CN108197105B - Natural language processing method, device, storage medium and electronic equipment - Google Patents
Natural language processing method, device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN108197105B CN108197105B CN201711466311.7A CN201711466311A CN108197105B CN 108197105 B CN108197105 B CN 108197105B CN 201711466311 A CN201711466311 A CN 201711466311A CN 108197105 B CN108197105 B CN 108197105B
- Authority
- CN
- China
- Prior art keywords
- information
- natural language
- semantic analysis
- semantic
- weight
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a natural language processing method and device, a storage medium and electronic equipment. The method comprises the following steps: acquiring natural language information input by a user and related information associated with the natural language information; obtaining a plurality of semantic analysis information according to the natural language information; inputting the semantic analysis information and the relevant information into a prediction model, and obtaining a plurality of probability values corresponding to the semantic analysis information by the prediction model according to the relevant information; and determining the semantic analysis information with the maximum probability value from the plurality of probability values as target semantic analysis information. The natural language information is not only analyzed and identified, but also assisted and identified by the related information in the prediction model, so that the accuracy of analyzing and identifying the natural language information is improved.
Description
Technical Field
The present application relates to the field of communications technologies, and in particular, to a natural language processing method and apparatus, a storage medium, and an electronic device.
Background
The man-machine interaction mode between people and electronic equipment mainly comprises modes of clicking an icon menu by a mouse, inputting a command by a keyboard, controlling a touch screen and the like. However, these man-machine interaction methods require the user to perform specific control operations, such as clicking a specific icon and inputting a specific command, which is inconvenient for interaction.
With the development of artificial intelligence technology, human-computer interaction is carried out through the natural language of a user, the human-computer interaction can be conveniently and rapidly carried out, and the human-computer interaction can not be carried out only by being limited by a specific command or an icon. The natural language can enable a user to express own intention conveniently, quickly and accurately, can express the intention of the user really, and gradually becomes the most important man-machine interaction mode in the field of intelligent services.
However, because of the characteristics of openness, randomness, etc., semantic parsing is performed on natural language, and ambiguity is easily caused when the real meaning of the natural language is identified.
Disclosure of Invention
The application provides a natural language processing method, a natural language processing device, a storage medium and an electronic device, which can improve the recognition accuracy of natural language.
In a first aspect, an embodiment of the present application provides a natural language processing method, which is applied to an electronic device, and the method includes:
acquiring natural language information input by a user and related information associated with the natural language information;
obtaining a plurality of semantic analysis information according to the natural language information;
inputting the semantic analysis information and the relevant information into a prediction model, and obtaining a plurality of probability values corresponding to the semantic analysis information by the prediction model according to the relevant information;
and determining the semantic analysis information with the maximum probability value from the plurality of probability values as target semantic analysis information.
In a second aspect, an embodiment of the present application provides a natural language processing apparatus, which is applied to an electronic device, and the apparatus includes:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring natural language information input by a user and related information associated with the natural language information;
the second acquisition module is used for acquiring a plurality of semantic analysis information according to the natural language information;
a probability value obtaining module, configured to input the semantic parsing information and the related information into a prediction model, where the prediction model obtains probability values corresponding to the semantic parsing information according to the related information;
and the determining module is used for determining the semantic analysis information with the maximum probability value from the plurality of probability values as the target semantic analysis information.
In a third aspect, an embodiment of the present application provides a storage medium, on which a computer program is stored, which, when running on a computer, causes the computer to execute the above-mentioned natural language processing method.
In a fourth aspect, an embodiment of the present application provides an electronic device, which includes a processor and a memory, where the memory has a computer program, and the processor is configured to execute the above natural language processing method by calling the computer program.
According to the natural language processing method, the device, the storage medium and the electronic equipment, the natural language information input by a user and the related information associated with the natural language information are acquired; obtaining a plurality of semantic analysis information according to the natural language information; inputting the semantic analysis information and the related information into a prediction model, and obtaining a plurality of probability values corresponding to the semantic analysis information by the prediction model according to the related information; and determining the semantic analysis information with the maximum probability value from the plurality of probability values as target semantic analysis information. The natural language information is not only analyzed and identified, but also assisted and identified by the related information in the prediction model, so that the accuracy of analyzing and identifying the natural language information is improved, and the obtained final target semantic analysis information is more consistent with the real idea of the user.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments will be briefly introduced below. It is obvious that the drawings in the following description are only some embodiments of the application, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
Fig. 1 is a schematic view of an application scenario of a natural language processing apparatus according to an embodiment of the present application.
Fig. 2 is a first flowchart of a natural language processing method according to an embodiment of the present application.
Fig. 3 is a second flowchart of the natural language processing method according to the embodiment of the present application.
Fig. 4 is a third flowchart illustrating a natural language processing method according to an embodiment of the present application.
Fig. 5 is a fourth flowchart illustrating a natural language processing method according to an embodiment of the present application.
Fig. 6 is a fifth flowchart illustrating a natural language processing method according to an embodiment of the present application.
Fig. 7 is a schematic structural diagram of a natural language processing apparatus according to an embodiment of the present application.
Fig. 8 is a schematic structural diagram of a second natural language processing apparatus according to an embodiment of the present application.
Fig. 9 is a schematic structural diagram of a natural language processing apparatus according to an embodiment of the present application.
Fig. 10 is a schematic diagram of a fourth structure of a natural language processing apparatus according to an embodiment of the present application.
Fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Fig. 12 is another schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Referring to the drawings, wherein like reference numbers refer to like elements, the principles of the present application are illustrated as being implemented in a suitable computing environment. The following description is based on illustrated embodiments of the application and should not be taken as limiting the application with respect to other embodiments that are not detailed herein.
