parameters of the candidate videos are determined, wherein the video information includes one or more of the following: the number of complete sentences in the candidate videos, video duration, speech rate, video source, percentage of words of target difficulty, and richness of video scenes. The candidate videos are sorted according to the video sorting parameters to obtain the target video sorting result; If the number of candidate videos is greater than the preset number of videos, the top N candidate videos in the target video sorting result are determined as the learning videos, and the display order of each learning video is determined based on the target video sorting result, where N represents the preset number of videos.

2. The method according to claim 1, characterized in that, The step of determining multiple words to be learned and their word order based on words in the vocabulary list includes: If the number of words in the vocabulary book does not exceed the preset number of words, then all the words in the vocabulary book are identified as the words to be learned. For each word to be learned, the word sorting parameters of the word to be learned are determined according to the word information of the word to be learned, wherein the word information includes one or more of the following: addition time, word exposure frequency, word mastery level, and word collection method; The words to be learned are sorted according to the word sorting parameters to determine the word sorting order.

3. The method according to claim 1, characterized in that, The step of determining multiple words to be learned and their word order based on words in the vocabulary list includes: If the number of words in the vocabulary book exceeds the preset number of words, then for each word, the first word sorting parameter of the word is determined according to the first word information of the word, wherein the first word information includes the addition time and the number of times the word is exposed; According to the first word sorting parameter in descending order, select a preset number of words and determine them as the words to be learned; For each word to be learned, a second word sorting parameter is determined based on the second word information of the word to be learned, wherein the second word information includes one or more of the first word information, word mastery level, and word collection method; The words to be learned are sorted according to the second word sorting parameter to determine the word sorting of the words to be learned.

4. The method according to claim 1, characterized in that, Determining the target definition of the word to be learned includes: If the word to be learned has a corresponding disambiguation result, then the definition represented by the disambiguation result is determined as the target definition, wherein the disambiguation result is used to represent the actual definition of the word to be learned from the sentence in the sentence; If the word to be learned does not have a corresponding disambiguation result, then the first definition of the word to be learned in the dictionary is determined as the target definition.

5. The method according to claim 1, characterized in that, The step of sorting the candidate videos according to the video sorting parameters to obtain the target video sorting result includes: The candidate videos are sorted in descending order according to the video sorting parameters to obtain an initial video sorting result; If at least two candidate videos belong to different video files, and candidate videos in adjacent positions in the initial video sorting result belong to the same video file, then the candidate video in the adjacent position that is later in the sorting is moved backward by a preset number of positions to obtain the target video sorting result, wherein the candidate video is a video slice obtained from the video file.

6. The method according to claim 1, characterized in that, The step of sorting the candidate videos according to the video sorting parameters to obtain the target video sorting result includes: The candidate videos are sorted in descending order according to the video sorting parameters to obtain an initial video sorting result; If at least two candidate videos represent different themes, and candidate videos in adjacent positions in the initial video ranking result represent the same theme, then the candidate video in the adjacent positions that is ranked later is moved backward by a preset number of positions to obtain the target video ranking result.

7. The method according to claim 1, characterized in that, The step of determining multiple candidate videos for the word to be learned based on the target definition includes: Based on the target definition, identify the associated videos of the word to be learned under the target definition from the video library; If multiple words to be learned correspond to the same video in the associated videos, then for each group of words to be learned corresponding to the same video, determine the number of associated videos for each word in that group of words to be learned. In the group of words to be learned, if the number of associated videos is different, the associated video of the word with the fewest associated videos is determined as the candidate video of that word. For other words other than the word with the fewest associated videos, the videos of the associated videos of that word other than the videos that are the same as the original video are taken as the candidate videos of that word. In the group of words to be learned, if the number of associated videos is the same, the associated video of the word with the highest word ranking is determined as the candidate video of that word. For other words besides the word with the highest word ranking, the videos in the associated videos of that word other than the same video are taken as the candidate videos of that word.

8. A word-based video recommendation device, characterized in that, include: The first determining module is used to determine multiple words to be learned and the word order of the words to be learned based on the words in the vocabulary book; The second determining module is used to determine the target definition of the word to be learned, and to determine the learning video corresponding to each word to be learned based on the target definition. The display module is used to sort the words and display the learning video corresponding to each word to be learned; The second determining module is specifically used to: determine multiple candidate videos for the word to be learned based on the target definition; determine video sorting parameters for the candidate videos based on the video information of the candidate videos, wherein the video information includes one or more of the following: the number of complete sentences in the candidate videos, video duration, speaking speed, video source, the proportion of words of target difficulty, and video scene richness; sort the candidate videos according to the video sorting parameters to obtain a target video sorting result; if the number of candidate videos is greater than a preset number of videos, then the top N candidate videos in the target video sorting result are determined as the learning videos, and the display order of each learning video is determined based on the target video sorting result, wherein N represents the preset number of videos.

9. A computer-readable medium having a computer program stored thereon, characterized in that, When executed by the processing device, the program implements the steps of the method described in any one of claims 1-7.

10. An electronic device, characterized in that, include: A storage device on which computer programs are stored; A processing device for executing the computer program in the storage device to implement the steps of the method according to any one of claims 1-7.

Images