CN114519347A

CN114519347A - Method and device for generating conversation content for language and vocabulary learning training

Info

Publication number: CN114519347A
Application number: CN202111621285.7A
Authority: CN
Inventors: 朱奇峰
Original assignee: Suzhou Qingrui Intelligent Technology Co ltd
Current assignee: Suzhou Qingrui Intelligent Technology Co ltd
Priority date: 2021-12-28
Filing date: 2021-12-28
Publication date: 2022-05-20

Abstract

The invention discloses a method and a device for generating conversation contents for language and vocabulary learning training, which relate to the technical field of artificial intelligence, and the specific scheme comprises the following steps: the computer device obtains at least one target word, the at least one target word is used for sentence making training of a user, responds to input operation of the user, obtains user input conversation content, and generates conversation content based on the user input conversation content and the at least one target word, wherein the conversation content is used for guiding the user to use the at least one target word in a conversation. The embodiment of the invention automatically converses with the user by the conversation content generated based on the conversation content input by the user and the at least one target word, thereby creating a real interactive language communication environment, guiding the user to use the at least one target word for sentence making practice, helping the user to more effectively master the usage of the at least one target word, and improving the word learning efficiency.

Description

Method and device for generating conversation content for language and vocabulary learning training

Technical Field

The invention relates to the technical field of artificial intelligence, in particular to a method and a device for generating conversation content for language and vocabulary learning training.

Background

In language learning, students have little impression of new words just learned and are not familiar with the usage of new words. In order to deepen the impression and deeply master the usage of the new words, students can learn the new words through sentence making practice in a man-machine interaction mode.

However, the man-machine interaction mode in the prior art is simple, context interaction is lacked, and the efficiency of word learning is low.

Disclosure of Invention

The invention provides a method and a device for generating conversation contents for language and vocabulary learning training, which solve the problems of simple form, lack of context interaction and low efficiency of word learning.

In order to achieve the purpose, the invention adopts the following technical scheme:

in a first aspect, the present invention provides a method for generating conversational content for language and vocabulary learning training, the method comprising:

obtaining at least one target word, wherein the at least one target word is used for sentence making training of a user;

responding to the input operation of a user, and acquiring the input session content of the user;

generating conversation content based on the user input conversation content and the at least one target word; the conversation content is used to guide the user to use at least one target word in the conversation.

With reference to the first aspect, in one possible implementation manner, the user input session content includes at least one of: inputting a sentence, inputting voice data, the input voice data corresponding to the input sentence; the session content includes at least one of: conversation sentences, conversation voice data, conversation pictures and conversation videos; the conversation voice data is obtained by voice conversion of conversation sentences, the picture content of the conversation pictures comprises the conversation sentences, and the conversation video is a video generated based on the conversation sentences.

With reference to the first aspect, in one possible implementation manner, generating conversation content based on user input conversation content and at least one target word includes: determining M alternative conversation contents matched with the conversation contents input by the user, wherein M is a positive integer; when M is equal to 1, determining the alternative session content as the session content; when M is larger than 1, determining a related word according to at least one target word, determining the degree of association between the related word and each alternative conversation content, and determining the alternative conversation content corresponding to the maximum degree of association in the M degrees of association as the conversation content; wherein the associated words comprise words with the same or similar semantics as the words in the at least one target word, and the relevancy is used for indicating the semantic similarity of the associated words and each alternative conversation content.

With reference to the first aspect, in one possible implementation manner, determining a degree of association of the associated word with each alternative conversation content includes: acquiring keywords in each alternative conversation content according to the part of speech of the words included in each alternative conversation content; determining the association degree of each association word and each alternative conversation content according to the association degree of each association word and each keyword included by each alternative conversation content; and determining the association degree of each alternative conversation content according to the association degree of each association word and each alternative conversation content.

With reference to the first aspect, in one possible implementation manner, the determining M candidate session contents that match the user input session content includes: determining the similarity between the user input conversation content and each sentence in a preset sentence library; and determining sentences with the similarity larger than a preset threshold value in a preset sentence library as the alternative conversation contents to obtain M alternative conversation contents.

With reference to the first aspect, in a possible implementation manner, the method for generating conversation content for language and vocabulary learning training further includes: determining the complexity of the user input conversation content according to the number of key words and a grammatical structure in the user input conversation content; acquiring the occurrence times of scoring terms in user input conversation content, wherein the scoring terms are terms in at least one target term; and determining the evaluation parameters corresponding to the user input conversation content according to the complexity of the user input conversation content and the occurrence frequency of the scoring words in the user input conversation content.

With reference to the first aspect, in a possible implementation manner, the method for generating conversation content for language and vocabulary learning training further includes: after obtaining the conversation content input by the user, increasing the recorded sentence making times by a preset value; under the condition that the sentence making times after the preset value is increased are equal to the preset times, responding to the operation of ending the conversation of the user, and outputting prompt information, wherein the prompt information is used for prompting the user to share the conversation; and responding to the confirmation operation of the user on the prompt message, and transmitting the session to the sharing platform.

With reference to the first aspect, in one possible implementation manner, the conversation content includes a conversation sentence and conversation voice data, and the method for generating conversation content for language and vocabulary learning training further includes: outputting conversation voice data, wherein the conversation voice data is used for guiding the voice training of the user; after outputting the conversational speech data, a conversational sentence is displayed.

With reference to the first aspect, in a possible implementation manner, the method for generating conversation content for language and vocabulary learning training further includes: responding to the translation operation of the user on the conversation, converting the conversation content input by the user into first data of a preset language type, and converting the conversation content into second data of the preset language type; the first data and the second data are displayed in a dialog interface.

With reference to the first aspect, in one possible implementation manner, the obtaining at least one target word includes: responding to the operation of inputting words in a dialogue interface by a user, and acquiring at least one target word; or responding to the voice input of the user in the dialogue interface, acquiring target voice data, and acquiring at least one target word according to the target voice data; or displaying a word bank button in the conversation interface, and displaying a word list in the conversation interface in response to the operation of the user on the word bank button, wherein the word list comprises words in a preset word bank; responding to the selection operation of a user in the word list, and acquiring at least one target word; or responding to the word training instruction, acquiring word learning data, and taking words in a preset time period in the word learning data as at least one target word.

