CN114125184A - Word extraction method, device, terminal and storage medium - Google Patents
Word extraction method, device, terminal and storage medium Download PDFInfo
- Publication number
- CN114125184A CN114125184A CN202111393118.1A CN202111393118A CN114125184A CN 114125184 A CN114125184 A CN 114125184A CN 202111393118 A CN202111393118 A CN 202111393118A CN 114125184 A CN114125184 A CN 114125184A
- Authority
- CN
- China
- Prior art keywords
- prompt
- manuscript
- current
- signal
- word
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/2222—Prompting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/381—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using identifiers, e.g. barcodes, RFIDs
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/221—Parsing markup language streams
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
Abstract
The application relates to the field of communication, in particular to a method, a device, a terminal and a storage medium for prompting, which are used for splitting manuscripts for prompting into at least two prompting manuscript packages, wherein each prompting manuscript package comprises a plurality of prompting contents, each prompting manuscript package is provided with a corresponding stepping label, and the method for prompting comprises the following steps: acquiring a current stepping label; acquiring a current word-extracting signal; and matching the current prompt signal with the prompt content in the prompt manuscript packet corresponding to the current stepping label, and if the matching is successful, outputting a control signal for controlling the prompt content to be displayed. According to the method and the device, the manuscripts for the word extraction can be directly split into at least two word extraction manuscript packages without considering the length of each word extraction manuscript package and the speed of a specified object, and when the new record is needed, the new record can be rapidly re-recorded only by re-acquiring the stepping labels corresponding to the word extraction manuscript packages which need to be re-recorded.
Description
Technical Field
The present application relates to the field of communications, and in particular, to a method, an apparatus, a terminal, and a storage medium for providing a word.
Background
The prompter, when in use, will send the text to be displayed to the display device for display, and the display device is typically positioned near the camera (e.g., above the camera) so that the designated object (which may be a presenter) can look at the text facing the camera, creating a sense of closeness that the designated object always faces the audience. However, the number of words that can be accommodated on the display device is limited, which requires frequent subtitle scrolling or frequent switching of screen content.
In the related technology, a part of the designated objects are directly turned by manual work, and the manual work often causes inaccurate page turning time in the process of turning the pages, for example, the designated objects are turned for too long time in advance or the pages are forgotten to turn the pages all the time, so that the speech process of the designated objects is seriously influenced; some of them are to automatically scroll or turn pages according to a preset scrolling speed or switching frequency, but because the speeds of speech of different people are different and the same person has different speeds of speech under different semantic environments, the setting of the scrolling speed or the switching frequency is complicated.
In view of the above-mentioned related art, the inventor believes that although several solutions of the prompter in the related art can implement text prompting, the using effect is not good.
Disclosure of Invention
In order to improve the using effect of the prompter, the application provides a prompter method, a device, a terminal and a storage medium.
In a first aspect, the present application provides a method for providing a word, which adopts the following technical scheme:
a method for extracting words divides a manuscript for extracting words into at least two words extracting manuscript packages, wherein each words extracting manuscript package comprises a plurality of words extracting contents, each words extracting manuscript package is provided with a corresponding stepping label, and the method for extracting words comprises the following steps:
acquiring a current stepping label;
acquiring a current word-extracting signal;
and matching the current prompt signal with the prompt content in the prompt manuscript packet corresponding to the current stepping label, and if the matching is successful, outputting a control signal for controlling the prompt content to be displayed.
By adopting the technical scheme, the manuscript for the extraction can be directly split into at least two extraction manuscript packages without considering the length of each extraction manuscript package and the speed of a specified object, and when the specified object needs to be re-recorded when the recording of a certain extraction manuscript package is not satisfactory or errors occur in the recording process and the like, the specified object can be re-recorded quickly by only re-acquiring the step label corresponding to the extraction manuscript package needing to be re-recorded.
Optionally, the obtaining the current prompt signal specifically includes:
acquiring voice data;
converting the voice data into character data;
and taking the text data as the current word-prompting signal.
By adopting the technical scheme, the voice data of the designated object is acquired in real time and converted into corresponding character data, so that the currently displayed prompter content is updated in real time.
Optionally, the matching the current prompt signal with the prompt content in the prompt manuscript packet corresponding to the current stepping label specifically includes: and directly matching the current prompt signal with the prompt content in the prompt manuscript packet corresponding to the current stepping label by adopting a similarity algorithm.
By adopting the technical scheme, the current prompt signal is directly matched with the prompt content in the prompt manuscript packet corresponding to the current stepping label, the prompt content is character data basically the same as the current prompt signal, and the matching mode is simple and clear.
Optionally, the matching the current prompt signal with the prompt content in the prompt manuscript packet corresponding to the current stepping label specifically includes: and each of the prompt contents is provided with a corresponding prompt signal, and the current prompt signal is matched with the prompt signal in the prompt manuscript packet corresponding to the current stepping label.
By adopting the technical scheme, the prompt contents in the prompt manuscript packet are respectively provided with corresponding prompt signals, namely, a one-to-one correspondence relationship is established between the prompt contents and the prompt signals, the prompt contents are generally relatively simplified characters, and more prompt contents can be displayed in a display device with the same size.
Optionally, the plurality of prompt contents are arranged in a preset sequence, each prompt content is provided with a position tag indicating a corresponding sequence, and if the position tag corresponding to the prompt content successfully matched currently is not continuous with the position tag corresponding to the prompt content successfully matched last time, the control signal is not output.
By adopting the technical scheme, when a designated object broadcasts or speaks the manuscript content corresponding to one of the prompt contents, certain extension expansion is often performed according to the manuscript content, and in the process of extension expansion, some content is sometimes matched with the content in discontinuous prompt contents, so that the adjacent prompt contents are easily ignored before being prompted, and the occurrence of the situation can be reduced by adopting the mode.
Optionally, the plurality of prompt contents are arranged in a preset sequence, and if the interval between the prompt content successfully matched currently and the prompt content successfully matched last time exceeds a preset length, the control signal is not output.
By adopting the technical scheme, when a designated object broadcasts or speaks the manuscript content corresponding to one of the prompt contents, certain extension expansion is often performed according to the manuscript content, and in the process of extension expansion, some content is sometimes matched with the content in the prompt contents with the interval exceeding the preset length, so that the prompt contents with the interval within the preset length are easily ignored before being prompted, and the occurrence of the situation can be reduced by adopting the mode.
Optionally, each of the prompt manuscript packages is arranged according to the step label, and if the prompt contents in the prompt manuscript package corresponding to the current step label are successfully matched, the next step label is automatically obtained.
By adopting the technical scheme, if the matching of the abstract contents in the abstract manuscript packet corresponding to the current stepping label is successful, the fact that the abstract manuscript packet is completely displayed is indicated, and after a signal that the matching of the abstract contents in the abstract manuscript packet is successful is obtained, the next stepping label can be automatically obtained and enters the next abstract manuscript packet for matching.
In a second aspect, the present application further provides a word-prompting device, which adopts the following technical scheme:
a word presentation device comprising:
the memory is used for storing the prompter program;
and the processor executes the steps of the word extraction method when the word extraction program is run.
By adopting the technical scheme, the word-extracting method is presented in the form of computer readable codes and stored in the memory, and the steps of the word-extracting method are executed when the processor runs the computer readable codes in the memory.
In a third aspect, the present application further provides a word-proposing terminal, which adopts the following technical scheme:
a word-prompting terminal, comprising:
the signal acquisition device is used for acquiring a current prompt signal;
the display device is used for displaying the prompter content;
in the above-mentioned prompter device, the input end is connected to the signal acquisition device, and the output end is connected to the display device.
By adopting the technical scheme, the terminal acquires the current prompt signal by means of the signal acquisition device, the prompt device is used for matching and outputting the corresponding control signal, the display device is used for displaying the corresponding prompt content according to the control signal, the re-recording can be carried out quickly, and the using effect of the prompt terminal is improved.
In a fourth aspect, the present application further provides a computer-readable storage medium, which adopts the following technical solutions:
a computer-readable storage medium storing a computer program that can be loaded by a processor and executed to perform the above-mentioned prompter method.
In summary, the present application can directly split the manuscript for performing a speech extraction into at least two speech extraction manuscript packages without considering the length of each speech extraction manuscript package and the speed of a designated object, and when the designated object needs to be re-recorded, such as when the designated object does not satisfy the recording of a certain speech extraction manuscript package or makes an error in the recording process, the designated object needs to re-obtain the step label corresponding to the speech extraction manuscript package to be re-recorded, so as to perform the re-recording quickly.
Drawings
Fig. 1 is a schematic block diagram of a terminal of the present application.
FIG. 2 is a schematic diagram of a manuscript structure for use in the present application.
Fig. 3 is a schematic flow chart of the method of the present application.
Description of reference numerals:
1. a signal acquisition device; 2. a word-prompting device; 3. a display device.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is further described in detail below with reference to fig. 1-3 and the embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In the related art of performing automatic scrolling or page turning according to the preset scrolling speed or switching frequency, since the speeds of different people are different and the same person has different speeds in different semantic environments, the setting of the scrolling speed or the switching frequency is complicated. For example, the speech rates of different persons are different, and therefore, the scrolling speed or the switching frequency needs to be set according to the actual speech rate of the specified object; in addition, even the same person has different speech rates in different semantic environments or different emotional states, and therefore, it is necessary to set a scroll speed or a switching frequency according to the different semantic environments of the text to be actually displayed. In addition, by adopting the automatic scrolling or page turning mode, when the designated object needs to extend and expand some contents outside the text range which is actually required to be displayed, word extraction errors are easily caused.
The embodiments of the present invention will be described in detail with reference to the accompanying drawings.
The embodiment of the application provides a prompt terminal, as shown in fig. 1, the terminal includes a signal acquisition device 1, a display device 3 and a prompt device 2, an input end of the prompt device 2 is connected with the signal acquisition device 1, and an output end is connected with the display device 3; the prompter device 2 is integrated with a memory and a processor, the memory is used for storing a prompter program, and the processor is used for executing the steps of the prompter method when the prompter program is operated; the signal acquisition device 1 is used for acquiring a current prompt signal; the display device 3 is used for displaying the content of the prompter.
The implementation of the prompter method is described in detail below with reference to the prompter terminal:
the embodiment of the application discloses a word-prompting method. Referring to fig. 2, a manuscript for performing a term extraction is divided into at least two term extraction manuscript packages, each term extraction manuscript package comprises a plurality of term extraction contents, each term extraction manuscript package is provided with a corresponding stepping label, the plurality of term extraction contents are arranged according to a preset term extraction sequence, and the preset term extraction sequence is determined according to the actual contents of the manuscript.
Specifically, the method for splitting the article for providing the terms may be splitting according to actual article contents, for example, assuming that the actual article contents relate to five pieces of news, the article for providing the terms may be split into five article packages corresponding to the five pieces of news one by one in a manner that each piece of news is a term article package, it should be noted that, in the splitting method, the article may be directly split into five complete pieces of news articles without considering the length of each piece of news and the speed of a designated object, and when the designated object needs to be re-recorded, the designated object is not satisfactory for recording a certain piece of news or has an error in the recording process, and the like, the article for providing the terms may be re-recorded quickly by only re-obtaining a step label corresponding to the term article package that needs to be re-recorded.
The method for splitting the manuscript for proposing the term may also be splitting according to the repetition degree in the actual manuscript content, for example, if the actual manuscript content relates to five news, but some keyword with higher repetition degree exists in some news, and the keyword easily causes errors in matching and positioning, the manuscript may be split according to the keyword with higher repetition degree, and the keyword with higher repetition degree appearing at different positions is split into different submission packages, that is, under such a condition, the keyword can be split into six or more than six submission packages, so as to reduce mismatching.
Referring to fig. 3, the method of prompting includes the steps of:
s01: and acquiring the current stepping label.
Specifically, the current step label refers to a step label corresponding to the present article package to be recognized. The current step label can be obtained manually or automatically; when a manual acquisition mode is adopted, the designated object can switch the step labels corresponding to the article files to be identified by pressing the remote control button, or the instruction can switch the article files by pressing the remote control button or directly select the step labels corresponding to the article files to be identified on the article device 2; when the automatic obtaining mode is adopted, firstly, arranging each prompting manuscript packet according to a preset sequence of the stepping labels, wherein the preset sequence can be set in advance according to the actual content of the manuscript for prompting, and marking the stepping labels, if the prompting contents in the prompting manuscript packet corresponding to the current stepping label are successfully matched (the specific judgment mode of whether the matching is successful or not can be that whether the next prompting content exists or not is judged, and if the matching is not successful or not is proved), automatically obtaining the next stepping label, entering the prompting manuscript packet corresponding to the next stepping label for matching, and outputting a control signal for controlling and displaying the prompting contents in the prompting manuscript packet corresponding to the next stepping label.
S02: and acquiring a current prompt signal.
Specifically, the current utterance signal refers to an utterance signal corresponding to currently recognized speech data. The sequence between step S01 and step S02 is not limited, that is, step S01 and step S02 may be performed simultaneously or first.
For example, the obtaining of the current word-lifting signal specifically includes the following steps:
s21: voice data is acquired.
Specifically, when voice data is acquired, the voice data can be directly acquired through a sound pickup device, wherein the sound pickup device can be a microphone or other voice acquisition devices, and the voice data of the specified object is acquired in real time when the specified object carries out lecture or presentation.
S22: and converting the voice data into text data.
Specifically, the voice data may be converted into text data by a voice recognition system, which may be an existing voice recognition software, wherein the voice recognition system inputs the voice data and outputs the text data as text in the voice data, and the text data is used in a subsequent matching process. In addition, the text data may be directly displayed on the display device 3, or the text data may be displayed on the display device 3 in a manner that the text data corresponds to the text data and is favorable for prompting the designated object through a preset correspondence relationship.
S23: and taking the text data as a current prompt signal.
Specifically, after the voice data is converted into the text data, the text data may be further processed to some extent, for example, irrelevant contents such as punctuation marks and auxiliary words are filtered out from the text data, or only keywords may be retained, and any mode that is favorable for text matching and can be realized by existing voice recognition software or other text processing software may be freely selected.
S03: matching the current word-extracting signal with the word-extracting content in the word-extracting manuscript packet corresponding to the current stepping label, and if the matching is successful, outputting a control signal for controlling the word-extracting content to be displayed. The control signal for controlling the prompt content to be displayed may be: a control signal for controlling the corresponding prompt content of the current prompt signal and the next prompt content adjacent to the current prompt content to be displayed; for example, suppose that a plurality of referral contents stored in the referral manuscript packet corresponding to the current stepping label are respectively: "related art", "some" is to directly use manual turning "and" manual turning "… …; if the current prompt signal is "in the related art", the control signal for controlling the prompt content to be displayed may be: and a control signal for controlling the display of the corresponding prompt content of the current prompt signal (in the related art) and the next prompt content adjacent to the current prompt content (a part of the prompt content is directly turned by a manual operation).
As an implementation manner of outputting the control signal, a similarity calculation method may be adopted, and the current prompt signal is directly matched with the prompt content in the prompt manuscript packet corresponding to the current step label, if the matching is successful, the control signal for controlling the prompt content to be displayed is output, and if the matching is failed, no signal is output.
Specifically, the similarity calculation method may be a fuzzy matching algorithm, and the similarity between the current utterance signal and the utterance content in the utterance manuscript packet corresponding to the current step tag is determined, when the similarity reaches a preset threshold, the matching is successful, and a control signal for displaying the current utterance content and a next utterance content adjacent to the current utterance content is sent to the display device 3, otherwise, the matching is failed, wherein the specific preset similarity threshold may be adjusted according to an actual situation, and in actual use, the specific preset similarity threshold may be related to other influencing factors such as a mandarin standard degree of a specified object, and the like, and the preset threshold needs to be adjusted according to the actual situation, for example, mandarin is relatively standard, the speech recognition accuracy is relatively high, the preset threshold may be correspondingly increased to reduce mismatching, mandarin is not very standard, and the speech recognition accuracy is relatively low, the preset threshold value can be correspondingly reduced so as to improve the matching success rate.
As another embodiment of outputting the control signal, each of the prompt contents in the prompt manuscript packet is provided with a corresponding prompt signal, the current prompt signal is matched with the prompt signal in the prompt manuscript packet corresponding to the current step label, if the matching is successful, a control signal for controlling the prompt contents to be displayed is output, and if the matching is failed, no signal is output.
Specifically, in this embodiment, the text displayed in the display device 3 may be the content of a word presentation corresponding to the current word presentation signal, which may be different from the word presentation signal, that is: the content of the hint may be text information specifying a specific meaning that the object can understand. For example, if the text data corresponding to the current word-lifting signal is "space shuttle", the corresponding word-lifting content may be text information with a specific meaning that can be understood by a specified object such as "flight", and generally, these word-lifting contents are relatively simplified texts, so that the utilization rate of the display device 3 is improved, and more word-lifting contents can be displayed on the display device 3 of the same size.
As an implementation manner for reducing the mismatching, firstly, a plurality of the prompt contents are arranged according to a preset sequence, and each prompt content is provided with a position tag indicating a corresponding sequence, wherein the preset sequence may be arranged according to the broadcast sequence of the actual manuscript, and if the position tag corresponding to the prompt content which is successfully matched currently is not continuous with the position tag corresponding to the prompt content which is successfully matched last time, the control signal is not output.
For example, if three pieces of abstract content are "a", "b" and "c", respectively, and the position tag corresponding to "a" is the first bit, the position tag corresponding to "b" is the second bit, the position tag corresponding to "c" is the third bit, and the abstract content successfully matched last time is "a", if the current abstract content successfully matched is "c", since the position tag corresponding to "c" is the third bit, the position tag corresponding to "a" is the first bit, that is: and the position label corresponding to the current matched prompt content is not continuous with the position label corresponding to the last matched prompt content, and the control signal is not output at the moment.
As another implementation way for reducing the mismatching, firstly, a plurality of the prompt contents are arranged according to a preset sequence, wherein the preset sequence may be arranged according to a broadcast sequence of an actual manuscript, and if an interval between the prompt content which is successfully matched currently and the prompt content which is successfully matched last time exceeds a preset length, the control signal is not output.
For example, if five pieces of word-lines are sequentially "a", "B", "C", "D", and "E", the preset length is 2, the last word-line that successfully matches is "a", and if the current word-line that successfully matches is "E", the interval between "E" and "a" is 3, which exceeds the preset length 2, that is: and the interval between the current successfully matched prompter content and the last successfully matched prompter content exceeds the preset length, and no control signal is output at the moment.
Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium, which can be loaded and executed by a processor to implement the steps in the process of the word-extracting method.
The computer-readable storage medium includes, for example: 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.
It will be clear to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional modules is merely used as an example, and in practical applications, the above function distribution may be performed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to perform all or part of the above described functions. For the specific working processes of the system, the apparatus and the unit described above, reference may be made to the corresponding processes in the foregoing method embodiments, and details are not described here again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments 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 may be integrated into another system, 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 application 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 unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: u disk, removable hard disk, read only memory, random access memory, magnetic or optical disk, etc. for storing program codes.
The foregoing is a preferred embodiment of the present application and is not intended to limit the scope of the application in any way, and any features disclosed in this specification (including the abstract and drawings) may be replaced by alternative features serving equivalent or similar purposes, unless expressly stated otherwise. That is, unless expressly stated otherwise, each feature is only an example of a generic series of equivalent or similar features.
Claims (10)
1. A method for extracting words is characterized in that a manuscript for extracting words is divided into at least two words extracting manuscript packages, each words extracting manuscript package comprises a plurality of words extracting contents, each words extracting manuscript package is provided with a corresponding stepping label, and the method for extracting words comprises the following steps:
acquiring a current stepping label;
acquiring a current word-extracting signal;
and matching the current prompt signal with the prompt content in the prompt manuscript packet corresponding to the current stepping label, and if the matching is successful, outputting a control signal for controlling the prompt content to be displayed.
2. A method of prompting a word as recited in claim 1, wherein: the acquiring of the current prompt signal specifically includes:
acquiring voice data;
converting the voice data into character data;
and taking the text data as the current word-prompting signal.
3. A method of prompting a word as recited in claim 1, wherein: the matching of the current prompt signal and the prompt content in the prompt manuscript packet corresponding to the current stepping label specifically includes: and directly matching the current prompt signal with the prompt content in the prompt manuscript packet corresponding to the current stepping label by adopting a similarity algorithm.
4. A method of prompting a word as recited in claim 1, wherein: the matching of the current prompt signal and the prompt content in the prompt manuscript packet corresponding to the current stepping label specifically includes: and each of the prompt contents is provided with a corresponding prompt signal, and the current prompt signal is matched with the prompt signal in the prompt manuscript packet corresponding to the current stepping label.
5. A method of prompting a word according to claim 3 or 4, characterized in that: the plurality of the prompt contents are arranged according to a preset sequence, each prompt content is provided with a position tag representing the corresponding sequence, and if the position tag corresponding to the prompt content which is successfully matched currently is not continuous with the position tag corresponding to the prompt content which is successfully matched last time, the control signal is not output.
6. A method of prompting a word according to claim 3 or 4, characterized in that: the plurality of prompt contents are arranged according to a preset sequence, and if the interval between the prompt contents which are successfully matched currently and the prompt contents which are successfully matched last time exceeds a preset length, the control signal is not output.
7. A method of prompting a word as recited in claim 1, wherein: and arranging the prompt article packages according to the stepping labels, and if the prompt contents in the prompt article package corresponding to the current stepping label are successfully matched, automatically acquiring the next stepping label.
8. A prompter device, comprising:
the memory is used for storing the prompter program;
a processor, which when running the prompter executes the steps of the prompter method of any one of claims 1-7.
9. A word-prompting terminal, comprising:
a signal acquisition device (1) for acquiring a current prompt signal;
a display device (3) for displaying the content of the word;
the prompter device (2) as claimed in claim 8, having an input connected to the signal acquisition device (1) and an output connected to the display device (3).
10. A computer-readable storage medium, in which a computer program is stored which can be loaded by a processor and which executes the method of proposing a word as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111393118.1A CN114125184A (en) | 2021-11-23 | 2021-11-23 | Word extraction method, device, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111393118.1A CN114125184A (en) | 2021-11-23 | 2021-11-23 | Word extraction method, device, terminal and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114125184A true CN114125184A (en) | 2022-03-01 |
Family
ID=80439901
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111393118.1A Pending CN114125184A (en) | 2021-11-23 | 2021-11-23 | Word extraction method, device, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114125184A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117499560A (en) * | 2023-11-03 | 2024-02-02 | 杭州希德智能科技有限公司 | Automatic prompter method and system for studio |
| CN117499560B (en) * | 2023-11-03 | 2024-05-03 | 杭州希德智能科技有限公司 | Automatic prompter method and system for studio |
-
2021
- 2021-11-23 CN CN202111393118.1A patent/CN114125184A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117499560A (en) * | 2023-11-03 | 2024-02-02 | 杭州希德智能科技有限公司 | Automatic prompter method and system for studio |
| CN117499560B (en) * | 2023-11-03 | 2024-05-03 | 杭州希德智能科技有限公司 | Automatic prompter method and system for studio |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8954329B2 (en) | Methods and apparatus for acoustic disambiguation by insertion of disambiguating textual information | |
| CN110164435A (en) | Audio recognition method, device, equipment and computer readable storage medium | |
| US20200126583A1 (en) | Discovering highlights in transcribed source material for rapid multimedia production | |
| US20200126559A1 (en) | Creating multi-media from transcript-aligned media recordings | |
| US10978077B1 (en) | Knowledge point mark generation system and method thereof | |
| JPS61107430A (en) | Editing unit for voice information | |
| CN109033060B (en) | Information alignment method, device, equipment and readable storage medium | |
| CN110781328A (en) | Video generation method, system, device and storage medium based on voice recognition | |
| CN110740275B (en) | Nonlinear editing system | |
| CN112399269B (en) | Video segmentation method, device, equipment and storage medium | |
| EP4322029A1 (en) | Method and apparatus for generating video corpus, and related device | |
| CN112114771A (en) | Presentation file playing control method and device | |
| CN110781649A (en) | Subtitle editing method and device, computer storage medium and electronic equipment | |
| CN111610901B (en) | AI vision-based English lesson auxiliary teaching method and system | |
| WO2022206198A1 (en) | Audio and text synchronization method and apparatus, device and medium | |
| CN114125184A (en) | Word extraction method, device, terminal and storage medium | |
| CN110428668B (en) | Data extraction method and device, computer system and readable storage medium | |
| CN113923479A (en) | Audio and video editing method and device | |
| KR20220135901A (en) | Devices, methods and programs for providing customized educational content | |
| CN110782899A (en) | Information processing apparatus, storage medium, and information processing method | |
| KR102541162B1 (en) | Electronic apparatus and methoth for caption synchronization of contents | |
| KR102656262B1 (en) | Method and apparatus for providing associative chinese learning contents using images | |
| CN111506744B (en) | Click-to-read method and terminal equipment | |
| CN106168945B (en) | Audio output device and audio output method | |
| CN115688704A (en) | Text time axis information generation method and device, storage medium and computer 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 |