JP2023104183A - Program and information processing method - Google Patents

Abstract

To provide a program and an information processing method capable of presenting a summary sentence of a retrieved file.SOLUTION: A program executed by a processor allows the processor to implement a function of generating a summary sentence of a text included in a retrieval object file; the function of acquiring retrieval information for retrieving the file; the function of retrieving the file from the retrieval object file, on the basis of the retrieval information; and the function of outputting identification information for identifying the retrieved file and the summary sentence of the text included in the retrieved file.SELECTED DRAWING: Figure 1

Description

The embodiment of the present invention relates to a program and an information processing method.

Systems are provided that search for files containing text based on search words or the like. Such systems present the user with a list of retrieved files.

The user checks the contents of the files one by one in order to search for useful files from the list of searched files. Therefore, the user spends a lot of time searching for useful files.

JP-A-10-207891

In order to solve the above problems, a program and an information processing method capable of presenting a summary of a searched file are provided.

According to the embodiment, the program executed by the processor provides the processor with a function of generating a summary of text contained in a search target file, a function of obtaining search information for searching the file, and a function of obtaining search information for searching the file; Based on the information, a function of retrieving a file from the files to be searched and a function of outputting identification information for identifying the retrieved file and a summary of the text included in the retrieved file are realized. .

FIG. 1 is a block diagram showing a configuration example of a search system according to an embodiment. FIG. 2 is a block diagram illustrating a configuration example of a server according to the embodiment; FIG. 3 is a diagram illustrating a display example of a user terminal according to the embodiment; FIG. 4 is a flow chart showing an operation example of the search system according to the embodiment. FIG. 5 is a flow chart showing an operation example of the search system according to the embodiment.

Hereinafter, embodiments will be described with reference to the drawings.
A search system according to an embodiment inputs information (search words, etc.) for searching files from a user. The search system searches for files based on the information. The search system presents the user with a list of searched files.

FIG. 1 is a block diagram showing a configuration example of a search system 1 according to an embodiment. As shown in FIG. 1, the search system 1 includes a server 10, user terminals 20, and the like. The server 10 and the user terminal 20 are connected to each other via a network or the like.

The server 10 pre-stores files containing text. The server 10 acquires information (search information) for searching for files from the user terminal 20 . The server 10 causes the user terminal 20 to display the file and the summary sentence searched according to the search information. The server 10 will be detailed later.

The user terminal 20 (external device) is a terminal used by a user who searches for files. The user terminal 20 includes an operation unit such as a keyboard and a display unit such as a monitor. The user terminal 20 inputs search information from the user through the operation unit. After inputting search information, the user terminal 20 transmits a request including the input search information to the server 10 .

The user terminal 20 receives a response from the server 10 to display the searched file and the abstract. Upon receiving the response, the user terminal 20 displays the searched file and the abstract on the display unit according to the response.

For example, the user terminal 20 is a desktop PC, notebook PC, tablet PC, smart phone, wearable terminal, or the like.
Note that the search system 1 may be provided with a plurality of user terminals 20 .

Next, the server 10 will be explained.
FIG. 2 shows a configuration example of the server 10 according to the embodiment. As shown in FIG. 2, the server 10 includes a processor 11, a ROM 12, a RAM 13, an NVM 14, a communication section 15, an operation section 16, a display section 17, and the like.

The processor 11, ROM 12, RAM 13, NVM 14, communication unit 15, operation unit 16, and display unit 17 are connected to each other via a data bus, an interface, or the like.
It should be noted that the server 10 may have a configuration other than the configuration shown in FIG. 2 as necessary, or a specific configuration may be excluded from the server 10 .

The processor 11 has a function of controlling the operation of the server 10 as a whole. Processor 11 may include an internal cache, various interfaces, and the like. The processor 11 implements various processes by executing programs pre-stored in the internal memory, ROM 12 or NVM 14 .

Note that some of the various functions realized by the processor 11 executing the program may be realized by hardware circuits. In this case, processor 11 controls the functions performed by the hardware circuits.

The ROM 12 is a nonvolatile memory in which control programs, control data, and the like are stored in advance. The control programs and control data stored in the ROM 12 are installed in advance according to the specifications of the server 10 .

RAM 13 is a volatile memory. The RAM 13 temporarily stores data being processed by the processor 11 . RAM 13 stores various application programs based on instructions from processor 11 . Also, the RAM 13 may store data necessary for executing the application program, execution results of the application program, and the like.

The NVM 14 is a non-volatile memory in which data can be written and rewritten. The NVM 14 is composed of, for example, an HDD (Hard Disk Drive), SSD (Solid State Drive), flash memory, or the like. The NVM 14 stores control programs, applications, various data, etc. according to the operational use of the server 10 .

The NVM 14 stores in advance a plurality of files (search target files) containing text. For example, files to be searched include files generated by word processing software (word files, etc.), files generated by presentation software (PowerPoint files, etc.), files generated by printing software (PDF (Portable Document Format) files ) and so on. Also, the search target file may be a file generated by performing OCR (Optical Character Recognition) processing on paper materials. Also, the search target file may be a file composed of information obtained from a web page by web scraping technology or the like. Also, the files to be searched may include images, moving images, or the like.
The configuration of the files to be searched is not limited to a specific configuration.

For example, the processor 11 stores the search target file in the NVM 14 according to an operator's operation or the like. Also, the processor 11 may update or delete the search target file according to an operator's operation or the like.

The communication unit 15 is an interface for communicating with the user terminal 20 and the like. For example, the communication unit 15 connects to the user terminal 20 through a network such as the Internet. For example, the communication unit 15 is an interface that supports wired or wireless LAN (Local Area Network) connection.

The operation unit 16 receives input of various operations from the operator. The operation unit 16 transmits a signal indicating the input operation to the processor 11 . Here, the operation unit 16 is composed of a touch panel.

The display unit 17 displays image data from the processor 11 . For example, the display unit 17 is composed of a liquid crystal monitor. When the operation unit 16 is composed of a touch panel, the display unit 17 is formed integrally with the touch panel as the operation unit 16 .

Next, functions realized by the server 10 will be described. The functions realized by the server 10 are realized by the processor 11 executing a program stored in the internal memory, the ROM 12, the NVM 14, or the like.

First, the processor 11 has a function of morphologically analyzing the text contained in the search target file.

Processor 11 acquires one file from NVM 14 . Upon obtaining a file, processor 11 obtains the text contained in the obtained file. Upon obtaining the text, the processor 11 morphologically analyzes the obtained text. That is, the processor 11 decomposes the text into morphemes (for example, parts of speech). Note that the processor 11 may decompose the text into morphemes such that a predetermined technical term or abbreviation is recognized as one morpheme.

When the text is morphologically analyzed, the processor 11 generates morpheme data indicating the morphemes that make up the text.

The processor 11 also has a function of generating a text summary based on the morphological data.

For example, the NVM 14 stores in advance a generative model that outputs a summary when morphological data is input. For example, a generative model outputs morphemes that make up a summary sentence.

A generative model consists of a neural network. The generative model inputs morphological data to the input layer of the neural network, performs operations based on the weighting coefficients of the neural network, and outputs a summary sentence from the output layer of the neural network.

The weighting coefficients of the generative model are obtained by learning using text morpheme data and summary sentences as teacher data.

For example, the teacher data consists of morpheme data of a text and a summary sentence (morpheme data of the summary sentence) generated from the text by the operator.

A generative model is a model trained to output a summary sentence in teacher data in response to input of morphological data of text in teacher data.

The processor 11 inputs text morphological data to the generative model to generate a summary sentence.

After generating the abstract, the processor 11 generates attribute information that associates identification information (file name, identifier, etc.) identifying the search target file containing the text with the abstract of the text. After generating the attribute information, processor 11 stores the generated attribute information in NVM 14 .

If the NVM 14 already stores the attribute information, the processor 11 adds the identification information and the abstract to the attribute information.
The processor 11 similarly generates a summary sentence for each search target file.

The processor 11 also has a function of acquiring search information from the user terminal 20 .
For example, the processor 11 causes the user terminal 20 to display an input screen for accepting input of search information through the communication unit 15 .

Here, it is assumed that the user inputs search information on the input screen displayed by the user terminal 20 . The user terminal 20 transmits a request including the input search information to the server 10 . The request requests to retrieve files based on the search information.

The processor 11 receives a request including search information from the user terminal 20 through the communication unit 15 .

Search information is information for searching for a search target file. For example, search information includes search words. The search information may also indicate the creator of the file, date and time of creation, date of update, type, extension, size, and the like. Also, the search information may include multiple elements. The structure of search information is not limited to a specific structure.

The processor 11 also has a function of searching for a file among search target files based on the search information.

After obtaining the search information, the processor 11 searches for files from the search target files based on the search information. Processor 11 may retrieve multiple files.

For example, if the search information contains a search word, the processor 11 searches for files containing the search word in text from the files to be searched. The processor 11 acquires identification information of the searched file as a search result.

Note that the processor 11 may search the file based on the abstract. For example, if the attribute information includes a search word, processor 11 obtains identification information corresponding to a summary including the search word from the attribute information. Processor 11 may acquire the acquired identification information as a search result.

In addition, the processor 11 may search for files from the search target files based on the number of search words included in the text.
The method by which processor 11 retrieves files is not limited to any particular method.

The processor 11 also has a function of presenting a retrieved file and a summary of the file. That is, the processor 11 outputs the searched file and the abstract of the file.

After retrieving a file from the search target files, the processor 11 acquires a summary sentence corresponding to the identification information of the retrieved file from the attribute information. If there are multiple pieces of identification information for the searched file, processor 11 acquires a summary sentence corresponding to each piece of identification information.

After acquiring the digest, the processor 11 transmits to the user terminal 20 via the communication unit 15 a response for displaying the identification information of the retrieved file and the digest of the retrieved file. The response includes identification information of the retrieved file and a summary of the retrieved file.

By transmitting the response to the user terminal 20, the processor 11 causes the user terminal 20 to display the identification information and the abstract of the searched file.

FIG. 3 shows an example of a screen (display screen) that the processor 11 causes the user terminal 20 to display. As shown in FIG. 3, the display screen includes areas 31 and 32, and the like. Here, the display screen displays multiple identification information and multiple abstracts.

Area 31 displays the file search results. That is, the area 31 displays the identification information of the files searched based on the search information. Here, area 31 consists of three boxes. Each box in area 31 displays one identification.

Note that the area 31 may display a link or icon for displaying or downloading the searched file.

Area 32 also displays a summary of the retrieved file. Here, each box in area 32 displays a summary sentence corresponding to the identification information of the adjacent box in area 31 .

Area 32 may display a portion of the abstract (eg, the first few lines). Also, the area 32 may display a link or an icon that displays the full text of the abstract.

Next, an operation example of the server 10 will be described.
First, an operation example in which the server 10 generates a summary will be described.
FIG. 4 is a flow chart for explaining an operation example in which the server 10 generates a summary sentence.

First, the processor 11 of the server 10 acquires one search target file from the NVM 14 (S11). After acquiring one search target file, the processor 11 acquires text from the acquired search target file (S12).

After obtaining the text, the processor 11 generates morphological data from the text (S13). After acquiring the morphological data, the processor 11 generates a summary based on the morphological data (S14).

After generating the abstract, the processor 11 associates the identification information of the search target file with the abstract and adds them to the attribute information (S15). Note that if the NVM 14 does not store attribute information, the processor 11 generates attribute information.

When the identification information of the search target file and the summary are added to the attribute information in association with each other, the processor 11 determines whether there is a search target file whose summary has not yet been created (S16).

If it is determined that there is a search target file whose abstract has not yet been created (S16, YES), the processor 11 returns to S11.

If it is determined that there is no search target file for which no abstract has been created (S16, NO), the processor 11 terminates the operation.

Next, an operation example in which the server 10 presents a summary will be described.
FIG. 5 is a flow chart for explaining an operation example of the server 10 presenting a summary.
Here, it is assumed that the NVM 14 stores attribute information.

First, the processor 11 of the server 10 receives a request including search information from the user terminal 20 through the communication unit 15 (S21). Upon receiving the request, the processor 11 searches for a file from the search target files based on the search information included in the request (S22).

After retrieving the file, the processor 11 acquires the abstract of the retrieved file from the attribute information (S23). After acquiring the abstract, the processor 11 transmits a response including the identification information of the searched file and the abstract to the user terminal 20 (S24).

After transmitting the response to the user terminal 20, the processor 11 terminates its operation.

Note that the processor 11 may execute S11 to S16 according to the operator's operation. Further, the processor 11 may execute S11 to S16 for the search target file at the timing when the search target file is added or updated.

The processor 11 may also input search information through the operation unit 16 . In this case, the processor 11 may display the identification information and the abstract of the searched file on the display section 17 .

Also, the search target file may be stored in another device. The server 10 may acquire a search target file from another device and generate a summary sentence.

The search system configured as described above generates a summary of a search target file. In addition, the search system searches for files from search target files based on a search request from a user. The search system presents the user with a summary of the files found. As a result, the search system can reduce the user's effort to search for useful files from the search results.

While several embodiments of the invention have been described, these embodiments have been presented by way of example and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, replacements, and modifications can be made without departing from the scope of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are included in the scope of the invention described in the claims and equivalents thereof.

Reference Signs List 1 search system 10 server 11 processor 12 ROM 13 RAM 14 NVM 15 communication unit 16 operation unit 17 display unit 20 user terminal 31 area 32 …region.

Claims (9)

A program executed by a processor,
to the processor;
the ability to generate a summary of the text contained in the searched files;
A function to obtain search information for searching files;
a function of searching for a file from the search target files based on the search information;
a function of outputting identification information identifying the searched file and a summary of the text contained in the searched file;
program to realize to the processor;
realizing a function of storing, in a memory, attribute information that associates identification information identifying the search target file with a summary of the text contained in the search target file;
A program according to claim 1. Acquiring the search information is acquiring a request including the search information from an external device;
Outputting identification information identifying the searched file and a summary of the text included in the searched file is transmitting a response for displaying the identification information and the summary to the external device. is
3. A program according to claim 1 or 2. searching for the file is searching for the file from the search target files based on the abstract;
A program according to any one of claims 1 to 3. The search information includes a search word,
A program according to any one of claims 1 to 4. Generating the summary sentence includes:
generating morpheme data representing morphemes of the text from the text;
generating the summary sentence based on the morphological data;
A program according to any one of claims 1 to 5. generating the summary sentence is inputting the morphological data into a generative model to generate the summary sentence;
7. A program according to claim 6. The generative model performs an operation based on the weighting coefficients of the neural network on the morphological data input to the input layer of the neural network, and outputs the summary sentence from the output layer of the neural network. A model for making a processor work,
The weighting coefficient is obtained by learning using the morpheme data and the summary sentence as teacher data,
8. A program according to claim 7. An information processing method performed by a processor, comprising:
generate a summary of the text contained in the searched files,
Get search information to search for files,
searching for a file from the search target file based on the search information;
outputting identification information identifying the retrieved files and a summary of the text contained in the retrieved files;
Information processing methods.