CN107506407B - File classification and calling method and device - Google Patents
File classification and calling method and device Download PDFInfo
- Publication number
- CN107506407B CN107506407B CN201710667530.5A CN201710667530A CN107506407B CN 107506407 B CN107506407 B CN 107506407B CN 201710667530 A CN201710667530 A CN 201710667530A CN 107506407 B CN107506407 B CN 107506407B
- Authority
- CN
- China
- Prior art keywords
- information
- classification
- voice
- file
- text
- 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
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000004590 computer program Methods 0.000 claims description 18
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 abstract description 20
- 239000000284 extract Substances 0.000 abstract description 11
- 238000013145 classification model Methods 0.000 description 16
- 230000011218 segmentation Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 238000011160 research Methods 0.000 description 7
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/16—File or folder operations, e.g. details of user interfaces specifically adapted to file systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/54—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for retrieval
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention is applicable to the technical field of file classification, and provides a method and a device for classifying and calling files. The method extracts the voice label information from the first voice information by receiving the first voice of the user, binds the classification information for the target classification file at the same time, wherein the classification information comprises the voice label information, and finally classifies the target classification file according to the classification information. In the implementation process of file classification, the user only needs to send voice to the device, the files can be classified, the operation is convenient and fast, the efficiency is high, the requirement on the user is low, and the use experience of the user is improved.
Description
Technical Field
The invention belongs to the technical field of file classification, and particularly relates to a method and a device for classifying and calling files.
Background
Current file classification techniques are mainly based on file formats, such as placing picture, video and document distinctions in a directory. Generally, a user can only classify files in a file large class; the required documents can be searched only in the file large class, and the searching efficiency is greatly reduced when the number of the files is increased. In order to increase the searching speed, each file is usually required to be labeled with a text label during storage, and then the file is classified, so that the operation is complex and the efficiency is low. Meanwhile, the manual typing mode has low efficiency, and is inconvenient to manage when too many labels are available; the setting of the label also has high requirements for the user, and the user is required to be able to summarize the keyword, but the manually summarized keyword is not always covered completely.
Therefore, the existing file classification technology based on the simple format has the problems of complex operation, low searching efficiency and poor effect under the condition of multiple files.
Disclosure of Invention
The embodiment of the invention aims to provide a method and a device for classifying and calling files, and aims to solve the problems of complex operation, low searching efficiency and poor effect of the existing file classification technology based on a simple format under the condition of multiple files.
In a first aspect, an embodiment of the present invention provides a method for classifying files, where the method includes:
receiving a first voice sent by a user;
extracting voice tag information from the first voice information;
binding classification information for the target classification file, wherein the classification information comprises the voice tag information;
and classifying the target classified files according to the classification information.
In a second aspect, an embodiment of the present invention provides a method for calling a file, where the file is classified by the method for classifying a file as described above, and the method for calling a file includes:
receiving a second voice sent by a user;
matching the second voice with the classification information, and generating a file list according to a matching result, wherein the classification information bound to the files in the file list is matched with the second voice;
and extracting a target calling file from the file list.
In a third aspect, an embodiment of the present invention provides an apparatus for classifying files, where the apparatus includes:
the first receiving unit is used for receiving a first voice sent by a user;
a first extraction unit configured to extract voice tag information from the first voice information;
a binding unit, configured to bind classification information to a target classification file, where the classification information includes the voice tag information;
and the classification unit is used for classifying the target classification files according to the classification information.
In a fourth aspect, an embodiment of the present invention provides a device for calling a file, where the file is classified by using the device for classifying a file as described above, and the device for calling a file includes:
the second receiving unit is used for receiving a second voice sent by the user;
the matching unit is used for matching the second voice with the classification information and generating a file list according to a matching result, wherein the classification information bound to the files in the file list is matched with the second voice;
and the third extraction unit is used for extracting the target call file from the file list.
In a fifth aspect, an embodiment of the present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the following steps when executing the computer program:
receiving a first voice sent by a user;
extracting voice tag information from the first voice information;
binding classification information for the target classification file, wherein the classification information comprises the voice tag information;
and classifying the target classified files according to the classification information.
In a sixth aspect, an embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored, and the computer program, when executed by a processor, implements the following steps:
receiving a first voice sent by a user;
extracting voice tag information from the first voice information;
binding classification information for the target classification file, wherein the classification information comprises the voice tag information;
and classifying the target classified files according to the classification information.
The method and the device for classifying and calling the files have the following beneficial effects that:
the embodiment of the invention extracts the voice label information from the first voice information by receiving the first voice of the user, binds the classification information for the target classification file at the same time, wherein the classification information comprises the voice label information, and finally classifies the target classification file according to the classification information. In the implementation process of file classification, the user only needs to send voice to the device, the files can be classified, the operation is convenient and fast, the efficiency is high, the requirement on the user is low, and the use experience of the user is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
FIG. 1 is a flowchart illustrating an implementation of a method for classifying files according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating an implementation of a method for classifying files according to another embodiment of the present invention;
FIG. 3 is a flowchart illustrating an implementation of a method for file invocation according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of an apparatus for classifying documents according to FIG. 1 according to an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of an apparatus for classifying documents corresponding to the document classification shown in FIG. 2 according to an embodiment of the present invention;
FIG. 6 is a schematic structural diagram of an apparatus for invoking a file corresponding to FIG. 3 according to an embodiment of the present invention;
fig. 7 is a schematic diagram of a terminal device according to another embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Fig. 1 shows a flowchart of an implementation of a method for classifying files according to an embodiment of the present invention, which is detailed as follows:
in S101, a first voice transmitted by a user is received.
In the embodiment of the present invention, the first voice is a voice sent to the device when the user needs to classify the file.
Optionally, in this embodiment, S101 may specifically be:
s1011: the first voice electric signal is collected through a microphone sensor.
S1012: the first speech electrical signal is converted into a first digital signal.
In one embodiment of the present invention, step S101 may be performed by a voice collecting module in the apparatus, wherein the voice collecting module may preferably include a microphone sensor, a digital-to-analog converter and a main controller. A first voice sent by a user is propagated through the air, the microphone sensor collects an electric signal, and the digital-to-analog converter converts the electric signal of the first voice into a first digital signal.
In S102, voice tag information is extracted from the information of the first voice.
In the embodiment of the present invention, the first voice includes information related to file classification, that is, voice tag information, and in a specific embodiment, the whole first voice may be used as the voice tag information; information unrelated to document classification may also be included, such as certain words or spoken buddhist. When classifying files, the voice tag information related to the file classification needs to be extracted first to perform the related steps of subsequent file classification. In one embodiment, the apparatus may extract the voice tag information from the first voice by dividing the frequency of the first voice, and re-encoding and compressing information obtained by the frequency division process to obtain a series of voice information, where the set of voice information is the voice tag information. For example, if the user needs to classify a video file having a file name of "company spring basketball game", and the user sends a voice of "video classification of company spring basketball game", the voice tag information extracted therefrom may be a set of "company spring basketball game", "video", and "classification".
In S103, classification information is bound for the target classified file, and the classification information includes voice tag information.
In the embodiment of the invention, the target classification file refers to a file which needs to be classified by a user, and the file can be a file to be classified which is already stored on a hard disk of the device, or a file which needs to be classified while being stored; the classification information is the basis for classifying the target classified files, each target classified file has corresponding classification information, the classification information determines the classification result of the target classified files, and the target classified files are bound with the classification information, so that the target classified files can be classified according to the classification information. And the classification information comprises voice label information, and the classification information is bound with the target classification file, namely the voice label information is bound with the target classification file.
In S104, the target classified file is classified according to the classification information.
In the embodiment of the invention, after the voice tag information is bound with the target classified file, the target classified file is classified according to the voice tag information. In one embodiment, the probability value that each piece of voice information of the voice tag information belongs to each voice tag classification model can be determined according to the voice tag information and a preset voice tag classification model, so that the total probability value of all voice tag classification models corresponding to the whole voice tag information is counted, and the classification category is determined according to the total probability value. For example, if a user needs to classify a document named "2000-year master research paper", the comprehensive analysis result of the probabilities of the voice tag information of "2000-year", "master research" and "paper" in the preset voice tag classification model is extracted to determine the category to which the document of "2000-year master research paper" belongs. For example, the probabilities that "master students" and "papers" belong to "study period papers" in the voice tag classification model are both 0.7, and the probabilities that "2000 s" and "papers" belong to "yearly documents" in the voice tag classification model are 0.6 and 0.5, respectively, then the total probability values corresponding to the two voice tag classification models are counted, and the total probability value of "study period papers" is higher, and then it is determined that the "2000 s master students papers" file is classified into the category corresponding to the "study period papers". The voice tag classification model can be established by normal distribution statistics of the device according to all stored file classifications, and can also be set manually through the classification habit of the user's own files.
The embodiment of the invention extracts the voice label information from the first voice information by receiving the first voice of the user, binds the classification information for the target classification file at the same time, wherein the classification information comprises the voice label information, and finally classifies the target classification file according to the classification information. In the implementation process of file classification, the user only needs to send voice to the device, the files can be classified, the operation is convenient and fast, the efficiency is high, the requirement on the user is low, and the use experience of the user is improved.
Fig. 2 shows a flowchart of an implementation of a method for classifying files according to another embodiment of the present invention, which is detailed as follows:
in S201, a first voice transmitted by a user is received.
In S202, voice tag information is extracted from the information of the first voice.
In the embodiment of the present invention, the description of step S201 and step S202 is consistent with the description of step S101 and step S102 in the previous embodiment, and the explanation is please refer to the description of the previous embodiment, which is not repeated herein.
In S203, the first speech digital signal is converted into first text information.
In the embodiment of the present invention, the first speech may be converted into the first text information by an existing speech conversion technique.
In S204, text label information is extracted from the first text information.
In the embodiment of the present invention, the first text information includes information related to file classification, that is, text label information; it is also possible to include information that is not relevant to the classification of the document, such as words or spoken buddhist. When classifying files, text label information related to the file classification needs to be extracted first to perform a related step of subsequent file classification. In one embodiment, the text label information may be obtained by segmenting the first text information by the device, and recoding and compressing information obtained by segmenting the first text information to obtain a series of keywords, where a set of the keywords is the text label information. For example, if the information of the first text information after the first voice conversion is "a video of a basketball game in spring of a company", the result of segmenting the information is "the company", "the" spring "," the basketball game "," the "and" the video ", where" the "is information irrelevant to the file classification, and if the information needs to be removed after the segmentation, the finally obtained text label information is a set of keywords such as" the company "," the spring "," the basketball game "and" the video ".
In S205, classification information is bound for the target classified file, and the classification information includes voice tag information and text tag information.
In the embodiment of the invention, the target classification file refers to a file which needs to be classified by a user, and the file can be a file to be classified which is already stored on a hard disk of the device, or a file which needs to be classified while being stored; the classification information is the basis for classifying the target classified files, each target classified file has corresponding classification information, the classification information determines the classification result of the target classified files, and the target classified files are bound with the classification information, so that the target classified files can be classified according to the classification information. The classification information comprises voice label information and text label information, and the classification information is bound with the target classification file, namely the voice label information and the text label information are bound with the target classification file.
In S206, the target classified file is classified according to the classification information.
In the embodiment of the invention, after the voice tag information and the text tag information are bound with the target classified file, the target classified file is classified according to the voice tag information or the text tag information. The description of classifying the target classification file according to the voice tag information is consistent with the corresponding description in the previous embodiment, and the description is given in detail in the above embodiments, and is not repeated here.
In one embodiment of the present invention, the text label information includes first text label information and second text label information, where the first text label information refers to classification information of a broad category, such as file attribute information, and specifically, such as a format of a file; the first text label information refers to classification information of a subclass category, such as a subject keyword of a document, specifically, such as a title name of the document. For example, the text tag information may be keywords of "company", "spring", "basketball game", and "video", where "video" is classified as the first text tag information, and "company", "spring", and "basketball game" may be classified as the second text tag information.
Optionally, in this embodiment, the classifying the target classification file according to the text label information may specifically be:
s2061: and carrying out first class classification on the target classification file according to the first text label information.
In the embodiment of the invention, first text label information is obtained according to the text label information, and then first class classification is carried out on the target classification file according to the first text label information. In one embodiment, the first text label information may be file format information, and the target classified file is classified for the first time according to the file format information, that is, the first class classification. Such as dividing all video files into a large category, dividing all music files into a large category, etc. The first category classification of the target classified files may increase the accuracy of the target individual file description.
S2062: and carrying out second class classification on the target classification file according to the second text label information.
In the embodiment of the present invention, after the first classification is performed on the target classification file, a second classification may be further performed according to the second text label information, for example, according to the classification of the document topic keyword, that is, the document in the major category is subdivided for the second time and is classified into the minor category. In one embodiment, the probability value that each keyword of each second text label information belongs to each keyword classification model can be determined according to the document subject keyword and a preset keyword classification model, so that the total probability value of all keyword classification models corresponding to the text content of the whole second text label information is counted, and the finally-belonging subclass classification category is determined according to the total probability value. For example, if a user needs to classify a document named "2000-year master research paper", after the first classification type of the document is determined, the subclass type to which the document "2000-year master research paper" belongs is determined according to the comprehensive analysis result of the probabilities occupied by the three acquired keyword results of "2000-year", "master research" and "paper" in the preset keyword classification model. For example, the probabilities that "master students" and "papers" belong to "study period papers" in the keyword classification model are both 0.7, and the probabilities that "2000 s" and "papers" belong to "year documents" in the keyword classification model are 0.6 and 0.5, respectively, then the total probability values corresponding to the two keyword classification models and the "study period papers" are counted, and the total probability value of the "study period papers" is higher, and then it is determined that the "2000 s master students papers" file is classified into the subclass category corresponding to the "study period papers". And performing secondary classification on the target classification files through the subclass classes, and further accurately classifying the classes of the target classification files. The keyword classification model can be established by normal distribution statistics of the device according to all stored file classifications, and can also be set manually through the classification habit of the user's own files.
The embodiment of the invention extracts the voice label information from the first voice by receiving the first voice of the user, converts the first voice into the first text information, extracts the text label information from the first voice, binds the classification information for the target classification file, wherein the classification information comprises the voice label information and the text label information, and finally classifies the target classification file according to the classification information. In the implementation process of file classification, files can be classified according to voice tag information, files can also be classified through text tag information, the efficiency of file classification is further improved by combining the files, the classification is more accurate, a user only needs to send voice to the device, the files can be classified, the operation is convenient and fast, the efficiency is high, the requirement on the user is low, and the use experience of the user is improved.
It should be understood that, in the embodiment of the present invention, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiment of the present invention.
On the basis of fig. 1 and fig. 2, fig. 3 shows a flowchart of an implementation of a method for calling a file according to an embodiment of the present invention, where the file is classified by the method for classifying a file according to the previous embodiment, which is described in detail as follows:
in S301, a second voice transmitted by the user is received.
In this embodiment of the present invention, the second voice is a voice sent to the device when the user needs to call the target call file, where the second voice includes call information of the target call file, and the call information includes, but is not limited to, file text information and file attribute information that the target call file needs to have. The target calling file refers to a file that the user needs to call, and the file may be a file already stored on the hard disk of the device. For example, if the user needs to call a video file with the file name "a company spring basketball game", the user sends a voice "call a video of the company spring basketball game", and the device will receive the voice.
Optionally, in this embodiment, S301 may specifically be:
s3011: and acquiring a second voice electric signal through the microphone sensor.
S3012: and converting the second voice electric signal into a second digital signal to obtain second voice.
In this embodiment, step S301 may be performed by a voice acquisition module in the apparatus, wherein the voice acquisition module may preferably include a microphone sensor, a digital-to-analog converter, and a main controller. The second voice sent by the user is transmitted through the air, the microphone sensor collects the electric signal, and the digital-to-analog converter converts the electric signal of the second voice into a second digital signal to obtain the second voice.
In S302, the second voice is matched with the classification information, a file list is generated according to the matching result, and the classification information bound to the files in the file list is matched with the second voice.
In the embodiment of the invention, after the second voice is received, the second voice is matched with the classification information bound with all the stored files to obtain all the files matched with the second voice, the files meeting the matching condition are obtained, and all the matched files are arranged to generate a file list so as to further screen out the target calling file in the subsequent process.
Optionally, in this embodiment, in step S302, the second voice is matched with the classification information bound to all the stored files, specifically, after the second voice is converted into the second text information, the second text information is matched with the text tag information in the classification information, and then, since the text tag information is bound to the stored files, a file list can be generated according to the matching result; or directly matching the second voice with the first voice in the classification information, and then generating a file list according to a matching result because the first voice is bound with the stored file.
Specifically, S302 may include:
s30211: the second speech is converted into second text information.
S30212: and extracting the calling information from the second text information.
The second text information includes calling information related to the calling of the target calling file, and may also include information unrelated to the calling of the target calling file, and after the obtained second text information, the calling information of the target calling file may be extracted from the second text information.
S30213: and matching the calling information with the text label information, generating a file list according to a matching result, and matching the classification information bound to the files in the file list with the second text information.
In one embodiment of the invention, the calling information includes but is not limited to keywords of the target calling file and file attribute information, and the file attribute information has a larger selection range for the target calling file, because the efficiency of searching the target calling file from the aspect of the file attribute information is low, the keywords can be directly used for searching, so that the searching time can be greatly reduced. The keywords of the target calling file can be obtained by extracting calling information from the second text information, segmenting the calling information, and recoding and compressing information obtained by segmenting the words. The word segmentation specifically refers to segmenting the Chinese character sequence of the calling information into meaningful words, namely word segmentation. For example, if the call information is "i am a student" then the result of the word segmentation is: "i", "is", "one", "student", and the last keyword obtained is "i" and "student". The word segmentation can be specifically realized by the existing word segmentation algorithm, for example, a word segmentation method based on character string matching, a word segmentation method based on understanding, or a word segmentation method based on statistics is adopted.
In one specific embodiment, after the keywords of the target calling file are obtained, the keywords are compared with the text label information, and the text label information with the matching degree higher than a preset threshold value is matched through a fuzzy algorithm. Specifically, the stored text label information of the keywords corresponding to the target calling file is compared to obtain the text label information matched with all or part of the keywords in the second text information. Since each text label information can be divided into one or more keywords, and a keyword may also be derived from one or more text label information, one or more text label information may be matched by a fuzzy algorithm in the process of matching keywords. Therefore, a plurality of matched text label information needs to be screened for the first time, specifically, a threshold value of the matching degree can be preset, whether the search result of the text label information matches the requirement or not is judged, when the matching degree of the text label information is higher than the preset threshold value, the search result is retained, and otherwise, the search result is abandoned. For example, the matching degrees of the plurality of files matched by the keywords are distributed between 30% and 90%, and if the preset threshold of the matching degrees is set to be 60%, only the files with the matching degrees distributed between 60% and 90% are reserved in each file matched by the keywords.
Specifically, S302 may further include:
s30221: and matching the second voice with the first voice, generating a file list according to a matching result, and matching the classification information bound to the files in the file list with the second voice.
In the embodiment of the invention, the second voice is matched with the first voice, and the second voice and the first voice are possibly completely or partially consistent, so that a threshold value of the matching degree can be preset, whether the first voice matched by the second voice is matched with the requirement or not is judged, when the matching degree of the first voice is higher than the preset threshold value, the first voice search result is retained, otherwise, the first voice search result is abandoned, and finally, a file list of the matched files bound with the first voice is generated.
S303: and extracting the target calling file from the file list.
In the embodiment of the present invention, after the matched file list is generated in step S302, the user may directly view the file list, and extract the target call file from the list.
The files in the file list can be arranged from high to low or from low to high according to the matching degree. For example, when the user needs to call the document of the "2000-s-study thesis", the documents related to the keywords such as "2000-s", "s-study", "thesis", etc. are searched in the classification information, and the comprehensive matching is performed to calculate the matching degree. For example, the searched matching degree of "the first composition of the XXX master thesis paper of the physical academy of 2000" is 80%, the matching degree of "the modification of the research master thesis" is 59%, and the matching degree of "the report of the master issue of 2013" is 40%. When the preset threshold of the matching degree is set to 50%, the list generated by the "first composition of the XXX master thesis of physical academy 2000" and the "amendment of the study master thesis" in the search result is displayed (preferably, corresponding matching degree information is simultaneously reserved in the list) so that the user can directly view the list in a text form to extract the target calling file.
According to the embodiment of the invention, the second voice sent by the user is received, the second voice is matched with the classification information, the file list is generated according to the matching result, and the target calling file is finally extracted from the file list, so that the calling of the file is realized. In the implementation process of file calling, a user can search out a matched file list only by sending voice information to the device, and then a target calling file is obtained.
It should be understood that, in the embodiment of the present invention, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiment of the present invention.
Fig. 4 is a schematic structural diagram of an apparatus for performing document classification corresponding to the method steps in fig. 1 according to an embodiment of the present invention, and referring to fig. 4, the apparatus for document classification includes:
the first receiving unit 41 is configured to receive a first voice sent by a user.
A first extracting unit 42, configured to extract voice tag information from information of the first voice.
A binding unit 43 for binding the classification information for the target classified file, the classification information including voice tag information.
And a classification unit 44, configured to classify the target classified file according to the classification information.
Optionally, the first receiving unit 41 specifically includes:
the first acquisition unit is used for acquiring a first voice electric signal through the microphone sensor.
The first conversion unit is used for converting the first voice electric signal into a first digital signal.
The file classification device provided by the embodiment of the invention extracts the voice tag information from the first voice information by receiving the first voice of the user, binds the classification information for the target classification file at the same time, wherein the classification information comprises the voice tag information, and finally classifies the target classification file according to the classification information. In the implementation process of file classification, the user only needs to send voice to the device, the files can be classified, the operation is convenient and fast, the efficiency is high, the requirement on the user is low, and the use experience of the user is improved.
Fig. 5 is a schematic structural diagram of an apparatus for performing document classification corresponding to the method steps in fig. 2 according to an embodiment of the present invention, and referring to fig. 5, the apparatus for document classification includes:
the first receiving unit 51 is configured to receive a first voice sent by a user.
A first extracting unit 52, configured to extract voice tag information from the information of the first voice.
A second conversion unit 53, configured to convert the first speech digital signal into first text information.
A second extracting unit 54 for extracting text label information from the first text information.
A binding unit 55, configured to bind classification information for the target classified file, where the classification information includes voice tag information and text tag information.
And a classification unit 56 for classifying the target classified file according to the classification information.
The description of the first receiving unit 51 is consistent with the description of the first receiving unit 41, and the description is please refer to the description of the above embodiments, which is not repeated herein.
Optionally, the classifying unit 56 includes a voice tag information classifying unit and a text tag information classifying unit, where the text tag information classifying unit specifically includes:
and the first classification unit is used for performing first class classification on the target classification file according to the first text label information.
And the second classification unit is used for performing second class classification on the target classification file according to the second text label information.
The file classification device provided by the embodiment of the invention extracts the voice tag information from the first voice by receiving the first voice of the user, converts the first voice into the first text information, extracts the text tag information from the first voice, binds the classification information for the target classification file, wherein the classification information comprises the voice tag information and the text tag information, and finally classifies the target classification file according to the classification information. In the implementation process of file classification, files can be classified according to voice tag information, files can also be classified through text tag information, the efficiency of file classification is further improved by combining the files, the classification is more accurate, a user only needs to send voice to the device, the files can be classified, the operation is convenient and fast, the efficiency is high, the requirement on the user is low, and the use experience of the user is improved.
Fig. 6 is a schematic structural diagram illustrating an apparatus for executing a file call corresponding to the method step in fig. 3 according to an embodiment of the present invention, and referring to fig. 6, the apparatus for file call includes:
and a second receiving unit 61, configured to receive a second voice sent by the user.
And the matching unit 62 is configured to match the second voice with the classification information, and generate a file list according to a matching result, where the classification information bound to the files in the file list is matched with the second voice.
And a third extracting unit 63, configured to extract the target call file in the file list.
Optionally, the second receiving unit 61 specifically includes:
and the second acquisition unit is used for acquiring a second voice electric signal through the microphone sensor.
And the third conversion unit is used for converting the second voice electric signal into a second digital signal to obtain second voice.
Optionally, the matching unit 62 specifically includes:
and a fourth conversion unit for converting the second voice into second text information.
And the fourth extraction unit is used for extracting the calling information from the second text information.
And the first matching subunit is used for matching the calling information with the text label information, generating a file list according to a matching result, and matching the classification information bound to the files in the file list with the second text information.
And the second distribution subunit is used for matching the second voice with the first voice, generating a file list according to the matching result, and matching the classification information bound to the files in the file list with the second voice.
Therefore, the device for calling the file provided by the embodiment of the invention matches the second voice with the classification information by receiving the second voice sent by the user, generates the file list according to the matching result, and finally extracts the target calling file from the file list to realize the calling of the file. In the implementation process of file calling, a user can search out a matched file list only by sending voice information to the device, and then a target calling file is obtained.
Fig. 7 is a schematic diagram of a terminal device according to another embodiment of the present invention. As shown in fig. 7, the terminal device 7 of this embodiment includes: a processor 70, a memory 71 and a computer program 72, such as a method program for file classification, stored in said memory 71 and executable on said processor 70. The processor 70, when executing the computer program 72, implements the steps in the above-described embodiments of the method for classifying documents, such as S101 to S104 shown in fig. 1. Alternatively, the processor 70, when executing the computer program 72, implements the functions of the units in the above-described device embodiments, such as the functions of the units 41 to 44 shown in fig. 4.
Illustratively, the computer program 72 may be divided into one or more units, which are stored in the memory 71 and executed by the processor 70 to accomplish the present invention. The one or more units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program 72 in the terminal device 7. For example, the computer program 72 may be divided into a first receiving unit, a first extracting unit, a binding unit, and a classifying unit, and the specific functions of each unit are as follows:
the first receiving unit is used for receiving a first voice sent by a user.
The first extraction unit is used for extracting voice label information from the information of the first voice.
And the binding unit is used for binding the classification information for the target classification file, wherein the classification information comprises voice label information.
And the classification unit is used for classifying the target classification files according to the classification information.
The terminal device 7 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The terminal device may include, but is not limited to, a processor 70, a memory 71. It will be appreciated by those skilled in the art that fig. 7 is merely an example of a terminal device 7 and does not constitute a limitation of the terminal device 7 and may comprise more or less components than shown, or some components may be combined, or different components, for example the terminal device may further comprise input output devices, network access devices, buses, etc.
The Processor 70 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 71 may be an internal storage unit of the terminal device 7, such as a hard disk or a memory of the terminal device 7. The memory 71 may also be an external storage device of the terminal device 7, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the terminal device 7. Further, the memory 71 may also include both an internal storage unit and an external storage device of the terminal device 7. The memory 71 is used for storing the computer program and other programs and data required by the terminal device. The memory 71 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the above-mentioned apparatus may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another apparatus, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention 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, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (9)
1. A method of classifying a document, comprising:
receiving a first voice sent by a user;
extracting voice tag information from the information of the first voice;
binding classification information for the target classification file, wherein the classification information comprises the voice tag information;
classifying the target classified files according to the classification information;
the method further comprises the following steps:
converting the first voice into first text information;
extracting text label information from the first text information;
the classification information includes the voice tag information and the text tag information.
2. The method of claim 1, wherein the text label information comprises first text label information and second text label information, and wherein classifying the target classified file according to the classification information comprises:
performing first class classification on the target classification file according to the first text label information;
and performing second category classification on the target classification file according to the second text label information.
3. A method of file invocation, said file being classified by the method of file classification according to claim 1 or 2, characterized in that it comprises:
receiving a second voice sent by a user;
matching the second voice with the classification information, and generating a file list according to a matching result, wherein the classification information bound to the files in the file list is matched with the second voice;
and extracting a target calling file from the file list.
4. The method of claim 3, wherein the classification information includes text label information, the matching the second speech with the classification information, and generating a file list according to a matching result, the classification information bound to files in the file list matching the second speech, comprises:
converting the second voice into second text information;
extracting calling information from the second text information;
and matching the calling information with the text label information, and generating a file list according to a matching result, wherein the classification information bound to the files in the file list is matched with the second text information.
5. The method according to claim 3, wherein matching the second voice with the classification information, and generating a file list according to a matching result, wherein the classification information bound to the files in the file list matches the second voice, comprises:
and matching the second voice with the first voice, and generating a file list according to a matching result, wherein the classification information bound to the files in the file list is matched with the second voice.
6. An apparatus for classifying documents, comprising:
the first receiving unit is used for receiving a first voice sent by a user;
a first extraction unit configured to extract voice tag information from information of the first voice;
a binding unit, configured to bind classification information to a target classification file, where the classification information includes the voice tag information;
the classification unit is used for classifying the target classification files according to the classification information;
a text conversion unit for converting the first voice into first text information;
a second extraction unit configured to extract text label information from the first text information;
wherein the classification information includes the voice tag information and the text tag information.
7. The apparatus of claim 6, wherein the text label information comprises first text label information and second text label information, and wherein the classifying unit comprises:
the first classification unit is used for performing first classification on the target classification file according to the first text label information;
and the second class classification unit is used for carrying out second class classification on the target classification file according to the second text label information.
8. An apparatus for calling a document, the document being classified by the apparatus for classifying a document according to claim 6 or 7, comprising:
the second receiving unit is used for receiving a second voice sent by the user;
the matching unit is used for matching the second voice with the classification information and generating a file list according to a matching result, wherein the classification information bound to the files in the file list is matched with the second voice;
and the third extraction unit is used for extracting the target call file from the file list.
9. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710667530.5A CN107506407B (en) | 2017-08-07 | 2017-08-07 | File classification and calling method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710667530.5A CN107506407B (en) | 2017-08-07 | 2017-08-07 | File classification and calling method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107506407A CN107506407A (en) | 2017-12-22 |
| CN107506407B true CN107506407B (en) | 2020-03-27 |
Family
ID=60688907
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710667530.5A Active CN107506407B (en) | 2017-08-07 | 2017-08-07 | File classification and calling method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107506407B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446339B (en) * | 2018-02-28 | 2020-09-25 | 维沃移动通信有限公司 | Application icon classification method and mobile terminal |
| CN111079849A (en) * | 2019-12-23 | 2020-04-28 | 西南交通大学 | Method for constructing new target network model for voice-assisted audio-visual collaborative learning |
| CN117648298B (en) * | 2024-01-30 | 2024-04-16 | 深圳市华瑞安科技有限公司 | Intelligent management system, method and device for tablet personal computer |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104615769A (en) * | 2015-02-15 | 2015-05-13 | 小米科技有限责任公司 | Image classification method and device |
| US9298813B1 (en) * | 2012-12-03 | 2016-03-29 | Adobe Systems Incorporated | Automatic document classification via content analysis at storage time |
| CN105632501A (en) * | 2015-12-30 | 2016-06-01 | 中国科学院自动化研究所 | Deep-learning-technology-based automatic accent classification method and apparatus |
| CN106954095A (en) * | 2017-04-17 | 2017-07-14 | 腾讯科技（深圳）有限公司 | The player method and device of a kind of multimedia file |
-
2017
- 2017-08-07 CN CN201710667530.5A patent/CN107506407B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9298813B1 (en) * | 2012-12-03 | 2016-03-29 | Adobe Systems Incorporated | Automatic document classification via content analysis at storage time |
| CN104615769A (en) * | 2015-02-15 | 2015-05-13 | 小米科技有限责任公司 | Image classification method and device |
| CN105632501A (en) * | 2015-12-30 | 2016-06-01 | 中国科学院自动化研究所 | Deep-learning-technology-based automatic accent classification method and apparatus |
| CN106954095A (en) * | 2017-04-17 | 2017-07-14 | 腾讯科技（深圳）有限公司 | The player method and device of a kind of multimedia file |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107506407A (en) | 2017-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107766371B (en) | Text information classification method and device | |
| CN107346336B (en) | Information processing method and device based on artificial intelligence | |
| JP6894534B2 (en) | Information processing method and terminal, computer storage medium | |
| CN108920675B (en) | Information processing method and device, computer storage medium and terminal | |
| CN109460551B (en) | Signature information extraction method and device | |
| CN111046656B (en) | Text processing method, text processing device, electronic equipment and readable storage medium | |
| CN108509569A (en) | Generation method, device, electronic equipment and the storage medium of enterprise's portrait | |
| CN108682421B (en) | Voice recognition method, terminal equipment and computer readable storage medium | |
| US10108698B2 (en) | Common data repository for improving transactional efficiencies of user interactions with a computing device | |
| CN107506407B (en) | File classification and calling method and device | |
| CN111177462B (en) | Video distribution timeliness determination method and device | |
| CN111930792A (en) | Data resource labeling method and device, storage medium and electronic equipment | |
| US20200204688A1 (en) | Picture book sharing method and apparatus and system using the same | |
| CN111563382A (en) | Text information acquisition method and device, storage medium and computer equipment | |
| CN103942328A (en) | Video retrieval method and video device | |
| CN112783825A (en) | Data archiving method, data archiving device, computer device and storage medium | |
| CN110532449B (en) | Method, device, equipment and storage medium for processing service document | |
| CN114241501B (en) | Image document processing method and device and electronic equipment | |
| CN112307318A (en) | Content publishing method, system and device | |
| CN111368504A (en) | Voice data labeling method and device, electronic equipment and medium | |
| CN111062221A (en) | Data processing method, data processing device, electronic equipment and storage medium | |
| CN111949793B (en) | User intention recognition method and device and terminal equipment | |
| CN105512270B (en) | Method and device for determining related objects | |
| CN110597765A (en) | Large retail call center heterogeneous data source data processing method and device | |
| CN111046632A (en) | Data extraction and conversion method, system, storage medium 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |