CN111401074A - Short text emotion tendency analysis method, system and device based on Hadoop - Google Patents
Short text emotion tendency analysis method, system and device based on Hadoop Download PDFInfo
- Publication number
- CN111401074A CN111401074A CN202010258426.2A CN202010258426A CN111401074A CN 111401074 A CN111401074 A CN 111401074A CN 202010258426 A CN202010258426 A CN 202010258426A CN 111401074 A CN111401074 A CN 111401074A
- Authority
- CN
- China
- Prior art keywords
- emotion
- module
- word segmentation
- short text
- hadoop
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a short text emotion tendency analysis method, system and device based on Hadoop, belonging to the field of big data; the system is used for acquiring short text data related to microblog hot events, performing word segmentation processing on the data based on a Hadoop platform, performing matching by using an emotion analysis corpus, and comprehensively calculating the emotion direction and the emotion intensity of the hot events according to the matching result, so that the emotion tendency of the short text is higher in accuracy and value, the microblog data related to the hot events are processed and analyzed, the attitude of a microblog user on a conversation topic is mastered, the development trend of the topic on the microblog platform is further judged, and the value-added effect of the data is finally realized.
Description
Technical Field
The invention discloses a short text emotion tendency analysis method, system and device based on Hadoop, and relates to the technical field of big data.
Background
With the development of the internet, social network platforms such as forums, blogs and microblogs are emerging continuously, and microblogs are developed rapidly by means of the characteristics of fragmentization of propagation contents, rooting of propagation main bodies and the like. The platform with the largest user group scale and social influence belongs to the Xinlang microblog. Massive short text information is generated due to the interactivity and instantaneity of the microblog, the short text contains a large amount of data information content, the data information content is analyzed to obtain the public opinion condition of the hot event in the social network platform, namely the emotional tendency analysis of the hot event, but the accuracy and the value of the data content obtained by analyzing the emotional direction of the text are low, and the analysis of the text emotional strength is lacked;
hadoop is a distributed system infrastructure developed by the Apache foundation, and the most core design of the Hadoop framework is HDFS and MapReduce. The HDFS provides storage for massive data, and the MapReduce provides calculation for the massive data;
therefore, the problems are solved by designing a method, a system and a device for analyzing short text emotion tendentiousness based on Hadoop.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a short text emotion tendency analysis method, a system and a device based on Hadoop, and the adopted technical scheme is as follows:
a short text emotion tendency analysis method based on Hadoop comprises the following specific steps:
acquiring short text data related to a microblog hot event; the word segmentation processing is carried out on the data based on a Hadoop platform, matching is carried out by utilizing an emotion analysis corpus, and the emotion direction and the emotion intensity of the hot event are obtained through comprehensive calculation according to the matching result, so that the emotion tendentiousness of the short text is obtained.
The Hadoop platform performs word segmentation processing on data by using a MapReduce model, and specifically comprises the following steps:
the method comprises the steps that S01, a Map function divides an input text into a key value and microblog content in a behavior unit;
s02, calling an IKAnalyzer tool by a Map function to perform word segmentation processing on microblog contents, and performing matching by utilizing an emotion analysis corpus;
and the S03Reduce function summarizes the intermediate results and outputs the final result to the HDFS file system.
The emotion analysis corpus in the step S02 includes a positive evaluation corpus and a negative evaluation corpus, and the specific steps include:
s12, utilizing the Map function to call an IKAnalyzer tool package to perform word segmentation processing on microblog contents;
s22, matching each obtained word with a positive evaluation corpus and a negative evaluation corpus in an emotion analysis corpus respectively;
s32 outputs a key-value pair in the form of < key, value >, completing the word segmentation process.
The method for acquiring short text data related to microblog hot events comprises the following steps:
obtaining through an API (application program interface) of the microblog; or distributed data acquisition by simulating login by using the web crawler.
A short text sentiment tendency analysis system based on Hadoop comprises a data acquisition module, a word segmentation processing module and a sentiment tendency calculation module;
a data acquisition module: acquiring short text data related to a microblog hot event;
a word segmentation processing module: performing word segmentation processing on the data based on a Hadoop platform, and performing matching by using an emotion analysis corpus;
an emotion tendency calculation module: and comprehensively calculating the emotion direction and the emotion intensity of the hot spot event according to the matching result, thereby obtaining the emotion tendentiousness of the short text.
The word segmentation processing module is used for carrying out word segmentation processing on data through a MapReduce model based on a Hadoop platform and carrying out matching by utilizing an emotion analysis corpus;
the word segmentation processing module specifically comprises a text splitting module, a word segmentation matching module and a result summarizing module:
a text splitting module: splitting an input text into a key value and microblog content by a Map function in a behavior unit;
a word segmentation matching module: the Map function calls an IKAnalyzer tool to perform word segmentation processing on microblog content, and matching is performed by utilizing an emotion analysis corpus;
a result summarizing module: and the Reduce function summarizes the intermediate results and outputs the final result to the HDFS file system.
The word segmentation matching module specifically comprises a calling module, a classification matching module and a key value pair output module;
a calling module: utilizing a Map function to call an IKAnalyzer tool package to perform word segmentation processing on microblog contents;
a classification matching module: matching each obtained word with a positive evaluation corpus and a negative evaluation corpus in an emotion analysis corpus respectively;
a key-value pair output module: and outputting the key value pair in the form of < key, value > to complete the word segmentation processing flow.
The data acquisition module acquires short text data related to microblog hot events through a microblog API (application program interface) interface or by utilizing distributed data acquisition of web crawler simulated login.
A Hadoop-based short text sentiment orientation analysis device comprises a memory and a sentiment orientation analysis processor;
the memory is used for storing a computer program for analyzing the emotion tendentiousness of the short text;
the emotion tendentiousness analysis processor, when executing the computer program, is configured to implement the Hadoop-based short text emotion tendentiousness analysis method according to any one of claims 1 to 4.
The invention has the beneficial effects that: the system is used for acquiring short text data related to microblog hot events, performing word segmentation processing on the data based on a Hadoop platform, performing matching by using an emotion analysis corpus, and comprehensively calculating the emotion direction and the emotion intensity of the hot events according to the matching result, so that the emotion tendency of the short text is higher in accuracy and value, the microblog data related to the hot events are processed and analyzed, the attitude of a microblog user on a conversation topic is mastered, the development trend of the topic on the microblog platform is further judged, and the value-added effect of the data is finally realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of the operation of the system of the present invention; FIG. 2 is a block diagram of the architecture of the system of the present invention; FIG. 3 is a schematic diagram of the structure of the apparatus of the present invention; FIG. 4 is a program structure diagram of the MapReduce model in the present invention; FIG. 5 is a word segmentation process flow diagram of the present invention.
Detailed Description
The present invention is further described below in conjunction with the following figures and specific examples so that those skilled in the art may better understand the present invention and practice it, but the examples are not intended to limit the present invention.
The first embodiment is as follows:
a short text emotion tendency analysis method based on Hadoop comprises the following specific steps:
acquiring short text data related to a microblog hot event through an API (application programming interface) of a microblog; performing word segmentation processing on the data based on a Hadoop platform, performing matching by using an emotion analysis corpus, and comprehensively calculating the emotion direction and the emotion intensity of a hot event according to a matching result so as to obtain the emotion tendency of the short text;
after authorized by an Oauth2.0 user, a worker uses twenty types of API interfaces including microblogs, comments, users and relations opened by a microblog platform in any development environment to meet the requirements of various products.
Example two:
acquiring short text data related to a microblog hot event by using distributed data acquisition of simulated login of a web crawler; performing word segmentation processing on the data based on a Hadoop platform, performing matching by using an emotion analysis corpus, and comprehensively calculating the emotion direction and the emotion intensity of a hot event according to a matching result so as to obtain the emotion tendency of the short text;
further, the Hadoop platform performs word segmentation processing on the data by using a MapReduce model, and the specific steps are as follows:
the method comprises the steps that S01, a Map function divides an input text into a key value and microblog content in a behavior unit;
s02, calling an IKAnalyzer tool by a Map function to perform word segmentation processing on microblog contents, and performing matching by utilizing an emotion analysis corpus;
s03, summarizing the intermediate results by the Reduce function, and outputting the final result to an HDFS file system;
further, the emotion analysis corpus in S02 includes a positive evaluation corpus and a negative evaluation corpus, and the specific steps include:
s12, utilizing the Map function to call an IKAnalyzer tool package to perform word segmentation processing on microblog contents;
s22, matching each obtained word with a positive evaluation corpus and a negative evaluation corpus in an emotion analysis corpus respectively;
s32, outputting key value pairs in a form of < key, value > to complete the word segmentation processing flow;
after the word segmentation processing of S12, reading in the forward corpus, if the word appears in the text word segmentation, scoring +1, reading in the next forward word, and repeating the matching; if the word does not appear in the text segmentation, directly reading the next forward word, and repeatedly matching; reading a negative corpus, if the word appears in the text segmentation, scoring-1, reading the next negative word, and repeatedly matching; and if the negative words do not appear in the text word segmentation, directly reading the next negative word, and repeatedly matching. And calculating a final tendency value, outputting a key value pair in a form of < key, value >, and finishing the word segmentation processing flow.
Example three:
a short text sentiment tendency analysis system based on Hadoop comprises a data acquisition module, a word segmentation processing module and a sentiment tendency calculation module;
a data acquisition module: acquiring short text data related to a microblog hot event through an API (application programming interface) of a microblog;
a word segmentation processing module: performing word segmentation processing on the data based on a Hadoop platform, and performing matching by using an emotion analysis corpus;
an emotion tendency calculation module: and comprehensively calculating the emotion direction and the emotion intensity of the hot spot event according to the matching result, thereby obtaining the emotion tendentiousness of the short text.
After authorized by an Oauth2.0 user, a worker uses twenty types of API interfaces including microblogs, comments, users and relations opened by a microblog platform in any development environment to meet the requirements of various products, after microblog data of related hot events are acquired by a data acquisition module of the system, word segmentation processing is performed and distributed by a word segmentation processing module, and finally, analysis results of emotion tendencies and text emotion intensities of the related microblogs are obtained by an emotion tendency calculation module, so that the microblog data related to the hot events are processed and analyzed, the attitude of microblog user conversation topics is mastered, the accuracy and microblog value of short text emotion tendentiousness analysis are improved, the development trend of the microblog platform is judged, and the value-added effect of the data is finally realized.
Example four:
a short text sentiment tendency analysis system based on Hadoop comprises a data acquisition module, a word segmentation processing module and a sentiment tendency calculation module;
a data acquisition module: acquiring short text data related to a microblog hot event by using distributed data acquisition of simulated login of a web crawler;
a word segmentation processing module: performing word segmentation processing on the data based on a Hadoop platform, and performing matching by using an emotion analysis corpus;
an emotion tendency calculation module: and comprehensively calculating the emotion direction and the emotion intensity of the hot spot event according to the matching result, thereby obtaining the emotion tendentiousness of the short text.
Furthermore, the microblog data read by the data acquisition module is a short text with length limitation; the short text is limited within 140 characters, so that the user viewpoint is easier to extract;
further, the word segmentation processing module performs word segmentation processing on microblog data by using a MapReduce model based on a Hadoop platform, and specifically comprises a text splitting module, a word segmentation matching module and a result summarizing module:
a text splitting module: splitting an input text into a key value and microblog content by a Map function in a behavior unit;
a word segmentation matching module: the Map function calls an IKAnalyzer tool to perform word segmentation processing on microblog content, and matching is performed by utilizing an emotion analysis corpus;
a result summarizing module: and the Reduce function summarizes the intermediate results and outputs the final result to the HDFS file system.
Still further, the emotion analysis corpus in the word segmentation matching module comprises a positive evaluation corpus and a negative evaluation corpus, and the word segmentation matching module specifically comprises a calling module, a classification matching module and a key value pair output module;
a calling module: utilizing a Map function to call an IKAnalyzer tool package to perform word segmentation processing on microblog contents;
a classification matching module: matching each obtained word with a positive evaluation corpus and a negative evaluation corpus in an emotion analysis corpus respectively;
a key-value pair output module: outputting key value pairs in a form of < key, value > to complete word segmentation processing flow;
after word segmentation processing is carried out by a calling module, a forward corpus is read in by a classification matching module, if the word appears in text word segmentation, the score is +1, the next forward word is read in, and matching is repeated; if the word does not appear in the text segmentation, directly reading the next forward word, and repeatedly matching; reading a negative corpus, if the word appears in the text segmentation, scoring-1, reading the next negative word, and repeatedly matching; if the negative words do not appear in the text word segmentation, the next negative word is directly read in, repeated matching is carried out, the final tendency value is calculated, the key value pair output module outputs the key value pairs in the form of < key, value >, and the word segmentation processing flow is completed.
Example five:
a Hadoop-based short text sentiment orientation analysis device comprises a memory and a sentiment orientation analysis processor;
the memory is used for storing a computer program for analyzing the emotion tendentiousness of the short text;
the emotion orientation analysis processor is used for implementing the Hadoop-based short text emotion orientation analysis method according to the first embodiment or the second embodiment when the computer program is executed.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (9)
1. A short text emotion tendency analysis method based on Hadoop is characterized by comprising the following specific steps:
acquiring short text data related to a microblog hot event; the word segmentation processing is carried out on the data based on a Hadoop platform, matching is carried out by utilizing an emotion analysis corpus, and the emotion direction and the emotion intensity of the hot event are obtained through comprehensive calculation according to the matching result, so that the emotion tendentiousness of the short text is obtained.
2. The Hadoop-based short text emotion tendency analysis method as claimed in claim 1, wherein said Hadoop platform performs word segmentation processing on data by using MapReduce model, and the specific steps are as follows:
the method comprises the steps that S01, a Map function divides an input text into a key value and microblog content in a behavior unit;
s02, calling an IKAnalyzer tool by a Map function to perform word segmentation processing on microblog contents, and performing matching by utilizing an emotion analysis corpus;
and the S03Reduce function summarizes the intermediate results and outputs the final result to the HDFS file system.
3. The Hadoop-based short text emotion tendentiousness analysis method as claimed in claim 2, wherein the emotion analysis corpus in S02 includes a positive evaluation corpus and a negative evaluation corpus, and the specific steps include:
s12, utilizing the Map function to call an IKAnalyzer tool package to perform word segmentation processing on microblog contents;
s22, matching each obtained word with a positive evaluation corpus and a negative evaluation corpus in an emotion analysis corpus respectively;
s32 outputs a key-value pair in the form of < key, value >, completing the word segmentation process.
4. The Hadoop-based short text sentiment orientation analysis method according to claim 3, wherein the method for acquiring short text data related to microblog hot events comprises the following steps:
obtaining through an API (application program interface) of the microblog; or distributed data acquisition by simulating login by using the web crawler.
5. A short text sentiment tendency analysis system based on Hadoop is characterized by comprising a data acquisition module, a word segmentation processing module and a sentiment tendency calculation module;
a data acquisition module: acquiring short text data related to a microblog hot event;
a word segmentation processing module: performing word segmentation processing on the data based on a Hadoop platform, and performing matching by using an emotion analysis corpus;
an emotion tendency calculation module: and comprehensively calculating the emotion direction and the emotion intensity of the hot spot event according to the matching result, thereby obtaining the emotion tendentiousness of the short text.
6. The Hadoop-based short text sentiment orientation analysis system according to claim 5, wherein the word segmentation processing module performs word segmentation processing on data through a MapReduce model based on a Hadoop platform and performs matching by using a sentiment analysis corpus;
the word segmentation processing module specifically comprises a text splitting module, a word segmentation matching module and a result summarizing module:
a text splitting module: splitting an input text into a key value and microblog content by a Map function in a behavior unit;
a word segmentation matching module: the Map function calls an IKAnalyzer tool to perform word segmentation processing on microblog content, and matching is performed by utilizing an emotion analysis corpus;
a result summarizing module: and the Reduce function summarizes the intermediate results and outputs the final result to the HDFS file system.
7. The Hadoop-based short text sentiment orientation analysis system according to claim 8, wherein the word segmentation matching module specifically comprises a calling module, a classification matching module and a key-value pair output module;
a calling module: utilizing a Map function to call an IKAnalyzer tool package to perform word segmentation processing on microblog contents;
a classification matching module: matching each obtained word with a positive evaluation corpus and a negative evaluation corpus in an emotion analysis corpus respectively;
a key-value pair output module: and outputting the key value pair in the form of < key, value > to complete the word segmentation processing flow.
8. The Hadoop-based short text sentiment orientation analysis system according to claim 7, wherein the data acquisition module acquires short text data related to microblog hot events through a microblog API (application program interface) interface or distributed data acquisition by using web crawler simulated login.
9. A short text sentiment orientation analysis device based on Hadoop is characterized by comprising a memory and a sentiment orientation analysis processor;
the memory is used for storing a computer program for analyzing the emotion tendentiousness of the short text;
the emotion tendentiousness analysis processor, when executing the computer program, is configured to implement the Hadoop-based short text emotion tendentiousness analysis method according to any one of claims 1 to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010258426.2A CN111401074A (en) | 2020-04-03 | 2020-04-03 | Short text emotion tendency analysis method, system and device based on Hadoop |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010258426.2A CN111401074A (en) | 2020-04-03 | 2020-04-03 | Short text emotion tendency analysis method, system and device based on Hadoop |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111401074A true CN111401074A (en) | 2020-07-10 |
Family
ID=71431512
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010258426.2A Pending CN111401074A (en) | 2020-04-03 | 2020-04-03 | Short text emotion tendency analysis method, system and device based on Hadoop |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111401074A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113221534A (en) * | 2021-05-25 | 2021-08-06 | 深圳和锐网络科技有限公司 | Text emotion analysis method and device, electronic equipment and storage medium |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102402606A (en) * | 2011-11-28 | 2012-04-04 | 中国科学院计算机网络信息中心 | High-efficiency text data mining method |
CN103544255A (en) * | 2013-10-15 | 2014-01-29 | 常州大学 | Text semantic relativity based network public opinion information analysis method |
WO2015043075A1 (en) * | 2013-09-29 | 2015-04-02 | 广东工业大学 | Microblog-oriented emotional entity search system |
CN105718590A (en) * | 2016-01-27 | 2016-06-29 | 福州大学 | Multi-tenant oriented SaaS public opinion monitoring system and method |
CN106372105A (en) * | 2016-08-19 | 2017-02-01 | 中国科学院信息工程研究所 | Spark platform-based microblog data preprocessing method |
CN107315778A (en) * | 2017-05-31 | 2017-11-03 | 温州市鹿城区中津先进科技研究院 | A kind of natural language the analysis of public opinion method based on big data sentiment analysis |
CN108549692A (en) * | 2018-04-13 | 2018-09-18 | 重庆邮电大学 | The method that sparse multivariate logistic regression model under Spark frames classifies to text emotion |
CN108763583A (en) * | 2018-06-11 | 2018-11-06 | 山东汇贸电子口岸有限公司 | A kind of microblog hot topic extracting method and system based on keyword search |
CN108829811A (en) * | 2018-06-08 | 2018-11-16 | 东莞迪赛软件技术有限公司 | healthy public sentiment monitoring method and system |
CN110472119A (en) * | 2019-07-17 | 2019-11-19 | 广东鼎义互联科技股份有限公司 | One kind being applied to government affairs the analysis of public opinion platform |
-
2020
- 2020-04-03 CN CN202010258426.2A patent/CN111401074A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102402606A (en) * | 2011-11-28 | 2012-04-04 | 中国科学院计算机网络信息中心 | High-efficiency text data mining method |
WO2015043075A1 (en) * | 2013-09-29 | 2015-04-02 | 广东工业大学 | Microblog-oriented emotional entity search system |
CN103544255A (en) * | 2013-10-15 | 2014-01-29 | 常州大学 | Text semantic relativity based network public opinion information analysis method |
CN105718590A (en) * | 2016-01-27 | 2016-06-29 | 福州大学 | Multi-tenant oriented SaaS public opinion monitoring system and method |
CN106372105A (en) * | 2016-08-19 | 2017-02-01 | 中国科学院信息工程研究所 | Spark platform-based microblog data preprocessing method |
CN107315778A (en) * | 2017-05-31 | 2017-11-03 | 温州市鹿城区中津先进科技研究院 | A kind of natural language the analysis of public opinion method based on big data sentiment analysis |
CN108549692A (en) * | 2018-04-13 | 2018-09-18 | 重庆邮电大学 | The method that sparse multivariate logistic regression model under Spark frames classifies to text emotion |
CN108829811A (en) * | 2018-06-08 | 2018-11-16 | 东莞迪赛软件技术有限公司 | healthy public sentiment monitoring method and system |
CN108763583A (en) * | 2018-06-11 | 2018-11-06 | 山东汇贸电子口岸有限公司 | A kind of microblog hot topic extracting method and system based on keyword search |
CN110472119A (en) * | 2019-07-17 | 2019-11-19 | 广东鼎义互联科技股份有限公司 | One kind being applied to government affairs the analysis of public opinion platform |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113221534A (en) * | 2021-05-25 | 2021-08-06 | 深圳和锐网络科技有限公司 | Text emotion analysis method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP2021089705A (en) | Method and device for evaluating translation quality | |
US9710829B1 (en) | Methods, systems, and articles of manufacture for analyzing social media with trained intelligent systems to enhance direct marketing opportunities | |
Rizki et al. | Comparison of stemming algorithms on Indonesian text processing | |
US10331723B2 (en) | Messaging digest | |
CN111767394A (en) | Abstract extraction method and device based on artificial intelligence expert system | |
CN110532575A (en) | Text interpretation method and device | |
CN110738056B (en) | Method and device for generating information | |
Alhassan et al. | A novel framework for Arabic dialect chatbot using machine learning | |
CN113204953A (en) | Text matching method and device based on semantic recognition and device readable storage medium | |
CN114357195A (en) | Knowledge graph-based question-answer pair generation method, device, equipment and medium | |
Quan et al. | Decoding social sentiment in dao: A comparative analysis of blockchain governance communities | |
CN113722441A (en) | Method, device and equipment for generating similar text and storage medium | |
CN111401074A (en) | Short text emotion tendency analysis method, system and device based on Hadoop | |
CN110377706B (en) | Search sentence mining method and device based on deep learning | |
CN116955578A (en) | Information processing method, device, equipment and medium of pre-training language model | |
US20230206007A1 (en) | Method for mining conversation content and method for generating conversation content evaluation model | |
CN112711943A (en) | Uygur language identification method, device and storage medium | |
CN112487188A (en) | Public opinion monitoring method and device, electronic equipment and storage medium | |
CN110263346B (en) | Semantic analysis method based on small sample learning, electronic equipment and storage medium | |
US20230317058A1 (en) | Spoken language processing method and apparatus, and storage medium | |
CN115130481A (en) | Model training method, model training device, model translation device, model training equipment and model translation equipment, and storage medium | |
CN110895924B (en) | Method and device for reading document content aloud, electronic equipment and readable storage medium | |
CN115510203B (en) | Method, device, equipment, storage medium and program product for determining answers to questions | |
CN117235236B (en) | Dialogue method, dialogue device, computer equipment and storage medium | |
US20240086768A1 (en) | Learning device, inference device, non-transitory computer-readable medium, learning method, and inference method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |