JP2022055353A - Text processing method, device, apparatus, and computer-readable storage medium - Google Patents

Abstract

To provide a text processing method, a device, an apparatus, and a storage medium that can reduce low processing complexity and do not require consideration of grammar issues when all keywords are covered.SOLUTION: A text processing method includes the steps of: receiving an original text, one or more keywords contained in the original text, and a first processing result obtained by simplifying the original text; determining whether the first processing result includes all keywords; and when the first processing result does not include all keywords, deleting one or more sentences in the original text, continuing deletion processing until a combination of the first processing result and sentences in the original text after deletion processing includes all the keywords and the number of sentences in the original text after processing is minimum, and setting the combination as a final processing result.SELECTED DRAWING: Figure 1

Description

The present application relates to the field of text processing, specifically to text processing methods, devices, equipment and computer-readable storage media.

Text summarization generation is the generation of a text summarization by highly generalizing and abstracting some textual content that has a clear meaning. If the user wants the summary to contain all the desired keywords, but the generated summary does not contain all the desired keywords, then generally for each of the keywords, the keywords are iterated from the original text. A sentence containing the selected keyword is selected, and the sentence containing the selected keyword is combined with the generated summary to form a new summary. However, this method becomes more complex as the number of desired keywords increases.

In view of the above problems, the present disclosure provides text processing methods, devices, devices and computer readable storage media.

According to one aspect of the present disclosure, a text processing method is provided, wherein the text processing method is obtained by simplifying the original text, one or more keywords contained in the original text, and the original text. A step of receiving the obtained first processing result, a step of determining whether or not the first processing result includes all keywords, and a case where the first processing result does not include all keywords. , One or more sentences in the original text are deleted, the combination of the first processing result and the sentence in the original text after the deletion process includes all keywords, and the said after the deletion process. The deletion process is continued until the number of sentences in the original text is minimized, and the combination is used as the final process result.

According to one example of the present disclosure, when the first processing result does not include all the keywords, one or more sentences in the original text are deleted, and the first processing result and the deletion are deleted. The step of continuing the deletion process until the combination with the sentence in the original text after processing includes all the keywords and the number of sentences in the original text after the deletion process is the minimum is the first step. If the processing result of the above does not include all the keywords, the sentences in the original text are deleted based on the degree of association between each sentence of the original text and all the keywords, and the first processing result and the above first processing result are obtained. The deletion process is continued until the combination with the sentence in the original text after the deletion process includes all the keywords and the number of sentences in the original text after the deletion process is minimized.

According to one example of the present disclosure, the step of deleting a sentence in the original text based on the degree of association between each sentence of the original text and all the keywords is a step of deleting each sentence of the original text and all of the above. Includes a step of sorting each sentence of the original text in ascending order of relevance based on the degree of relevance to the keyword, and a step of deleting each sentence in the original text based on the sort.

According to one example of the present disclosure, the step of deleting each sentence in the original text in ascending order of relevance is the first sentence after the first sentence of each sentence in the original text is deleted. The step of determining whether or not the combination of the processing result of the above and the sentence in the original text after the deletion processing includes all the keywords, and the first processing result and the sentence in the original text after the deletion processing. When the combination of contains all keywords, the step of determining the deletion operation and continuing the processing of the next sentence of the original text, and the combination of the first processing result and the sentence in the original text after the deletion processing. Includes a step of canceling the delete operation, leaving the first sentence, and continuing processing of the next sentence of the original text, if does not contain all the keywords.

According to one example of the present disclosure, after one sentence in the original text has been deleted, the combination of the first processing result and the sentence in the original text after the deletion processing is all. Before determining whether or not to include a keyword, it further includes a step of deleting a sentence in the original text that does not contain any of the keywords in ascending order of relevance.

According to one example of the present disclosure, the degree of association between each sentence of the original text and all the keywords is determined based on the number of the one or more keywords included in each sentence of the original text. It is a thing.

According to another aspect of the present disclosure, a text processing device is provided, wherein the text processing device is obtained by simplifying the original text, one or more keywords contained in the original text, and the original text. A receiving unit for receiving the first processing result, a determination unit for determining whether or not the first processing result includes all keywords, and the first processing result are all keywords. If one or more sentences in the original text are deleted, the combination of the first processing result and the sentence in the original text after the deletion processing includes all the keywords, and , The deletion unit for continuing the deletion process until the number of sentences in the original text after the deletion process is minimized, and making the combination the final processing result.