In the description that follows, specific embodiments of the present application will be described with reference to steps and symbols executed by one or more computers, unless otherwise indicated. Accordingly, these steps and operations will be referred to, several times, as being performed by a computer, the computer performing operations involving a processing unit of the computer in electronic signals representing data in a structured form. This operation transforms the data or maintains it at locations in the computer's memory system, which may be reconfigured or otherwise altered in a manner well known to those skilled in the art. The data maintains a data structure that is a physical location of the memory that has particular characteristics defined by the data format. However, while the principles of the application have been described in language specific to above, it is not intended to be limited to the specific form set forth herein, and it will be recognized by those of ordinary skill in the art that various of the steps and operations described below may be implemented in hardware.
The term module, as used herein, may be considered a software object executing on the computing system. The various components, modules, engines, and services described herein may be viewed as objects implemented on the computing system. The apparatus and method described herein may be implemented in software, but may also be implemented in hardware, and are within the scope of the present application.
The terms "first", "second", and "third", etc. in this application are used to distinguish between different objects and not to describe a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or modules is not limited to only those steps or modules listed, but rather, some embodiments may include other steps or modules not listed or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
Referring to fig. 1, fig. 1 is a schematic view of an application scenario of a natural language processing apparatus according to an embodiment of the present application. For example, the natural language processing device first obtains natural language information input by a user and related information associated with the natural language information; obtaining a plurality of semantic analysis information according to the natural language information, wherein the semantic analysis information comprises semantic analysis information a, semantic analysis information b and semantic analysis information c; inputting the semantic analysis information and the related information into a prediction model, and obtaining a plurality of probability values corresponding to the semantic analysis information by the prediction model according to the related information; and determining semantic analysis information a with the maximum probability value from the plurality of probability values as target semantic analysis information. And then displaying display information corresponding to the target semantic analysis information on the electronic equipment.
An execution subject of the natural language processing method may be the natural language processing apparatus provided in the embodiment of the present application, or an electronic device integrated with the natural language processing apparatus, where the natural language processing apparatus may be implemented in a hardware or software manner.
Embodiments of the present application will be described from the perspective of a natural language processing apparatus, which may be particularly integrated in an electronic device. The natural language processing method comprises the following steps: acquiring natural language information input by a user and related information associated with the natural language information; obtaining a plurality of semantic analysis information according to the natural language information; inputting the semantic analysis information and the related information into a prediction model, and obtaining a plurality of probability values corresponding to the semantic analysis information by the prediction model according to the related information; and determining the semantic analysis information with the maximum probability value from the plurality of probability values as target semantic analysis information.
It can be understood that the execution subject of the embodiment of the present application may be a terminal device such as a smart phone or a tablet computer.
Referring to fig. 2, fig. 2 is a first flowchart illustrating a natural language processing method according to an embodiment of the present application. The natural language processing method provided by the embodiment of the application is applied to the electronic equipment, and the specific flow can be as follows:
Natural language information may refer to language information that people use daily. The method can also be understood as the information of the user's daily expression or the similar daily expression composition mode.
The natural language information input by the user can be acquired by inputting the acquired character information through a keyboard, the keyboard input comprises a physical keyboard and a virtual keyboard, the virtual keyboard can comprise a keyboard displayed by a touch screen or a keyboard displayed by a display screen, and then the information is input in a mouse clicking mode and the like. The natural language information input by the user can also be obtained by voice input, such as obtaining input voice information through a microphone of the electronic equipment, and then recognizing and analyzing the voice information to convert the voice information into text information. The composing method of the character information is a composing mode of natural language. For example, the natural language information may be "i want to watch a movie".
When acquiring the natural language information, related information associated with the natural language information is also acquired.
Referring to fig. 3, fig. 3 is a second flowchart illustrating a natural language processing method according to an embodiment of the present application. The step of acquiring related information associated with the natural language information may include the following specific processes:
When the natural language information is acquired, recording a time point at this time as a mark time point. The marked point in time may be a current system time of the electronic device. The system time of the electronic device may be time shared by network synchronization, or may be time calculated according to a component of the electronic device after the time is set.
And after the marking time point is obtained, acquiring historical display information of a preset time period before the marking time point. The preset time may be a time set by the electronic device system, such as 3 minutes, 5 minutes, 10 minutes, and the like. The preset time may also be a time set by a user.
The history display information includes information appearing in a display screen of the electronic device. The history display information includes at least one of history input information, history dialogue information, history search information, and history browsing information.
The historical input information may be input within a predetermined time period, such as 3 minutes, before the time point is marked, and the input information from the user may be saved, such as stored in a memory, a cache, or the like. The input information includes information input in a chat interface, a search interface, and the like, and may also be information input in an input method interface. Even information entered at the input method interface, but later deleted. Such as information entered in a chat interface, followed by information not sent and deleted.
The historical conversation information may be conversation information that appears in the chat interface, including information entered by the user and information entered by other users.
The historical search information may be search information that the user clicked open in a search interface. If the user inputs a noun, a plurality of pieces of search information are popped up according to the name, then the user clicks one of the pieces of search information and enters a webpage corresponding to the search information, and the noun and the information corresponding to the webpage are both history search information. For example, the user inputs "Beijing Shenzhen", and retrieves information such as the air ticket from Beijing to Shenzhen, the train from Beijing to Shenzhen, different life experiences of Beijing Shenzhen, and the weather of Beijing Shenzhen are popped up, and then the weather of Beijing Shenzhen is clicked, so that the weather of Beijing Shenzhen and the weather of Beijing Shenzhen are kept as historical retrieval information.
The historical browsing information may be information that the user browses on the web page, such as the user does not enter any information in the browser, but clicks in a link provided by the browser.
And step 1013, screening from the history display information according to the natural language information to obtain related information related to the natural language information.
After the historical display information within the preset time period is obtained, screening is carried out according to the natural language information, irrelevant information is deleted, and relevant information relevant to the natural language information is reserved. If information including one or more characters in the natural language information is set as related information, the category of the natural language information is identified, information of the same category as the natural language information is set as related information, for example, if the natural language information is identified as a movie category, information about a movie is set as related information including movie name information, actor name information, scenario information, and the like.
