Method and system for constructing resource library of teaching Chinese as a foreign language

Abstract

The present application is applicable to the technical field of constructing a resource library for teaching Chinese as a foreign language, and in particular, to a method and system for constructing a resource library for teaching Chinese as a foreign language, the method comprising: obtaining dialogue information; wherein the dialogue information is used to reflect the dialogue content generated when two or more communicators communicate; based on the dialogue information, obtaining the regional information corresponding to the dialogue information; analyzing the dialogue information to obtain communication characteristics and sentence meanings; analyzing the dialogue information, communication characteristics and sentence meanings to obtain differential vocabulary information; constructing based on the communication characteristics according to the differential vocabulary information and regional information to obtain a resource library for teaching Chinese as a foreign language. The method for constructing a resource library for teaching Chinese as a foreign language provided in the present application can improve the communication ability of non-native Chinese learners with a certain Chinese foundation with local people.

Description

Technical Field

[0001] The present application belongs to the technical field of constructing a resource library for teaching Chinese as a foreign language, and in particular, relates to a method and system for constructing a resource library for teaching Chinese as a foreign language. Background Art

[0002] The method of constructing a resource library for teaching Chinese as a foreign language is to create a systematic and comprehensive collection of teaching resources to meet the needs of non-native Chinese learners. This resource library usually includes teaching materials, exercises, multimedia materials, interactive platforms and other forms of content, aiming to provide comprehensive, practical and high-quality teaching resources for non-native Chinese learners.

[0003] The Chinese teaching resource library in the related art may rely too much on standard Mandarin, which leads to the situation that when non-native Chinese learners with a certain Chinese foundation travel or work in different regions, they ignore the special communication environment needs of non-native Chinese learners in different dialect regions of my country. As a result, non-native Chinese learners with a certain Chinese foundation cannot better learn and understand local dialects, which in turn reduces the communication ability of non-native Chinese learners with local people. Summary of the invention

[0004] The embodiments of the present application provide a method and system for constructing a resource library for teaching Chinese as a foreign language, which can improve the problem that non-native Chinese learners with a certain Chinese foundation cannot better learn and understand local dialects.

[0005] In a first aspect, the present application embodiment provides a method for constructing a resource library for teaching Chinese as a foreign language, including:

[0006] Acquiring dialogue information; wherein the dialogue information is used to reflect the dialogue content generated when two or more communicators communicate;

[0007] Based on the conversation information, obtaining the region information corresponding to the conversation information; wherein the region information is used to reflect the regional location associated with the conversation information;

[0008] Analyze the dialogue information to obtain communication characteristics and sentence meanings; wherein the communication characteristics are used to reflect the characteristics and attributes reflected in the process of interpersonal communication; the sentence meanings are used to reflect the information conveyed by the dialogue information and the meaning expressed;

[0009] Analyzing the communication characteristics and the meaning of the sentences to obtain differential vocabulary; wherein the differential vocabulary is used to reflect the difference between the vocabulary used by people in different regions in their daily lives and the vocabulary used in standard Mandarin;

[0010] A Chinese teaching resource library for foreigners is constructed based on the communication characteristics, the differential vocabulary and the regional information.

[0011] The above technical solutions in the embodiments of the present application have at least the following technical effects:

[0012] The method for constructing a resource library for teaching Chinese as a foreign language provided in an embodiment of the present application first obtains dialogue information for reflecting the content of dialogue generated when two or more communicators communicate with each other. By obtaining the dialogue information, basic construction content can be provided for the resource library for teaching Chinese as a foreign language. Based on the dialogue information, regional information for reflecting the regional location associated with the dialogue information is obtained. By obtaining the regional information, the dialogue information and the regional information can be better correlated. By analyzing the dialogue information, communication features for reflecting the language characteristics and language attributes reflected in the process of interpersonal communication and sentence meanings for reflecting the information conveyed by the dialogue information and the meaning expressed can be obtained, which can better help analyze the content of the dialogue information and facilitate the analysis and extraction of features related to the region. Then, according to the communication features, dialogue information and sentence meanings, analysis is performed to obtain difference vocabulary information for reflecting the formal differences and meaning differences between the vocabulary used by people in different regions in their daily lives and the vocabulary used in standard Mandarin, which can better help construct the resource library for teaching Chinese as a foreign language. Finally, the resource library for teaching Chinese as a foreign language is constructed based on the communication features, the difference vocabulary information and the regional information. This method can effectively extract different vocabulary information for different regions from the conversation content based on the different emotional and linguistic characteristics of each region. It can better help non-native Chinese learners with a certain Chinese foundation to learn and understand local dialects when traveling or working in different regions, and ultimately improve the communication ability of non-native Chinese learners with a certain Chinese foundation with local people.

[0013] In a possible implementation manner of the first aspect, analyzing according to the dialogue information to obtain communication characteristics and sentence meanings includes:

[0014] Data processing is performed on the dialogue information to obtain sentence information and voice information; wherein the sentence information is used to reflect a sentence in the dialogue information that expresses a complete thought, viewpoint or information; and the voice information is used to reflect the voice audio in the dialogue information;

[0015] Analyze the sentence information to obtain the sentence meaning;

[0016] The communication features are obtained by analyzing the voice information and the sentence information.

[0017] In a possible implementation manner of the first aspect, performing data processing according to the dialogue information to obtain sentence information includes:

[0018] Based on the separators in the dialogue information, a sentence subset is obtained from the dialogue information; wherein the separators include a period, a question mark, and an exclamation mark appearing in a sentence; and the sentence subset is used to reflect a set of independent sentences in the dialogue information;

[0019] Performing a similarity comparison analysis on the words in each independent sentence in the sentence subset and the words in each corresponding independent sentence in the preset sentence set, and obtaining a plurality of similarities corresponding to the words in each independent sentence; the preset sentence set is used to reflect the set of independent sentences in standard Mandarin; the similarity is used to reflect the degree of similarity between the words in each independent sentence in the sentence subset and the words in each corresponding independent sentence in the preset sentence set;

[0020] Performing mean processing on the multiple similarities to obtain a screening value; wherein the screening value is used to reflect the degree of similarity between each independent sentence in the sentence subset and each corresponding independent sentence in the preset sentence set;

[0021] A comparative analysis is performed based on the filtering value and a preset filtering value, and sentence information is obtained from the sentence subset.

[0022] In a possible implementation manner of the first aspect, the analyzing the voice information and the sentence information to obtain the communication feature includes:

[0023] Analyzing the voice information and the sentence information to obtain an emotional feature; wherein the emotional feature is used to reflect the emotional attitude embodied when the sentence information is expressed;

[0024] Analyzing the sentence information to obtain language features; the language features are used to reflect the peculiarities of vocabulary selection and grammatical structure usage habits in the dialogue information;

[0025] The emotional feature and the language feature are identified as communication features.

[0026] In a possible implementation manner of the first aspect, the analyzing the voice information and the sentence information to obtain the emotion feature includes:

[0027] Analyze the voice information to obtain a plurality of voice data; wherein the voice data corresponds to the sentence information one by one, and the voice data includes speech speed and intonation;

[0028] Processing the plurality of voice data to obtain average voice data; wherein the average voice data is used to reflect the average value of the plurality of voice data, including the average value of speech speed and the average value of intonation;

[0029] The emotion feature is obtained by analyzing the average voice data and the voice data.

[0030] In a possible implementation manner of the first aspect, the emotion feature is obtained by analyzing the average voice data and the voice data:

[0031] According to the comparison and analysis between the voice data and the average voice data, a speech speed difference value and a intonation difference value are obtained; wherein the speech speed difference value is used to reflect the difference between the speech speed in the voice data and the speech speed in the average voice data; the intonation difference value is used to reflect the difference between the intonation in the voice data and the intonation in the average voice data;

[0032] Analyzing the speech speed difference to obtain an emotion polarity value; wherein the emotion polarity value is used to reflect the value of the emotion tendency;

[0033] Analyze the intonation difference to obtain an emotion intensity value; wherein the emotion intensity value is used to reflect the intensity of the emotion;

[0034] Analyzing the emotion polarity value and the emotion intensity value to obtain an emotion feature point; wherein the emotion feature point is used to reflect the emotion embodied by the emotion polarity value and the emotion intensity value of the speech data;

[0035] The emotional feature points are matched with a preset emotional quadrant to obtain an emotional feature; wherein the preset emotional quadrant is used to reflect a quadrant composed of the emotional polarity value and the emotional intensity value.