In a second aspect, the present invention provides an apparatus for generating conversational content for language and vocabulary learning training, the apparatus comprising:

the acquisition module is used for acquiring at least one target word, and the at least one target word is used for sentence making training of a user; responding to the input operation of a user, and acquiring the input session content of the user;

the generation module is used for generating conversation content based on the user input conversation content and at least one target word; the conversation content is used to guide the user to use at least one target word in the conversation.

With reference to the second aspect, in one possible implementation manner, the user input session content includes at least one of: inputting a sentence, inputting voice data, the input voice data corresponding to the input sentence; the session content includes at least one of: conversation sentences, conversation voice data, conversation pictures and conversation videos; the conversation voice data is obtained by voice conversion of conversation sentences, the picture content of the conversation pictures comprises the conversation sentences, and the conversation video is a video generated based on the conversation sentences.

With reference to the second aspect, in a possible implementation manner, the generating module is specifically configured to: determining M alternative conversation contents matched with the conversation contents input by the user, wherein M is a positive integer; when M is equal to 1, determining the alternative session content as the session content; when M is larger than 1, determining a related word according to at least one target word, determining the degree of association between the related word and each alternative conversation content, and determining the alternative conversation content corresponding to the maximum degree of association in the M degrees of association as the conversation content; wherein the associated words comprise words with the same or similar semantics as the words in the at least one target word, and the relevancy is used for indicating the semantic similarity of the associated words and each alternative conversation content.

With reference to the second aspect, in a possible implementation manner, the generating module is specifically configured to: acquiring keywords in each alternative conversation content according to the part of speech of the words included in each alternative conversation content; determining the association degree of each association word and each alternative conversation content according to the association degree of each association word and each keyword included by each alternative conversation content; and determining the association degree of each alternative conversation content according to the association degree of each association word and each alternative conversation content.

With reference to the second aspect, in a possible implementation manner, the generating module is specifically configured to: determining the similarity between the user input conversation content and each sentence in a preset sentence library; and determining sentences with the similarity larger than a preset threshold value in a preset sentence library as the alternative conversation contents to obtain M alternative conversation contents.

With reference to the second aspect, in a possible implementation manner, the generating apparatus of conversation content for language and vocabulary learning training further includes an evaluation module. An evaluation module to: and determining the complexity of the user input conversation content according to the number of the keywords and the syntactic structure in the user input conversation content. The acquisition module is further used for acquiring the occurrence frequency of the scoring terms in the user input conversation content, and the scoring terms are terms in at least one target term. And the evaluation module is also used for determining the evaluation parameters corresponding to the user input conversation content according to the complexity of the user input conversation content and the occurrence frequency of the scoring words in the user input conversation content.

With reference to the second aspect, in a possible implementation manner, the apparatus for generating conversation content for language and vocabulary learning training further includes an adding module, an outputting module, and a sharing module. An adding module for: and after the conversation content input by the user is acquired, increasing the recorded sentence making times by a preset value. And the output module is used for responding to the session ending operation of the user and outputting prompt information under the condition that the sentence making times after the preset value is increased are equal to the preset times, wherein the prompt information is used for prompting the user to share the session. And the sharing module is used for responding to the confirmation operation of the user on the prompt message and transmitting the conversation to the sharing platform.

With reference to the second aspect, in one possible implementation manner, the conversation content includes a conversation sentence and conversation voice data, and the output module is further configured to: outputting conversation voice data, wherein the conversation voice data is used for guiding the voice training of the user; after outputting the conversational speech data, a conversational sentence is displayed.

With reference to the second aspect, in a possible implementation manner, the apparatus for generating conversation content for language and vocabulary learning training further includes a translation module, where the translation module is configured to: responding to the translation operation of the user on the conversation, converting the conversation content input by the user into first data of a preset language type, and converting the conversation content into second data of the preset language type; the first data and the second data are displayed in a dialog interface.

With reference to the second aspect, in a possible implementation manner, the obtaining module is specifically configured to: responding to the operation of inputting words in a dialogue interface by a user, and acquiring at least one target word; or responding to the voice input of the user in the dialogue interface, acquiring target voice data, and acquiring at least one target word according to the target voice data; or displaying a word bank button in the conversation interface, and displaying a word list in the conversation interface in response to the operation of the user on the word bank button, wherein the word list comprises words in a preset word bank; responding to the selection operation of a user in the word list, and acquiring at least one target word; or responding to the word training instruction, acquiring word learning data, and taking words in a preset time period in the word learning data as at least one target word.

In a third aspect, the present invention provides a computer apparatus comprising: a processor and a memory. The memory is for storing computer program code, the computer program code including computer instructions. When the processor executes the computer instructions, the computer device performs the method of generating conversational content for language and vocabulary learning training as described in the first aspect and any one of its possible implementations.

In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon computer instructions which, when run on a computer device, cause the computer device to perform a method of generating conversational content for language and vocabulary learning training as described in the first aspect or any one of its possible implementations.

According to the generation method of the conversation content for the language and vocabulary learning training, provided by the embodiment of the invention, the computer equipment acquires at least one target word, the at least one target word is used for sentence making training of a user, responds to the input operation of the user, acquires the user input conversation content, and generates the conversation content based on the user input conversation content and the at least one target word, wherein the conversation content is used for guiding the user to use the at least one target word in the conversation. The embodiment of the invention automatically converses with the user by the conversation content generated based on the conversation content input by the user and the at least one target word, thereby creating a real interactive language communication environment, guiding the user to use the at least one target word for sentence making practice, helping the user to more effectively master the usage of the at least one target word, and improving the word learning efficiency.

Drawings

FIG. 1 is a schematic diagram of an application environment of a method for generating conversational content for language and vocabulary learning training according to an embodiment of the present invention;

FIG. 2 is a flowchart illustrating a method for generating conversational content for language and vocabulary learning training according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of a dialog interface provided in an embodiment of the present invention;

fig. 4 is a second schematic diagram of a dialog interface according to the embodiment of the present invention;

fig. 5 is a third schematic diagram of a dialog interface according to an embodiment of the present invention;

FIG. 6 is a fourth schematic diagram of a dialog interface according to an embodiment of the present invention;

FIG. 7 is a second flowchart illustrating a method for generating conversation content for language and vocabulary learning training according to an embodiment of the present invention;

FIG. 8 is a third flowchart illustrating a method for generating conversation content for language and vocabulary learning training according to an embodiment of the present invention;

FIG. 9 is a fourth flowchart illustrating a method for generating conversational content for language and vocabulary learning training according to an embodiment of the present invention;

FIG. 10 is a fifth flowchart illustrating a method for generating conversational content for language and vocabulary learning training according to an embodiment of the present invention;

FIG. 11 is a fifth illustration of a dialog interface according to an embodiment of the present invention;

FIG. 12 is a flowchart illustrating a sixth method for generating conversation content for language and vocabulary learning training according to an embodiment of the present invention;

FIG. 13 is a sixth schematic view of a dialog interface according to an embodiment of the present invention;

FIG. 14 is a block diagram illustrating an apparatus for generating conversation contents for training language and vocabulary according to an embodiment of the present invention;

FIG. 15 is a second schematic diagram illustrating an apparatus for generating conversation contents for training language and vocabulary learning according to an embodiment of the present invention;

fig. 16 is a third schematic composition diagram of an apparatus for generating conversation contents for language and vocabulary learning training according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

In the following, the terms "first", "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the embodiments of the present disclosure, "a plurality" means two or more unless otherwise specified. Additionally, the use of "based on" or "according to" means open and inclusive, as a process, step, calculation, or other action that is "based on" or "according to" one or more stated conditions or values may in practice be based on additional conditions or exceeding the stated values.

In order to solve the problems of simple form of word learning, lack of context interaction and low efficiency of word learning, the embodiment of the invention provides a method and a device for generating conversation content for language and vocabulary learning training.

Therefore, the embodiment of the invention automatically converses with the user through the conversation content generated based on the conversation content input by the user and the at least one target word, thereby creating a real interactive language communication environment, guiding the user to use the at least one target word for sentence making practice, helping the user to more effectively master the usage of the at least one target word, and improving the word learning efficiency.

The execution subject of the method for generating the conversation content for the language and vocabulary learning training provided by the embodiment of the invention is a device for generating the conversation content for the language and vocabulary learning training, and the device for generating the conversation content for the language and vocabulary learning training can be computer equipment, a processor of the computer equipment, or a client installed in the computer equipment. The embodiment of the invention is described by taking the example that the computer device executes the generation method of the conversation content for language and vocabulary learning training.

In one scenario, the computer device may be a terminal device, and the method for generating conversation content for language and vocabulary learning training according to the embodiment of the present invention may be executed by the terminal device. For example, the terminal device may be a mobile phone, a tablet computer, a notebook computer, or the like.

In another scenario, the computer device may be a terminal device or a server, and the terminal device and the server may jointly perform the generation method of the session content for language and vocabulary learning training according to the embodiment of the present invention. The server may be one server, a server cluster, or a cloud platform computing center. When the server is a server cluster, different servers included in the server cluster may provide different services for the terminal device, such as voice recognition, text matching, and the like.

Fig. 1 is a schematic application environment diagram of a possible session content generation method for language and vocabulary learning training according to an embodiment of the present invention. As shown in fig. 1, a terminal device 10, a speech recognition server 11, and a text matching server 12 may be included in the scenario. The terminal device 10 is connected to the voice recognition server 11 and the text matching server 12 in a wired or wireless communication manner.

And the terminal equipment 10 is used for acquiring at least one target word and responding to the input operation of the user to acquire the conversation content input by the user. The terminal device 10 is further configured to generate conversation content based on the user input conversation content and the at least one target word. Wherein the user input session content comprises at least one of: input sentence, input voice data. The session content includes at least one of: conversation sentences, conversation voice data, conversation pictures and conversation videos.

Illustratively, when the input operation by the user is voice input, the content of the user input session acquired by the terminal device 10 is input voice data. The terminal device 10 is also configured to send a speech recognition request containing sentence speech data to the speech recognition server 11.

And the voice recognition server 11 is used for recognizing the sentence voice data, obtaining a corresponding input sentence, and returning the input sentence to the terminal device 10.

The terminal device 10 is further configured to send the content of the user input session to the text matching server 12 by carrying the content in a text matching request. And the text matching server 12 is used for determining alternative conversation content matched with the conversation content input by the user. And is further configured to determine session content from the M candidate session contents and transmit the session content to the terminal device 10 when M is greater than 1. And a terminal device 10 for outputting the received session content.

Based on the introduction of the application environment of the above-described generation method of the conversation content for language and vocabulary learning training, the embodiment of the present invention provides a generation method of the conversation content for language and vocabulary learning training. As shown in fig. 2, the generation method of conversation contents for language and vocabulary learning training may include the following steps S201 to S203.

It should be noted that at least one target word involved in the embodiments of the present invention may be a word of any language type. For example, the target word may be an english word, may also be a chinese word, and may also be a french word, and the embodiment of the present invention is not particularly limited. For convenience of understanding, the embodiment of the present invention is exemplified by taking the target word as an english word, that is, by performing sentence making practice on the english word.

S201, the terminal equipment obtains at least one target word, and the at least one target word is used for sentence making training.

The sentence making training application is installed in the terminal equipment, when sentence making training is required to be carried out on a plurality of words through the sentence making training application, a user can open the sentence making training application, the terminal equipment can respond to the operation of the user, a conversation interface is displayed, and at least one target word is obtained in the conversation interface. The at least one target word may be a word input by the user, a word recently learned by the user and directly obtained, or a word selected by the user in a preset word library.

Optionally, the terminal device may acquire the at least one target word in the following manners, and the specific manner of acquiring the at least one target word is not limited in the embodiment of the present invention.

In one possible implementation manner, when a user inputs at least one target word in a dialogue interface of a sentence making training application, the terminal device may obtain the at least one target word in response to an input operation of the user in the dialogue interface.

In another possible implementation manner, the terminal device may obtain the target speech data in response to a speech input operation of the user in the dialog interface, and obtain at least one target word according to the target speech data.

Optionally, the manner in which the terminal device obtains the at least one target word according to the target speech data may be that the terminal device recognizes the target speech data as the at least one target word according to a pre-stored speech recognition model. Alternatively, the terminal device may send a voice recognition request including the target voice data to the voice recognition server, so that the voice recognition server recognizes the target voice data as at least one target word and returns the target word to the terminal device. The terminal device can receive at least one target word sent by the voice recognition server.