According to one example of the present disclosure, the deletion unit is based on the degree of association between each sentence of the original text and all the keywords, if the first processing result does not include all the keywords. , The sentence in the original text is deleted, the combination of the first processing result and the sentence in the original text after the deletion process includes all keywords, and the number of sentences in the original text after the deletion process. The deletion process is continued until is the minimum.

According to one example of the present disclosure, the deletion unit sorts each sentence of the original text in ascending order of relevance based on the degree of association between each sentence of the original text and all the keywords. Based on the sort, each sentence in the original text is deleted.

According to one example of the present disclosure, the deletion unit has the first processing result and the sentence in the original text after the deletion processing after the first sentence of each sentence in the original text is deleted. It is determined whether or not the combination with and contains all the keywords, and if the combination of the first processing result and the sentence in the original text after the deletion processing includes all the keywords, the deletion operation is determined. If the processing of the next sentence of the original text is continued, and the combination of the first processing result and the sentence in the original text after the deletion processing does not include all the keywords, the deletion operation is canceled and the deletion operation is canceled. Leave the sentence 1 and continue processing the next sentence of the original text.

According to one example of the present disclosure, the deletion unit is after one sentence in the original text has been deleted, with the first processing result and the sentence in the original text after the deletion processing. It is further used to delete sentences in the original text that do not contain any of the keywords in ascending order of relevance before determining whether or not the combination of the above includes all the keywords.

According to another aspect of the present disclosure, a text processing device comprising a processor and a storage device for storing computer-readable instructions is such that the computer-readable instructions are stored by the processor. When executed, a step of receiving the original text, one or more keywords contained in the original text, and the first processing result obtained by simplifying the original text, and the first processing. The step of determining whether the result contains all the keywords, and if the first processing result does not include all the keywords, one or more sentences in the original text are deleted and the first processing result is deleted. The deletion process is continued until the combination of the processing result of 1 and the sentence in the original text after the deletion process includes all the keywords and the number of sentences in the original text after the deletion process is the minimum. , A step of making the combination a final processing result, and a text processing method.

According to another aspect of the present disclosure, a computer-readable storage medium for storing a computer-readable program is provided, wherein the program performs the text processing method according to any one of the above embodiments on the computer. Let me.

In the above aspect of the present disclosure, referring to the first processing result, one or more sentences in the original text are deleted based on the degree of relevance between each sentence of the original text and all the keywords, and the first processing is performed. The deletion process is continued until the combination of the result and the sentence in the original text after the deletion process includes all the keywords and the number of sentences in the original text after the deletion process is the minimum. By making it the final processing result, it is not necessary to consider the grammatical problem while reducing the processing complexity.

By describing the embodiments of the present disclosure in more detail with reference to the accompanying drawings, the above and other purposes, features, and advantages of the present disclosure will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present disclosure, which form part of the specification and are used in conjunction with the embodiments of the present disclosure to illustrate the present disclosure and limit the disclosure. It's not something to do. In the drawings, the same reference numerals usually represent the same member or step.

It is a flowchart of the text processing method which concerns on embodiment of this disclosure. It is a flowchart of the method of deleting the sentence in the original text which concerns on embodiment of this disclosure. It is another flowchart of the method of deleting the sentence in the original text which concerns on embodiment of this disclosure. It is a block diagram of the text processing method which concerns on embodiment of this disclosure. It is a schematic diagram of the example of the text processing method which concerns on embodiment of this disclosure. It is a functional block diagram of the text processing apparatus which concerns on embodiment of this disclosure. It is a functional block diagram of the text processing apparatus which concerns on embodiment of this disclosure. It is a schematic diagram of the computer-readable storage medium which concerns on embodiment of this disclosure. It is a figure which shows an example of the hardware structure of the electronic device which concerns on embodiment of this disclosure.

Hereinafter, the technical solutions of the embodiments of the present disclosure will be clearly and completely described with reference to the drawings of the embodiments of the present disclosure. Of course, the examples described are only partial examples of the present disclosure, not all examples. All other embodiments that a person skilled in the art obtains without creative labor under the embodiments of the present disclosure are all within the scope of the present disclosure.

In this application, flowcharts are used to describe the steps of the method according to the embodiments of the present application. It should be understood that the previous or next step is not always performed exactly in sequence. Alternatively, the various steps can be processed in reverse order or simultaneously. At the same time, other operations may be added to these processes. Alternatively, one step or a plurality of steps may be reduced from these processes.

First, with reference to FIG. 1, a text processing method 100 for realizing the embodiment of the present disclosure will be described. The present disclosure refers to the first processing result (eg, text summary) and deletes one or more sentences in the original text based on the relevance of each sentence in the original text to all keywords. The deletion process is continued until the combination of the first processing result and the sentence in the original text after the deletion process includes all the keywords and the number of sentences in the original text after the deletion process is the minimum. By using the above combination as the final processing result, it is not necessary to consider the grammatical problem while reducing the processing complexity.

Hereinafter, examples of the present disclosure and examples thereof will be described in detail with reference to the drawings.

At least one embodiment of the present disclosure provides text processing methods, devices, equipment and computer readable storage media. Hereinafter, the text processing according to at least one embodiment of the present disclosure will be described in a non-limiting manner in a plurality of examples and examples, and as described below, specific examples thereof when they do not contradict each other. And the different features of the examples can be combined with each other to give new examples and examples, all of which are within the scope of the present disclosure.

Hereinafter, the text processing method according to the embodiment of the present disclosure will be described with reference to FIGS. 1 to 5.

First, the text processing method according to the embodiment of the present disclosure will be described with reference to FIG. The method may be completed automatically by a computer or the like. For example, the method applies to text summarization generation, text summarization, and the like. For example, the text processing acquisition method may be realized in the form of software, hardware, firmware, or any combination thereof, and may be realized by a processor in a device such as a mobile phone, a tablet PC, a notebook personal computer, a desktop personal computer, or a network server. It may be loaded and executed.

As shown in FIG. 1, the text processing method includes the following steps S101 to S103.

In step S101, the original text, one or more keywords included in the original text, and the first processing result are received.

In step S102, it is determined whether or not the first processing result includes all the keywords.

In step S103, when the first processing result does not include all the keywords, one or a plurality of sentences in the original text are deleted, and the first processing result and the original text after the deletion processing are deleted. The deletion process is continued until the combination with the sentence inside includes all the keywords and the number of sentences in the original text after the deletion process is the minimum, and the combination is used as the final processing result.

In step S101, for example, the original text may be text in any language format (for example, Chinese, English, Japanese, etc.), but is not limited thereto. For example, the keyword may be one or more letters, words or phrases or short sentences that the user considers important.

For example, the first processing result is one or more sentences obtained by simplifying the original text. As an example, the first processing result may be a text summary. For example, the first processing result may be obtained by, for example, a text generation model based on a neural network. The method for acquiring the first processing result may be any appropriate method, but is not limited thereto.

In step S102, for example, by traversing all the sentences of the first processing result for each of one or a plurality of keywords, it is determined whether or not the first processing result includes all the keywords. You may. For example, whether all the sentences of the first processing result are decomposed into each word vector, all the keywords are also converted into the word vector format, and the first processing result includes all the keywords by the method based on the neural network. You may decide whether or not. The method for determining whether or not the first processing result includes all keywords is not limited to this, and using another appropriate method, whether or not the first processing result includes all keywords is determined. You may decide, but keep in mind that we are not limited here.

In step S103, for example, when the first processing result does not include all the keywords, the sentences in the original text are deleted based on the degree of association between each sentence of the original text and the all keywords. Then, until the combination of the first processing result and the sentence in the original text after the deletion process includes all the keywords and the number of sentences in the original text after the deletion process is the minimum, the deletion process is performed. Continue.

For example, the degree of relevance between each sentence of the original text and all the keywords is determined based on the number of the one or more keywords included in each sentence of the original text. For example, when sentence A of the original text contains one keyword and sentence B contains three keywords, the degree of association between sentence B of the original text and all keywords is the relationship between sentence A of the original text and all keywords. It may be considered higher than the degree.

Hereinafter, a method of deleting a sentence in the original text according to the embodiment of the present disclosure will be described with reference to FIGS. 2 to 3.

FIG. 2 shows a flowchart of the method 200 for deleting a sentence in the original text according to the embodiment of the present disclosure. For example, as shown in FIG. 2, a step of deleting a sentence in the original text based on the degree of association between each sentence of the original text and all the keywords is a step of deleting each sentence of the original text and all of the above. A step of sorting each sentence of the original text in ascending order of the degree of relevance based on the degree of relevance to the keyword (S201), and a step of deleting each sentence in the original text based on the sort (S202). , May be included.

For example, when sorting the original text based on the degree of relevance, the sentences of the original text are sorted as they are, so it is not necessary to consider grammatical problems.

FIG. 3 shows another flowchart of the method 300 for deleting a sentence in the original text according to the embodiment of the present disclosure. For example, as shown in FIG. 3, the step of deleting each sentence in the original text in ascending order of the degree of relevance is the first sentence after the first sentence of each sentence in the original text is deleted. In the step (S301) of determining whether or not the combination of the processing result and the sentence in the original text after the deletion processing includes all the keywords, and in the first processing result and the original text after the deletion processing. When the combination with the sentence includes all the keywords, the step (S302) of determining the deletion operation and continuing the processing of the next sentence of the original text, and the first processing result and the original text after the deletion processing If the combination with the sentence does not include all the keywords, it may include a step (S303) of canceling the delete operation, leaving the first sentence, and continuing the processing of the next sentence of the original text. ..

For example, the received keyword set is {m, n, p, q}, the received first processing result is G (G may include one or more sentences), and each of the original texts. Assuming that the original text sorted according to the ascending order of relevance of the sentence (A, B, C, D, E, F) and all the keywords is BDFACE, the text processing method according to FIG. After the sentence B is deleted, the combination of G and the original text sentence DFACE after the deletion process, the step of determining whether GDFACE contains all the keywords {m, n, p, q}, and GDFACE all When the keyword {m, n, p, q} is included, the deletion operation of the sentence B is determined (that is, the sentence B is deleted from the original text), the first processing result G and the original text after the deletion processing are performed. Following the original text according to step S301, until the combination with the sentence in the text contains all the keywords {m, n, p, q} and the number of sentences in the original text after the deletion process is minimized. It may include a step of continuing the processing of the sentence D of the above and making the combination the final processing result. On the other hand, when GDFACE does not include all the keywords {m, n, p, q}, the reduction operation of sentence B is canceled, the sentence B of the original text is left, and the first processing result G and the deletion processing are performed. The original according to step S301 until the combination with the sentence in the original text includes all the keywords {m, n, p, q} and the number of sentences in the original text after the deletion process is minimized. It may include a step of continuing the processing of the next sentence D of the text and making the combination the final processing result.

Alternatively, whether the combination of the first processing result and the sentence in the original text after the deletion processing includes all the keywords after the first sentence in the original text is deleted. Before determining whether or not, a step of deleting a sentence containing none of the keywords in the original text may be further included in ascending order of relevance. In the process, first, the sentences containing none of the keywords in the original text are deleted, and then the sentences containing one or more keywords left in the original text are subjected to steps S301 to S303. The complexity of the process can be reduced by performing the process of.

FIG. 4 shows a block diagram 400 of a text processing method according to an embodiment of the present disclosure. As shown in FIG. 4, the text processing method of the present disclosure includes an original text, a step (S401) of receiving one or a plurality of keywords included in the original text, and a first processing result, and a first processing result. A step (S402) for determining whether or not all the keywords are included, and a step (S403) for the first processing result as the final processing result when the first processing result includes all the keywords. If the first processing result does not include all the keywords, each sentence of the original text is sorted in ascending order of the degree of relevance based on the relevance of each sentence of the original text and all the keywords. Then, based on the sort, the step (S404) of deleting each sentence in the original text is mainly included. Then, after the first sentence of each sentence in the original text is deleted, whether or not the combination of the first processing result and the sentence in the original text after the deletion processing includes all the keywords. Judgment (S405). When the combination of the first processing result and the sentence in the original text after the deletion processing includes all the keywords, the deletion operation is determined, and the first processing result and the sentence in the original text after the deletion processing are determined. Until the combination with the sentence includes all the keywords and the number of sentences in the original text after the deletion process is the minimum (S408), the process of the next sentence of the original text is performed according to the steps S404 to S405. Continue (S406) and use the combination as the final processing result (S409). On the other hand, if the combination of the first processing result and the sentence in the original text after the deletion process does not include all the keywords, the deletion operation is canceled, the first sentence is left, and the first sentence is left. S404 to S405 until the combination of the processing result and the sentence in the original text after the deletion process includes all the keywords and the number of sentences in the original text after the deletion process is the minimum (S408). According to the steps, the processing of the next sentence of the original text is continued (S407), and the combination is used as the final processing result (S409).

Hereinafter, an example of the text processing method according to the embodiment of the present disclosure will be described with reference to FIG. As shown in FIG. 5, first, the original text 50, a plurality of keywords 52, and the first processing result are received (for example, a summary 51 is generated from the original text 50 by using a conventional text generation model or the like). As can be seen from FIG. 5, if the summary 51 generated by the model does not contain all the keywords (without the keyword "Coubertin"), the method of the present disclosure will result in all the keywords 52 and the final processing result. A new summary 53 can be obtained, including the summary 51 generated by the model. As can be seen from the above, with reference to the summary 51 generated by the model, the sentences in the original text 50 are gradually deleted based on the idea of "decreasing", and the sentences in the original text after the deletion process (for example, for example). In Figure 5, "1500 years after the end of the ancient Olympics, the Frenchman Coubertin proposed to host the modern Olympics at the end of the 19th century."), Combined with the model-generated summary 51. By setting the final processing result (processed summary 53 in FIG. 5), the final processing result includes all keywords, and each sentence of the final processing result is generated by the model without duplication. The number of sentences contained is minimal compared to the combination of the summary 51 and other sentences of the original text. It should be noted that the above method of the present disclosure reduces the complexity of calculation because it is not necessary to consider the number of keywords and the grammatical problem between sentences.

The present disclosure combines the abstract with the entire original text, based on the idea of "decrease", and refers to the original text with reference to the abstract until it produces a minimal set of sentences containing all the keywords. By deleting the sentences inside, the calculation complexity is reduced.

The text processing method according to the embodiment of the present disclosure will be described above with reference to the drawings. Hereinafter, the text processing apparatus according to the embodiment of the present disclosure will be described.

FIG. 6 is a functional block diagram showing a text processing device according to an embodiment of the present disclosure. As shown in FIG. 6, the text processing apparatus 1000 according to the embodiment of the present disclosure includes a receiving unit 1010, a determination unit 1020, and a deletion unit 1030. Each of the above modules can execute each step of the text processing method according to the embodiment of the present disclosure described above with reference to FIGS. 1 to 5. Those skilled in the art may realize these unit modules in various forms by hardware alone, software alone, or a combination thereof, and the present disclosure is not limited to any of these. For example, a central processing unit (CPU), text processor (GPU), tensor processor (TPU), field programmable gate array (FPGA), or other form of processing unit with data processing and / or instruction execution capabilities. And these units may be executed at the instruction of the corresponding computer.

For example, the receiving unit 1010 is used to receive the original text, one or more keywords contained in the original text, and the first processing result obtained by simplifying the original text.

For example, the first processing result is one or more sentences obtained by simplifying the original text. As an example, the first processing result may be a text summary. For example, the first processing result may be obtained by, for example, a text generation model based on a neural network. The method for acquiring the first processing result may be any appropriate method, but is not limited thereto.

For example, the determination unit 1020 is used to determine whether or not the first processing result includes all the keywords.

For example, the determination unit 1020 determines whether or not the first processing result includes all the keywords by traversing all the sentences of the first processing result for each of one or a plurality of keywords. You may. For example, it may be determined whether or not the first processing result includes all the keywords by a method based on the neural network. The method by which the determination unit 1020 determines whether or not the first processing result includes all the keywords is not limited to this. The determination unit 1020 may determine whether or not the first processing result includes all the keywords by using other appropriate methods, but is not limited thereto.

For example, the deletion unit 1030 deletes one or more sentences in the original text when the first processing result does not include all the keywords, and the first processing result and the deletion processing are performed. The deletion process is continued until the combination with the sentence in the original text includes all the keywords and the number of sentences in the original text after the deletion process is the minimum, and the combination is the final processing result. It is used to.

For example, if the first processing result does not include all the keywords, the deletion unit 1030 may use the sentences in the original text based on the degree of association between each sentence of the original text and all the keywords. The deletion is performed until the combination of the first processing result and the sentence in the original text after the deletion process includes all the keywords and the number of sentences in the original text after the deletion process is the minimum. The process may be continued.

For example, the degree of relevance between each sentence of the original text and all the keywords is determined based on the number of the one or more keywords included in each sentence of the original text.

For example, the deletion unit 1030 sorts each sentence of the original text in ascending order of the degree of relevance based on the degree of association between each sentence of the original text and the all keywords, and based on the sort, the original text. You may delete each sentence in it.

For example, in the deletion unit 1030, after the first sentence of each sentence in the original text is deleted, the combination of the first processing result and the sentence in the original text after the deletion processing sets all the keywords. If the combination of the first processing result and the sentence in the original text after the deletion processing includes all the keywords, the deletion operation is determined and the processing of the next sentence of the original text is determined. If the combination of the first processing result and the sentence in the original text after the deletion process does not include all the keywords, the deletion operation is canceled, the first sentence is left, and the original text is left. You may continue processing the next statement in.

Alternatively, in the deletion unit 1030, after one sentence in the original text is deleted, all combinations of the first processing result and the sentence in the original text after the deletion processing are all. Before determining whether or not a keyword is included, a sentence that does not include any of the keywords in the original text may be deleted in ascending order of relevance. In this process, the deletion unit 1030 first deletes a sentence in the original text that does not contain any of the keywords, and then for a sentence that contains one or more keywords left in the original text. By performing the above processing, the complexity of the processing can be reduced.

Hereinafter, the text processing apparatus 1100 according to the embodiment of the present disclosure will be described with reference to FIG. 7. FIG. 7 is a schematic diagram of the text processing device according to the embodiment of the present disclosure. Since the functions of the text processing device of this embodiment are the same as the details of the method described above with reference to FIG. 1, detailed description of the same contents is omitted here for convenience.

The text processing apparatus of the present disclosure includes a processor 1102, a storage device 1101 for storing computer-readable instructions, and executes a text processing method when the computer-readable instructions are executed by the processor. .. The method comprises receiving the original text, one or more keywords contained in the original text, and the first processing result obtained by simplifying the original text, and the first processing result. The step of determining whether or not all the keywords are included, and if the first processing result does not include all the keywords, one or more sentences in the original text are deleted, and the first process is performed. The deletion process is continued until the combination of the processing result of the above and the sentence in the original text after the deletion process includes all the keywords and the number of sentences in the original text after the deletion process is the minimum. A step of making the combination a final processing result, and the like are included.

Regarding the technical effects of the text processing apparatus 1000 and the text processing apparatus 1100 in each embodiment, the technical effects of the text processing method according to the embodiments of the present disclosure can be referred to, and the present invention will not be repeated here.

The text processing device 1000 and the text processing device 1100 are applied to various suitable electronic devices.

FIG. 8 is a schematic diagram of a computer-readable storage medium 1200 according to an embodiment of the present disclosure.

As shown in FIG. 8, the present disclosure further comprises a computer-readable storage medium 1200 in which computer-readable instructions 1201 are stored, and when the computer-readable instructions are executed by the computer, the original text, said. The step of receiving one or more keywords included in the original text and the first processing result obtained by simplifying the original text, and whether or not the first processing result includes all the keywords. If the step of determining whether or not the first processing result does not include all the keywords, one or more sentences in the original text are deleted, and the first processing result and the deletion processing are performed. The deletion process is continued until the combination with the sentence in the original text includes all the keywords and the number of sentences in the original text after the deletion process is the minimum, and the combination is the final processing result. And perform computer text processing methods, including.

<Hardware structure>
The block diagram used in the description of the above embodiment shows a block of functional units. These functional blocks (structural parts) are realized by any combination of hardware and / or software. Further, the means for realizing each functional block is not particularly limited. That is, each functional block may be realized by one physically and / or logically coupled device, and two or more physically and / or logically separated devices are directly and / or indirectly separated. It may be realized by the above-mentioned plurality of devices by connecting (for example, wired and / or wirelessly).

For example, the electronic device in one embodiment of the present disclosure may function as a computer that performs the processing of the text processing method of the present disclosure. FIG. 9 is a diagram of an example of the hardware structure of the electronic device according to the embodiment of the present disclosure. The electronic device 10 may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.

In the following description, the word "device" can be replaced with a circuit, device, unit, or the like. The hardware structure of the electronic device 10 may include one or more of the devices shown in the figure, or may not include some of the devices.

For example, although the figure shows only one processor 1001, a plurality of processors may be provided. Further, the processing may be executed by one processor, or the processing may be executed simultaneously by one or more processors, sequentially, or by another method. The processor 1001 may be installed by one or more chips.

For each function of the electronic device 10, for example, by loading predetermined software (program) onto hardware such as the processor 1001 and the memory 1002, the processor 1001 performs an operation, and communication by the communication device 1004, the memory 1002, and the memory 1002 and the like. It is realized by controlling the reading and / or writing of data in the storage 1003.

Processor 1001 operates, for example, an operating system to control the entire computer. The processor 1001 may be configured by a central processing unit (CPU, Central Processing Unit) including an interface with peripheral devices, a control device, an arithmetic unit, a register, and the like.

The processor 1001 reads a program (program code), a software module, data, and the like from the storage 1003 and / or the communication device 1004 into the memory 1002, and executes various processes according to them. As the program, a program that causes a computer to execute at least a part of the operations described in the above embodiment is used. For example, the control unit 401 of the electronic device 10 may be realized by a control program stored in the memory 1002 and operated by the processor 1001, and may be similarly realized for other functional blocks.

The memory 1002 is a computer-readable recording medium, such as a read-only memory (ROM, Read Only Memory), a programmable read-only memory (EPROM, Erasable Programmable ROM), and an electrically programmable read-only memory (EPROM). , Electrically EPROM), random access memory (RAM, Random Access Memory), and at least one of other suitable storage media. The memory 1002 may be referred to as a register, a cache, a main memory (main storage device), or the like. The memory 1002 can store an executable program (program code), a software module, and the like for implementing the wireless communication method according to one embodiment of the present disclosure.

The storage 1003 is a computer-readable recording medium, and is, for example, a flexible disk, a floppy (registered trademark) disk, or an optical magnetic disk (for example, a compact disk (CD-ROM)). Digital universal discs, Blu-ray (registered trademark) discs, removable discs, hard drives, smart cards, flash memory devices (eg, cards, sticks, key drivers), magnetic strips, etc. , Database, server, and other suitable storage medium. Storage 1003 may be referred to as an auxiliary storage device.

The communication device 1004 is hardware (transmission / reception device) for communicating between computers via a wired and / or wireless network, and is also called, for example, a network device, a network controller, a network card, a communication module, or the like.

The input device 1005 is an input device (for example, a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives an input from the outside. The output device 1006 is an output device (for example, a display, a speaker, a light emitting diode (LED, a Light Emitting Diode) lamp, or the like) that outputs to the outside. The input device 1005 and the output device 1006 may have an integrated structure (for example, a touch panel).

Each device such as the processor 1001 and the memory 1002 is connected via the bus 1007 for communicating information. Bus 1007 may be composed of a single bus or may be composed of different buses between devices.

The electronic device 10 includes a microprocessor, a digital signal processor (DSP, Digital Signal Processor), an integrated circuit for a specific application (ASIC, Application Specific Integrated Circuit), a programmable logic device (PLD, Programmable Logic Device), and a programmable logic device. Hardware such as an array (FPGA, Field Processor Gate Array) may be provided, and a part or all of each functional block can be realized through the hardware. For example, processor 1001 may be installed by at least one of these hardware.

Software, whether called software, firmware, middleware, microcode, hardware description language, or other names, commands, command sets, codes, code segments, program codes, programs, subprograms, software modules. , Applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, steps, features, etc. should be broadly interpreted.

Note that software, commands, information, and the like may be transmitted or received via a transmission medium. For example, using wired technology (coaxial cable, optical cable, twisted pair, digital subscriber line (DSL, Digital Subscriber Line), etc.) and / or wireless technology (infrared, microwave, etc.), website, server, or other. When transmitting software from a remote source, these wired and / or wireless technologies are included within the definition of transmission medium.

Each of the embodiments / embodiments described herein may be used alone or in combination, or may be switched and used during execution. The order of the processing steps, sequences, flowcharts, etc. of each method / embodiment described in the present specification may be changed as long as there is no contradiction. For example, with respect to the methods described herein, the various step units are given in an exemplary order, but are not limited to the particular order given.

As used herein, "based on" does not mean "based on" unless expressly stated in another paragraph. That is, the expression "based on" means both "based on only" and "based on at least."

Any reference to units using names such as "first", "second" as used herein does not generally limit the quantity or order of these units. As used herein, these names can be used as a convenient way to distinguish between two or more units. Therefore, references to the first and second units do not mean that only two units can be employed there, or that the first unit must precede the second unit.

As long as "inclusion", "comprising", and variations thereof are used herein or within the scope of the claims, these terms are as comprehensive as the term "comprising". Is intended to be. Moreover, the term "or" as used herein or in the claims is not an exclusive OR.

Those skilled in the art will appreciate that various aspects of this application include new and useful combinations of processes, machines, products, or substances, or any combinations thereof, or new and useful improvements to them. Understand what can be explained and described through patentable categories or situations. Accordingly, various aspects of the present application may be performed entirely by hardware, may be performed entirely by software (including firmware, resident software, microcode, etc.), or may be performed entirely by hardware and software. It may be executed by a combination. Any of the above hardware or software may be referred to as a "data block", "module", "engine", "unit", "assembly", or "system". It should be noted that various aspects of the present application may be embodied as computer products provided on one or more computer-readable media, the product including computer-readable program code.

This application uses specific words to describe examples of this application. For example, "one example," "one example," and / or "several examples" mean a particular feature, structure, or characteristic associated with at least one example of the present application. Therefore, it is emphasized that "one example" or "one example" or "one alternative example" referred to in different positions more than once in the present specification does not necessarily refer to the same embodiment. , Should be noted. It should be noted that some features, structures, or properties in one or more embodiments of the present application may be combined appropriately.

Unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by those skilled in the art of the present disclosure. It should be noted that terms such as those defined in ordinary dictionaries should be construed as having a meaning consistent with the meaning in the context of the relevant technology and are ideal unless explicitly stated here. It should also be understood that it should not be interpreted in a targeted or extremely formalized sense.

Although the present disclosure has been described in detail above, it will be apparent to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure may be implemented as amended and modified forms without departing from the gist and scope of the present disclosure as determined by the description of the scope of the patent claim. Therefore, the description herein is for purposes of illustration only and has no limiting meaning to the present disclosure.

Claims (9)

It ’s a text processing method.
A step of receiving the original text, one or more keywords contained in the original text, and a first processing result obtained by simplifying the original text.
The step of determining whether or not the first processing result includes all the keywords, and
When the first processing result does not include all the keywords, one or more sentences in the original text are deleted, and the first processing result and the sentence in the original text after the deletion processing are deleted. The deletion process is continued until the combination of the above includes all the keywords and the number of sentences in the original text after the deletion process is minimized, and the combination is used as the final processing result. , Text processing method. When the first processing result does not include all the keywords, one or more sentences in the original text are deleted, and the first processing result and the sentence in the original text after the deletion processing are deleted. The step of continuing the deletion process until the combination of the above includes all the keywords and the number of sentences in the original text after the deletion process is the minimum is
When the first processing result does not include all the keywords, the sentences in the original text are deleted based on the degree of association between each sentence of the original text and the all keywords, and the first sentence is deleted. The deletion process is continued until the combination of the processing result and the sentence in the original text after the deletion process includes all the keywords and the number of sentences in the original text after the deletion process is the minimum. The text processing method according to claim 1. The step of deleting a sentence in the original text based on the degree of association between each sentence in the original text and all the keywords is
A step of sorting each sentence of the original text in ascending order of the degree of association based on the degree of association between each sentence of the original text and all the keywords.
The text processing method according to claim 2, comprising a step of deleting each sentence in the original text based on the sort. The step of deleting each sentence in the original text in ascending order of relevance is
After the first sentence of each sentence in the original text is deleted, it is determined whether or not the combination of the first processing result and the sentence in the original text after the deletion processing includes all the keywords. Steps and
When the combination of the first processing result and the sentence in the original text after the deletion processing includes all the keywords, the step of determining the deletion operation and continuing the processing of the next sentence of the original text, and
If the combination of the first processing result and the sentence in the original text after the deletion process does not include all the keywords, the deletion operation is canceled, the first sentence is left, and the sentence following the original text is left. 3. The text processing method according to claim 3, comprising the step of continuing the processing of. After one sentence in the original text is deleted, but before it is determined whether or not the combination of the first processing result and the sentence in the original text after the deletion processing includes all the keywords. To,
The text processing method according to claim 4, further comprising a step of deleting a sentence containing none of the keywords in the original text in ascending order of relevance. The degree of relevance between each sentence of the original text and all the keywords is determined based on the number of the one or more keywords included in each sentence of the original text, claim 2 to claim. Item 5. The text processing method according to any one of items 5. It ’s a text processing device.
An original text, one or more keywords contained in the original text, and a receiving unit for receiving the first processing result obtained by simplifying the original text.
A determination unit for determining whether or not the first processing result includes all keywords, and
When the first processing result does not include all the keywords, one or more sentences in the original text are deleted, and the first processing result and the sentence in the original text after the deletion processing are deleted. With a deletion unit for continuing the deletion process until the combination of the above includes all keywords and the number of sentences in the original text after the deletion process is the minimum, and making the combination the final processing result. , A text processing device. With the processor
A text processing device comprising a storage device for storing computer-readable instructions.
When the computer-readable instruction is executed by the processor,
A step of receiving the original text, one or more keywords contained in the original text, and a first processing result obtained by simplifying the original text.
The step of determining whether or not the first processing result includes all the keywords, and
When the first processing result does not include all the keywords, one or more sentences in the original text are deleted, and the first processing result and the sentence in the original text after the deletion processing are deleted. The deletion process is continued until the combination of the above includes all the keywords and the number of sentences in the original text after the deletion process is minimized, and the combination is used as the final processing result. A text processing device that performs a text processing method. A computer-readable storage medium for storing computer-readable programs.
A computer-readable storage medium that causes a computer to execute the text processing method according to any one of claims 1 to 6 by the program.

Images