[0036] In a possible implementation manner of the first aspect, the analyzing according to the sentence information to obtain the language feature includes:

[0037] Analyze the sentence information to obtain sentence structure and sentence vocabulary; wherein the sentence structure is used to reflect the combination mode within the sentence; and the sentence vocabulary is used to reflect the words that make up the sentence;

[0038] The language features are obtained by analyzing the sentence vocabulary and the sentence structure.

[0039] In a possible implementation manner of the first aspect, the analyzing according to the sentence information to obtain the sentence structure and sentence vocabulary includes:

[0040] Based on vocabulary types, the sentence information is split and processed to obtain sentence vocabulary; wherein the vocabulary types include verbs, nouns, adjectives, adverbs and prepositions;

[0041] Analyzing the sentence vocabulary to obtain a vocabulary sequence; wherein the vocabulary sequence is used to reflect the sequence of appearance order of the sentence vocabulary obtained by splitting the sentence information;

[0042] Analyze the vocabulary sequence to obtain a sentence structure.

[0043] In a possible implementation manner of the first aspect, the analyzing the sentence vocabulary and the sentence structure to obtain the language feature includes:

[0044] Extracting features according to the sentence structure to obtain structural features of the language features; wherein the structural features are used to reflect the characteristics of the grammatical structure shown in the language used in different regions;

[0045] The vocabulary of the sentence is analyzed to obtain the vocabulary features of the language features; wherein the vocabulary features are used to reflect the characteristics of vocabulary selection shown in the language used in different regional locations.

[0046] In a possible implementation manner of the first aspect, the analyzing according to the dialogue information, the communication characteristics, and the sentence meaning to obtain the difference vocabulary information includes:

[0047] Based on the communication characteristics, extracting difference words to obtain difference vocabulary information from the dialogue information; wherein the difference words are used to reflect the words representing the same thing or concept in different locations and the words representing the same thing or concept in standard Mandarin;

[0048] Based on the communication features, the sentence meaning is split to obtain word meanings; wherein the word meanings are used to reflect the meanings expressed by the words in the sentence meaning;

[0049] The difference words are matched with the word meanings to obtain the difference word meanings of the difference vocabulary information; wherein the difference word meanings are used to reflect the meanings expressed by the difference words.

[0050] In a second aspect, the present application embodiment provides a system for constructing a resource library for teaching Chinese as a foreign language, including:

[0051] A first acquisition module is used to acquire dialogue information; wherein the dialogue information is used to reflect the dialogue content generated when two or more communicators communicate;

[0052] A second acquisition module, configured to acquire, based on the conversation information, region information corresponding to the conversation information; wherein the region information is used to reflect a region location associated with the conversation information;

[0053] A first analysis module is used to analyze the dialogue information to obtain communication characteristics and sentence meanings; wherein the communication characteristics are used to reflect the language characteristics and language attributes reflected in the process of interpersonal communication; and the sentence meaning is used to reflect the meaning expressed by the dialogue information;

[0054] A second analysis module is used to analyze the dialogue information, the communication characteristics and the sentence meaning to obtain difference vocabulary information; wherein the difference vocabulary information is used to reflect the difference in form and meaning between the vocabulary used in daily life by people in different regions and the vocabulary used in standard Mandarin;

[0055] A construction module is used to construct a Chinese teaching resource library for foreign languages ​​based on the communication characteristics, the difference vocabulary information and the regional information.

[0056] In a third aspect, an embodiment of the present application provides a device for constructing a resource library for teaching Chinese as a foreign language, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the method described in any one of the first aspects above is implemented.

[0057] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the first aspects above is implemented.

[0058] In a fifth aspect, an embodiment of the present application provides a computer program. When the computer program is run on a Chinese teaching resource library construction device, the Chinese teaching resource library construction device enables the Chinese teaching resource library construction device to execute the Chinese teaching resource library construction method described in any one of the first aspects above.

[0059] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0061] Figure 1 It is a flowchart of a method for constructing a resource library for teaching Chinese as a foreign language provided in an embodiment of the present application;

[0062] Figure 2It is a schematic diagram of the implementation process of the method for constructing a resource library for teaching Chinese as a foreign language provided in one embodiment of the present application;

[0063] Figure 3 It is a structural diagram of a system for building a resource library for teaching Chinese as a foreign language provided in an embodiment of the present application;

[0064] Figure 4 It is a structural diagram of a device for constructing a resource library for teaching Chinese as a foreign language provided in one embodiment of the present application. DETAILED DESCRIPTION

[0065] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0066] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0067] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0068] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0069] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0070] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0071] The Chinese teaching resource library in the related art may rely too much on standard Mandarin, which leads to the situation that when non-native Chinese learners with a certain Chinese foundation travel or work in different regions, they ignore the special communication environment needs of non-native Chinese learners in different dialect regions of my country. As a result, non-native Chinese learners with a certain Chinese foundation cannot better learn and understand local dialects, which in turn reduces the communication ability of non-native Chinese learners with local people.

[0072] To solve the above problems, the embodiments of the present application provide a method and system for constructing a resource library for teaching Chinese as a foreign language.

[0073] In the method, firstly, dialogue information for reflecting the dialogue content generated when two or more communicators communicate is obtained, and the dialogue information can provide basic construction content for the Chinese teaching resource library as a foreign language. Based on the dialogue information, regional information for reflecting the regional location associated with the dialogue information is obtained. By obtaining the regional information, the dialogue information and the regional information can be better correlated. By analyzing the dialogue information, communication features for reflecting the language characteristics and language attributes reflected in the process of interpersonal communication and sentence meanings for reflecting the information conveyed by the dialogue information and the meaning expressed can be obtained, which can better help analyze the content of the dialogue information and facilitate the analysis and extraction of features related to the region. Then, according to the communication features, the dialogue information and the sentence meanings, the difference vocabulary information for reflecting the difference in form and meaning between the vocabulary used by people in different regions in daily life and the vocabulary used in standard Mandarin can be obtained, which can better help build the Chinese teaching resource library as a foreign language. Finally, based on the communication features, the difference vocabulary information and the regional information are constructed to obtain the Chinese teaching resource library as a foreign language. This method can effectively extract different vocabulary information for different regions from the conversation content based on the different emotional and linguistic characteristics of each region. It can better help non-native Chinese learners with a certain Chinese foundation to learn and understand local dialects when traveling or working in different regions, and ultimately improve the communication ability of non-native Chinese learners with a certain Chinese foundation with local people.

[0074] The method for constructing a resource library for teaching Chinese as a foreign language provided in the embodiment of the present application can be applied to a device for constructing a resource library for teaching Chinese as a foreign language. In this case, the device for constructing a resource library for teaching Chinese as a foreign language is the executor of the method for constructing a resource library for teaching Chinese as a foreign language provided in the embodiment of the present application. The embodiment of the present application does not impose any restrictions on the specific type of the device for constructing a resource library for teaching Chinese as a foreign language.

[0075] For example, the device for constructing a Chinese teaching resource library for foreigners can be a station (STAION, ST) in a WLAN, and can be a mobile phone, tablet computer, laptop computer, ultra-mobile personal computer (UMPC), netbook, desktop computer, smart large screen, computing device or other processing device connected to a wireless modem, computer, laptop computer, handheld computing device, for example, a mobile terminal in a 5G network or a mobile terminal in a future evolved public land mobile network (Public Land Mobile Network, PLMN), etc.

[0076] In order to better understand the method for constructing a Chinese teaching resource library for a foreign language provided in the embodiment of the present application, the specific implementation process of the method for constructing a Chinese teaching resource library for a foreign language provided in the embodiment of the present application is exemplarily introduced below.

[0077] Figure 1 and Figure 2 A schematic flow chart of a method for constructing a resource library for teaching Chinese as a foreign language provided in an embodiment of the present application is presented. The method for constructing a resource library for teaching Chinese as a foreign language includes:

[0078] S100, obtaining dialogue information; wherein the dialogue information is used to reflect the dialogue content generated when two or more communicators communicate.

[0079] It can be understood that the conversation content includes the audio corresponding to the conversation information and the subtitles corresponding to the audio. The conversation information can be crawled from major video platforms (such as Douyin, Bilibili, etc.) through web crawlers. Web crawlers refer to the use of automated programs to capture web page content (such as text content, image content, audio and video content, etc.) from web pages. The workflow of web crawlers is initialization, web page request, web page parsing, data storage, link tracking, and termination conditions. Conversation information can also be directly obtained through offline interviews, online Q&A, etc.

[0080] S200, based on the dialogue information, obtaining the region information corresponding to the dialogue information; wherein the region information is used to reflect the regional location associated with the dialogue information.