Referring to fig. 4, fig. 4 is a third flowchart illustrating a natural language processing method according to an embodiment of the present application. The step of screening from the history display information according to the natural language information to obtain the related information associated with the natural language information may include the following specific processes:
According to the natural language information, the screening model screens out relevant information associated with the natural language information from the historical display information. More accurate and convenient. The text information corresponding to the natural language information can be disassembled and identified, if the words are disassembled, the words can be disassembled into 'I', 'want', 'see' and 'films', the words are screened respectively according to the disassembled words, the words can be further analyzed according to the disassembled words, the 'films' are main screening modes, the information related to the films is obtained by screening in the first round, then screening in the second round is carried out according to the 'see', the information related to the views is obtained, and the information related to the views is the information of videos. And then screening is carried out according to the 'I', and if others mention in the chat records, the information can be deleted, and only the related information in the history display information of the local electronic equipment is reserved. It should be noted that "i" and "want" may not be screened. After the natural language information is disassembled and identified, the importance of each disassembled sub-information can be set, the screening is carried out in sequence according to the importance, the screening can be stopped when the information obtained by screening is lower than a certain amount, and then the information obtained by the last screening or the last screening is determined to be the related information associated with the natural language information.
And 102, obtaining a plurality of semantic analysis information according to the natural language information.
And identifying the natural language information to obtain a plurality of semantic analysis information. One or more preset scenes can be preset, and then the natural language information is substituted into the one or more preset scenes to obtain a plurality of semantic analysis information.
Referring to fig. 5, fig. 5 is a fourth flowchart illustrating a natural language processing method according to an embodiment of the present application.
The keywords of the natural language information can be extracted first, if the natural language information is that "i want to see laughing and pride river lake", the natural language information is split first, so that several pieces of sub-information of "i", "want to see", "laughing and pride river lake" can be obtained, then the sub-information is sorted according to importance, and the first few are selected as the keywords.
And then, acquiring a corresponding preset scene according to the keyword, wherein the preset scene can comprise a movie scene, a novel scene and the like according to the keyword 'lauao river lake'.
And 1023, acquiring a plurality of semantic analysis information corresponding to the natural language information according to the plurality of preset semantic scenes.
And then semantic analysis information corresponding to the film and semantic analysis information corresponding to the novel are obtained.
The prediction model can be a convolutional neural network model, a cyclic neural network model, a Bayesian algorithm model or the like.
And inputting the plurality of semantic analysis information and the related information into a prediction model, wherein the prediction model can predict the plurality of semantic analysis information and obtain the probability corresponding to each semantic analysis information. And the related information can be combined to predict a plurality of semantic analysis information to obtain the probability corresponding to each semantic analysis information. The information source is richer, and the prediction is more accurate. It should be noted that the screening model in the above embodiments may be a different part of the same model as the prediction model, or the screening model may be a part of the prediction model. If the natural language information is 'i want to see laughing and pride river lake', the preset scenes can be obtained according to the keyword laughing and pride river lake and can comprise movie scenes, novel scenes and the like, and then semantic analysis information corresponding to the movies and semantic analysis information corresponding to the novel are obtained. The related information comprises the information of the film, so that the probability value of the semantic analysis information corresponding to the film can be improved, and the probability value is obviously larger than other semantic analysis information. For another example, the free language information is "beijing woolen", and the preset scene may include beijing basic information, beijing tourist attractions, beijing weather and the like according to the keyword beijing, so as to obtain semantic analysis information corresponding to the beijing basic information and semantic analysis information corresponding to the beijing tourist attractions, the beijing weather and the like. The related information includes information of weather, specifically, weather information of other places is included in the preceding sentences in the chat records, so that the probability value of semantic analysis information corresponding to Beijing weather can be improved, and the probability value is obviously greater than that of other semantic analysis information.
And 104, determining semantic analysis information with the maximum probability value from the plurality of probability values as target semantic analysis information.
And after the probability values corresponding to the plurality of semantic analysis information are obtained, the semantic analysis information with the maximum probability value is selected from the probability values, and the semantic analysis information is determined to be target analysis information. And then, corresponding information can be displayed according to the target analysis information. Such as showing movie links of luao river lake, movie blurs of luao river lake, etc.
Referring to fig. 6, fig. 6 is a fifth flowchart illustrating a natural language processing method according to an embodiment of the present application.
In step 201, natural language information input by a user and related information associated with the natural language information are acquired.
Natural language information may refer to language information that people use daily. The method can also be understood as the information of the user's daily expression or the similar daily expression composition mode. When acquiring the natural language information, related information associated with the natural language information is also acquired.
Step 202, obtaining a plurality of preset semantic scenes according to the natural language information and the related information, and respectively corresponding to a plurality of first weighted values of the plurality of preset semantic scenes.
The history display information includes information appearing in a display screen of the electronic device. The history display information includes at least one of history input information, history dialogue information, history search information, and history browsing information.
Obtaining a plurality of preset semantic scenes according to the natural language information, and then carrying out weight assignment on the plurality of preset semantic scenes according to the historical display information, namely, giving a weight value to each preset semantic scene and corresponding to the probability value of the weight value. Similarly, the natural language information and the historical display information can be input into a weight prediction model for prediction, and weight values corresponding to various preset semantic scenes are obtained. It should be noted that preset semantic scenes with weight values lower than the weight threshold may be excluded.
The natural language information can be analyzed in a preset semantic scene to obtain one or more semantic analysis information, and the weight value of the semantic analysis information analyzed in the same preset semantic scene can be a corresponding first weight value or a second weight value obtained after adjustment.
And inputting the plurality of semantic analysis information and the related information into a prediction model, wherein the prediction model can predict the plurality of semantic analysis information and obtain the probability corresponding to each semantic analysis information. And the related information can be combined to predict a plurality of semantic analysis information to obtain the probability corresponding to each semantic analysis information. The information source is richer, and the prediction is more accurate.