In another possible implementation manner, a word bank button is displayed in the dialog interface, and when the user clicks the word bank button, the terminal device may display a word list in the dialog interface in response to the user operating the word bank button, where the word list includes words in the preset word bank. The terminal equipment can acquire at least one target word according to the selection operation of the user in the word list.

In another possible implementation manner, the terminal device may respond to the word training instruction, acquire the word learning data, and use a word in the word learning data for a preset time period as at least one target word. Specifically, the terminal device may respond to an operation of opening a sentence making training application by a user, display a dialogue interface, acquire the word learning data, use a word in a preset time period in the word learning data as at least one target word, and display the at least one target word in the dialogue interface.

It is to be understood that the term learning data may be data in another term learning application installed in the terminal device, the term learning data may include english words recently learned by the user, and after the sentence making training application is opened, the terminal device may use at least one english word recently learned in the term learning data as the at least one target term. Or, the word learning data may be history data of a sentence making training application, the word learning data may include english words recently used by the user for making a sentence, and the terminal device may use at least one english word poorly grasped in the history data as the at least one target word after the sentence making training application is opened. Of course, the word learning data may be other data including a plurality of words.

This embodiment provides the acquisition mode of abundant diversified at least one target word for the user can carry out the training of pertinence word as required and conveniently, has improved the flexibility of word training.

Illustratively, when a user opens a sentence making training application, the terminal device may display an initial dialog interface in response to an opening operation of the user, and acquire word learning data if acquiring five words that the user has learned last from the word learning data includes: again, school, communication, nice, slow. Then, as shown in fig. 3, the terminal device may pop up a sentence making prompt box in the initial dialog interface, where the sentence making prompt box includes a word such as "please make a sentence using the following words and talk to me: the sentence making prompt information of again, school, communication, nice, slow style, and buttons such as "chatty" and "OK" styles.

When the user clicks the "OK" button, the terminal device may close the sentence creation prompt box and display the dialog interface as shown in fig. 4 in response to the user's operation of the "OK" button. As shown in fig. 4, the terminal device may display "√" in front of a button shown as "word sentence making mode" in the dialog interface to indicate that the current dialog interface has entered a word training state. As shown in fig. 4, the terminal device may display an open sentence, for example, "I am used to interior myself to you, Tom" in the dialog interface, thereby prompting and guiding the user to start sentence-making practice. As shown in fig. 4, the dialog interface may further include prompt information of sentence-making words, such as "sentence-making word: again, school, communication, nice, slow ", in order to remind the user to make sentences using words in the prompt message as much as possible.

S202, the terminal equipment responds to the input operation of the user and obtains the input session content of the user.

The input operation may be a voice input operation or a text input operation.

Optionally, the user input session content may include at least one of: input sentence, input voice data. The input speech data corresponds to an input sentence.

Optionally, when the user performs a voice input operation on the dialog interface, the terminal device may respond to the voice input operation of the user on the dialog interface, acquire input voice data input by the user, and convert the input voice data into a corresponding input sentence through a voice recognition technology. Alternatively, after acquiring input speech data input by the user, the terminal device may send a speech recognition request including the input speech data to the speech recognition server, and receive a speech recognition result, i.e., an input sentence, sent by the speech recognition server.

Optionally, when the user performs a text input operation on the dialog interface, the terminal device may directly obtain the input sentence in response to the text input operation of the user on the dialog interface.

It is to be understood that the input sentence may be a sentence input to the dialog interface after the user makes a sentence according to the at least one target word.

Illustratively, a voice input operation is taken as an example. In conjunction with fig. 4, when a user needs to perform a voice input operation, the user can click a voice input button in the dialog interface as shown in fig. 4. The terminal equipment can receive the clicking operation of the voice input button by the user. In response to this operation, the terminal device may pop up a voice input box in the dialog interface and start recording, as shown in fig. 5. And then in response to the user actuating the end recording button in the speech input box: and finishing the operation of the 'speaking' button, finishing recording, and acquiring input voice data so as to obtain an input sentence corresponding to the input voice data.

In addition, as shown in fig. 5, a text input box may be displayed in the dialog interface. When the user inputs a sentence in the text input box and clicks the "send" button after the input is completed, the terminal device may acquire the input sentence from the text input box in response to the user's operation of the "send" button in the dialog interface.

S203, the terminal equipment generates conversation content based on the conversation content input by the user and at least one target word; the conversation content is used to guide the user to use at least one target word in the conversation.

The session content may include at least one of: conversation sentences, conversation voice data, conversation pictures and conversation videos. The conversation voice data is obtained by voice conversion of conversation sentences, the picture content of the conversation pictures comprises the conversation sentences, and the conversation video is a video generated based on the conversation sentences.

It is understood that the session content may be reply content based on the user input content, may be question content based on the user input content, and may further include reply content based on the user input content and question content based on the user input content.

Optionally, in this embodiment of the present invention, the terminal device may determine M candidate session contents that match the user input session, where M is a positive integer. When M is equal to 1, the terminal device may determine the alternative session content as the session content. When M is greater than 1, the terminal device may determine the associated word according to the at least one target word, determine the association degree of the associated word with each alternative conversation content, and determine the alternative conversation content corresponding to the maximum association degree of the M association degrees as the conversation content. Wherein the associated words comprise words with the same or similar semantics as the words in the at least one target word, and the relevancy is used for indicating the semantic similarity of the associated words and each alternative conversation content.

It will be appreciated that the higher the semantic similarity, the more closely the contextual semantic relatedness in the text, and the greater the probability of appearing in a group of dialog texts at the same time. For example, "How are you" and "I'm fine, thank you" have a very close semantic relationship in the context, and there is a high probability that both will appear in a group of dialog texts.

Optionally, when the user inputs the conversation content as an input sentence and the candidate conversation content is a candidate conversation sentence, the terminal device may determine, in the preset sentence library, M candidate conversation sentences matching the input sentence through a Natural Language Processing (NLP) technique. Alternatively, the terminal device may also send a text matching request including the input sentence to the text matching server, so that the text matching server determines the M candidate conversational sentences that match the input sentence.

Optionally, in the embodiment of the present invention, in addition to determining, by the terminal device itself, the association degree between the at least one target word and each candidate conversation sentence may also be determined by the server.

Optionally, in the embodiment of the present invention, in addition to determining the conversation sentence by the terminal device itself, the server may determine the conversation sentence, and return the conversation sentence to the terminal device.

It can be understood that, on one hand, the conversation sentences and the input sentences have strong correlation, and a real interactive language communication environment can be created. On the other hand, the relevance of the conversation sentence and the K words to be trained is strong, and the user can be continuously guided to use at least one target word to make a sentence.

Further, the terminal device may output the conversation content at a position associated with the user input conversation content in the dialog interface. For example, the terminal device may display a conversation sentence corresponding to the input sentence in a lower part of the input sentence, and may also display the conversation sentence corresponding to the input sentence in a relative position after the input sentence is misrouted. The specific location of the associated position is not particularly limited herein.

Illustratively, in conjunction with fig. 5, as shown in fig. 6, the open-field sentence is: "How are you, Tom". After the user uses five words to make sentences in the dialog interface, the terminal device can acquire the input sentence "Keep on growing new seven up" and display the input sentence in the dialog box in a wrong row at the right. Then, the terminal device matches out alternative conversation sentences based on the input sentences, and after determining the conversation sentences from the alternative conversation sentences, the conversation sentences "article well talking about talking by the way, please try to use the words in the box, while the while switching with the me" can be displayed in the dialog box at left.

It is to be understood that the terminal device may also set the minimum number of sentences required for the word learning round, for example, 5 times, in response to the user's operation of the "set minimum number of sentences required to complete a conversation" button in the conversation interface. As shown in fig. 6, the dialog interface may display "the number of sentences in the turn" and the corresponding current number and total number, so as to prompt the user of the number of sentences to be made.

According to the method for generating the conversation content for the language and vocabulary learning training, the terminal equipment acquires at least one target word, the at least one target word is used for sentence making training of a user, the input conversation content of the user is acquired in response to the input operation of the user, and the conversation content is generated based on the input conversation content of the user and the at least one target word, wherein the conversation content is used for guiding the user to use the at least one target word in conversation. The embodiment of the invention automatically converses with the user by the conversation content generated based on the conversation content input by the user and the at least one target word, thereby creating a real interactive language communication environment, guiding the user to use the at least one target word for sentence making practice, helping the user to more effectively master the usage of the at least one target word, and improving the word learning efficiency.

Optionally, on the basis of the foregoing embodiment, with reference to fig. 2, as shown in fig. 7, the foregoing step S203 may include:

s301, the terminal device obtains the keywords in each alternative conversation content according to the part of speech of the words included in each alternative conversation content.

Parts of speech may include verbs, nouns, prepositions, etc. The proportion of the words with different parts of speech in the semantics of the sentence is different. For example, the keywords may be verbs or nouns in each alternative session content, and the number of the keywords may be one or more, which is not limited herein.

S302, the terminal device determines the association degree of each associated word and each alternative conversation content according to the association degree of each associated word and each keyword included in each alternative conversation content.

Specifically, the computer device may calculate, through NLP techniques, a degree of association of each associated word with each keyword included in each alternative conversation content.

It is understood that the degree of association between a word and a sentence can be expressed by the degree of association of the word with all keywords included in the sentence.

For example, the terminal device may determine the sum of the association degrees of the associated word and each keyword included in each alternative conversation content as the association degree of the associated word and the alternative conversation content, where the calculation manner of the association degree of the associated word and the alternative conversation content is not limited herein.

S303, the terminal equipment determines the association degree of each alternative conversation content and each associated word according to the association degree of each associated word and each alternative conversation content.

Specifically, the terminal device may determine the sum of the association degrees of each associated word and the alternative conversation content as the association degree of the associated word and the alternative conversation content, may also determine an average value of the association degrees of each associated word and the alternative conversation content as the association degree of the associated word and the alternative conversation content, and may also determine a maximum value of the association degrees of each associated word and the alternative conversation content as the association degree of the associated word and the alternative conversation content. The manner of determining the degree of association of the associated terms with each alternative session content is not limited herein.

Furthermore, the terminal device can also identify any word in at least one target word in the user input content, and screen out the associated words corresponding to the words when calculating the association degree, so that the relevance between the conversation content and the words in at least one target word which is not trained by the user is stronger, the user is guided to use the words in at least one target word which is not trained to make sentences in a targeted manner, and the word learning efficiency is further improved.

In this embodiment, the terminal device obtains the keywords in each alternative conversation content according to the part of speech of the word included in each alternative conversation content, determines the association degree of each associated word with each alternative conversation content according to the association degree of each associated word with each keyword included in each alternative conversation content, and determines the association degree of each associated word with each alternative conversation content according to the association degree of each associated word with each alternative conversation content, so that the association degree can accurately represent the semantic association degree of each associated word with each alternative conversation content, and an accurate basis is provided for determining the conversation sentence.

Optionally, on the basis of the foregoing embodiment, as shown in fig. 8, the determining M candidate session contents that match the user input session content specifically may include:

s401, the terminal device determines the similarity between the user input conversation content and each sentence in a preset sentence library.

The preset sentence library may store a large number of various sentences for active question asking or passive answer, and the alternative conversation content may be a sentence with a high correlation with the user input conversation content in the preset sentence library.

Specifically, the computer device may determine, by using an NLP technique, a similarity between the input sentence and each sentence in the preset sentence library, where a calculation manner of the similarity is similar to a calculation manner of the relevance in the foregoing embodiment, and details are not repeated here.

S402, the terminal device determines sentences with the similarity larger than a preset threshold value in a preset sentence library as alternative conversation contents to obtain M alternative conversation contents.

Specifically, the computer device may determine sentences with similarity greater than a preset threshold as candidate conversation contents, and obtain M candidate conversation contents. After the similarity is arranged from large to small, the content of the alternative session can be determined according to a preset percentage. For example, the sentences in the preset sentence library corresponding to the similarity of the first five percent are determined as the alternative conversation contents, and the screening manner of the alternative conversation contents is not limited here.

In this embodiment, the terminal device determines the similarity between the user input conversation content and each sentence in the preset sentence library, determines the sentences in the preset sentence library, the similarity of which is greater than the preset threshold, as the alternative conversation content, obtains M alternative conversation contents, and provides a sample basis for subsequently further screening the conversation contents, so that a real and vivid interactive language training environment can be created, and the method is favorable for guiding the user to perform sentence making practice, thereby improving the word training efficiency.

Optionally, on the basis of the foregoing embodiment, as shown in fig. 9, the method for generating conversation content for language and vocabulary learning training further includes:

s501, the terminal device determines the complexity of the user input conversation content according to the number of the keywords and the grammar structure in the user input conversation content.

It can be understood that the complexity of the user inputting the session content is related to the number of keywords and the syntactic structure in the user inputting the session content, and generally, the more the number of keywords in the user inputting the session content is, the more the syntactic structure is complex, the higher the complexity of the user inputting the session content is, and the higher the sentence making quality of the user inputting the session content is.

Specifically, the terminal device may determine the complexity of the input sentence according to the number of keywords and the syntactic structure in the user input conversation content.

S502, the terminal equipment obtains the frequency of the occurrence of the scoring terms in the user input conversation content, and the scoring terms are the terms in at least one target term.

It can be understood that the more the types and the number of the scoring words, the higher the sentence making quality of the user input conversation content.

Specifically, the terminal device may obtain the number of times the scoring term appears in the user input session content.

S503, the terminal equipment determines the evaluation parameters corresponding to the user input conversation content according to the complexity of the user input conversation content and the occurrence frequency of the scoring words in the user input conversation content.

The evaluation parameters can be used for expressing the sentence making quality of the user input conversation content and the word training effect of the user. The evaluation parameter may be an evaluation score or an evaluation level, and is not limited herein.

For example, taking fig. 6 as an example, the terminal device may display the evaluation score in "this point" in the dialog interface. In order to evaluate the word learning effect of the user input conversation content more accurately, the terminal device may determine the total chat score, the highest score, the sentence making number, the vocabulary amount of each sentence, the chat vocabulary amount and the repetition rate of each sentence of the conversation process according to each user input conversation content and each conversation content, and display the total chat score, the highest score, the sentence making number, the vocabulary amount of each sentence, the chat vocabulary amount and the repetition rate of each sentence in the conversation interface respectively. In addition, under the condition that the evaluation score or the total chat score reaches a preset value, the terminal equipment can also output an encouragement voice or pop up an encouragement prompt box, such as 'your true club', on a conversation interface to encourage the user to make sentences with high quality.

In the embodiment, the terminal device determines the complexity of the user input session content according to the number of the keywords and the grammar structure in the user input session content, acquires the times of the scoring words appearing in the user input session content, determines the evaluation parameters corresponding to the user input session content according to the complexity of the user input session content and the times of the scoring words appearing in the user input session content, and visually evaluates the sentence making quality of the user and the word learning effect, so that the user can be more effectively encouraged to make high-quality sentences, and the word training efficiency is improved.

Optionally, on the basis of the foregoing embodiment, as shown in fig. 10, the method for generating conversation content for language and vocabulary learning training further includes:

s601, after the terminal device obtains the conversation content input by the user, the recorded sentence making times are increased by a preset value.

Specifically, the terminal device may record the current accumulated sentence making times of the user, and increase the accumulated sentence making times by a preset value after obtaining the user input session content, where the preset value may be 1 for example.

And S602, under the condition that the sentence making times after the preset value is increased are equal to the preset times, the terminal equipment responds to the session ending operation of the user and outputs prompt information, and the prompt information is used for prompting the user to share the session.

The prompt information may be a visual prompt box or a prompt voice.

It can be understood that, when the sentence making times after the preset value is increased is equal to the preset times, it means that the sentence making number in the word learning process of the current round of the user already meets the minimum number required for completing the current round of the conversation.

Specifically, the terminal device may respond to the session ending operation of the user when the sentence making times after the preset value is increased is equal to the preset times, and output a prompt message to prompt the user to share the session.

For example, taking the prompt information as a prompt box, a dialog ending button may be displayed in the dialog interface, the terminal device may respond to a click operation of the user on the dialog ending button when the number of times of sentence creation after adding the preset value is equal to the preset number of times, and display the prompt box, where the prompt box may include a sharing button and a cancel button for supporting the user to share a session, where the session may include user input of session content and session content. Further, the computer device may return to the dialog interface in response to user operation of the cancel button.

And S603, the terminal equipment responds to the confirmation operation of the user on the prompt information and transmits the session to the sharing platform.

The sharing platform can be a public information sharing platform such as a social media platform, a chat software platform and the like.

Specifically, the terminal device may transmit the session to the sharing platform in response to a confirmation operation of the user on the prompt information. Further, the computer device may return to the dialog interface in response to a user cancelling the prompt.

For example, as shown in fig. 11, when the sentence making training frequency of the user reaches a preset frequency and the end dialog button is clicked, the terminal device may receive a click operation of the end dialog button by the user, display "dialog is ended" as a response to the click operation, and display a prompt box in the dialog interface, where the prompt box includes a text "whether you want to publish the session content to the sharing platform", and also includes a sharing button: a "willing" button and a cancel button: a "do not want" button. When the user clicks the 'willing' button, the terminal device can respond to the operation of the user and transmit the session in the conversation interface to the sharing platform.

It can be understood that, in the case that the sentence making times after the preset value is increased is less than the preset times, the end dialog button may be in a locked state and cannot be operated, thereby indicating that the word learning of the current round has not been ended.

In this embodiment, after the terminal device obtains the session content input by the user, a preset value is added to the recorded sentence making times, and when the sentence making times after the preset value is added is equal to the preset times, the terminal device responds to the session ending operation of the user, outputs prompt information, prompts the user to share the session, responds to the confirmation operation of the user on the prompt information, and transmits the session to the sharing platform, so that the user can disclose the process of word learning of the current turn to other people on the sharing platform, the interactivity of the word learning is enhanced, and the efficiency of the word learning is improved.

Optionally, on the basis of the foregoing embodiment, the conversation content includes a conversation sentence and conversation voice data as shown in fig. 12, and the above method for generating conversation content for language and vocabulary learning training further includes:

and S701, the terminal equipment outputs conversation voice data, and the conversation voice data is used for guiding the voice training of the user.

Specifically, the terminal device may perform voice conversion on the conversation sentence after determining the conversation sentence, so as to obtain conversation voice data. The terminal device may also determine, after determining the conversation sentence, conversation voice data corresponding to the conversation sentence from a preset conversation voice database, and acquire the conversation voice data.

And S702, after the terminal equipment outputs the conversation voice data, displaying a conversation sentence.

Specifically, the terminal device may display the conversation sentence after outputting the conversation voice data.

Illustratively, taking fig. 6 as an example, a "hearing training mode" button is also displayed in the dialog interface, and when the user makes a check in a frame before the hearing training mode, the terminal device may display a conversation sentence after outputting the conversation voice data in response to the user's operation of the "hearing training mode" button.

In this embodiment, the terminal device outputs the conversational speech data for guiding the speech training of the user, and displays the conversational sentence after outputting the conversational speech data, thereby helping the user to grasp the usage of the at least one target word and training the hearing of the user.

Optionally, on the basis of the foregoing embodiment, the method for generating conversation content for language and vocabulary learning training further includes:

the terminal equipment responds to the translation operation of the user on the conversation, converts the conversation content input by the user into first data of a preset language type, converts the conversation content into second data of the preset language type, and displays the first data and the second data in a conversation interface.

The preset language type can be set according to the user requirement, such as Chinese.

Specifically, a translation button is also displayed in the dialog interface, and in the process of word learning, the terminal device can respond to the operation of the translation button by the user, translate the user input conversation content and the conversation content, convert the user input conversation content into first data of a preset language type, convert the conversation content into second data of the preset language type, and display the first data and the second data at associated positions in the dialog interface. For example, the translated first data or second data is displayed below each session in the dialog interface. The first data or the second data may be text data.

Illustratively, as shown in fig. 13, the terminal device may display the corresponding chinese translation below the user-entered conversation content and the conversation content in the dialog interface in response to user operation of a "machine translation" button.

In this embodiment, the terminal device responds to the operation of the user on the translation button, converts the user input conversation content into the first data of the preset language type, converts the conversation content into the second data of the preset language type, and displays the first data and the second data in the conversation interface, so that the conversation process is more intuitively and vividly displayed, the user can correct the errors according to the first data and the second data, and the efficiency of word learning is improved.

The above description mainly introduces the scheme provided by the embodiment of the present invention from the perspective of the terminal device. It will be appreciated that the apparatus, in order to carry out the above-described functions, comprises corresponding hardware structures and/or software modules for performing the respective functions. Those of skill in the art will readily appreciate that the present invention can be implemented in hardware or a combination of hardware and computer software, in conjunction with the exemplary algorithm steps described in connection with the embodiments disclosed herein. Whether a function is performed as hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

Fig. 14 is a schematic block diagram of a possible generation apparatus of the session content for language and vocabulary learning training, and as shown in fig. 14, the generation apparatus of the session content for language and vocabulary learning training may include: an acquisition module 1501 and a generation module 1502.

An obtaining module 1501, configured to obtain at least one target word, where the at least one target word is used for sentence making training of a user; and responding to the input operation of the user, and acquiring the input session content of the user.

A generation module 1502 for generating conversation content based on user input conversation content and at least one target word; the conversation content is used to guide the user to use at least one target word in the conversation.

Optionally, the user input session content includes at least one of: inputting a sentence, inputting voice data, the input voice data corresponding to the input sentence; the session content includes at least one of: conversation sentences, conversation voice data, conversation pictures and conversation videos; the conversation voice data is obtained by voice conversion of conversation sentences, the picture content of the conversation pictures comprises the conversation sentences, and the conversation video is a video generated based on the conversation sentences.

Optionally, the generating module 1502 is specifically configured to: determining M alternative conversation contents matched with the conversation contents input by the user, wherein M is a positive integer; when M is equal to 1, determining the alternative session content as the session content; when M is larger than 1, determining a related word according to at least one target word, determining the degree of association between the related word and each alternative conversation content, and determining the alternative conversation content corresponding to the maximum degree of association in the M degrees of association as the conversation content; wherein the associated words comprise words with the same or similar semantics as the words in the at least one target word, and the relevancy is used for indicating the semantic similarity of the associated words and each alternative conversation content.

Optionally, the generating module 1502 is specifically configured to: acquiring keywords in each alternative conversation content according to the part of speech of the words included in each alternative conversation content; determining the association degree of each association word and each alternative conversation content according to the association degree of each association word and each keyword included by each alternative conversation content; and determining the association degree of each alternative conversation content according to the association degree of each association word and each alternative conversation content.

Optionally, the generating module 1502 is specifically configured to: determining the similarity between the user input conversation content and each sentence in a preset sentence library; and determining sentences with the similarity larger than a preset threshold value in a preset sentence library as the alternative conversation contents to obtain M alternative conversation contents.

Optionally, as shown in fig. 15, the generating device of the conversation content for language and vocabulary learning training further includes an evaluation module 1503. An evaluation module 1503 configured to: and determining the complexity of the user input conversation content according to the number of the keywords and the syntactic structure in the user input conversation content. The obtaining module 1501 is further configured to obtain the number of times that the scoring term appears in the user input session content, where the scoring term is a term in at least one target term. The evaluation module 1503 is further configured to determine an evaluation parameter corresponding to the user input session content according to the complexity of the user input session content and the occurrence frequency of the scoring term in the user input session content.

With reference to the second aspect, as shown in fig. 16, in one possible implementation manner, the generating device of the conversation content for language and vocabulary learning training further includes an adding module 1504, an outputting module 1505, and a sharing module 1506. An adding module 1504 configured to: and after the conversation content input by the user is acquired, increasing the recorded sentence making times by a preset value. The output module 1505 is configured to, in response to the session ending operation of the user, output a prompt message for prompting the user to share the session when the sentence making times after the preset value is increased is equal to the preset times. The sharing module 1506 is configured to transmit the session to the sharing platform in response to a confirmation operation of the user on the prompt information.

Optionally, the conversation content includes a conversation sentence and conversation voice data, and the output module 1505 is further configured to: outputting conversation voice data, wherein the conversation voice data is used for guiding the voice training of the user; after outputting the conversational speech data, a conversational sentence is displayed.

Optionally, the apparatus for generating session content for language and vocabulary learning training further includes a translation module, and the translation module is configured to: responding to the translation operation of the user on the conversation, converting the conversation content input by the user into first data of a preset language type, and converting the conversation content into second data of the preset language type; the first data and the second data are displayed in a dialog interface.

Optionally, the obtaining module 1501 is specifically configured to: responding to the operation of inputting words in a dialogue interface by a user, and acquiring at least one target word; or responding to the voice input of the user in the dialogue interface, acquiring target voice data, and acquiring at least one target word according to the target voice data; or displaying a word bank button in the conversation interface, and displaying a word list in the conversation interface in response to the operation of the user on the word bank button, wherein the word list comprises words in a preset word bank; responding to the selection operation of a user in the word list, and acquiring at least one target word; or responding to the word training instruction, acquiring word learning data, and taking words in a preset time period in the word learning data as at least one target word.

The apparatus for generating conversation contents for language and vocabulary learning training according to the embodiment of the present invention is used for executing the above method for generating conversation contents for language and vocabulary learning training, and therefore, the same effect as the above method for generating conversation contents for language and vocabulary learning training can be achieved.

The above description is only an embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.

Claims

1. A method for generating conversational content for language and vocabulary learning training, comprising:

generating conversational content based on the user input conversational content and the at least one target word; the conversation content is used to guide the user to use the at least one target word in the conversation.

2. The method of claim 1, wherein the training is performed by a computer system,

the user input session content includes at least one of: an input sentence, input speech data, the input speech data corresponding to the input sentence;

the session content includes at least one of: conversation sentences, conversation voice data, conversation pictures and conversation videos;

the conversation voice data is obtained by performing voice conversion on the conversation sentence, the picture content of the conversation picture comprises the conversation sentence, and the conversation video is a video generated based on the conversation sentence.

3. The method of generating conversational content for language and vocabulary learning training of claim 1 or 2, wherein the generating conversational content based on the user input conversational content and the at least one target word comprises:

determining M alternative conversation contents matched with the user input conversation contents, wherein M is a positive integer;

when M is equal to 1, determining the alternative session content as the session content;

when M is larger than 1, determining a related word according to the at least one target word, determining the degree of association between the related word and each alternative conversation content, and determining the alternative conversation content corresponding to the maximum degree of association in the M degrees of association as the conversation content;

wherein the associated terms comprise terms having the same or similar semantics as the terms in the at least one target term, and the relevancy is used to indicate semantic similarity of the associated terms to each alternative conversation content.

4. The method of claim 3, wherein said determining the relevancy of the associated word to each alternative conversational content comprises:

acquiring keywords in each alternative conversation content according to the part of speech of the words included in each alternative conversation content;

determining the association degree of each association word and each alternative conversation content according to the association degree of each association word and each keyword included by each alternative conversation content;

and determining the association degree of each association word and each alternative conversation content according to the association degree of each association word and each alternative conversation content.

5. The method of claim 3, wherein said determining M candidate conversational contents that match said user input conversational contents comprises:

determining the similarity between the user input conversation content and each sentence in a preset sentence library;

and determining sentences with the similarity larger than a preset threshold value in the preset sentence library as alternative conversation contents to obtain the M alternative conversation contents.

6. The method for generating conversational content for language and vocabulary learning training as claimed in claim 1 or 2, wherein the method for generating conversational content for language and vocabulary learning training further comprises:

determining the complexity of the user input session content according to the number of key words and a syntactic structure in the user input session content;

acquiring the occurrence times of scoring terms in the user input session content, wherein the scoring terms are terms in the at least one target term;

and determining the evaluation parameters corresponding to the user input session content according to the complexity of the user input session content and the occurrence frequency of the scoring words in the user input session content.

7. The method of claim 1 or 2, wherein the method of generating conversational content for language and vocabulary learning training further comprises:

after obtaining the conversation content input by the user, increasing the recorded sentence making times by a preset value;

under the condition that the sentence making times after the preset value is increased are equal to the preset times, responding to the operation of ending the conversation of the user, and outputting prompt information, wherein the prompt information is used for prompting the user to share the conversation;

and responding to the confirmation operation of the user on the prompt message, and transmitting the conversation to a sharing platform.

8. An apparatus for generating conversational content for language and vocabulary learning training, comprising:

the system comprises an acquisition module, a sentence making module and a sentence making module, wherein the acquisition module is used for acquiring at least one target word, and the at least one target word is used for sentence making training of a user; responding to the input operation of a user, and acquiring the input session content of the user;

a generation module for generating conversation content based on the user input conversation content and the at least one target word; the conversation content is used to guide the user to use the at least one target word in the conversation.

9. The apparatus for generating conversation contents for language and vocabulary learning training as claimed in claim 8,

the conversation voice data is obtained by voice conversion of the conversation sentence, the picture content of the conversation picture comprises the conversation sentence, and the conversation video is a video generated based on the conversation sentence.

10. The apparatus of claim 8 or 9, wherein the generation module is specifically configured to:

11. The apparatus of claim 10, wherein the generation module is specifically configured to:

determining the association degree of each association term and each alternative conversation content according to the association degree of each association term and each keyword included by each alternative conversation content;

12. The apparatus of claim 10, wherein the generation module is specifically configured to:

13. The apparatus for generating conversational content for language and vocabulary learning training of claim 8 or 9, wherein the apparatus for generating conversational content for language and vocabulary learning training further comprises an evaluation module;

the evaluation module is used for determining the complexity of the user input session content according to the number of key words and the syntactic structure in the user input session content;

the acquisition module is further used for acquiring the occurrence frequency of scoring terms in the user input session content, wherein the scoring terms are terms in the at least one target term;

the evaluation module is further used for determining evaluation parameters corresponding to the user input conversation content according to the complexity of the user input conversation content and the occurrence frequency of the scoring words in the user input conversation content.

14. The apparatus for generating conversational content for language and vocabulary learning training of claim 8 or 9, wherein the apparatus for generating conversational content for language and vocabulary learning training further comprises an adding module, an outputting module, and a sharing module;

the adding module is used for adding a preset value to the recorded sentence making times after the conversation content input by the user is obtained;

the output module is used for responding to the operation of ending the conversation of the user and outputting prompt information under the condition that the sentence making times after the preset value is increased by the increasing module is equal to the preset times, wherein the prompt information is used for prompting the user to share the conversation;

and the sharing module is used for responding to the confirmation operation of the user on the prompt message output by the output module and transmitting the conversation to a sharing platform.

15. A computer device, characterized in that the computer device comprises: a processor and a memory; the memory for storing computer program code, the computer program code comprising computer instructions; when the processor executes the computer instructions, the computer device performs the method of generating conversational content for language and vocabulary learning training of any one of claims 1-7.

16. A computer-readable storage medium comprising computer instructions which, when executed on a computer device, cause the computer device to perform the method of generating conversational content for language and vocabulary learning training of any one of claims 1-7.