[0081] It is understandable that different dialects in Chinese will produce different differences in different regions. Regional location refers to the geographical location represented by different provincial, prefectural-level cities, different county-level and different township-level cities in China. The regional location can be directly obtained from the dialogue information. For example, the regional location is obtained by matching the dialogue information with the preset regional mapping table. The matching process can be that the names of different Chinese cities and regions in the preset regional mapping table are used as features, and then the dialogue information is matched with features to obtain the most frequently appearing regional name features, that is, the regional location corresponding to the dialogue information. The preset regional mapping table refers to a mapping table of different Chinese city names, administrative divisions, and regional codes that are preset. The preset regional mapping table can be manually input by humans, and the preset regional mapping table can also be directly obtained from the city database. The city database refers to data containing the names, administrative divisions, and regional codes of various cities in China. These data can be obtained by recording files. After obtaining, the collected data is sorted, classified and archived, useful information and rules are extracted, and the relevant data is saved in the database to form a city database. The regional location can also be obtained from the regional IP in the dialogue information crawled by the web crawler. And so on, but not limited to this.

[0082] S300, analyzing the dialogue information to obtain communication features and sentence meanings; wherein the communication features are used to reflect the language characteristics and emotional attributes reflected in the process of interpersonal communication; and the sentence meanings are used to reflect the meaning expressed by the dialogue information.

[0083] It can be understood that language characteristics refer to the grammatical characteristics and vocabulary characteristics of the dialects used by people in different regions, and emotional attributes refer to the emotions expressed in the discourse of people in different regions. By analyzing the dialogue information, multiple sentences in the dialogue information and the audio corresponding to the multiple sentences can be obtained, and then by analyzing the multiple sentences, multiple meanings corresponding to the multiple sentences can be obtained, and then the sentence meanings can be obtained by parsing the multiple meanings, and then the communication characteristics can be obtained by analyzing the sentences and the audio corresponding to the sentences. The dialogue information can also be processed by establishing an analysis model to obtain communication characteristics and sentence meanings. The analysis model can be a tool model such as natural language processing (NLP), sentiment analysis model, dialogue management system, and machine learning model. That is, the dialogue information is input into the analysis model, and the analysis model outputs the corresponding communication characteristics and sentence meanings. The training process of the analysis model can first clean the conversation information (process missing values, duplicate values ​​and outliers) to remove outliers (for example, outliers may be caused by environmental noise, errors in collection equipment or other abnormal conditions), noise (for example, random errors or meaningless interference in the conversation information may lead to inaccuracy and reduced usability of the conversation information, so as to ensure the quality of the conversation information. Finally, the conversation information after data processing, communication characteristics and sentence meaning are used as training data sets, and the training data sets are input into the analysis model for training and learning, so as to finally obtain the analysis model.

[0084] In a possible implementation, in step S300, analyzing the dialogue information to obtain communication features and sentence meanings includes:

[0085] S310, performing data processing according to the dialogue information to obtain sentence information and voice information; wherein the sentence information is used to reflect a sentence in the dialogue information that expresses a complete thought, viewpoint or information; and the voice information is used to reflect the voice audio in the dialogue information.

[0086] It can be understood that by processing the dialogue information, a set of independent sentences and voice information in the dialogue information can be obtained, and then by processing the set of independent sentences, sentences that meet the conditions of a complete thought, viewpoint or information can be screened out from the set of independent sentences, which is sentence information. An independent sentence refers to a sentence that can be formed independently and express a complete meaning. The dialogue information can also be processed by python code and spaCy library to obtain sentence information. First, the dialogue information is tagged with parts of speech and named entity recognition by the spaCy library, and then the dialogue information that has been tagged with parts of speech and named entity recognition by the spaCy library is extracted by python code to finally obtain sentence information. Part-of-speech tagging is the process of marking each word in the dialogue information with the corresponding part of speech (such as noun, verb, adjective, etc.). Named entity recognition is the process of identifying entities with specific meanings (such as names, place names, organization names, dates, times, etc.) in dialogue information.

[0087] In a possible implementation, in step S310, data processing is performed according to the dialogue information to obtain sentence information, including:

[0088] S311, based on the separators in the dialogue information, obtaining a sentence subset from the dialogue information; wherein the separators include a period, a question mark, and an exclamation mark appearing in a sentence; the sentence subset is used to reflect a set of independent sentences in the dialogue information.

[0089] It can be understood that a sentence expressing a complete thought, viewpoint or information is terminated by a delimiter such as a period, question mark, exclamation mark and quotation mark. Therefore, the dialogue information can be segmented by the delimiters in the dialogue information to obtain a subset of sentences. The delimiters can be manually input or directly obtained from a symbol database. The symbol database refers to data containing different delimiters. These data can be obtained by recording files. After obtaining, the collected data is sorted, classified and archived, useful information and rules are extracted, and the relevant data is saved in the database to form a symbol database. And so on, but not limited to this.

[0090] For example, when a conversation content in a conversation message includes "Oh, the weather is really nice today! You said that the autumn sunshine is so warm and comfortable! Do you want to go out for a walk? Otherwise, it's boring to stay at home and stare blankly.", the conversation content is divided into sentence subsets of "(Oh, the weather is really nice today!), (You said that the autumn sunshine is so warm and comfortable!), (Do you want to go out for a walk?), (Otherwise, it's boring to stay at home and stare blankly.)" according to the delimiter.

[0091] S312, performing a similarity comparison analysis on the words in each independent sentence in the sentence subset and the words in the corresponding independent sentence in the preset sentence set, and obtaining multiple similarities corresponding to the words in each independent sentence; the preset sentence set is used to reflect the set of independent sentences in standard Mandarin; the similarity is used to reflect the degree of similarity between the words in each independent sentence in the sentence subset and the words in each corresponding independent sentence in the preset sentence set.

[0092] It can be understood that the preset sentence set refers to a set of independent sentences formed in daily communication using standard Mandarin as the communication language. For example, "(Have you eaten?), (Do you want to go for a walk?), (How about we go out together this weekend?)", etc. The words in each independent sentence in the sentence subset are compared one by one with the words in each corresponding independent sentence in the preset sentence set to obtain the similarity of each word in each independent sentence.

[0093] For example, assuming that the sentence subset is "(Oh, it's so hot today, I want to have some chili water to relieve fatigue.), (Are you free, let's go to the riverside together?), (The skewers there are delicious, very good!)", and the preset sentence set is "(Oh, it's so hot today, I want to have some chili water to relieve fatigue.), (Are you free, let's go to the riverside together?), (The skewers there are delicious, very good!)", the sentence subset "(Oh, it's so hot today, I want to have some chili water to relieve fatigue.)" is consistent with the preset sentence set "(Oh, It feels so hot today, I want to go have some chili water to relieve fatigue. )”, and we get that the similarity between “Oh yeah” and “Oh yeah” is 100%, the similarity between “today” and “today” is 100%, the similarity between “feel” and “feel” is 100%, the similarity between “it’s so hot” and “it’s so hot” is 75%, the similarity between “want to go” and “want to go” is 100%, the similarity between “eat something” and “eat something” is 80%, the similarity between “chili water” and “chili water” is 100%, the similarity between “relieve fatigue” and “relieve fatigue” is 100%, and so on.

[0094] S313, performing mean processing according to multiple similarities to obtain a screening value; wherein the screening value is used to reflect the degree of similarity between each independent sentence in the sentence subset and each corresponding independent sentence in the preset sentence set.

[0095] It can be understood that, based on the similarity of each word in each independent sentence, the degree of similarity between each independent sentence in the sentence subset and each corresponding independent sentence in the preset sentence set is obtained, which is the screening value. By screening the sentence subset according to the screening value, sentences with dialect characteristics can be separated from the sentence subset. By performing mean processing on multiple similarities, the degree of similarity between the independent sentences in the sentence subset and the corresponding independent sentences in the preset sentence set is obtained. Mean processing refers to calculating the average value of multiple similarities to obtain the average value of multiple similarities.

[0096] For example, assuming that the multiple similarities are 100%, 100%, 100%, 100%, 75%, and 80%, the screening value is 92.5% [(100%+100%+100%+100%+75%+80%)÷6], and so on.

[0097] S314, performing comparative analysis based on the filter value and the preset filter value, and obtaining statement information from the statement subset.

[0098] It can be understood that the preset screening value refers to a pre-set screening value, which is used to compare the screening value and screen out sentences below the preset screening value from the sentence subset, that is, the sentence information. The preset screening value can be manually input by humans, or it can be directly obtained from the screening database. The screening database refers to data containing the degree of similarity between each independent sentence in the sentence subset and each corresponding independent sentence in the preset sentence set. These data can be obtained through laboratory experiments and past experience. After obtaining, the collected data will be sorted, classified and archived, useful information and rules will be extracted, and the relevant data will be saved in the database to form a screening database. And so on, but not limited to this.

[0099] In this way, by using periods, question marks, and exclamation marks as separators, independent sentences can be effectively extracted from the conversation information, and the messy conversation information can be converted into a clearer and easier to process sentence subset. By comparing the similarity of the words in each independent sentence one by one, the language similarity between different sentences can be quantified. By averaging the similarity, a screening value that can reflect the similarity between each independent sentence and the preset sentence is obtained. The screening value can improve the quality and processing efficiency of sentence information.

[0100] S320, analyzing the sentence information to obtain the sentence meaning.

[0101] It can be understood that the sentence meaning is a set of meanings corresponding to all sentence information. By analyzing the meaning of each independent sentence, the expression meaning corresponding to each sentence can be obtained, which is the sentence meaning. Sentence meaning refers to the expression meaning corresponding to the independent sentence in the dialogue information. The sentence meaning can be obtained from the sentence information through the translation model, that is, the sentence information is input into the translation model, and the translation model outputs the corresponding sentence meaning. The training process of the translation model can be obtained by using the data processed from the sentence information and the corresponding sentence meaning as the training data set of the translation model, and then inputting the training data set of the translation model into the translation model for training and learning, and finally obtaining the translation model. Then, by integrating the sentence meaning corresponding to each sentence, the meaning expressed by the dialogue information is obtained, which is the sentence meaning. Data integration refers to the process of summarizing and merging the expression meanings corresponding to different independent sentences. Meaning analysis refers to the process of interpreting independent sentences. For example, the sentence information is ("Have you eaten yet?"), ("Mao Qia."), ("Take Nen Qie to eat, let's go!"), the sentence information "Have you eaten yet?" corresponds to the sentence meaning "Have you eaten?", the sentence information "Mao Qia." corresponds to the sentence meaning "No.", the sentence information "Take Nen Qie to eat, let's go!" corresponds to the sentence meaning "Take you to eat, let's go!", then the sentence meaning is [("Have you eaten?"), ("No"), ("Take you to eat, let's go!")]. And so on.

[0102] S330, analyzing the voice information and the sentence information to obtain communication features.

[0103] It can be understood that by analyzing the language information and sentence information, the emotional attitude reflected in the expression of sentence information can be obtained, and then the differences in the dialogue information (including vocabulary selection and grammatical structure) can be obtained by analyzing the sentence information. Finally, the communication characteristics can be obtained through the emotional attitude reflected in the expression of sentence information and the differences in the dialogue information.

[0104] Communication features can also be obtained from voice information and sentence information through a feature analysis model, that is, voice information and sentence information are input into the feature analysis model, and the feature analysis model then outputs the corresponding communication features. The training process of the feature analysis model can be performed by processing the voice information, sentence information, and corresponding communication features as a training data set for the feature analysis model, and then the training data set of the feature analysis model is input into the feature analysis model for training and learning, and finally a feature analysis model is obtained.

[0105] In this way, by analyzing the dialogue information, sentence information and voice information are obtained, which is convenient for providing basic data for communication feature analysis. By analyzing the sentence information and obtaining the sentence meaning, it can help understand the meaning expressed by the sentence and the main idea of ​​the dialogue information.

[0106] In a possible implementation, in step S330, the speech information and the sentence information are analyzed to obtain communication features, including:

[0107] S331, analyzing the voice information and the sentence information to obtain emotional features; wherein the emotional features are used to reflect the emotional attitude reflected when the sentence information is expressed.

[0108] It can be understood that by analyzing the voice information, multiple speaking speeds and multiple intonations corresponding to the sentence information can be obtained, and then by performing mean processing on the multiple speaking speeds and intonations respectively, the average speaking speed and the average intonation can be obtained, and then analysis can be performed based on the average intonation, average speaking speed, speaking speed and intonation to finally obtain the emotional characteristics.

[0109] Emotional features can also be obtained by establishing a sentiment analysis model. That is, language information and sentence information are input into the sentiment analysis model, and the sentiment analysis model then outputs the corresponding emotional features. The training process of the sentiment analysis model can be done by using the data processed from language information, sentence information, and emotional features as the training data set of the sentiment analysis model, and then inputting the training data set of the sentiment analysis model into the sentiment analysis model for training and learning, and finally obtaining the sentiment analysis model.

[0110] In a possible implementation, in step S331, the emotion features are obtained by analyzing the speech information and the sentence information, including:

[0111] S3311, analyzing the voice information to obtain a plurality of voice data; wherein the voice data corresponds to the sentence information one by one, and the voice data includes speech speed and intonation.

[0112] It can be understood that speaking rate refers to the amount of language spoken by the speaker in a unit of time. For example, if 30 words are spoken per minute, the speaking rate is 30 words / minute, 3 words per second, the speaking rate is 3 words / second, and so on. Intonation refers to the change in the pitch of the sound during speaking. The language information can be analyzed by using speech analysis software (such as Audacity, Praat, etc.) to measure the speaking rate and pitch corresponding to the sentence information. The language information can also be processed to obtain a sound waveform, and then the sound waveform is analyzed to identify the change in pitch and obtain the pitch in the language data. The sound waveform is a graph that represents the sound intensity in the voice information, that is, the change of pitch over time.

[0113] S3312, processing is performed based on the plurality of voice data to obtain average voice data; wherein the average voice data is used to reflect the average value of the plurality of voice data, including the average value of the speech speed and the average value of the intonation.

[0114] It can be understood that the average speech rate refers to the number of voices or words contained in the voice expression within a preset time (usually in minutes or seconds). The average tone refers to the pitch level of the tone within a certain period of time. The average voice data is obtained by performing mean processing on multiple voice data. The preset time refers to a preset time interval. The preset time is used to calculate the average speech rate of the speaker within the preset time. The preset time can be manually input. The preset time can also be directly obtained from the time database. The time database refers to data containing different time intervals. These data can be obtained by recording files. After obtaining, the collected data is sorted, classified and archived, useful information and rules are extracted, and the relevant data is saved in the database to form a time database. And so on, but not limited to this.

[0115] For example, if two communicators are communicating, one of them spends 5 minutes to explain a 300-word opinion and spends 2 minutes to explain another 200-word opinion, the average speaking speed is 80 words / minute {[(300÷5)+(200÷2)]÷2}, and so on.

[0116] S3313, analyzing the average voice data and the voice data to obtain emotional features.

[0117] It can be understood that the average voice data can be used as an emotional feature that can represent stable emotions. The language data and the average voice data can be compared to obtain the difference between the speech speed in the voice data and the speech speed in the average voice data, and the difference between the intonation in the voice data and the intonation in the average voice data. Then, the speech speed difference and the set of pre-set speech speed difference values ​​are matched and analyzed to obtain a value for reflecting the emotional tendency, and the intonation difference and the set of pre-set intonation difference values ​​are analyzed and processed to obtain a value for reflecting the intensity of the emotion. Then, the value reflecting the emotional tendency and the value reflecting the intensity of the emotion are integrated to obtain the emotional polarity and emotional intensity reflected by the voice data.

[0118] You can also construct the average speech data and the speech data to obtain the emotion matrix, and then perform operations based on the emotion matrix to obtain the matrix standard deviation of the emotion matrix, and then match the matrix standard deviation with the preset emotion axis to obtain the emotion feature. The emotion matrix refers to a structured matrix that can represent the emotion feature through the attributes of speech rate and intonation. The matrix standard deviation is the square root of the matrix variance. The matrix variance is the average of the squares of the differences from the matrix mean. The matrix mean is the average value calculated in the emotion matrix. The preset emotion axis refers to a pre-set data axis, and each data interval in the data axis corresponds to an emotion feature.

[0119] This setting can provide more accurate and real-time analysis of emotional features through the potential of voice data in emotion recognition. It can improve the understanding of emotions in sentence information. By analyzing voice data, multiple voice data can be obtained, which can provide a rich data basis for subsequent analysis of emotional features. The average voice data can reflect the characteristics of the overall conversation and can be used as a more general communication model.

[0120] In a possible implementation, in step S3313, the emotional features are obtained by analyzing the average voice data and the voice data, including:

[0121] S33131, based on the comparative analysis of the speech data and the average speech data, obtain the speech speed difference and the intonation difference; wherein the speech speed difference is used to reflect the difference between the speech speed in the speech data and the speech speed in the average speech data; the intonation difference is used to reflect the difference between the intonation in the speech data and the intonation in the average speech data.

[0122] It can be understood that by comparing the speech rate in the speech data with the average speech rate in the average speech data, the speech rate difference is obtained, that is, the speech rate minus the average speech rate. Then, by comparing the intonation in the speech data with the average intonation in the average speech data, the intonation difference is obtained, that is, the intonation minus the average intonation.

[0123] For example, assume that the speaking speed in the speech data is 10 words / minute, the speaking speed in the average speech data is 15 words / minute, the speaking speed difference is -5 words / minute, the intonation in the speech data is 300Hz, the intonation in the average speech data is 290Hz, the intonation difference is 10Hz, and so on.

[0124] S33132, analyzing the speech speed difference to obtain an emotion polarity value; wherein the emotion polarity value is used to reflect the value of the emotion tendency.

[0125] It can be understood that emotional tendency refers to the use of evaluating and identifying emotional attitudes, and emotional tendency includes positive emotions, negative emotions, and neutral emotions. Positive emotions can be positive emotions such as happiness, excitement, and satisfaction. Negative emotions can be negative emotions such as sadness and disappointment. Neutral emotions refer to the use of objective descriptions of emotional attitudes that tend to be stable. When a speaker expresses positive emotions (such as excitement and happiness) compared to neutral emotions, he will show a faster speaking speed. When a speaker expresses negative emotions (such as sadness and disappointment), he will show a slower speaking speed compared to neutral emotions. Under different emotional tendency conditions, different speech speed differences correspond to an emotional polarity value.

[0126] The emotional polarity difference can be obtained by matching the speech speed difference with the preset speech speed difference set. The preset speech speed difference set refers to a set of pre-set speech speed difference values. The preset speech speed difference set includes multiple speech speed differences, and each speech speed difference corresponds to an emotional polarity value. For example, the preset speech speed difference set can be -5 words / minute, -4 words / minute, -1 word / minute, 3 words / minute, and 4 words / minute. The emotional polarity difference corresponding to the preset speech speed difference set is that the emotional polarity value corresponding to -5 words / minute is -0.3, the emotional polarity value corresponding to -4 words / minute is -0.28, the emotional polarity value corresponding to -1 word / minute is -0.1, the emotional polarity value corresponding to 3 words / minute is 0.3, the emotional polarity value corresponding to 4 words / minute is 0.7, and so on, but not limited to this.

[0127] The sentiment polarity value can also be obtained through the sentiment tendency model. That is, the speech rate difference value is input into the sentiment analysis model, and the sentiment tendency model then outputs the corresponding sentiment polarity value. The training process of the sentiment tendency model can be performed by processing the speech rate difference value and the corresponding sentiment polarity value as the training data set of the sentiment tendency model, and then the training data set of the sentiment tendency model is input into the sentiment tendency model for training and learning, and finally the sentiment tendency model is obtained.

[0128] Exemplarily, assuming that the preset speech speed difference set can be -5 words / minute, -4 words / minute, -1 word / minute, 3 words / minute, and 4 words / minute, the emotion polarity difference corresponding to the preset speech speed difference set is that the emotion polarity value corresponding to -5 words / minute is -0.3, the emotion polarity value corresponding to -4 words / minute is -0.28, the emotion polarity value corresponding to -1 word / minute is -0.1, the emotion polarity value corresponding to 3 words / minute is 0.3, and the emotion polarity value corresponding to 4 words / minute is 0.7. When the speech speed difference is -5 words / minute, the emotion polarity value is -0.3, when the speech speed difference is -3 words / minute, the emotion polarity value is -0.24, when the speech speed difference is 3 words / minute, the emotion polarity value is 0.3, and so on.

[0129] S33133, analyzing the intonation difference to obtain an emotion intensity value; wherein the emotion intensity value is used to reflect the intensity of the emotion.

[0130] It can be understood that the intensity of emotion refers to the strength or depth of emotion when expressing emotion. The intensity of emotion can be strong (for example, very, extreme, etc.), calm (for example, slight, calm, etc.) and soothing (for example, gentle). When a speaker expresses a strong emotion (such as very, extreme), he or she tends to use a louder tone than a calm tone. When a speaker expresses a soothing emotion (such as gentle), he or she tends to use a lighter and smaller tone than a calm tone. Under different emotion intensity conditions, different tone differences correspond to an emotion intensity value.

[0131] The emotional intensity value can be obtained by matching the intonation difference value with the preset intonation difference value set. The preset intonation difference value set refers to a set of pre-set intonation difference values. The preset intonation difference value set includes multiple intonation difference values, and each intonation difference value corresponds to an emotional intensity value. For example, the preset intonation difference value set can be -20Hz, -10Hz, -5Hz, 10Hz, 20Hz, and the emotional intensity value corresponding to the preset intonation difference value set is -0.5 for -20Hz, -0.24 for -10Hz, -0.13 for -5Hz, 0.3 for 10Hz, 0.7 for 20Hz, and so on, but not limited to this.

[0132] The emotional intensity value can also be obtained through the emotional intensity model. That is, the intonation difference value is input into the emotional intensity model, and the emotional intensity model then outputs the corresponding emotional intensity value. The training process of the emotional intensity model can be performed by using the data after data processing of the intonation difference value and the corresponding emotional intensity value as the training data set of the emotional intensity model, and then inputting the training data set of the emotional intensity model into the emotional intensity model for training and learning, and finally obtaining the emotional intensity model.

[0133] Exemplarily, assuming that the preset intonation difference set can be -20Hz, -10Hz, -5Hz, 10Hz, and 20Hz, the emotion intensity value corresponding to the preset intonation difference set is -0.5 for -20Hz, -0.24 for -10Hz, -0.13 for -5Hz, 0.3 for 10Hz, and 0.7 for 20Hz. When the intonation difference is -20Hz, the emotion intensity value is -0.5, when the intonation difference is -10Hz, the emotion intensity value is -0.24, when the intonation difference is 10Hz, the emotion intensity value is 0.3, and so on.

[0134] S33134, analyzing the emotion polarity value and the emotion intensity value to obtain emotion feature points; wherein the emotion feature points are used to reflect the emotion polarity and emotion intensity expressed by the speech data.

[0135] It can be understood that sentiment feature points can be used to represent the sentiment attitude expressed by independent sentences. Sentiment feature points are (sentiment polarity value, sentiment intensity value). For example, if the sentiment polarity value is -0.3 and the sentiment intensity value is -0.3, then the corresponding sentiment feature point is (-0.3, -0.3); if the sentiment polarity value is -0.1 and the sentiment intensity value is -0.24, then the corresponding sentiment feature point is (-0.1, -0.24); if the sentiment polarity value is 0.7 and the sentiment intensity value is 0.3, then the corresponding sentiment feature point is (0.7, 0.3).

[0136] S33135, matching the emotional feature points with the preset emotional quadrant to obtain the emotional features; wherein the preset emotional quadrant is used to reflect the quadrant composed of the emotional polarity value and the emotional intensity value.

[0137] It can be understood that the preset emotional quadrant refers to different dimensions that are pre-set for describing and visualizing emotions. The preset emotional quadrant has a range of [-1,1] on the X-axis and a range of [-1,1] on the Y-axis. The X-axis represents the emotional polarity value and the Y-axis represents the emotional intensity value. The preset emotional quadrant can be manually input or directly obtained through the emotional quadrant library. The emotional quadrant library refers to a database containing different emotional polarity values, different emotional intensity values, and corresponding different emotional characteristics. These data can be obtained through laboratory experiments, on-site measurements and monitoring, and past experience. After obtaining, the collected data will be sorted, classified and archived, useful information and rules will be extracted, and the relevant data will be saved in the database to form an analytical emotional quadrant library. Each area in the preset emotional quadrant corresponds to an emotional characteristic.

[0138] For example, assuming that in the preset emotional quadrant, the range representing very excitement is [(0.7 to 1), (0.8 to 1)], the range representing very happy is [(0.6 to 0.7), (0.8 to 1)], and the range representing very sad is [(-1 to -0.8), (-1 to -0.8)]. When the emotional feature point is (0.75, 0.85), the emotional feature is very excited, and when the emotional feature point is (-0.9, -0.86), the emotional feature is very sad, and so on.

[0139] With this setting, by comparing the voice data with the average voice data, we can get the difference between the voice data and the normal communication mode. By analyzing the emotion polarity value and the emotion intensity value, we can provide the basic definition data for building an emotional feature, and we can better analyze the data to get different data expressed by different emotional features.

[0140] S332, analyzing the sentence information to obtain language features; the language features are used to reflect the peculiarities of vocabulary selection and usage habits of grammatical structures in the dialogue information.

[0141] It can be understood that the singularity refers to the difference between the dialects in different regions and the standard Mandarin in terms of vocabulary selection, grammatical structure, etc. By analyzing the sentence information, the internal combination mode of independent sentences and the words that make up the independent sentences can be obtained, and then the internal combination mode of independent sentences and the words that make up the independent sentences can be analyzed to finally obtain the language features. The language features can also be obtained through machine learning model methods such as SVM, decision tree, deep learning, etc. That is, the sentence information is input into the learning model, and the learning model outputs the language features. The training process of the learning model can be obtained by using the data processed from the sentence information and the language features as the training data set of the learning model, and then the training data set of the learning model is input into the learning model for training and learning, and finally the learning model is obtained.

[0142] In a possible implementation, in step S332, analysis is performed based on the sentence information to obtain language features, including:

[0143] S3321, analyzing the sentence information to obtain sentence structure and sentence vocabulary; wherein the sentence structure is used to reflect the combination method within the sentence; and the sentence vocabulary is used to reflect the words that make up the sentence.

[0144] It can be understood that the sentence information can be split to obtain the vocabulary that makes up independent sentences, and then the sentence structure can be obtained by analyzing the splitting order, that is, the order in which the sentence vocabulary appears. Finally, the language features can be obtained by analyzing the sentence vocabulary and sentence structure.

[0145] The sentence information can also be analyzed by a machine learning model method to obtain the sentence structure and sentence vocabulary. That is, the sentence information is directly input into the learning model, and the learning model then outputs the sentence structure and sentence vocabulary. The training process of the learning model can be achieved by using the sentence information and the sentence structure and sentence vocabulary corresponding to the sentence information as the training data set of the learning model, and then inputting the training data set of the learning model into the learning model for training and learning, and finally obtaining the learning model.

[0146] In a possible implementation, in step S3321, the sentence information is analyzed to obtain the sentence structure and sentence vocabulary, including:

[0147] S33211, based on vocabulary types, the sentence information is split and processed to obtain sentence vocabulary; wherein the vocabulary types include verbs, nouns, adjectives, adverbs and prepositions.

[0148] It can be understood that vocabulary type refers to the classification of vocabulary according to its function and meaning, and the resulting vocabulary type. It includes nouns representing people, animals, things, places, concepts, etc., verbs representing actions, states or processes, adjectives describing the nature and state of nouns or pronouns, modifying verbs, adjectives, adverbs or other sentence components, adverbs representing time, place, manner, degree, etc., and prepositions representing the relationship between nouns or pronouns and other sentence components. Sentence information is marked by type through vocabulary type, and then the sentence information is split according to the splitting order from the beginning to the end of the independent sentence in the sentence information as the splitting process to obtain sentence vocabulary.

[0149] For example, if the sentence information is "Hey, are you going to eat today? There is a new restaurant opened near my home, and the food there is simply amazing!", then the sentence vocabulary is "Hey", "you", "today", "go", "eat", "yes", "I", "home", "there", "new", "opened", "a", "restaurant", "that", "dish", "simply", "amazing".

[0150] S33212, analyzing the sentence vocabulary to obtain a vocabulary sequence; wherein the vocabulary sequence is used to reflect the sequence of appearance order of the sentence vocabulary obtained by splitting the sentence information.

[0151] It can be understood that the order of appearance of the words in the sentences after the sentence information is split is used as the word sequence. By analyzing the word sequence, the combination mode inside the independent sentence can be obtained.

[0152] S33213, analyze according to the vocabulary sequence to obtain the sentence structure.

[0153] It can be understood that sentence structure refers to the relationship and arrangement of words or phrases in an independent sentence, which may include inversion, emphasis, passive, interrogative, and exclamatory sentences, but is not limited thereto. Sentence structure can be constructed by using syntactic rules (such as CFG, Context-Free Grammar), and grammatical structure can be obtained by constructing vocabulary sequences through syntactic rules.

[0154] In this way, by analyzing information such as sentence vocabulary and word sequence, the structural features of independent sentences can be more accurately identified, which helps to better understand the language characteristics of speakers in different regions. By analyzing sentence vocabulary and word sequence, the sentence structure can be obtained. The sentence structure can reflect the logical relationship between the main components of the sentence, which helps to better understand and analyze the sentence.

[0155] S3322, analyzing the sentence vocabulary and sentence structure to obtain language features.

[0156] It can be understood that by counting the usage frequency of each word, we can obtain the word usage preferences in different regions and analyze the common word collocations, that is, the special way of collocation of specific words, as the peculiarities expressed by the word selection in the dialogue information, and then use the different sentence structures in different regions as the peculiarities expressed by the grammatical structure in the dialogue information, which together constitute the voice characteristics expressed by different regions.

[0157] The feature model can also be used to extract features from sentence vocabulary and sentence structure to directly obtain language features. That is, the sentence vocabulary and sentence structure are input into the feature model, and the feature model then outputs the corresponding language features. The training process of the feature model can use the data processed from the sentence vocabulary, sentence structure and language features as the training data set of the sentiment tendency model, and then input the training data set of the feature model into the feature model for training and learning, and finally obtain the feature model.

[0158] In a possible implementation, in step S3322, the language features are obtained by analyzing the sentence vocabulary and sentence structure, including:

[0159] S33221, extracting features according to the sentence structure to obtain structural features of the language features; wherein the structural features are used to reflect the characteristics of the grammatical structure shown in the language used in different regions.

[0160] It is understandable that different regions have different usage habits of sentence structure features. By analyzing the sentence structure, the dependency relationship of each word in the sentence structure is obtained, and the dependency relationship is determined as the structural feature of the language feature. For example, compared with the structural feature of (subject-predicate-object) in standard Mandarin, the dependency relationship of each word in the Shandong dialect can be a dependency relationship of (predicate-object-subject), which is the structural feature of the Shandong dialect. Or the dependency relationship of each word in the southwest region can be a dependency relationship of (predicate-object), which is the structural feature of the southwest dialect. And so on, but not limited to this.

[0161] S33222. Analyze according to the sentence vocabulary to obtain the lexical features of the language features, where the lexical features are used to reflect the characteristics of lexical selection shown in the languages used in different regional locations.

[0162] It can be understood that by using a word frequency statistics tool to analyze the sentence vocabulary, common words, rare words, common collocations, etc. can be obtained as the lexical features of different regional locations. For example, "做咩" in Cantonese, "食咗饭未" in Cantonese, "恰饭" in the southern region of China, "你摸几岁?" in Xiang dialect, etc., but not limited to this.

[0163] Such a setting can help better understand the grammatical structure and lexical selection of the languages used in different regional locations, thereby improving the ability to understand and master the languages. It can also help better understand the vocabulary usage and language style preferences in the languages, so as to better understand and express the meaning and emotions of the languages.

[0164] S333. Confirm the emotional features and language features as communication features.

[0165] It can be understood that the emotional features and language features demonstrated by the dialects in different regional locations are used as the communication features corresponding to different regional locations.

[0166] With such a setting, through emotional feature analysis, the emotional state and attitude tendency in the dialogue information can be accurately obtained. Through language feature analysis, information such as the words and syntactic structures used in the dialogue information can be obtained. By combining and analyzing the emotional features and language features, more comprehensive and accurate communication features can be obtained.

[0167] S400. Analyze according to the dialogue information, communication features and sentence meaning to obtain differential vocabulary information, where the differential vocabulary information is used to reflect the formal differences and semantic differences between the vocabulary used by people in different regional locations in their daily lives and the vocabulary used in standard Mandarin.

[0168] It can be understood that the formal difference refers to the difference between the styles of the vocabulary used in standard Mandarin to express the same meaning and the styles of the vocabulary used in different regional locations. For example, "咩" in Cantonese and "什么" in standard Mandarin express the same meaning, but use different vocabulary styles. The semantic difference refers to the difference between the meaning expressed by the same vocabulary style in different regional locations and the meaning expressed in standard Mandarin. For example, "恰" in the southern region means "eat", while in standard Mandarin, "恰" is usually used as an adverb to describe that the degree, state and expectation are in line.

[0169] Dialogue information can be screened and extracted based on communication features to obtain words that represent the same thing or concept in different regional locations and the vocabulary in standard Mandarin that represents the same thing or concept. Then, it is split according to the sentence meaning and meaning-matched with each word to finally obtain differential vocabulary information.

[0170] It is also possible to compare the dialogue information with a preset sentence set to obtain differential sentences, and finally compare the differential sentences with the sentence meaning to ultimately obtain differential vocabulary information. The preset sentence set refers to a collection of independent sentences formed in daily communication using standard Mandarin as the communication language.

[0171] In a possible implementation manner, in step S400, based on the dialogue information, communication features, and sentence meaning, analysis is performed to obtain differential vocabulary information, including:

[0172] S410, based on the communication features, extract the differential words for obtaining differential vocabulary information from the dialogue information; among them, the differential words are used to reflect words that represent the same thing or concept in different regional locations and the vocabulary in standard Mandarin that represents the same thing or concept.

[0173] It can be understood that the language features in the communication features are used as extraction features in the dialogue information to extract the dialogue information and obtain differential words from the dialogue information. Exemplarily, if a piece of dialogue information is "你最近忙咩呀?有冇时间一齐去饮茶?" (What have you been busy with lately? Do you have time to go for tea together?), by using the voice features in the communication features to extract features from the dialogue information, the differential words for differential vocabulary information obtained are "咩", "冇", "齐", and so on.

[0174] S420, based on the communication features, split the sentence meaning to obtain the word meaning; among them, the word meaning is used to reflect the meaning expressed by the vocabulary in the sentence meaning.

[0175] It can be understood that according to the language features in the communication features, the sentence meaning is split. A complex sentence is decomposed into multiple independent words, and the specific meaning of each word is extracted from them. Exemplarily, if the sentence meaning is "你最近忙什么呀?有没有时间一起去喝茶?" (What have you been busy with lately? Do you have time to go for tea together?), by splitting the sentence meaning, the word meaning obtained is "你", "最近", "忙", "什么", "呀", "有", "没有", "时间", "一起", "去", "喝", "茶", and so on.

[0176] S430, match the differential words with the word meaning to obtain the differential word meaning of the differential vocabulary information; among them, the differential word meaning is used to reflect the meaning expressed by the differential words.

[0177] It can be understood that the style and meaning of a word together constitute a complete word. By matching the different words with the word meanings, the different meanings of the different words can be finally obtained. Exemplarily, if the different words are "咩", "冇", "齐", and the word meanings are "你", "最近", "忙", "什么", "呀", "有", "没有", "时间", "一起", "去", "喝", "茶", by matching the different words with the word meanings, it is finally obtained that the word meaning corresponding to the different word "咩" is "什么", the word meaning corresponding to the different word "冇" is "没有", and the word meaning corresponding to the different word "齐" is "一起", and so on.

[0178] With such settings, non-standard words used in different regions can be analyzed and identified. The information of different words can be effectively extracted, and their word meanings can be deeply understood. It provides basic construction resources for the teaching resource library of teaching Chinese as a foreign language. By matching the meaning of each different word in the sentence, the specific meaning of the different word can be obtained. The ambiguity of the word can be eliminated to ensure the exact meaning of each word in a specific context.

[0179] S500, construct a teaching resource library of teaching Chinese as a foreign language based on communication characteristics, different word information, and regional information.

[0180] It can be understood that based on communication characteristics, constructing from different word information and regional information can identify the language characteristics and emotional characteristics of different regional locations, including different words and sentence expressions of local dialects. By collecting and organizing this information, it can help learners of teaching Chinese as a foreign language better understand and use Chinese in different regional locations. The construction steps of the teaching resource library of teaching Chinese as a foreign language can be to first confirm that the construction goal is to strengthen the communication ability between non-Chinese native learners with a certain Chinese foundation and local people. The construction steps of the teaching resource library of teaching Chinese as a foreign language can be to create a learning module, an audio teaching module, and a scenario analysis module through communication characteristics, different word information, and regional information. Finally, the teaching resource library of teaching Chinese as a foreign language is composed of the learning module, the audio teaching module, and the scenario analysis module.

[0181] Exemplarily, the communication characteristics and the difference vocabulary information can be classified according to the regional information to obtain the regional information label of the Chinese teaching resource library for foreign languages. A learning module is created according to the difference vocabulary information. The creation process of the learning module can be to list a difference vocabulary table reflecting the difference vocabulary interpretation through the difference vocabulary information. List the difference words and the marked difference meanings through the difference vocabulary table, and provide context example sentences using the difference vocabulary. The difference vocabulary table and the context example sentences are determined as a learning module. An emotional module is created according to the communication characteristics and the difference vocabulary information. The creation process of the emotional module can be to list a pronunciation example table reflecting the difference vocabulary under different emotional conditions through the communication characteristics and the difference vocabulary. Provide an emotional example table corresponding to the difference vocabulary under different emotional conditions through the communication characteristics. Determine the pronunciation example table and the emotional example table as an emotional module. A situation analysis module is created according to the communication characteristics and the difference vocabulary information. The creation process of the situation analysis module can be to list a background example sentence table with difference vocabulary under different situation backgrounds according to the difference vocabulary information, and then describe the situation communication characteristics (such as grammar, tone, etc.) under different situation backgrounds in the background example sentence table through the communication characteristics, and determine the background example sentence table and the situation communication characteristics as a situation analysis module.

[0182] In this way, different communication characteristics of Chinese in different regions are obtained from the dialogue information, and a resource library of Chinese teaching as a foreign language is constructed. A large amount of construction data of the resource library of Chinese teaching as a foreign language can be quickly obtained. By constructing the resource library of Chinese teaching as a foreign language by combining the difference vocabulary information with the regional information, the dialects can be classified and collected from different regions, so as to help non-native Chinese learners better understand the actual situations that may be encountered in daily communication and enhance the language application ability of non-native Chinese learners.

[0183] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0184] Corresponding to the method for constructing a resource library for teaching Chinese as a foreign language described in the above embodiment, the embodiment of the present application also provides a system for constructing a resource library for teaching Chinese as a foreign language, and each module of the system can implement each step of the method for constructing a resource library for teaching Chinese as a foreign language. Figure 3 A structural block diagram of a system for constructing a resource library for teaching Chinese as a foreign language provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0185] Reference Figure 3 , the Chinese teaching resource library construction system for foreign languages ​​includes:

[0186] The first acquisition module is used to acquire dialogue information; wherein the dialogue information is used to reflect the dialogue content generated when two or more communicators communicate.

[0187] The second acquisition module is used to acquire the region information corresponding to the dialogue information based on the dialogue information; wherein the region information is used to reflect the regional location associated with the dialogue information.

[0188] The first analysis module is used to analyze the dialogue information to obtain communication characteristics and sentence meanings; wherein the communication characteristics are used to reflect the language characteristics and language attributes reflected in the process of interpersonal communication; and the sentence meaning is used to reflect the meaning expressed by the dialogue information.

[0189] The second analysis module is used to analyze the dialogue information, communication characteristics and sentence meaning to obtain differential vocabulary information; wherein the differential vocabulary information is used to reflect the formal differences and meaning differences between the vocabulary used by people in different regions in their daily lives and the vocabulary used in standard Mandarin.

[0190] The construction module is used to construct a Chinese teaching resource library for foreigners based on communication characteristics, differential vocabulary information and regional information.

[0191] It should be noted that the information interaction, execution process and other contents between the above-mentioned modules are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0192] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the Chinese teaching resource library construction system is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0193] The present application also provides a device for constructing a resource library for teaching Chinese as a foreign language. Figure 4 This is a schematic diagram of the structure of a Chinese teaching resource library construction device 4 provided in an embodiment of the present application. Figure 4As shown, the Chinese teaching resource library construction device 4 of this embodiment includes: at least one processor 40 ( Figure 4 Only one is shown), at least one memory 41 ( Figure 4 Only one is shown in the figure) and a computer program 42 stored in the at least one memory 41 and executable on the at least one processor 40. When the processor 40 executes the computer program 42, the Chinese teaching resource library construction device 4 implements the steps in any of the above-mentioned methods for constructing a Chinese teaching resource library, or implements the functions of each module / unit in the above-mentioned system embodiments.

[0194] Exemplarily, the computer program 42 may be divided into one or more modules / units, which are stored in the memory 41 and executed by the processor 40 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 42 in the device 4 for constructing a resource library for teaching Chinese as a foreign language.

[0195] The Chinese teaching resource library construction device 4 can be a computing device such as a desktop computer, a notebook, a handheld computer, etc. The Chinese teaching resource library construction device 4 can include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art can understand that Figure 4 The device 4 for constructing a resource library for teaching Chinese as a foreign language is merely an example and does not constitute a limitation on the device 4 for constructing a resource library for teaching Chinese as a foreign language. The device 4 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the device may also include input and output devices, network access devices, buses, etc.

[0196] The processor 40 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0197] In some embodiments, the memory 41 may be an internal storage unit of the Chinese teaching resource library construction device 4, such as a hard disk or memory of the Chinese teaching resource library construction device 4. In other embodiments, the memory 41 may also be an external storage device of the Chinese teaching resource library construction device 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the Chinese teaching resource library construction device 4. Further, the memory 41 may also include both the internal storage unit of the Chinese teaching resource library construction device 4 and an external storage device. The memory 41 is used to store an operating system, an application program, a boot loader (BootLoader), data and other programs, such as the program code of the computer program, etc. The memory 41 may also be used to temporarily store data that has been output or is to be output.

[0198] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0199] The embodiment of the present application provides a computer program product. When the computer program product is run on a device for constructing a resource library for teaching Chinese as a foreign language, the device for constructing a resource library for teaching Chinese as a foreign language implements the steps in any of the above method embodiments.

[0200] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. According to this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the construction device of the Chinese teaching resource library for foreigners, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk.

[0201] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0202] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0203] In the embodiments provided in the present application, it should be understood that the disclosed Chinese teaching resource library construction equipment and system can be implemented in other ways. For example, the Chinese teaching resource library construction system embodiment described above is only schematic, for example, the division of the modules or units is only a logical function division, and there can be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0204] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0205] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for constructing a resource library for teaching Chinese as a foreign language, characterized in that: include: Acquiring dialogue information; wherein the dialogue information is used to reflect the dialogue content generated when two or more communicators communicate; Based on the conversation information, obtaining the region information corresponding to the conversation information; wherein the region information is used to reflect the regional location associated with the conversation information; Analyzing the dialogue information to obtain communication features and sentence meanings; wherein the communication features are used to reflect the language characteristics and emotional attributes reflected in the process of interpersonal communication; and the sentence meanings are used to reflect the meaning expressed by the dialogue information; Analyze the dialogue information, the communication features and the meaning of the sentences to obtain difference vocabulary information; wherein the difference vocabulary information is used to reflect the difference in form and meaning between the vocabulary used in daily life by people in different regions and the vocabulary used in standard Mandarin; A Chinese teaching resource library for foreigners is constructed based on the communication characteristics, the difference vocabulary information and the regional information.

2. The method for constructing a resource library for teaching Chinese as a foreign language according to claim 1, characterized in that: The analyzing the dialogue information to obtain communication features and sentence meanings includes: Data processing is performed on the dialogue information to obtain sentence information and voice information; wherein the sentence information is used to reflect a sentence in the dialogue information that expresses a complete thought, viewpoint or information; and the voice information is used to reflect the voice audio in the dialogue information; Analyze the sentence information to obtain the sentence meaning; The communication features are obtained by analyzing the voice information and the sentence information.

3. The method for constructing a resource library for teaching Chinese as a foreign language as claimed in claim 2, characterized in that: The step of performing data processing according to the dialogue information to obtain sentence information includes: Based on the separators in the dialogue information, a sentence subset is obtained from the dialogue information; wherein the separators include a period, a question mark, and an exclamation mark appearing in a sentence; and the sentence subset is used to reflect a set of independent sentences in the dialogue information; Performing a similarity comparison analysis on the words in each independent sentence in the sentence subset and the words in each corresponding independent sentence in the preset sentence set, and obtaining a plurality of similarities corresponding to the words in each independent sentence; the preset sentence set is used to reflect the set of independent sentences in standard Mandarin; the similarity is used to reflect the degree of similarity between the words in each independent sentence in the sentence subset and the words in each corresponding independent sentence in the preset sentence set; Performing mean processing on the multiple similarities to obtain a screening value; wherein the screening value is used to reflect the degree of similarity between each independent sentence in the sentence subset and each corresponding independent sentence in the preset sentence set; A comparative analysis is performed based on the filtering value and a preset filtering value, and sentence information is obtained from the sentence subset.

4. The method for constructing a resource library for teaching Chinese as a foreign language as claimed in claim 2, characterized in that: The analyzing the voice information and the sentence information to obtain the communication features includes: Analyzing the voice information and the sentence information to obtain an emotional feature; wherein the emotional feature is used to reflect the emotional attitude embodied when the sentence information is expressed; Analyzing the sentence information to obtain language features; the language features are used to reflect the peculiarities of vocabulary selection and grammatical structure usage habits in the dialogue information; The emotional features and the language features are identified as communication features.

5. The method for constructing a resource library for teaching Chinese as a foreign language as claimed in claim 4, characterized in that: The analyzing the voice information and the sentence information to obtain the emotion feature includes: Analyze the voice information to obtain a plurality of voice data; wherein the voice data corresponds to the sentence information one by one, and the voice data includes speech speed and intonation; Processing the plurality of voice data to obtain average voice data; wherein the average voice data is used to reflect the average value of the plurality of voice data, including the average value of speech speed and the average value of intonation; The emotion feature is obtained by analyzing the average voice data and the voice data.

6. The method for constructing a resource library for teaching Chinese as a foreign language according to claim 5, characterized in that: The emotional features are obtained by analyzing the average voice data and the voice data: According to the comparison and analysis between the voice data and the average voice data, a speech speed difference value and a intonation difference value are obtained; wherein the speech speed difference value is used to reflect the difference between the speech speed in the voice data and the speech speed in the average voice data; the intonation difference value is used to reflect the difference between the intonation in the voice data and the intonation in the average voice data; Analyzing the speech speed difference to obtain an emotion polarity value; wherein the emotion polarity value is used to reflect the value of the emotion tendency; Analyze the intonation difference to obtain an emotion intensity value; wherein the emotion intensity value is used to reflect the intensity of the emotion; Analyzing the emotion polarity value and the emotion intensity value to obtain an emotion feature point; wherein the emotion feature point is used to reflect the emotion embodied by the emotion polarity value and the emotion intensity value of the speech data; The emotional feature points are matched with a preset emotional quadrant to obtain an emotional feature; wherein the preset emotional quadrant is used to reflect a quadrant composed of the emotional polarity value and the emotional intensity value.

7. The method for constructing a resource library for teaching Chinese as a foreign language according to claim 4, characterized in that: The analyzing according to the sentence information to obtain language features includes: Analyze the sentence information to obtain sentence structure and sentence vocabulary; wherein the sentence structure is used to reflect the combination mode within the sentence; and the sentence vocabulary is used to reflect the words that make up the sentence; The language features are obtained by analyzing the sentence vocabulary and the sentence structure.

8. The method for constructing a resource library for teaching Chinese as a foreign language according to claim 7, characterized in that: The analyzing according to the sentence information to obtain the sentence structure and sentence vocabulary includes: Based on vocabulary types, the sentence information is split and processed to obtain sentence vocabulary; wherein the vocabulary types include verbs, nouns, adjectives, adverbs and prepositions; Analyzing the sentence vocabulary to obtain a vocabulary sequence; wherein the vocabulary sequence is used to reflect the sequence of appearance order of the sentence vocabulary obtained by splitting the sentence information; Analyze according to the vocabulary sequence to obtain a sentence structure; And / or, the analyzing the sentence vocabulary and the sentence structure to obtain language features includes: Extracting features according to the sentence structure to obtain structural features of the language features; wherein the structural features are used to reflect the characteristics of the grammatical structure shown in the language used in different regions; The vocabulary of the sentence is analyzed to obtain the vocabulary features of the language features; wherein the vocabulary features are used to reflect the characteristics of vocabulary selection shown in the language used in different regional locations.

9. The method for constructing a resource library for teaching Chinese as a foreign language according to claim 1, characterized in that: The analyzing according to the dialogue information, the communication characteristics and the sentence meaning to obtain the difference vocabulary information includes: Based on the communication characteristics, extracting difference words to obtain difference vocabulary information from the dialogue information; wherein the difference words are used to reflect the words representing the same thing or concept in different locations and the words representing the same thing or concept in standard Mandarin; Based on the communication features, the sentence meaning is split to obtain word meanings; wherein the word meanings are used to reflect the meanings expressed by the words in the sentence meaning; The difference words are matched with the word meanings to obtain the difference word meanings of the difference vocabulary information; wherein the difference word meanings are used to reflect the meanings expressed by the difference words.

10. A system for constructing a resource library for teaching Chinese as a foreign language, characterized in that: include: A first acquisition module is used to acquire dialogue information; wherein the dialogue information is used to reflect the dialogue content generated when two or more communicators communicate; A second acquisition module, configured to acquire, based on the conversation information, region information corresponding to the conversation information; wherein the region information is used to reflect a region location associated with the conversation information; A first analysis module is used to analyze the dialogue information to obtain communication characteristics and sentence meanings; wherein the communication characteristics are used to reflect the language characteristics and language attributes reflected in the process of interpersonal communication; and the sentence meaning is used to reflect the meaning expressed by the dialogue information; A second analysis module is used to analyze the dialogue information, the communication characteristics and the sentence meaning to obtain difference vocabulary information; wherein the difference vocabulary information is used to reflect the difference in form and meaning between the vocabulary used in daily life by people in different regions and the vocabulary used in standard Mandarin; A construction module is used to construct a Chinese teaching resource library for foreign languages ​​based on the communication characteristics, the difference vocabulary information and the regional information.

Images