And multiplying the probability value corresponding to the semantic analysis information by the second weight value to obtain a plurality of weight probability values, and multiplying the probability value obtained by the semantic analysis information through the prediction model by the second weight value obtained before to be closer to the preset semantic scene. And selecting semantic analysis information with the maximum probability value from the multiple weight probability values as target semantic analysis information. And then, corresponding information is displayed according to the target semantic analysis information.
As can be seen from the above, the natural language processing method provided in the embodiment of the present application obtains the natural language information input by the user and the related information associated with the natural language information; obtaining a plurality of semantic analysis information according to the natural language information; inputting the semantic analysis information and the related information into a prediction model, and obtaining a plurality of probability values corresponding to the semantic analysis information by the prediction model according to the related information; and determining the semantic analysis information with the maximum probability value from the plurality of probability values as target semantic analysis information. The natural language information is not only analyzed and identified, but also assisted and identified by the related information in the prediction model, so that the accuracy of analyzing and identifying the natural language information is improved, and the obtained final target semantic analysis information is more consistent with the real idea of the user.
Referring to fig. 7, fig. 7 is a first structural diagram of a natural language processing apparatus according to an embodiment of the present application. The natural language processing apparatus 300 is applied to an electronic device, and the natural language processing apparatus 300 includes a first obtaining module 301, a second obtaining module 302, a probability value obtaining module 303, and a determining module 304. Wherein:
the first obtaining module 301 is configured to obtain natural language information input by a user and related information associated with the natural language information.
Natural language information may refer to language information that people use daily. The method can also be understood as the information of the user's daily expression or the similar daily expression composition mode.
The natural language information input by the user can be acquired by inputting the acquired character information through a keyboard, the keyboard input comprises a physical keyboard and a virtual keyboard, the virtual keyboard can comprise a keyboard displayed by a touch screen or a keyboard displayed by a display screen, and then the information is input in a mouse clicking mode and the like. The natural language information input by the user can also be obtained by voice input, such as obtaining input voice information through a microphone of the electronic equipment, and then recognizing and analyzing the voice information to convert the voice information into text information. The composing method of the character information is a composing mode of natural language. For example, the natural language information may be "i want to watch a movie".
When acquiring the natural language information, related information associated with the natural language information is also acquired.
Referring to fig. 8, fig. 8 is a schematic diagram illustrating a second structure of a natural language processing apparatus according to an embodiment of the present application. In this embodiment, the first obtaining module 301 includes a marked time point obtaining sub-module 3011, a history display information obtaining sub-module 3012, and a related information obtaining sub-module 3013. Wherein:
and a marked time point obtaining sub-module 3011, configured to obtain the marked time point while obtaining the natural language information.
When the natural language information is acquired, recording a time point at this time as a mark time point. The marked point in time may be a current system time of the electronic device. The system time of the electronic device may be time shared by network synchronization, or may be time calculated according to a component of the electronic device after the time is set.
And the history display information acquisition submodule 3012 is configured to acquire history display information of a preset time period before the time point is marked.
And after the marking time point is obtained, acquiring historical display information of a preset time period before the marking time point. The preset time may be a time set by the electronic device system, such as 3 minutes, 5 minutes, 10 minutes, and the like. The preset time may also be a time set by a user.
The history display information includes information appearing in a display screen of the electronic device. The history display information includes at least one of history input information, history dialogue information, history search information, and history browsing information.
The historical input information may be input within a predetermined time period, such as 3 minutes, before the time point is marked, and the input information from the user may be saved, such as stored in a memory, a cache, or the like. The input information includes information input in a chat interface, a search interface, and the like, and may also be information input in an input method interface. Even information entered at the input method interface, but later deleted. Such as information entered in a chat interface, followed by information not sent and deleted.
The historical conversation information may be conversation information that appears in the chat interface, including information entered by the user and information entered by other users.
The historical search information may be search information that the user clicked open in a search interface. If the user inputs a noun, a plurality of pieces of search information are popped up according to the name, then the user clicks one of the pieces of search information and enters a webpage corresponding to the search information, and the noun and the information corresponding to the webpage are both history search information. For example, the user inputs "Beijing Shenzhen", and retrieves information such as the air ticket from Beijing to Shenzhen, the train from Beijing to Shenzhen, different life experiences of Beijing Shenzhen, and the weather of Beijing Shenzhen are popped up, and then the weather of Beijing Shenzhen is clicked, so that the weather of Beijing Shenzhen and the weather of Beijing Shenzhen are kept as historical retrieval information.
The historical browsing information may be information that the user browses on the web page, such as the user does not enter any information in the browser, but clicks in a link provided by the browser.
And the related information acquisition sub-module 3013 is configured to filter from the history display information according to the natural language information, and obtain related information associated with the natural language information.
After the historical display information within the preset time period is obtained, screening is carried out according to the natural language information, irrelevant information is deleted, and relevant information relevant to the natural language information is reserved. If information including one or more characters in the natural language information is set as related information, the category of the natural language information is identified, information of the same category as the natural language information is set as related information, for example, if the natural language information is identified as a movie category, information about a movie is set as related information including movie name information, actor name information, scenario information, and the like.
In some embodiments, the historical display information includes historical input information, historical search information, and historical browsing information;
and the related information acquisition submodule is also used for inputting the historical display information and the natural language information into the screening model, and the screening model screens the historical display information according to the natural language information to obtain related information related to the natural language information.
The second obtaining module 302 is configured to obtain a plurality of semantic parsing information according to the natural language information.
And identifying the natural language information to obtain a plurality of semantic analysis information. One or more preset scenes can be preset, and then the natural language information is substituted into the one or more preset scenes to obtain a plurality of semantic analysis information.
Referring to fig. 9, fig. 9 is a third structural diagram of a natural language processing apparatus according to an embodiment of the present application. In this embodiment, the second obtaining module 302 includes a keyword extracting sub-module 3021, a semantic scene obtaining sub-module 3022, and a semantic parsing information obtaining sub-module 3023. Wherein:
a keyword extraction sub-module 3021 for extracting one or more keywords from the natural language information.
The keywords of the natural language information can be extracted first, if the natural language information is that "i want to see laughing and pride river lake", the natural language information is split first, so that several pieces of sub-information of "i", "want to see", "laughing and pride river lake" can be obtained, then the sub-information is sorted according to importance, and the first few are selected as the keywords.
The semantic scene obtaining sub-module 3022 is configured to obtain multiple preset semantic scenes according to one or more keywords.
And then, acquiring a corresponding preset scene according to the keyword, wherein the preset scene can comprise a movie scene, a novel scene and the like according to the keyword 'lauao river lake'.
The semantic parsing information obtaining sub-module 3023 is configured to obtain multiple semantic parsing information corresponding to the natural language information according to multiple preset semantic scenes.
And then semantic analysis information corresponding to the film and semantic analysis information corresponding to the novel are obtained.
The probability value obtaining module 303 is configured to input the multiple semantic parsing information and the related information into the prediction model, and the prediction model obtains multiple probability values corresponding to the multiple semantic parsing information according to the related information.
The prediction model can be a convolutional neural network model, a cyclic neural network model, a Bayesian algorithm model or the like.
And inputting the plurality of semantic analysis information and the related information into a prediction model, wherein the prediction model can predict the plurality of semantic analysis information and obtain the probability corresponding to each semantic analysis information. And the related information can be combined to predict a plurality of semantic analysis information to obtain the probability corresponding to each semantic analysis information. The information source is richer, and the prediction is more accurate. It should be noted that the screening model in the above embodiments may be a different part of the same model as the prediction model, or the screening model may be a part of the prediction model. If the natural language information is 'i want to see laughing and pride river lake', the preset scenes can be obtained according to the keyword laughing and pride river lake and can comprise movie scenes, novel scenes and the like, and then semantic analysis information corresponding to the movies and semantic analysis information corresponding to the novel are obtained. The related information comprises the information of the film, so that the probability value of the semantic analysis information corresponding to the film can be improved, and the probability value is obviously larger than other semantic analysis information. For another example, the free language information is "beijing woolen", and the preset scene may include beijing basic information, beijing tourist attractions, beijing weather and the like according to the keyword beijing, so as to obtain semantic analysis information corresponding to the beijing basic information and semantic analysis information corresponding to the beijing tourist attractions, the beijing weather and the like. The related information includes information of weather, specifically, weather information of other places is included in the preceding sentences in the chat records, so that the probability value of semantic analysis information corresponding to Beijing weather can be improved, and the probability value is obviously greater than that of other semantic analysis information.
A determining module 304, configured to determine, from the multiple probability values, semantic parsing information with the maximum probability value as target semantic parsing information.
And after the probability values corresponding to the plurality of semantic analysis information are obtained, the semantic analysis information with the maximum probability value is selected from the probability values, and the semantic analysis information is determined to be target analysis information. And then, corresponding information can be displayed according to the target analysis information. Such as showing movie links of luao river lake, movie blurs of luao river lake, etc.
Referring to fig. 10, fig. 10 is a schematic diagram illustrating a fourth structure of a natural language processing apparatus according to an embodiment of the present application. The natural language processing apparatus 300 includes a first obtaining module 301, a second obtaining module 302, a probability value obtaining module 303, and a determining module 304. Wherein:
the first obtaining module 301 is configured to obtain natural language information input by a user and related information associated with the natural language information.
Natural language information may refer to language information that people use daily. The method can also be understood as the information of the user's daily expression or the similar daily expression composition mode. When acquiring the natural language information, related information associated with the natural language information is also acquired.
The second obtaining module 302 is configured to obtain a plurality of semantic parsing information according to the natural language information. Specifically, the second obtaining module 302 includes a first obtaining submodule 3024 and a second obtaining submodule 3025.
The first obtaining sub-module 3024 is configured to obtain multiple preset semantic scenes according to the natural language information and the related information, and obtain multiple first weight values corresponding to the multiple preset semantic scenes, respectively.
The history display information includes information appearing in a display screen of the electronic device. The history display information includes at least one of history input information, history dialogue information, history search information, and history browsing information.
Obtaining a plurality of preset semantic scenes according to the natural language information, and then carrying out weight assignment on the plurality of preset semantic scenes according to the historical display information, namely, giving a weight value to each preset semantic scene and corresponding to the probability value of the weight value. Similarly, the natural language information and the historical display information can be input into a weight prediction model for prediction, and weight values corresponding to various preset semantic scenes are obtained. It should be noted that preset semantic scenes with weight values lower than the weight threshold may be excluded.
The second obtaining sub-module 3025 is configured to obtain, according to multiple preset semantic scenes and multiple first weight values, multiple semantic analysis information corresponding to the natural language information and a second weight value corresponding to the semantic analysis information.
The natural language information can be analyzed in a preset semantic scene to obtain one or more semantic analysis information, and the weight value of the semantic analysis information analyzed in the same preset semantic scene can be a corresponding first weight value or a second weight value obtained after adjustment.
The probability value obtaining module 303 is configured to input the multiple semantic parsing information and the related information into the prediction model, and the prediction model obtains multiple probability values corresponding to the multiple semantic parsing information according to the related information.
And inputting the plurality of semantic analysis information and the related information into a prediction model, wherein the prediction model can predict the plurality of semantic analysis information and obtain the probability corresponding to each semantic analysis information. And the related information can be combined to predict a plurality of semantic analysis information to obtain the probability corresponding to each semantic analysis information. The information source is richer, and the prediction is more accurate.
The determining module 304 is further configured to multiply the probability value corresponding to the semantic analysis information by the second weight value to obtain a plurality of weight probability values, and select the semantic analysis information with the highest probability value from the plurality of weight probability values as the target semantic analysis information.
And multiplying the probability value corresponding to the semantic analysis information by the second weight value to obtain a plurality of weight probability values, and multiplying the probability value obtained by the semantic analysis information through the prediction model by the second weight value obtained before to be closer to the preset semantic scene. And selecting semantic analysis information with the maximum probability value from the multiple weight probability values as target semantic analysis information. And then, corresponding information is displayed according to the target semantic analysis information.
As can be seen from the above, the natural language processing apparatus provided in the embodiment of the present application obtains the natural language information input by the user and the related information associated with the natural language information; obtaining a plurality of semantic analysis information according to the natural language information; inputting the semantic analysis information and the related information into a prediction model, and obtaining a plurality of probability values corresponding to the semantic analysis information by the prediction model according to the related information; and determining the semantic analysis information with the maximum probability value from the plurality of probability values as target semantic analysis information. The natural language information is not only analyzed and identified, but also assisted and identified by the related information in the prediction model, so that the accuracy of analyzing and identifying the natural language information is improved, and the obtained final target semantic analysis information is more consistent with the real idea of the user.
In specific implementation, the above modules may be implemented as independent entities, or may be combined arbitrarily to be implemented as the same or several entities, and specific implementation of the above modules may refer to the foregoing method embodiments, which are not described herein again.
In the embodiment of the present application, the natural language processing apparatus and the natural language processing method in the above embodiment belong to the same concept, and any method provided in the embodiment of the natural language processing method may be run on the natural language processing apparatus, and a specific implementation process thereof is described in detail in the embodiment of the natural language processing method, and is not described herein again.
The embodiment of the application also provides the electronic equipment. Referring to fig. 11, the electronic device 600 includes a processor 601 and a memory 602. The processor 601 is electrically connected to the memory 602.
The processor 600 is a control center of the electronic device 600, connects various parts of the entire electronic device using various interfaces and lines, performs various functions of the electronic device 600 by running or loading a computer program stored in the memory 602, and calls data stored in the memory 602, and processes the data, thereby performing overall monitoring of the electronic device 600.
The memory 602 may be used for storing software programs and units, and the processor 601 executes various functional applications and data processing by running the computer programs and units stored in the memory 602. The memory 602 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, a computer program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to use of the electronic device, and the like. Further, the memory 602 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 602 may also include a memory controller to provide the processor 601 with access to the memory 602.
In the embodiment of the present application, the processor 601 in the electronic device 600 loads instructions corresponding to one or more processes of the computer program into the memory 602 according to the following steps, and the processor 601 runs the computer program stored in the memory 602, thereby implementing various functions as follows:
acquiring natural language information input by a user and related information associated with the natural language information;
obtaining a plurality of semantic analysis information according to the natural language information;
inputting the semantic analysis information and the relevant information into a prediction model, and obtaining a plurality of probability values corresponding to the semantic analysis information by the prediction model according to the relevant information;
and determining the semantic analysis information with the maximum probability value from the plurality of probability values as target semantic analysis information.
In some embodiments, the processor 601 is further configured to perform the following steps:
extracting one or more keywords from the natural language information;
acquiring a plurality of preset semantic scenes according to the one or more keywords;
and acquiring a plurality of semantic analysis information corresponding to the natural language information according to the plurality of preset semantic scenes.
In some embodiments, the processor 601 is further configured to perform the following steps:
obtaining the marking time point while obtaining the natural language information;
acquiring historical display information of a preset time period before the marking time point;
and screening the historical display information according to the natural language information to obtain related information associated with the natural language information.
In some embodiments, the historical display information includes at least one of historical input information, historical dialog information, historical search information, and historical browsing information;
the processor 601 is further configured to perform the following steps:
inputting the historical display information and the natural language information into a screening model;
and the screening model screens the historical display information according to the natural language information to obtain related information associated with the natural language information.
In some embodiments, the processor 601 is further configured to perform the following steps:
acquiring a plurality of preset semantic scenes according to the natural language information and the related information, and respectively corresponding to a plurality of first weighted values of the plurality of preset semantic scenes;
acquiring a plurality of semantic analysis information corresponding to the natural language information and a second weight value corresponding to the semantic analysis information according to the plurality of preset semantic scenes and the plurality of first weight values;
and multiplying the probability value corresponding to the semantic analysis information by the second weight value to obtain a plurality of weight probability values, and selecting the semantic analysis information with the maximum probability value from the plurality of weight probability values as target semantic analysis information.
As can be seen from the above, the electronic device provided in the embodiment of the present application obtains the natural language information input by the user and the related information associated with the natural language information; obtaining a plurality of semantic analysis information according to the natural language information; inputting the semantic analysis information and the related information into a prediction model, and obtaining a plurality of probability values corresponding to the semantic analysis information by the prediction model according to the related information; and determining the semantic analysis information with the maximum probability value from the plurality of probability values as target semantic analysis information. The natural language information is not only analyzed and identified, but also assisted and identified by the related information in the prediction model, so that the accuracy of analyzing and identifying the natural language information is improved, and the obtained final target semantic analysis information is more consistent with the real idea of the user.
Referring also to fig. 12, in some embodiments, the electronic device 600 may further include: a display 603, a radio frequency circuit 604, an audio circuit 605, and a power supply 606. The display 603, the rf circuit 604, the audio circuit 605 and the power supply 606 are electrically connected to the processor 601, respectively.
The display 603 may be used to display information entered by or provided to the user as well as various graphical user interfaces, which may be made up of graphics, text, icons, video, and any combination thereof. The Display 603 may include a Display panel, and in some embodiments, the Display panel may be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like.
The rf circuit 604 may be used for transceiving rf signals to establish wireless communication with a network device or other electronic devices through wireless communication, and for transceiving signals with the network device or other electronic devices.
The audio circuit 605 may be used to provide an audio interface between the user and the electronic device through a speaker, microphone.
The power supply 606 may be used to power various components of the electronic device 600. In some embodiments, the power supply 606 may be logically connected to the processor 601 through a power management system, so as to implement functions of managing charging, discharging, and power consumption management through the power management system.
Although not shown in fig. 12, the electronic device 600 may further include a camera, a bluetooth unit, and the like, which are not described in detail herein.
It can be understood that the electronic device of the embodiment of the present application may be a terminal device such as a smart phone or a tablet computer.
An embodiment of the present application further provides a storage medium, where the storage medium stores a computer program, and when the computer program runs on a computer, the computer is caused to execute the natural language processing method in any one of the embodiments, such as: acquiring natural language information input by a user and related information associated with the natural language information; obtaining a plurality of semantic analysis information according to the natural language information; inputting the semantic analysis information and the related information into a prediction model, and obtaining a plurality of probability values corresponding to the semantic analysis information by the prediction model according to the related information; and determining the semantic analysis information with the maximum probability value from the plurality of probability values as target semantic analysis information.
In the embodiment of the present application, the storage medium may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a Random Access Memory (RAM), or the like.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
It should be noted that, for the natural language processing method in the embodiment of the present application, it can be understood by a person skilled in the art that all or part of the process of implementing the natural language processing method in the embodiment of the present application can be completed by controlling the relevant hardware through a computer program, the computer program can be stored in a computer readable storage medium, such as a memory of an electronic device, and executed by at least one processor in the electronic device, and the process of executing the process can include, for example, the process of the embodiment of the natural language processing method. The storage medium may be a magnetic disk, an optical disk, a read-only memory, a random access memory, etc.
In the natural language processing device according to the embodiment of the present application, each functional unit may be integrated into one processing chip, each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit. The integrated unit, if implemented as a software functional unit and sold or used as a stand-alone product, may also be stored in a computer readable storage medium, such as a read-only memory, a magnetic or optical disk, or the like.
The natural language processing method, the natural language processing apparatus, the storage medium, and the electronic device provided in the embodiments of the present application are described in detail above, and a specific example is applied in the present application to explain the principle and the implementation of the present application, and the description of the above embodiments is only used to help understanding the method and the core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (8)
1. A natural language processing method applied to electronic equipment is characterized by comprising the following steps:
acquiring natural language information input by a user;
obtaining the marking time point while obtaining the natural language information;
acquiring historical display information of a preset time period before the marking time point, wherein the historical display information comprises information appearing in a display screen of the electronic equipment;
screening from the historical display information according to the natural language information to obtain related information associated with the natural language information;
obtaining a plurality of preset semantic scenes according to the natural language information, performing weight assignment on the plurality of preset semantic scenes according to the relevant information, excluding the preset semantic scenes with weight values lower than a weight threshold value, obtaining a plurality of preset semantic scenes with excluded weight values lower than the weight threshold value, and a plurality of first weight values respectively corresponding to the plurality of preset semantic scenes with excluded weight values lower than the weight threshold value, and obtaining a plurality of semantic analysis information corresponding to the natural language information and a second weight value corresponding to the semantic analysis information according to the plurality of preset semantic scenes with excluded weight values lower than the weight threshold value and the plurality of first weight values;
inputting the semantic analysis information and the relevant information into a prediction model, and obtaining a plurality of probability values corresponding to the semantic analysis information by the prediction model according to the relevant information;
and multiplying the probability value corresponding to the semantic analysis information by the second weight value to obtain a plurality of weight probability values, and selecting the semantic analysis information with the maximum probability value from the plurality of weight probability values as target semantic analysis information.
2. The natural language processing method according to claim 1, wherein the step of obtaining a plurality of semantic parsing information from the natural language information includes;
extracting one or more keywords from the natural language information;
acquiring a plurality of preset semantic scenes according to the one or more keywords;
and acquiring a plurality of semantic analysis information corresponding to the natural language information according to the plurality of preset semantic scenes.
3. The natural language processing method according to claim 1, wherein the history display information includes at least one of history input information, history dialogue information, history search information, and history browsing information;
the step of screening the history display information according to the natural language information to obtain the related information related to the natural language information comprises the following steps:
inputting the historical display information and the natural language information into a screening model;
and the screening model screens the historical display information according to the natural language information to obtain related information associated with the natural language information.
4. A natural language processing device applied to an electronic device, the device comprising:
the first acquisition module is used for acquiring natural language information input by a user;
the first obtaining module includes:
the marking time point acquisition submodule is used for acquiring the natural language information and simultaneously acquiring a marking time point;
the historical display information acquisition submodule is used for acquiring historical display information of a preset time period before the marking time point, and the historical display information comprises information appearing in a display screen of the electronic equipment;
the related information acquisition submodule is used for screening the historical display information according to the natural language information to obtain related information related to the natural language information;
a second acquisition module comprising:
the first obtaining submodule is used for obtaining a plurality of preset semantic scenes according to the natural language information, carrying out weight assignment on the plurality of preset semantic scenes according to the relevant information, excluding the preset semantic scenes with weight values lower than a weight threshold value, obtaining a plurality of preset semantic scenes excluding the preset semantic scenes with weight values lower than the weight threshold value, and respectively corresponding to a plurality of first weight values of the plurality of preset semantic scenes excluding the preset semantic scenes with weight values lower than the weight threshold value;
a second obtaining sub-module, configured to obtain, according to a plurality of preset semantic scenes excluding the preset semantic scenes whose weight values are lower than a weight threshold and the plurality of first weight values, a plurality of semantic analysis information corresponding to the natural language information and a second weight value corresponding to the semantic analysis information;
a probability value obtaining module, configured to input the semantic parsing information and the related information into a prediction model, where the prediction model obtains probability values corresponding to the semantic parsing information according to the related information;
and the determining module is used for multiplying the probability value corresponding to the semantic analysis information by the second weight value to obtain a plurality of weight probability values, and selecting the semantic analysis information with the maximum probability value from the plurality of weight probability values as target semantic analysis information.
5. The natural language processing apparatus according to claim 4, wherein the second acquisition module comprises:
a keyword extraction submodule for extracting one or more keywords from the natural language information;
the semantic scene obtaining submodule is used for obtaining various preset semantic scenes according to the one or more keywords;
and the semantic analysis information acquisition submodule is used for acquiring a plurality of semantic analysis information corresponding to the natural language information according to the plurality of preset semantic scenes.
6. The natural language processing apparatus according to claim 4, wherein the history display information includes history input information, history search information, and history browsing information;
the related information obtaining sub-module is further configured to input the historical display information and the natural language information into a screening model, and the screening model screens the historical display information according to the natural language information to obtain related information related to the natural language information.
7. A storage medium having stored thereon a computer program, characterized in that, when the computer program runs on a computer, it causes the computer to execute the natural language processing method according to any one of claims 1 to 3.
8. An electronic device comprising a processor and a memory, the memory having a computer program, wherein the processor is configured to execute the natural language processing method of any one of claims 1 to 3 by calling the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711466311.7A CN108197105B (en) | 2017-12-28 | 2017-12-28 | Natural language processing method, device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711466311.7A CN108197105B (en) | 2017-12-28 | 2017-12-28 | Natural language processing method, device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108197105A CN108197105A (en) | 2018-06-22 |
| CN108197105B true CN108197105B (en) | 2021-08-24 |
Family
ID=62585809
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711466311.7A Active CN108197105B (en) | 2017-12-28 | 2017-12-28 | Natural language processing method, device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108197105B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111784087A (en) * | 2019-04-03 | 2020-10-16 | 长鑫存储技术有限公司 | Production information processing method, device, system, equipment and readable storage medium |
| CN111797631B (en) * | 2019-04-04 | 2024-06-21 | 北京猎户星空科技有限公司 | Information processing method and device and electronic equipment |
| CN110941631B (en) * | 2019-10-30 | 2024-01-23 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN113704408A (en) * | 2021-08-31 | 2021-11-26 | 工银科技有限公司 | Retrieval method, retrieval apparatus, electronic device, storage medium, and program product |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103268313A (en) * | 2013-05-21 | 2013-08-28 | 北京云知声信息技术有限公司 | Method and device for semantic analysis of natural language |
| CN104199810A (en) * | 2014-08-29 | 2014-12-10 | 科大讯飞股份有限公司 | Intelligent service method and system based on natural language interaction |
| CN104360994A (en) * | 2014-12-04 | 2015-02-18 | 科大讯飞股份有限公司 | Natural language understanding method and natural language understanding system |
| CN105786793A (en) * | 2015-12-23 | 2016-07-20 | 百度在线网络技术（北京）有限公司 | Method and device for analyzing semanteme of spoken language text information |
| CN106057205A (en) * | 2016-05-06 | 2016-10-26 | 北京云迹科技有限公司 | Intelligent robot automatic voice interaction method |
-
2017
- 2017-12-28 CN CN201711466311.7A patent/CN108197105B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103268313A (en) * | 2013-05-21 | 2013-08-28 | 北京云知声信息技术有限公司 | Method and device for semantic analysis of natural language |
| CN104199810A (en) * | 2014-08-29 | 2014-12-10 | 科大讯飞股份有限公司 | Intelligent service method and system based on natural language interaction |
| CN104360994A (en) * | 2014-12-04 | 2015-02-18 | 科大讯飞股份有限公司 | Natural language understanding method and natural language understanding system |
| CN105786793A (en) * | 2015-12-23 | 2016-07-20 | 百度在线网络技术（北京）有限公司 | Method and device for analyzing semanteme of spoken language text information |
| CN106057205A (en) * | 2016-05-06 | 2016-10-26 | 北京云迹科技有限公司 | Intelligent robot automatic voice interaction method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108197105A (en) | 2018-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108319489B (en) | Application page starting method and device, storage medium and electronic equipment | |
| CN108090497B (en) | Video classification method and device, storage medium and electronic equipment | |
| CN108197105B (en) | Natural language processing method, device, storage medium and electronic equipment | |
| CN108363792B (en) | Link generation method and device of application page, storage medium and electronic equipment | |
| JP7394809B2 (en) | Methods, devices, electronic devices, media and computer programs for processing video | |
| CN108334608A (en) | Link generation method, device, storage medium and the electronic equipment of five application page | |
| CN107784034B (en) | Page type identification method and device for page type identification | |
| CN108228776B (en) | Data processing method, data processing device, storage medium and electronic equipment | |
| CN108038243A (en) | Music recommends method, apparatus, storage medium and electronic equipment | |
| CN112364799A (en) | Gesture recognition method and device | |
| CN113190695B (en) | Multimedia data searching method and device, computer equipment and medium | |
| WO2021147421A1 (en) | Automatic question answering method and apparatus for man-machine interaction, and intelligent device | |
| CN114357278B (en) | Topic recommendation method, device and equipment | |
| CN114205447B (en) | Shortcut setting method and device of electronic equipment, storage medium and electronic equipment | |
| CN112416212B (en) | Program access method, apparatus, electronic device and readable storage medium | |
| CN112199561A (en) | Application search method and device | |
| CN108052506B (en) | Natural language processing method, device, storage medium and electronic equipment | |
| CN107784037B (en) | Information processing method and device, and device for information processing | |
| WO2022166811A1 (en) | Information processing method and apparatus, electronic device, and storage medium | |
| CN116127062A (en) | Training method of pre-training language model, text emotion classification method and device | |
| CN115309487A (en) | Display method, display device, electronic equipment and readable storage medium | |
| CN113127653B (en) | Information display method and device | |
| CN112261321B (en) | Subtitle processing method and device and electronic equipment | |
| CN116453005A (en) | Video cover extraction method and related device | |
| CN110795178B (en) | Application sign-in method and device and electronic equipment |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Applicant after: OPPO Guangdong Mobile Communications Co.,Ltd. Address before: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Applicant before: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |