CN112632973A - Text processing method, device, equipment and storage medium - Google Patents
Text processing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112632973A CN112632973A CN202011640222.1A CN202011640222A CN112632973A CN 112632973 A CN112632973 A CN 112632973A CN 202011640222 A CN202011640222 A CN 202011640222A CN 112632973 A CN112632973 A CN 112632973A
- Authority
- CN
- China
- Prior art keywords
- sentence
- text
- target text
- keyword
- generating
- 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
- 238000003672 processing method Methods 0.000 title abstract description 5
- 238000012545 processing Methods 0.000 claims abstract description 99
- 238000000034 method Methods 0.000 claims abstract description 45
- 239000012634 fragment Substances 0.000 claims description 20
- 238000011156 evaluation Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 9
- 230000003993 interaction Effects 0.000 description 11
- 230000008569 process Effects 0.000 description 8
- 230000008676 import Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 235000012054 meals Nutrition 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012790 confirmation Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/253—Grammatical analysis; Style critique
-
- 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
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a text processing method, a text processing device, text processing equipment and a storage medium. The method comprises the following steps: receiving an original text; the original text comprises at least one sentence; determining a location of a keyword in the at least one sentence; the keywords include: main words, predicate words and object words; generating a target text according to the position; and presenting the target text. The method can provide more effective information for the reader so as to help the reader to quickly understand complex and lengthy sentences.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a storage medium for text processing.
Background
Text refers to the manifestation of written language. From a grammatical point of view, text is typically a sentence or a combination of sentences having a complete, systematic meaning (Message). A text may be a Sentence (sequence), a Paragraph (paramgraph), or a chapter (Discourse).
When a text includes a combination of a plurality of complex and lengthy sentences, it is difficult for a reader to directly and correctly understand what the text describes. In some scenarios, the text may be text of a project file that includes a sentence that describes the desired content of the project file. Since the content of the requirement is often more and complicated, and the sentence describing the content of the requirement is complicated and lengthy, it takes a long time for the reader to understand the content of the requirement.
Based on this, there is a need for a method that can help readers understand complicated and lengthy sentences.
Disclosure of Invention
In order to solve the technical problem, the application provides a method, a device, equipment and a storage medium for text processing. The method can provide more effective information for the reader so as to help the reader to quickly understand complex and lengthy sentences.
The application discloses following technical scheme:
in a first aspect, the present application provides a method for text processing, including:
receiving an original text; the original text comprises at least one sentence;
determining a location of a keyword in the at least one sentence; the keywords include: main words, predicate words and object words;
generating a target text according to the position;
and presenting the target text.
Optionally, the generating a target text according to the position includes:
splitting the at least one sentence into a plurality of sentence fragments according to the position;
combining the sentence fragments into a target text according to the sequence of the keywords;
and the key words are sequentially ordered into the main word, the predicate word and the guest word.
Optionally, the generating a target text according to the position includes:
acquiring a keyword corresponding to the position in the at least one statement according to the position;
combining the keywords into a target text according to the sequence of the keywords;
and the key words are sequentially ordered into the main word, the predicate word and the guest word.
Optionally, the generating a target text according to the position includes:
generating a keyword identifier at a keyword corresponding to the position in the at least one sentence according to the position;
and taking at least one sentence carrying the keyword identification as a target text.
Optionally, the generating a target text according to the position includes:
generating sentence break information at the position in the at least one sentence according to the position;
and taking at least one sentence carrying the sentence break information as a target text.
Optionally, the method further includes:
receiving updating information input by a user; the updated information is used to adjust the target text.
Optionally, the method further includes:
receiving evaluation information of a user on the target text;
and adjusting the strategy for determining the target text based on the evaluation information.
In a second aspect, the present application provides an apparatus for text processing, comprising: the device comprises a receiving module, a processing module and a display module;
the receiving module is used for receiving an original text; the original text comprises at least one sentence;
the processing module is used for determining the position of the keyword in the at least one sentence; the keywords include: main words, predicate words and object words; generating a target text according to the position;
the display module is used for presenting the target text.
Optionally, the processing module is specifically configured to split the at least one sentence into a plurality of sentence fragments according to the position; combining the sentence fragments into a target text according to the sequence of the keywords;
and the key words are sequentially ordered into the main word, the predicate word and the guest word.
Optionally, the processing module is specifically configured to obtain, according to the position, a keyword corresponding to the position in the at least one statement; combining the keywords into a target text according to the sequence of the keywords;
and the key words are sequentially ordered into the main word, the predicate word and the guest word.
Optionally, the processing module is specifically configured to generate a keyword identifier at a keyword corresponding to the position in the at least one statement according to the position; and taking at least one sentence carrying the keyword identification as a target text.
Optionally, the processing module is specifically configured to generate sentence break information at the position in the at least one sentence according to the position; and taking at least one sentence carrying the sentence break information as a target text.
Optionally, the receiving module is further configured to receive update information input by a user;
the processing module is specifically configured to use the update information to adjust the target text
Optionally, the receiving module is further configured to receive evaluation information of the target text from the user;
the processing module is specifically configured to adjust a policy for determining the target text based on the evaluation information.
In a third aspect, the present application provides a data processing apparatus, including:
a memory for storing a computer program and transmitting the computer program to the processor;
a processor for performing the method of any of the above first aspects in accordance with instructions in the computer program.
In a fourth aspect, the present application provides a computer readable storage medium for storing computer software instructions which, when run on a computer, cause the computer to perform the method of any of the first aspect above.
According to the technical scheme, the method has the following beneficial effects:
the application provides a text processing method, a text processing device, text processing equipment and a storage medium. On one hand, the method processes at least one sentence in the original text, and the pertinence is improved. On the other hand, the method determines the position of a keyword in at least one sentence, and then generates a target text according to the position, wherein the keyword comprises a main word, a predicate word and a guest word. Thus, the target text generated by the location is more useful for the reader to understand than the original text.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a block diagram of a document processing system according to an embodiment of the present disclosure;
fig. 2 is a schematic interface diagram of an interaction subsystem according to an embodiment of the present application;
FIG. 3 is a schematic interface diagram of another interaction subsystem provided in an embodiment of the present application;
fig. 4 is a flowchart of a text processing method provided in this embodiment.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
For the sake of understanding, the technical terms related to the present application will be described below.
Text is one manifestation of written language. The text is usually composed of one sentence or a combination of a plurality of sentences. A text can be a sentence, a paragraph, or a chapter.
When a text includes a combination of a plurality of complicated and lengthy sentences, it is difficult for a reader to directly and correctly understand what the text describes. In some scenarios, the text may be text of a project file that includes a statement describing the required content of the project file. Since the content of the requirement is often more and complicated, and the sentence describing the content of the requirement is complicated and lengthy, it takes a long time for the reader to understand the content of the requirement.
In view of this, embodiments of the present application provide a method for text processing, which may be implemented by a text processing system. Specifically, the text processing system receives an original text, the original text comprises at least one sentence, then determines the position of a keyword in the at least one sentence, the keyword comprises a main word, a predicate word and an object word, generates a target text according to the position, and finally presents the target text.
On one hand, the method processes at least one sentence in the original text, and the pertinence is improved. On the other hand, the method determines the position of a keyword in at least one sentence, and then generates a target text according to the position, wherein the keyword comprises a main word, a predicate word and a guest word. Thus, the target text generated by the location is more useful for the reader to understand than the original text.
The text processing system provided by the embodiment can be applied to the technical field of natural language processing, for example, when an enterprise expands a certain project, a project book is formulated. If the requirement in the project is more and the sentence in the project book is complicated and long, the reader can convert the original text of the project book into the target text by using the text processing system, and the target text provides more effective information, so that the reader can be helped to quickly understand the complicated and long sentence.
The text processing system may be deployed in a cloud environment, and may be specifically one or more computing devices on the cloud environment. The text processing system may also be deployed in an edge environment, and may specifically be one or more computing devices on the edge environment. The text processing system can also be deployed in end equipment, and the end equipment can be a computer, a tablet computer, a smart phone and the like. The present embodiment does not limit the deployment manner of the text processing system.
The subsystems and units in the text processing system may be divided in various ways, and this embodiment is not particularly limited. FIG. 1 illustrates an exemplary partitioning, and as shown in FIG. 1, text processing system 100 includes interaction subsystem 120 and processing subsystem 140. The functions of each subsystem and its included functional units are briefly described below, respectively.
The interaction subsystem 120 includes a communication unit 122 and a display unit 124. The display unit 124 is used to provide a Graphical User Interface (GUI). The communication unit 122 is configured to receive an original text through the GUI, the original text including at least one sentence. The display unit 124 is also used to present the target text to the user through the GUI.
Referring to fig. 2, the interface diagram of a main interface of an interaction subsystem according to an embodiment of the present application is shown. The main interface 200 carries an import control 202, a confirmation control 204, and a text preview area 206.
The user may import the original text through import control 202, which in some implementations may be imported from a server (e.g., a website, cloud disk, etc.) or locally. In other implementations, the user may also interface the text processing system 100 with other business systems, and then the user imports the original text transmitted by the other business systems through the import control 202.
When the user completes importing the original text, text preview area 206 previews the contents of the original text. As shown in the original text preview region 2061, the user can determine whether the original text is the text that the user wants to transmit to the text processing system 100 by previewing the content of the original text, and if not, the user can re-import through the import control 202.
The user may send processing information to the processing subsystem 140 via the confirmation control 204, the processing information instructing the processing subsystem 140 to process the original text to generate the target text, and the processing subsystem 140 transmits the generated target text to the interaction subsystem 120.
After the interaction subsystem 120 receives the target text, the display unit 124 presents the target text through the GUI, as shown in the target text preview region 2062 in fig. 2, where the target text carries more effective information, so that the user can understand the content of the target text faster.
In some implementations, the text processing system 100 also supports user adjustment of the generated target text or receives user evaluation information of the target text and then automatically adjusts when the target text presented in the target text preview region 2062 is inaccurate or mistiming.
Referring to the interface schematic diagram of the interactive subsystem main interface shown in fig. 3, the main interface 300 further carries an update control 302 and a rating point 304 on the basis of the main interface 200.
The user can modify the generated target text in the target text preview region 2062, and then validate the modified target text through the update control 302, that is, replace the modified target text with the original target text.
The user may also input evaluation information for the target text in the evaluation region 304 in the target text preview region 2062, where the evaluation information may be an evaluation of a certain sentence in the target text, for example, the evaluation information may be "the recognition of the second sentence is inaccurate" or the like. The interaction subsystem 120 transmits the evaluation information to the processing subsystem 140, and the processing subsystem 140 adjusts a policy for generating the target text according to the evaluation information. For example, the second sentence in the target text corresponds to the second sentence in the original text, and then the processing subsystem 140 invokes a policy to regenerate the target text corresponding to the second sentence in the original text.
Processing subsystem 140 includes a communication unit 142 and a processing unit 144. The communication unit 142 is used for receiving the original text sent by the interaction subsystem 120 and sending the target text to the interaction subsystem 120. The processing unit 144 is configured to determine a keyword in a sentence in the original text, where the keyword may be a main word, a predicate word, and an object word, determine a position of the keyword, and generate a target text according to the position.
In this embodiment, the processing subsystem 140 deploys a keyword recognition model in advance, and the keyword in the sentence in the original text and the position of the keyword in the sentence can be recognized through the keyword recognition model. Wherein, the keyword includes: a main word, a predicate word, and a guest word. The keyword recognition model is obtained by historical data training in advance.
The way in which the processing unit 144 generates the target text according to the position of the keyword is divided into the following four cases, which are described below separately.
The first condition is as follows:
the processing unit 144 splits the sentence into a plurality of sentence fragments according to the position of the keyword, and then combines the plurality of sentence fragments into the target text according to the sequence of the keyword, wherein the sequence of the keyword is [ main word, predicate word, object word ].
For ease of understanding, the original text is taken as an example to include an original sentence that is "has eaten in the morning, Xiaoming". Processing unit 144 splits the original sentence into three sentence fragments: the subject sentence fragment "Mingming", the predicate sentence fragment "has eaten in the morning", and the object sentence fragment "has eaten". The processing unit 144 then recombines the three sentence fragments according to the above-mentioned keyword ranking, and obtains "Xiaoming has eaten in the morning".
In case one, the processing unit 144 can process the inverted sentence to convert the inverted sentence into a normal-language-order sentence.
Case two:
the processing unit 144 obtains a keyword corresponding to the position in at least one sentence according to the position of the keyword, and then combines the keyword into a target text according to the sequence of the keyword, wherein the sequence of the keyword is [ main word, predicate word, object word ]. The keyword may be a word corresponding to the keyword, and the processing unit 144 obtains a plurality of keywords corresponding to the position as an example of continuation: the subject keyword "xiaoming", the predicate keyword "eat", and the object keyword "meal". Then, the processing unit 144 recombines the plurality of keywords according to the ranking of the keywords, thereby obtaining "diet".
In case two, the processing unit 144 can process the complex sentence, and simplify the complex sentence, so as to facilitate reading and understanding by the reader.
Case three:
the processing unit 144 generates a keyword identifier at a keyword corresponding to the position in the at least one sentence according to the position; and taking at least one sentence carrying the keyword identification as a target text. The keyword identifier may be used to add a background color to the keyword, change the font of the keyword, change the size of the keyword, and the like.
In case three, after the processing unit 144 generates the keyword identifier, the keyword identifier can facilitate the reader to read the sentence, so as to facilitate the reader to read and understand.
Case four:
the processing unit 144 generates sentence break information at the position in the at least one sentence according to the position; and taking at least one sentence carrying the sentence break information as a target text. The sentence break information may be a space added after the position of the keyword or other coincidences.
For ease of understanding, the original text is exemplified as including an original sentence "a Xiaoming classmate 25 years old is an on-duty employee of an enterprise". The processing unit 144 adds a symbol "/" after "Xiaoming", a symbol "/" after "Yes", and a symbol "/" after "employee", thereby obtaining "Mingming/classmate 25/employee of an enterprise/". Thus, the processing unit 144 provides sentence break information for the complex and lengthy sentences, and the generated target text carries more effective information, so as to help the reader to understand the complex and lengthy sentences faster.
After the processing unit 144 generates the target text, the communication unit 142 is configured to transmit the target text to the interaction subsystem 120.
The method of text processing provided herein is next presented in the context of a text processing system 100. Referring to fig. 4, this figure is a flowchart of a method for text processing according to this embodiment. The method comprises the following steps:
s401: the text processing system 100 receives the original text; the original text includes at least one sentence.
The text processing system 100 may receive the raw text through a graphical user interface (e.g., a GUI). Specifically, the file processing system 100 may receive the original text imported by the cloud or the local, or imported by other business systems into the original text.
S402: the text processing system 100 determines a location of the keyword in the at least one sentence; the keywords include: main words, predicate words and object words; and generating a target text according to the position.
In this embodiment, a keyword recognition model is deployed in the text processing system 100 in advance, and through the keyword recognition model, a keyword in a sentence in an original text and a position of the keyword in the sentence can be recognized. Wherein, the keyword includes: a main word, a predicate word, and a guest word. The keyword recognition model is obtained by historical data training in advance.
The ways in which the text processing system 100 generates the target text according to the position of the keyword are divided into the following four cases, which are described below.
The first condition is as follows:
the text processing system 100 splits a sentence into a plurality of sentence fragments according to the positions of keywords, and then combines the plurality of sentence fragments into a target text according to the sequence of the keywords, wherein the sequence of the keywords is [ main words, predicate words, object words ].
For ease of understanding, the original text is taken as an example to include an original sentence that is "has eaten in the morning, Xiaoming". The text processing system 100 splits the original sentence into three sentence fragments: the subject sentence fragment "Mingming", the predicate sentence fragment "has eaten in the morning", and the object sentence fragment "has eaten". The text processing system 100 then recombines the three sentence fragments according to the above-described ordering of the keywords, thereby obtaining "Xiaoming had eaten in the morning".
In case one, the text processing system 100 can process the inverted sentence to convert the inverted sentence into a normal-language-order sentence.
Case two:
the text processing system 100 obtains keywords corresponding to the position in at least one sentence according to the position of the keywords, and then combines the keywords into a target text according to the sequence of the keywords, wherein the sequence of the keywords is [ main words, predicate words, object words ]. The keyword may be a word corresponding to the keyword, and continuing the case one, the text processing system 100 obtains a plurality of keywords corresponding to the position: the subject keyword "xiaoming", the predicate keyword "eat", and the object keyword "meal". Then, the text processing system 100 recombines the plurality of keywords according to the ranking of the keywords, thereby obtaining "Xiaoming meal".
In the second case, the text processing system 100 can process the complex sentences, and simplify the complex sentences, so as to facilitate reading and understanding by the reader.
Case three:
the text processing system 100 generates a keyword identifier at a keyword corresponding to the position in the at least one sentence according to the position; and taking at least one sentence carrying the keyword identification as a target text. The keyword identifier may be used to add a background color to the keyword, change the font of the keyword, change the size of the keyword, and the like.
In the third case, after the text processing system 100 generates the keyword identifier, the keyword identifier can facilitate the reader to read the sentence, so as to facilitate the reader to read and understand.
Case four:
the text processing system 100 generates sentence break information at the position in the at least one sentence according to the position; and taking at least one sentence carrying the sentence break information as a target text. The sentence break information may be a space added after the position of the keyword or other coincidences.
For ease of understanding, the original text is exemplified as including an original sentence "a Xiaoming classmate 25 years old is an on-duty employee of an enterprise". The text processing system 100 adds a symbol "/" after "Xiaoming", a symbol "/" after "Yes", and a symbol "/" after "employee", and then obtains "Mingming/classmate 25/employee of an enterprise/". In this way, the text processing system 100 provides sentence break information for complex and lengthy sentences, and the generated target text carries more effective information to help the reader to understand the complex and lengthy sentences faster.
In each of the above cases one through four, the corresponding processing model may be deployed in the text processing system 100. Taking the above case two as an example, the text processing system 100 is deployed with a splitting and recombining model and a knowledge base. The text processing system 100 splits and then recombines the original sentence according to the split and recombination model, wherein rules of splitting and recombining are provided by a knowledge base.
In some implementations, the text processing system 100 receives user-entered update information; the updated information is used to adjust the target text.
S403: text processing system 100 renders the target text.
The text processing system 100 may present the target text through a graphical user interface (e.g., a GUI). In some implementations, the text processing system 100 can also export the target text.
In this embodiment, on the one hand, the method processes at least one sentence in the original text, thereby improving the pertinence. On the other hand, the method determines the position of a keyword in at least one sentence, and then generates a target text according to the position, wherein the keyword comprises a main word, a predicate word and a guest word. Thus, the target text generated by the location is more useful for the reader to understand than the original text.
The present application further provides a text processing apparatus, including: the device comprises a receiving module, a processing module and a display module;
the receiving module is used for receiving an original text; the original text comprises at least one sentence;
the processing module is used for determining the position of the keyword in the at least one sentence; the keywords include: main words, predicate words and object words; generating a target text according to the position;
the display module is used for presenting the target text.
The present application further provides a data processing apparatus, including:
a memory for storing a computer program and transmitting the computer program to the processor;
a processor for performing the method introduced in the above embodiments according to instructions in the computer program.
The present application also provides a computer-readable storage medium for storing computer software instructions which, when run on a computer, cause the computer to perform the method introduced in the above embodiments.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the apparatus embodiment, since it is substantially similar to the method embodiment, it is relatively simple to describe, and reference may be made to some descriptions of the method embodiment for relevant points. The above-described apparatus embodiments are merely illustrative, and the units and modules described as separate components may or may not be physically separate. In addition, some or all of the units and modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
The foregoing is merely a preferred embodiment of the present application and is not intended to limit the present application in any way. Although the present application has been described with reference to the preferred embodiments, it is not intended to limit the present application. Those skilled in the art can now make numerous possible variations and modifications to the disclosed embodiments, or modify equivalent embodiments, using the methods and techniques disclosed above, without departing from the scope of the claimed embodiments. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present application still fall within the protection scope of the technical solution of the present application without departing from the content of the technical solution of the present application.
Claims (10)
1. A method of text processing, comprising:
receiving an original text; the original text comprises at least one sentence;
determining a location of a keyword in the at least one sentence; the keywords include: main words, predicate words and object words;
generating a target text according to the position;
and presenting the target text.
2. The method of claim 1, wherein generating the target text according to the location comprises:
splitting the at least one sentence into a plurality of sentence fragments according to the position;
combining the sentence fragments into a target text according to the sequence of the keywords;
and the key words are sequentially ordered into the main word, the predicate word and the guest word.
3. The method of claim 1, wherein generating the target text according to the location comprises:
acquiring a keyword corresponding to the position in the at least one statement according to the position;
combining the keywords into a target text according to the sequence of the keywords;
and the key words are sequentially ordered into the main word, the predicate word and the guest word.
4. The method of claim 1, wherein generating the target text according to the location comprises:
generating a keyword identifier at a keyword corresponding to the position in the at least one sentence according to the position;
and taking at least one sentence carrying the keyword identification as a target text.
5. The method of claim 1, wherein generating the target text according to the location comprises:
generating sentence break information at the position in the at least one sentence according to the position;
and taking at least one sentence carrying the sentence break information as a target text.
6. The method according to any one of claims 1 to 5, further comprising:
receiving updating information input by a user; the updated information is used to adjust the target text.
7. The method of claim 1, further comprising:
receiving evaluation information of a user on the target text;
and adjusting the strategy for generating the target text based on the evaluation information.
8. An apparatus for text processing, comprising: the device comprises a receiving module, a processing module and a display module;
the receiving module is used for receiving an original text; the original text comprises at least one sentence;
the processing module is used for determining the position of the keyword in the at least one sentence; the keywords include: main words, predicate words and object words; generating a target text according to the position;
the display module is used for presenting the target text.
9. An apparatus for data processing, comprising:
a memory for storing a computer program and transmitting the computer program to the processor;
a processor for performing the method of any of the preceding claims 1 to 7 according to instructions in the computer program.
10. A computer readable storage medium for storing computer software instructions which, when run on a computer, cause the computer to perform the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011640222.1A CN112632973A (en) | 2020-12-31 | 2020-12-31 | Text processing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011640222.1A CN112632973A (en) | 2020-12-31 | 2020-12-31 | Text processing method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112632973A true CN112632973A (en) | 2021-04-09 |
Family
ID=75290432
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011640222.1A Pending CN112632973A (en) | 2020-12-31 | 2020-12-31 | Text processing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112632973A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113377965A (en) * | 2021-06-30 | 2021-09-10 | 中国农业银行股份有限公司 | Method and related device for perceiving text keywords |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108984600A (en) * | 2018-06-04 | 2018-12-11 | 百度在线网络技术（北京）有限公司 | Interaction processing method, device, computer equipment and readable medium |
| CN110473523A (en) * | 2019-08-30 | 2019-11-19 | 北京大米科技有限公司 | A kind of audio recognition method, device, storage medium and terminal |
| CN110704608A (en) * | 2019-08-29 | 2020-01-17 | 中国平安人寿保险股份有限公司 | Text theme generation method and device and computer equipment |
| CN110795553A (en) * | 2019-09-09 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Abstract generation method and device |
| CN110874531A (en) * | 2020-01-20 | 2020-03-10 | 湖南蚁坊软件股份有限公司 | Topic analysis method and device and storage medium |
| CN111309916A (en) * | 2020-03-05 | 2020-06-19 | 北京奇艺世纪科技有限公司 | Abstract extraction method and device, storage medium and electronic device |
| CN111950256A (en) * | 2020-06-23 | 2020-11-17 | 北京百度网讯科技有限公司 | Sentence break processing method and device, electronic equipment and computer storage medium |
-
2020
- 2020-12-31 CN CN202011640222.1A patent/CN112632973A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108984600A (en) * | 2018-06-04 | 2018-12-11 | 百度在线网络技术（北京）有限公司 | Interaction processing method, device, computer equipment and readable medium |
| CN110704608A (en) * | 2019-08-29 | 2020-01-17 | 中国平安人寿保险股份有限公司 | Text theme generation method and device and computer equipment |
| CN110473523A (en) * | 2019-08-30 | 2019-11-19 | 北京大米科技有限公司 | A kind of audio recognition method, device, storage medium and terminal |
| CN110795553A (en) * | 2019-09-09 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Abstract generation method and device |
| CN110874531A (en) * | 2020-01-20 | 2020-03-10 | 湖南蚁坊软件股份有限公司 | Topic analysis method and device and storage medium |
| CN111309916A (en) * | 2020-03-05 | 2020-06-19 | 北京奇艺世纪科技有限公司 | Abstract extraction method and device, storage medium and electronic device |
| CN111950256A (en) * | 2020-06-23 | 2020-11-17 | 北京百度网讯科技有限公司 | Sentence break processing method and device, electronic equipment and computer storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113377965A (en) * | 2021-06-30 | 2021-09-10 | 中国农业银行股份有限公司 | Method and related device for perceiving text keywords |
| CN113377965B (en) * | 2021-06-30 | 2024-02-23 | 中国农业银行股份有限公司 | Method and related device for sensing text keywords |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9411790B2 (en) | Systems, methods, and media for generating structured documents | |
| CN106471487B (en) | System and method for editing files in non-native applications using an application engine | |
| US20150199307A1 (en) | Pluggable Architecture For Optimizing Versioned Rendering of Collaborative Documents | |
| US9519699B1 (en) | Consistency of query results in a distributed system | |
| CN109635094B (en) | Method and device for generating answer | |
| EP4105848A1 (en) | Method and apparatus for evaluating joint training model | |
| JP4502615B2 (en) | Similar sentence search device, similar sentence search method, and program | |
| US10937033B1 (en) | Pre-moderation service that automatically detects non-compliant content on a website store page | |
| US20170235582A1 (en) | Systems and methods method for providing an interactive help file for host software user interfaces | |
| US20220121668A1 (en) | Method for recommending document, electronic device and storage medium | |
| US20190288962A1 (en) | Message providing device, non-transitory computer readable medium storing program, and display control method | |
| US10691877B1 (en) | Homogenous insertion of interactions into documents | |
| US20140331127A1 (en) | Template based copy and paste function | |
| CN105872635A (en) | Video resource distribution method and device | |
| US20210397646A1 (en) | Method, electronic device, and storage medium for processing visual data of deep model | |
| CN112632973A (en) | Text processing method, device, equipment and storage medium | |
| JP2022187507A (en) | Technical research support device, technical research support method and technical research support program | |
| KR102570471B1 (en) | Sentence making service method and sentence making service method based on user using text mining | |
| JP6618103B1 (en) | Sentence generating apparatus, sentence generating method, and sentence generating program | |
| JP2012113486A (en) | Intention extraction device, method and program | |
| CN115062589B (en) | Encyclopedia entry processing method, encyclopedia entry processing device, electronic equipment, medium and program product | |
| US20150169523A1 (en) | Smart Scoring And Filtering of User-Annotated Geocoded Datasets | |
| US12039460B2 (en) | Information providing system and data structure | |
| CN109522211B (en) | Interface parameter transmission method and device, electronic equipment and storage medium | |
| CN112597760A (en) | Method and device for extracting domain words in document |
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 |