CN112639767A - Shorthand item classification method, terminal and computer storage medium - Google Patents
Shorthand item classification method, terminal and computer storage medium Download PDFInfo
- Publication number
- CN112639767A CN112639767A CN201880097169.XA CN201880097169A CN112639767A CN 112639767 A CN112639767 A CN 112639767A CN 201880097169 A CN201880097169 A CN 201880097169A CN 112639767 A CN112639767 A CN 112639767A
- Authority
- CN
- China
- Prior art keywords
- shorthand
- terminal
- content
- item
- keywords
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The embodiment of the application discloses a classification method of shorthand projects, a terminal and a computer storage medium, wherein the classification method comprises the following steps: acquiring shorthand contents corresponding to the shorthand items; wherein the shorthand item is any shorthand in the shorthand application; extracting keywords corresponding to the shorthand content; obtaining a classification result corresponding to the shorthand item according to a preset classification model and the keywords; the preset classification model is obtained by training according to historical data.
Description
The embodiment of the application relates to the technical field of intelligent information processing and terminals, in particular to a shorthand item classification method, a terminal and a computer storage medium.
With the continuous development of terminal technology, the existing terminal has more comprehensive functions, for example, in order to provide a faster inspiration recording mode, the terminal can call a pre-installed shorthand application in any interface for recording or checking, so that the requirement of recording events and inspiration anytime and anywhere can be met through the shorthand application.
The shorthand application enables the terminal to have quickness when inspiration recording is carried out, however, the number of shorthand items obtained by recording inspiration and events at any time is large, when the terminal sorts and classifies a large number of shorthand items, the shorthand items need to be analyzed one by one according to selection instructions of users and classified, and the processing process is very complicated. Therefore, when the terminal classifies the shorthand items according to the instruction of the user, the classification process is complicated and the time consumption is large.
Disclosure of Invention
The embodiment of the application provides a shorthand item classification method, a terminal and a computer storage medium, which can greatly simplify the processing process of shorthand item classification, thereby effectively shortening the classification time of shorthand items and improving the intelligence of the terminal.
The technical scheme of the embodiment of the application is realized as follows:
the embodiment of the application provides a method for classifying shorthand projects, which comprises the following steps:
acquiring shorthand contents corresponding to the shorthand items; wherein the shorthand item is any shorthand in a shorthand application;
extracting keywords corresponding to the shorthand content;
obtaining a classification result corresponding to the shorthand item according to a preset classification model and the keywords; and the preset classification model is obtained by training according to historical data.
Optionally, before obtaining the classification result corresponding to the shorthand item according to the preset classification model and the keyword, the method further includes:
acquiring an identity corresponding to the shorthand item; wherein the identity is used for determining the recorder identity of the shorthand item.
Optionally, before the obtaining of the classification result corresponding to the shorthand item according to the preset classification model and the keyword, and after the obtaining of the identity corresponding to the shorthand item, the method further includes:
acquiring the historical data corresponding to the identity;
training the historical data to obtain the corresponding relation between the keywords corresponding to the historical data and the categories;
and establishing the preset classification model corresponding to the identity identification according to the corresponding relation between the keywords and the categories.
Optionally, when the shorthand content includes a text, the extracting a keyword corresponding to the shorthand content includes:
performing word segmentation processing and filtering processing on the shorthand content to obtain a phrase set;
and analyzing the phrase combination to obtain the keywords.
Optionally, when the shorthand content includes an image, the extracting a keyword corresponding to the shorthand content includes:
carrying out character recognition on the shorthand content to obtain a character set;
and performing word segmentation processing and filtering processing on the character set to obtain the keywords.
Optionally, the extracting the keyword corresponding to the shorthand content includes:
carrying out feature recognition on the shorthand content to obtain image feature information of the shorthand content;
and acquiring the keywords according to the graphic feature information.
Optionally, when the shorthand content includes a voice, the extracting the keyword corresponding to the shorthand content includes:
performing voice conversion on the shorthand content to obtain a text set corresponding to the shorthand content;
and performing word segmentation processing and filtering processing on the text set to obtain the keywords.
Optionally, the obtaining a classification result corresponding to the shorthand item according to a preset classification model and the keyword includes:
inputting the keywords into the preset classification model to obtain a classification set;
and carrying out fusion processing on the classification set to obtain the classification result.
The embodiment of the application provides a terminal, the terminal includes: an acquisition section and an extraction section,
the acquisition part is used for acquiring shorthand contents corresponding to the shorthand items; wherein the shorthand item is any shorthand in a shorthand application;
the extraction part is used for extracting the keywords corresponding to the shorthand content;
the acquisition part is further used for acquiring a classification result corresponding to the shorthand item according to a preset classification model and the keywords; and the preset classification model is obtained by training according to historical data.
Optionally, the terminal further includes: the set-up section is configured to establish,
the obtaining part is further used for obtaining the identity corresponding to the shorthand item before obtaining the classification result corresponding to the shorthand item according to a preset classification model and the keywords; wherein the identity is used for determining the recorder identity of the shorthand item; acquiring the historical data corresponding to the identity; training the historical data to obtain the corresponding relation between the keywords corresponding to the historical data and the categories;
and the establishing part is used for establishing the preset classification model corresponding to the identity identification according to the corresponding relation between the keywords and the categories.
Optionally, when the shorthand content includes a word, the extracting part is specifically configured to perform word segmentation processing and filtering processing on the shorthand content to obtain a phrase set; and analyzing the phrase combination to obtain the keywords.
Optionally, when the shorthand content includes an image, the extracting part is further specifically configured to perform character recognition on the shorthand content to obtain a character set; and performing word segmentation processing and filtering processing on the character set to obtain the keywords.
Optionally, the extracting part is further specifically configured to perform feature recognition on the shorthand content to obtain image feature information of the shorthand content; and obtaining the keywords according to the graphic feature information.
Optionally, when the shorthand content includes speech, the extracting part is further specifically configured to perform speech conversion on the shorthand content to obtain a text set corresponding to the shorthand content; and performing word segmentation processing and filtering processing on the text set to obtain the keywords.
Optionally, the obtaining part is further specifically configured to input the keyword into the preset classification model to obtain a classification set; and carrying out fusion processing on the classification set to obtain the classification result.
An embodiment of the present application provides a terminal, which includes a processor, a memory storing executable instructions of the processor, a communication interface, and a bus for connecting the processor, the memory, and the communication interface, wherein when the instructions are executed, the processor implements the shorthand item classification method as described above.
The embodiment of the application provides a computer readable storage medium, on which a program is stored, which is applied in a terminal, and when the program is executed by a processor, the program realizes the shorthand item classification method as described above.
The embodiment of the application provides a shorthand item classification method, a terminal and a computer storage medium, wherein the terminal acquires shorthand contents corresponding to the shorthand items; wherein the shorthand item is any shorthand in the shorthand application; extracting keywords corresponding to the shorthand content; obtaining a classification result corresponding to the shorthand item according to a preset classification model and the keywords; the preset classification model is obtained by training according to historical data. Therefore, in the embodiment of the application, after the shorthand content corresponding to the shorthand item is determined, the terminal extracts the keywords from the shorthand content, and directly classifies the shorthand item by combining the preset classification model and the keywords to obtain the classification result of the shorthand item, that is, the terminal can realize the shorthand item classification and can also ensure the individuation of the classification result, and the terminal automatically classifies according to the extracted keywords, so that the processing process of the shorthand item classification can be greatly simplified, the classification time of the shorthand item can be effectively shortened, and the intelligence of the terminal can be improved.
Fig. 1 is a schematic flow chart illustrating an implementation of a method for classifying shorthand items according to an embodiment of the present application;
FIG. 2 is a first diagram illustrating a shorthand item in an embodiment of the present application;
FIG. 3 is a second diagram of a shorthand project in an embodiment of the present application;
FIG. 4 is a first diagram illustrating a correspondence between keywords and categories according to an embodiment of the present application;
FIG. 5 is a diagram illustrating a second mapping relationship between keywords and categories according to an embodiment of the present application;
fig. 6 is a first schematic structural diagram of a terminal according to an embodiment of the present disclosure;
fig. 7 is a schematic structural diagram of a terminal according to an embodiment of the present application.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant application and are not limiting of the application. It should be noted that, for the convenience of description, only the parts related to the related applications are shown in the drawings.
In order to provide an entry for a user to conveniently record transient and vanishing inspiration, the embodiment of the application provides a shorthand application capable of quickly recording and quickly viewing, wherein the recording form of the terminal for shorthand through the shorthand application can include recording modes such as voice recording, character recording, photographing recording and recording the content of a current display screen.
Further, in the embodiment of the application, the terminal can quickly start the recording entrance in any interface, so that the user can be helped to realize the requirement of recording events and inspiration anytime and anywhere.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.
Example one
An embodiment of the present application provides a method for classifying shorthand items, where fig. 1 is a schematic flow chart illustrating an implementation of the method for classifying shorthand items provided in the embodiment of the present application, and as shown in fig. 1, in the embodiment of the present application, the method for classifying shorthand items by a terminal may include the following steps:
In an embodiment of the present application, the terminal may first obtain the shorthand content corresponding to the shorthand item. Wherein the shorthand content is information recorded in the shorthand item.
It should be noted that, in the embodiment of the present application, the terminal may be any terminal having communication and storage functions, for example: terminals such as tablet computers, mobile phones, electronic readers, remote controllers, Personal Computers (PCs), notebook computers, vehicle-mounted devices, network televisions, and wearable devices.
Further, in the embodiment of the present application, the shorthand content may be information in various forms, for example, the current display interface may display text information, image information, voice information, video information, any combination of different types of information, and the like.
In an embodiment of the present application, the terminal may obtain the shorthand content corresponding to the shorthand item and also obtain the identity corresponding to the shorthand content. The identity may be used to determine the identity of the recorder of the shorthand item, that is, the identity may be identity information of a user corresponding to the shorthand item.
Further, in an embodiment of the present application, the terminal may determine the identification according to user registration information corresponding to the terminal, or may determine the identification by reading detailed attributes corresponding to the shorthand items. For example, the user Ada uses the terminal, so that the identity corresponding to the shorthand item can be determined as Ada; or the attribute information of the shorthand item includes the recorder Jay, so that the identity corresponding to the shorthand item can be determined to be Jay.
It should be noted that, in the embodiment of the present application, the terminal may be installed with a shorthand application capable of quickly recording and quickly viewing, where the recording form of the terminal in shorthand through the shorthand application may include recording modes such as voice recording, text recording, photographing recording, and recording the content of the current display screen.
Further, in the embodiment of the present application, after the terminal performs shorthand according to the shorthand instruction, the shorthand item may be obtained. Fig. 2 is a first schematic diagram of a shorthand item in an embodiment of the present application, and as shown in fig. 2, the shorthand item in the terminal may store multiple forms of shorthand items, and the shorthand item in the shorthand application in fig. 2 is in a retracted state. Fig. 3 is a schematic diagram of a shorthand item in the embodiment of the application, and as shown in fig. 3, the expanded shorthand item includes text information and voice information.
And 102, extracting keywords corresponding to the shorthand content.
In an embodiment of the present application, after acquiring the shorthand content corresponding to the shorthand item, the terminal may extract a keyword corresponding to the shorthand content.
In the embodiment of the present application, the keyword corresponding to the shorthand content may be text information in the shorthand content, or may be feature information corresponding to the shorthand content.
Further, in an embodiment of the present application, for different shorthand items, the keywords obtained by the terminal may be the same or different; meanwhile, the way in which the terminal obtains the keyword is different for different types of the shorthand content.
In an embodiment of the present application, for the shorthand content in the form of characters, the terminal may obtain the keyword corresponding to the shorthand content by performing character processing on the shorthand content.
In an embodiment of the present application, for the shorthand content in the form of a voice, the terminal may obtain the keyword corresponding to the shorthand content by performing voice conversion on the shorthand content.
In an embodiment of the present application, for the shorthand content in the form of an image, the terminal may obtain the keyword corresponding to the shorthand content by performing character recognition or feature recognition on the shorthand content.
Further, in an embodiment of the present application, when the shorthand content in the shorthand item includes information in multiple forms, the terminal may obtain candidate keywords corresponding to the information in each form according to different processing manners, and then combine and filter all the candidate keywords to obtain the keywords corresponding to the shorthand content.
103, obtaining a classification result corresponding to the shorthand item according to a preset classification model and the keywords; the preset classification model is obtained by training according to historical data.
In an embodiment of the application, after the terminal extracts the keyword corresponding to the shorthand content, the terminal may obtain a classification result corresponding to the shorthand item according to the keyword and a preset classification model.
It should be noted that, in the embodiment of the present application, the preset classification model may be obtained by training according to historical data.
Further, in an embodiment of the application, the preset classification model may also be obtained by training according to historical data corresponding to the identity identifier.
It should be noted that, in the embodiment of the present application, since the terminal may obtain the identifier corresponding to the shorthand item before obtaining the classification result corresponding to the shorthand item according to the preset classification model and the keyword, the identifier may be used to obtain the preset classification model corresponding to the identifier when classifying the shorthand item.
Further, in an embodiment of the application, when the terminal obtains the classification result according to the preset classification model, the obtained classification result corresponding to the keyword is different for different preset classification models.
Further, in an embodiment of the application, the terminal may obtain the classification result corresponding to the identity identifier according to the preset classification model corresponding to the identity identifier. Specifically, in the embodiment of the present application, the identification labels corresponding to different users are different, so that the corresponding preset classification models are also different, and thus the obtained classification results corresponding to the keywords are also different.
In an embodiment of the present application, the classification result obtained by the terminal after classifying the shorthand item is not only related to the keyword corresponding to the shorthand content, but also related to the id corresponding to the shorthand item.
Further, in an embodiment of the application, the terminal obtains the classification result corresponding to the shorthand item according to the preset classification model corresponding to the identity and the keyword, and the classification result corresponds to a user corresponding to the shorthand item, so that personalization of shorthand item classification can be ensured.
In an embodiment of the application, further, before the terminal obtains the classification result corresponding to the shorthand item according to a preset classification model and the keyword, and after obtaining the identity identifier corresponding to the shorthand item, the method for classifying the shorthand item by the terminal may include the following steps:
and 104, acquiring historical data corresponding to the identity.
In an embodiment of the application, before the terminal obtains the classification result corresponding to the shorthand item according to the preset classification model and the keyword, and after obtaining the identifier corresponding to the shorthand item, the terminal may first obtain the historical data corresponding to the identifier.
It should be noted that, in an embodiment of the present application, the history data corresponding to the identifier may be a data record of a user corresponding to the identifier, which is acquired by the terminal. For example, the terminal may obtain a history browsing record, a history searching record, a history sharing record, and the like corresponding to the user.
Further, in an embodiment of the application, since the historical data corresponds to the identification, the terminal may further obtain the preset classification model corresponding to the identification through the historical data.
And 105, training the historical data to obtain the corresponding relation between the keywords corresponding to the historical data and the categories.
In an embodiment of the application, after the terminal acquires the historical data corresponding to the identifier, the terminal may train the historical data to obtain a correspondence between a keyword and a type corresponding to the historical data.
It should be noted that, in the embodiment of the present application, after obtaining the historical data, the terminal may train the historical data, so as to obtain a corresponding relationship between the corresponding keyword and the type, and specifically, when the terminal performs offline training on the historical data, the training process may be completed by manual classification or may be assisted by machine classification. In order to ensure the accuracy of the correspondence between the keywords and the types during offline training, the embodiment of the present application may use the historical data within a certain preset time interval, so as to avoid a situation that the correspondence between the keywords and the types deviates from a correct classification effect along with the continuous update of the historical data.
It should be noted that, in the embodiment of the present application, in the correspondence between the keywords and the categories, one keyword may correspond to at least one type, and meanwhile, one category may also correspond to at least one keyword. Fig. 4 is a schematic diagram illustrating a correspondence relationship between a keyword and a category in the embodiment of the present application, as shown in fig. 4, the keyword "R17" may correspond to multiple types, such as "OPPO", "mobile phone", and "release meeting". Fig. 5 is a schematic diagram illustrating a correspondence relationship between keywords and categories in the embodiment of the present application, and as shown in fig. 5, multiple keywords such as "R17", "Find X", and "heart location" may all correspond to the type "OPPO".
And 106, establishing a preset classification model corresponding to the identity identification according to the corresponding relation between the keywords and the categories.
In an embodiment of the application, after the terminal trains the historical data to obtain a correspondence between the keyword and the type corresponding to the historical data, the terminal may establish the preset classification model corresponding to the identity according to the correspondence between the keyword and the category.
Further, in an embodiment of the present application, after obtaining the correspondence between the keyword and the category, the terminal may establish the preset classification model according to the correspondence between the keyword and the category. The preset classification model is corresponding to the identity, because the corresponding relation between the keywords and the categories is corresponding to the identity.
According to the classification method for the shorthand projects, a terminal obtains shorthand contents corresponding to the shorthand projects; wherein the shorthand item is any shorthand in the shorthand application; extracting keywords corresponding to the shorthand content; obtaining a classification result corresponding to the shorthand item according to a preset classification model and the keywords; the preset classification model is obtained by training according to historical data. Therefore, in the embodiment of the application, after the shorthand content corresponding to the shorthand item is determined, the terminal extracts the keywords from the shorthand content, and directly classifies the shorthand item by combining the preset classification model and the keywords to obtain the classification result of the shorthand item, that is, the terminal can realize the shorthand item classification and can also ensure the individuation of the classification result, and the terminal automatically classifies according to the extracted keywords, so that the processing process of the shorthand item classification can be greatly simplified, the classification time of the shorthand item can be effectively shortened, and the intelligence of the terminal can be improved.
Example two
Based on the first embodiment, in an embodiment of the present application, if the shorthand content includes a text, the method for the terminal to extract the keyword corresponding to the shorthand content may include the following steps:
and 102a, performing word segmentation processing and filtering processing on the shorthand content to obtain a phrase set.
In an embodiment of the present application, after obtaining the shorthand content corresponding to the shorthand item, the terminal may perform word segmentation processing and filtering processing on the shorthand content to obtain a phrase set.
In an embodiment of the present application, the phrase set may be obtained by performing word segmentation processing and filtering processing on the shorthand content by the terminal, and specifically, the phrase set is partial text information of the shorthand content.
Further, in an embodiment of the present application, the terminal may first perform word segmentation by using the word segmentation tool, and segment the text information in the shorthand content into a series of words and parts of speech corresponding to the words; then, each word can be filtered according to the word and the corresponding part of speech thereof, and unnecessary words are filtered; and finally, generating the phrase set according to all the filtered words corresponding to the shorthand content.
In the embodiment of the present application, when the terminal performs filtering processing on the shorthand content, different filtering mechanisms may be adopted. Specifically, the terminal may perform filtering processing according to the word after the word segmentation processing, and the terminal may further perform filtering processing according to a part of speech corresponding to the word after the word segmentation processing. For example, words that are not needed in the filtering mechanism include stop words, words of length 1, pure numbers, and words beginning with numbers, and remaining words include nouns, organization community names, other proper names, nominal idioms, nominal morphemes, verbs, name verbs, trend verbs, form verbs, default verbs (inner verbs), verb idioms; words that are not needed in the filtering mechanism may also include: pronouns, quantifier, prepositions, conjunctions, helpers, sighs, ambiguities, vocabularies, punctuation marks.
It should be noted that, in the embodiment of the present application, the terminal performs the filtering process, so that the data size can be effectively reduced, and the effect of reducing the dimensionality is achieved.
And 102b, analyzing the phrase combination to obtain keywords.
In an embodiment of the application, after the terminal performs word segmentation processing and filtering processing on the shorthand content to obtain the phrase set, the phrase set may be analyzed to obtain the keyword.
In the implementation of the present application, the phrase set includes all valid text information corresponding to the shorthand content, and the terminal may further analyze the phrase set after obtaining the phrase set so as to select the keyword from the phrase set.
Further, in an embodiment of the present application, when the terminal analyzes the phrase set, the terminal may analyze the phrase set according to position information or quantity information corresponding to all phrases in the phrase set.
It should be noted that, in the embodiments of the present application, the position information may represent a specific position corresponding to a phrase in the shorthand content; the quantity information may represent the corresponding occurrence number of a phrase in the shorthand content.
Further, in an embodiment of the present application, if the shorthand content includes an image, the method for the terminal to extract the keyword corresponding to the shorthand content may include the following steps:
and 102c, carrying out character recognition on the shorthand content to obtain a character set.
In an embodiment of the application, after acquiring the shorthand content corresponding to the shorthand item, the terminal may perform character recognition on the shorthand content to obtain a character set.
In an embodiment of the present application, the character set may be obtained by the terminal after character recognition of the shorthand content, and specifically, the character set may be partial character information in the image information of the shorthand content.
Further, in an embodiment of the present application, when the shorthand content includes an image and characters are displayed in the image, the terminal may perform image analysis processing on the shorthand content, extract character information in the shorthand content, and combine the obtained character information into the character set.
And 102d, performing word segmentation processing and filtering processing on the character set to obtain keywords.
In an embodiment of the application, after the terminal performs character recognition on the shorthand content to obtain the character set, the terminal may perform word segmentation processing and filtering processing on the character set to obtain the keyword.
Further, in an embodiment of the present application, the terminal may first perform word segmentation by using a word segmentation tool, and segment the text information in the text set into a series of words and parts of speech corresponding to the words; then, each word can be filtered according to the word and the corresponding part of speech thereof, and unnecessary words are filtered; and finally, generating the keywords according to all the filtered words corresponding to the character set.
In an embodiment of the present application, further, if the shorthand content includes an image, the method for the terminal to extract the keyword corresponding to the shorthand content may further include the following steps:
and 102e, carrying out feature identification on the shorthand content to obtain image feature information of the shorthand content.
In an embodiment of the present application, after the terminal acquires the shorthand content corresponding to the shorthand item, the terminal may perform feature recognition on the shorthand content to obtain image feature information of the shorthand content.
In an embodiment of the present application, the terminal may create an image feature library in advance before performing feature recognition on the shorthand content to obtain the image feature information of the shorthand content, wherein the image feature library stores a plurality of types of feature information.
Further, in an embodiment of the present application, when the shorthand content includes an image, the terminal may perform image analysis processing on the shorthand content, and extract specific image information in the shorthand content by combining with a pre-established image feature library, so as to obtain the image feature information corresponding to the shorthand content.
And 102f, acquiring keywords according to the graphic characteristic information.
In an embodiment of the present application, the terminal may obtain the keyword based on the graphic feature information after performing feature recognition on the shorthand content to obtain the image feature information of the shorthand content.
Further, in an embodiment of the present application, after obtaining the image feature information, the terminal may perform word segmentation processing and filtering processing on the image feature information, and then may extract the keyword from the image feature information; meanwhile, the terminal may analyze and summarize the image feature information, and then summarize the keyword from the image feature information.
In an embodiment of the present application, based on the method described in the above steps 102c to 102f, for the shorthand content including an image, character recognition and feature recognition may be performed on the image in the shorthand content at the same time to obtain the character set and the image feature information in the image, and then the keyword is obtained together according to the character set and the image feature information.
Further, in an embodiment of the present application, if the shorthand content includes a voice, the method for the terminal to extract the keyword corresponding to the shorthand content may include the following steps:
and 102g, carrying out voice conversion on the shorthand content to obtain a text set corresponding to the shorthand content.
In an embodiment of the application, after the terminal acquires the shorthand content corresponding to the shorthand item, the terminal may perform voice conversion on the shorthand content and then obtain a text set corresponding to the shorthand content.
It should be noted that, in the embodiment of the present application, if the shorthand content includes a voice, the shorthand content needs to be subjected to voice conversion to obtain a text corresponding to the voice, that is, to obtain the text set.
Further, in the embodiment of the present application, when the terminal performs voice conversion on the shorthand content, the terminal may combine the pronunciation habits of the user corresponding to the shorthand item, that is, the pronunciation preferences of the user corresponding to the shorthand content, so as to improve the accuracy of the voice conversion and the accuracy of the voice conversion in the shorthand content into the text set.
And 102h, performing word segmentation processing and filtering processing on the text set to obtain keywords.
In an embodiment of the application, after the terminal performs voice conversion on the shorthand content to obtain the text set corresponding to the shorthand content, the terminal may perform word segmentation processing and filtering processing on the text set to obtain the keyword.
Further, in an embodiment of the present application, the terminal may first perform word segmentation by using a word segmentation tool, and segment the text information in the text set into a series of words and parts of speech corresponding to the words; then, each word can be filtered according to the word and the corresponding part of speech thereof, and unnecessary words are filtered; and finally, generating the keywords according to all the filtered words corresponding to the text set.
In an embodiment of the present application, based on the method described in the above steps 102a to 102h, for the shorthand content including multiple data formats, the text, the image, and the voice in the shorthand content may be processed at the same time to obtain the phrase set, the character set, the image feature information, and the text information corresponding to the shorthand content, and then the keywords may be obtained together according to the phrase set, the character set, the image feature information, and the text information.
According to the classification method for the shorthand projects, a terminal obtains shorthand contents corresponding to the shorthand projects; wherein the shorthand item is any shorthand in the shorthand application; extracting keywords corresponding to the shorthand content; obtaining a classification result corresponding to the shorthand item according to a preset classification model and the keywords; the preset classification model is obtained by training according to historical data. Therefore, in the embodiment of the application, after the shorthand content corresponding to the shorthand item is determined, the terminal extracts the keywords from the shorthand content, and directly classifies the shorthand item by combining the preset classification model and the keywords to obtain the classification result of the shorthand item, that is, the terminal can realize the shorthand item classification and can also ensure the individuation of the classification result, and the terminal automatically classifies according to the extracted keywords, so that the processing process of the shorthand item classification can be greatly simplified, the classification time of the shorthand item can be effectively shortened, and the intelligence of the terminal can be improved.
EXAMPLE III
Based on the first embodiment, in an embodiment of the application, the method for the terminal to obtain the classification result corresponding to the shorthand item according to the preset classification model and the keyword may further include the following steps:
step 103a, inputting the keywords into a preset classification model to obtain a classification set.
In an embodiment of the application, after extracting the keyword corresponding to the shorthand content, the terminal may input the keyword into the preset classification model, so as to obtain a classification set corresponding to the shorthand content.
It should be noted that, in an embodiment of the present application, when the terminal classifies the shorthand content according to the preset classification model corresponding to the user identifier and the keyword, at least one category may be obtained, and therefore, the terminal may combine all obtained categories into the classification set.
Further, in the embodiment of the present application, in the correspondence relationship between the keyword and the category obtained by the terminal, since one keyword may correspond to a plurality of different categories, the terminal may obtain a plurality of categories corresponding to the shorthand content after inputting the keyword into the preset classification model. For example, after the keyword "apple" is input into the preset classification model, the corresponding categories can be obtained as fruit, red fuji, electronic products, and release meetings.
And 103b, carrying out fusion processing on the classification set to obtain a classification result.
In an embodiment of the present invention, after the terminal inputs the keyword into the preset classification model to obtain the classification set corresponding to the shorthand content, the terminal may perform fusion processing on the classification set to obtain the classification result.
It should be noted that, in the embodiment of the present application, after the terminal obtains the classification set, the terminal may perform fusion processing on the classification set according to a preset fusion rule, so as to obtain a more accurate classification result. The preset fusion rule is a processing method which is preset by the terminal and is used for extracting the categories of the plurality of category information.
Further, in the embodiment of the present application, when the terminal performs the fusion processing according to the preset fusion rule, the terminal may first obtain the recent occurrence time or the occurrence frequency respectively corresponding to all the categories in the classification set according to the historical classification data, then perform the priority ranking on all the categories in the classification set according to the recent occurrence time or the occurrence frequency, and finally may select at least one category with a higher priority as the classification result.
According to the classification method for the shorthand projects, a terminal obtains shorthand contents corresponding to the shorthand projects; wherein the shorthand item is any shorthand in the shorthand application; extracting keywords corresponding to the shorthand content; obtaining a classification result corresponding to the shorthand item according to a preset classification model and the keywords; the preset classification model is obtained by training according to historical data. Therefore, in the embodiment of the application, after the shorthand content corresponding to the shorthand item is determined, the terminal extracts the keywords from the shorthand content, and directly classifies the shorthand item by combining the preset classification model and the keywords to obtain the classification result of the shorthand item, that is, the terminal can realize the shorthand item classification and can also ensure the individuation of the classification result, and the terminal automatically classifies according to the extracted keywords, so that the processing process of the shorthand item classification can be greatly simplified, the classification time of the shorthand item can be effectively shortened, and the intelligence of the terminal can be improved.
Example four
Based on the same inventive concept of the first to third embodiments, fig. 6 is a schematic view of a composition structure of the terminal according to the first embodiment, and as shown in fig. 6, the terminal 1 according to the first embodiment may include an obtaining portion 11, an extracting portion 12, and a establishing portion 13.
The acquisition part 11 is used for acquiring shorthand contents corresponding to shorthand items; wherein the shorthand item is any shorthand in a shorthand application.
The extracting part 12 is configured to extract the keyword corresponding to the shorthand content after the acquiring part 11 acquires the shorthand content corresponding to the shorthand item.
The obtaining part 11 is further configured to, after the extracting part 12 extracts the keyword corresponding to the shorthand content, obtain a classification result corresponding to the shorthand item according to a preset classification model and the keyword; and the preset classification model is obtained by training according to historical data.
Further, in an embodiment of the present application, the obtaining portion 11 is further configured to obtain an identity identifier corresponding to the shorthand item before obtaining a classification result corresponding to the shorthand item according to a preset classification model and the keyword; wherein the identity is used for determining the recorder identity of the shorthand item; acquiring the historical data corresponding to the identity; and training the historical data to obtain the corresponding relation between the keywords corresponding to the historical data and the categories.
The establishing part 13 is configured to establish the preset classification model corresponding to the identity identifier according to the correspondence between the keyword and the category after the obtaining part 11 obtains the historical data corresponding to the identity identifier.
Further, in an embodiment of the present application, when the shorthand content includes a text, the extracting part 12 is specifically configured to perform word segmentation processing and filtering processing on the shorthand content to obtain a phrase set; and analyzing the phrase combination to obtain the keywords.
Further, in the embodiment of the present application, when the shorthand content includes an image, the extracting portion 12 is further specifically configured to perform character recognition on the shorthand content to obtain a character set; and performing word segmentation processing and filtering processing on the character set to obtain the keywords.
Further, in the embodiment of the present application, when the shorthand content includes an image, the extracting portion 12 is further specifically configured to perform feature recognition on the shorthand content to obtain image feature information of the shorthand content; and obtaining the keywords according to the graphic feature information.
Further, in an embodiment of the present application, when the shorthand content includes a voice, the extracting part 12 is further specifically configured to perform voice conversion on the shorthand content to obtain a text set corresponding to the shorthand content; and performing word segmentation processing and filtering processing on the text set to obtain the keywords.
Further, in an embodiment of the present application, the obtaining part 11 is further specifically configured to input the keyword into the preset classification model to obtain a classification set; and carrying out fusion processing on the classification set to obtain the classification result.
Fig. 7 is a schematic diagram illustrating a second composition structure of the terminal according to the embodiment of the present disclosure, and as shown in fig. 7, the terminal 1 according to the embodiment of the present disclosure may further include a processor 14 and a memory 15 storing executable instructions of the processor 14. Optionally, the terminal 1 may further comprise a communication interface 16, and a bus 17 for connecting the processor 14, the memory 15 and the communication interface 16.
In an embodiment of the present Application, the Processor 14 may be at least one of an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a ProgRAMmable Logic Device (PLD), a Field ProgRAMmable Gate Array (FPGA), a Central Processing Unit (CPU), a controller, a microcontroller, and a microprocessor. It is understood that the electronic devices for implementing the above processor functions may be other devices, and the embodiments of the present application are not limited in particular. The apparatus 1 may further comprise a memory 15, which memory 15 may be connected to the processor 14, wherein the memory 15 is adapted to store executable program code comprising computer operating instructions, and wherein the memory 15 may comprise a high speed RAM memory and may further comprise a non-volatile memory, such as at least two disk memories.
In the embodiment of the present application, the bus 17 is used to connect the communication interface 16, the processor 14, and the memory 15 and the intercommunication among these devices.
In an embodiment of the present application, the memory 15 is used for storing instructions and data.
Further, in an embodiment of the present application, the processor 14 is configured to obtain shorthand contents corresponding to a shorthand item; wherein the shorthand item is any shorthand in a shorthand application; extracting keywords corresponding to the shorthand content; obtaining a classification result corresponding to the shorthand item according to a preset classification model and the keywords; and the preset classification model is obtained by training according to historical data.
In practical applications, the Memory 15 may be a volatile first Memory (volatile Memory), such as a Random-Access Memory (RAM); or a non-volatile first Memory (non-volatile Memory), such as a Read-Only first Memory (ROM), a flash Memory (flash Memory), a Hard Disk Drive (HDD) or a Solid-State Drive (SSD); or a combination of first memories of the above kind and provides instructions and data to the processor 14.
In addition, each functional module in this embodiment may be integrated into one processing unit, or 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 or a form of a software functional module.
Based on the understanding that the technical solution of the present embodiment essentially or a part contributing to the prior art, or all or part of the technical solution, may be embodied in the form of a software product stored in a storage medium, and include several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the method of the present embodiment. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
According to the terminal provided by the embodiment of the application, the terminal acquires shorthand contents corresponding to shorthand items; wherein the shorthand item is any shorthand in the shorthand application; extracting keywords corresponding to the shorthand content; obtaining a classification result corresponding to the shorthand item according to a preset classification model and the keywords; the preset classification model is obtained by training according to historical data. Therefore, in the embodiment of the application, after the shorthand content corresponding to the shorthand item is determined, the terminal extracts the keywords from the shorthand content, and directly classifies the shorthand item by combining the preset classification model and the keywords to obtain the classification result of the shorthand item, that is, the terminal can realize the shorthand item classification and can also ensure the individuation of the classification result, and the terminal automatically classifies according to the extracted keywords, so that the processing process of the shorthand item classification can be greatly simplified, the classification time of the shorthand item can be effectively shortened, and the intelligence of the terminal can be improved.
The embodiments of the present application provide a first computer-readable storage medium, on which a program is stored, which when executed by a processor implements the method according to the first to third embodiments.
Specifically, the program instructions corresponding to the classification method of a shorthand item in the embodiment may be stored on a storage medium such as an optical disc, a hard disc, or a usb disk, and when the program instructions corresponding to the classification method of a shorthand item in the storage medium are read or executed by an electronic device, the method includes the following steps:
acquiring shorthand contents corresponding to the shorthand items; wherein the shorthand item is any shorthand in a shorthand application;
extracting keywords corresponding to the shorthand content;
obtaining a classification result corresponding to the shorthand item according to a preset classification model and the keywords; and the preset classification model is obtained by training according to historical data.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of implementations of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart block or blocks and/or flowchart block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks in the flowchart and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present application, and is not intended to limit the scope of the present application.
The embodiment of the application provides a shorthand item classification method, a terminal and a computer storage medium, wherein the terminal acquires shorthand contents corresponding to the shorthand items; wherein the shorthand item is any shorthand in the shorthand application; extracting keywords corresponding to the shorthand content; obtaining a classification result corresponding to the shorthand item according to a preset classification model and the keywords; the preset classification model is obtained by training according to historical data. Therefore, in the embodiment of the application, after the shorthand content corresponding to the shorthand item is determined, the terminal extracts the keywords from the shorthand content, and directly classifies the shorthand item by combining the preset classification model and the keywords to obtain the classification result of the shorthand item, that is, the terminal can realize the shorthand item classification and can also ensure the individuation of the classification result, and the terminal automatically classifies according to the extracted keywords, so that the processing process of the shorthand item classification can be greatly simplified, the classification time of the shorthand item can be effectively shortened, and the intelligence of the terminal can be improved.
Claims (12)
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2018/105819 WO2020051907A1 (en) | 2018-09-14 | 2018-09-14 | Classification method for shorthand item, and terminal and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112639767A true CN112639767A (en) | 2021-04-09 |
Family
ID=69777475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201880097169.XA Pending CN112639767A (en) | 2018-09-14 | 2018-09-14 | Shorthand item classification method, terminal and computer storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112639767A (en) |
| WO (1) | WO2020051907A1 (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106095833A (en) * | 2016-06-01 | 2016-11-09 | 竹间智能科技（上海）有限公司 | Human computer conversation's content processing method |
| CN106503236A (en) * | 2016-10-28 | 2017-03-15 | 北京百度网讯科技有限公司 | Question classification method and device based on artificial intelligence |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7567895B2 (en) * | 2004-08-31 | 2009-07-28 | Microsoft Corporation | Method and system for prioritizing communications based on sentence classifications |
| CN106570109B (en) * | 2016-11-01 | 2020-07-24 | 深圳市点通数据有限公司 | Method for automatically generating question bank knowledge points through text analysis |
| CN108021605A (en) * | 2017-10-30 | 2018-05-11 | 北京奇艺世纪科技有限公司 | A kind of keyword classification method and apparatus |
-
2018
- 2018-09-14 WO PCT/CN2018/105819 patent/WO2020051907A1/en not_active Ceased
- 2018-09-14 CN CN201880097169.XA patent/CN112639767A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106095833A (en) * | 2016-06-01 | 2016-11-09 | 竹间智能科技（上海）有限公司 | Human computer conversation's content processing method |
| CN106503236A (en) * | 2016-10-28 | 2017-03-15 | 北京百度网讯科技有限公司 | Question classification method and device based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020051907A1 (en) | 2020-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11361759B2 (en) | Methods and systems for automatic generation and convergence of keywords and/or keyphrases from a media | |
| CN108806671B (en) | Semantic analysis, device and electronic equipment | |
| WO2019047849A1 (en) | News processing method, apparatus, storage medium and computer device | |
| WO2023273686A1 (en) | Information search method and apparatus, computer device, and storage medium | |
| CN110297880B (en) | Corpus product recommendation method, apparatus, device and storage medium | |
| US20140379719A1 (en) | System and method for tagging and searching documents | |
| US12316891B2 (en) | Video generating method and apparatus, electronic device, and readable storage medium | |
| CN114930278A (en) | Screen recording method and device and computer readable storage medium | |
| CN109119079A (en) | voice input processing method and device | |
| CN107741972A (en) | Image search method, terminal device and storage medium | |
| CN109783612B (en) | Report data positioning method and device, storage medium and terminal | |
| CN115098729A (en) | Video processing method, sample generation method, model training method and device | |
| CN116614669A (en) | Audio and video data processing method and device, electronic equipment and storage medium | |
| CN111046627A (en) | Chinese character display method and system | |
| US12038968B2 (en) | Method and device for personalized search of visual media | |
| WO2017211202A1 (en) | Method, device, and terminal device for extracting data | |
| CN115759048A (en) | Script text processing method and device | |
| CN115544214B (en) | Event processing method, device and computer readable storage medium | |
| CN112639767A (en) | Shorthand item classification method, terminal and computer storage medium | |
| CN117992592A (en) | Information processing method and device, electronic equipment and storage medium | |
| CN113626637B (en) | Video data screening method, device, computer equipment and storage medium | |
| WO2024139834A1 (en) | Search word determining method and apparatus, computer device, and storage medium | |
| CN117290542A (en) | Video question and answer method, computer equipment and storage medium | |
| JP2009134378A (en) | Document group presentation device and document group presentation program | |
| CN117076602A (en) | Content generation method, device, equipment and medium based on multimedia content |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210409 |
|
| RJ01 | Rejection of invention patent application after publication |