JP6125414B2 - Sentence analysis apparatus, sentence analysis method, program - Google Patents

Description

  The present invention relates to a sentence analyzing apparatus that analyzes a sentence included in text data and extracts an important character string from the text data.

  2. Description of the Related Art Conventionally, a system for extracting a topical word from contents such as a sentence input to a computer system or a homepage published on the Internet has been disclosed.

  For example, in the information acquisition devices disclosed in Patent Document 1 and Patent Document 2, in order to find the most topical information from input information input from a user, the morpheme group stored in the morpheme database The input information is collated, and a character string corresponding to the morpheme is extracted from the input information. A morpheme corresponds to a minimum unit such as “word” that constitutes a sentence included in input information or the like, and this minimum unit includes parts of speech such as nouns, adjectives, and verbs. In the morpheme database, morpheme groups including nouns, adjectives, verbs and the like used for general sentences are registered in advance.

Japanese Patent No. 4253487 Japanese Patent No. 4402868

  However, in the information acquisition devices disclosed in Patent Document 1 and Patent Document 2 described above, a morpheme database to be collated is created in advance in order to find the most topical information (word) from input information or the like. It must be very labor intensive. If nouns, adjectives, verbs, and the like used in everyday sentences are registered in the morpheme database so that they are generally covered, effective analysis of input information or the like cannot be realized.

  Furthermore, in this information acquisition apparatus, topical information can be grasped only in units of morphemes such as “words”.

  Further, in the information acquisition device, in order to find the most topical information from the input information or the like, it is necessary to perform a matching process with the morpheme database for each word included in the input information or the like. Since a lot of time is required for access, comparison processing, and the like, the response time becomes long. As a result, it is difficult to analyze input information and the like in real time.

  Furthermore, for other languages other than Japanese, in order to find the most topical information from the same processing, that is, input information, etc., a new morpheme database is prepared, and further, according to the grammar of each language. Analytical logic etc. must be reconstructed.

  Accordingly, an object of the present invention is to provide a sentence analysis apparatus, a sentence analysis method, and a program that can solve all the above-described problems.

  The present invention provides the following sentence analysis apparatus.

The first embodiment of the present invention comprises:
Character string search means (for example, a character string search processing unit 422 shown in FIG. 10) for searching for the same character string from text data (for example, text data 200 acquired from a collected WEB page);
For the same character string, it is an index indicating the degree of difference of the previous adjacent character (for example, how much the character appearing immediately before the searched “same character string” is different (there is a variation), Based on the number of patterns of characters appearing as adjacent characters of) and the degree of difference of the subsequent adjacent characters (for example, how much the character appearing immediately after the searched “same character string” is different (variation exists) A different degree determination means (for example, a different degree determination processing unit 423 shown in FIG. 10) for determining an index indicating the number of character patterns appearing as subsequent adjacent characters),
The degree of importance of the same character string is determined based on the degree of difference between the preceding adjacent characters, the degree of difference between the subsequent adjacent characters, and the appearance frequency of the same character string in the text data, and the same character string is identified. A sentence analysis device (for example, the sentence analysis shown in FIG. 10) configured to include a specific character string determination means (for example, the specific character string determination processing unit 424 shown in FIG. 10) for determining whether or not the character string. Device 400),
The specific character string determining means includes
In group including a plurality of different text data, if included is a plurality of specific character strings, based on the importance for each specific character string, performs the ranking of a specific character string in the previous Kigu the loop, the a plurality of specific character string, in association previously Kigu loop (e.g., in Figure 8 relates to text data batches and specific character string data were ranked specific character string based on the importance 135-1 , The specific character string data 135-3 is shown in which each site of the WEB page is grouped into three groups of A, B, and C, and the specific character strings are ranked based on importance.

According to such an embodiment of the present invention, for example, external information published on the Internet is collected as text data through a network, the character string search means searches for the same character string from the acquired text data, and the same After the degree of difference between the adjacent characters before and after the character string is determined by the difference degree determination unit, the difference between the adjacent characters before and after the determination by the difference degree determination unit and the appearance frequency of the same character string Thus, it is possible to determine the importance of the same character string, and to identify whether the same character string is a specific character string or not by using a specific character string determination unit, so that a topic is identified from text data without using a dictionary. Therefore, an important specific character string can be extracted. Further, according to this configuration, when the specific character string determination unit includes a plurality of specific character strings in a group including a plurality of different text data , the specific character string determination unit is based on the importance regarding each specific character string. Since the specific character strings are ranked in the group, the specific character strings are differentiated in each group, and improvement in the degree of freedom in analysis can be expected.

  According to a second embodiment of the present invention, in the first embodiment,
  The specific character string determining means further includes
  The importance of the same character string is determined based on the character length of the same character string, and it is configured to determine whether or not the same character string is a specific character string.

  If comprised in this way, in the said specific character string determination means, whether the same character string searched from text data is a specific character string, the difference degree of the adjacent character before and behind determined by the said difference degree determination means In addition to the appearance frequency of the same character string, the determination can be made based on the character length of the same character string.

The third embodiment of the present invention is:
A string search step for searching for the same string from text data;
For the same character string, a different degree determination step for determining a difference degree of a preceding adjacent character and a difference degree of a subsequent adjacent character;
The degree of importance of the same character string is determined based on the degree of difference between the preceding adjacent characters, the degree of difference between the subsequent adjacent characters, and the appearance frequency of the same character string in the text data, and the same character string is identified. A sentence analysis method including a specific string determination step for determining whether or not the string is a character string,
The specific character string determining step includes:
In group including a plurality of different text data, if included is a plurality of specific character strings, based on the importance for each specific character string, performs the ranking of a specific character string in the previous Kigu the loop, the a plurality of the specific character string, in association previously Kigu loop.
If comprised in this way, the method of having the effect similar to the said 1st embodiment can be provided.

  According to the embodiment of the present invention, it is possible to extract a specific character string important for identifying a topic from text data without using a dictionary.

The fourth embodiment of the present invention is:
On the computer,
String search means for searching for the same string from text data,
For the same character string, a different degree determination means for determining a difference degree of a preceding adjacent character and a difference degree of a subsequent adjacent character, and
The degree of importance of the same character string is determined based on the degree of difference between the preceding adjacent characters, the degree of difference between the subsequent adjacent characters, and the appearance frequency of the same character string in the text data, and the same character string is identified. A program that functions as a specific character string determining means for determining whether or not a character string,
The specific character string determining means includes
In group including a plurality of different text data, if included is a plurality of specific character strings, based on the importance for each specific character string, performs the ranking of a specific character string in the previous Kigu the loop, the a plurality of the specific character string, in association previously Kigu loop.

  According to the embodiment of the present invention, it is possible to extract a specific character string important for identifying a topic from text data without using a dictionary.

  By using the sentence analysis apparatus according to the present invention, it is possible to extract an important character string from the text data without using a database that is matched with the text data, thereby creating a database such as a morpheme database in advance, No need to maintain and manage. In addition, since character strings based on morphemes are not grasped, important character strings can be flexibly composed of phrases, clauses, and parts of other sentences that contain some words in addition to units such as words. Can be grasped in various ways.

  The sentence analysis apparatus according to the present invention searches for the same character string from text data, determines the degree of difference between adjacent characters before and after the character string, and determines the importance of the character string based on the degree of difference. Therefore, access to the database and comparison processing with a morpheme group stored in the database are not performed, and an important character string is extracted from text data at high speed.

  Furthermore, the sentence analysis apparatus according to the present invention determines the importance of the character string according to the degree of difference between adjacent characters before and after the character string as described above, without reconstructing the analysis logic or the like. Can easily handle languages other than Japanese.

It is a figure which shows the process outline | summary of the sentence analysis apparatus which concerns on one Embodiment of this invention. It is a front view which shows the WEB page displayed based on the HTML data which can become the original data of text data. It is a flowchart showing the process sequence of the character string search process which concerns on one Embodiment of this invention. It is a figure which shows the mechanism of the character string search using a suffix array and binary search. It is a figure which shows the mechanism of the character string search using a suffix array and binary search. It is a flowchart showing the process sequence of the different degree determination process which concerns on one Embodiment of this invention. It is a figure which shows the mechanism for determining the difference degree of the adjacent character before and behind. It is a figure which shows the concept of the ranking process which concerns on one Embodiment of this invention. It is a figure which shows the example of application of the sentence analysis apparatus which concerns on one Embodiment of this invention. It is a functional block diagram which shows each function part of the sentence analysis apparatus which concerns on one Embodiment of this invention. It is a figure which shows the example of the hardware constitutions of the computer which comprises the sentence analysis apparatus which concerns on one Embodiment of this invention. It is a figure which shows the process outline | summary of the information update apparatus which concerns on one Embodiment of this invention. It is a flowchart showing the process sequence of the character string extraction process of the information update apparatus which concerns on one Embodiment of this invention. It is a flowchart showing the process sequence of the dictionary comparison process of the information update apparatus which concerns on one Embodiment of this invention. It is a figure which shows the character string extraction process and dictionary comparison process of the information update apparatus which concerns on one Embodiment of this invention. It is a figure which shows the character string extraction process and dictionary comparison process of the information update apparatus which concerns on one Embodiment of this invention. It is a figure which shows the character string extraction process and dictionary comparison process of the information update apparatus which concerns on one Embodiment of this invention. It is a figure which shows the character string extraction process and dictionary comparison process of the information update apparatus which concerns on one Embodiment of this invention with the content of a related term dictionary. It is a figure which shows the content of the comparison result data memorize | stored by the dictionary comparison process of the information update apparatus which concerns on one Embodiment of this invention. It is a figure which shows the character string extraction process and dictionary comparison process of the information update apparatus which concerns on one Embodiment of this invention with the content of a related term dictionary. It is a figure which shows the character string extraction process and dictionary comparison process of the information update apparatus which concerns on one Embodiment of this invention with the content of a related term dictionary. It is a figure which shows the character string extraction process and dictionary comparison process of the information update apparatus which concerns on one Embodiment of this invention with the content of a related term dictionary. It is a figure which shows the outline | summary of the information update system containing the information update apparatus which concerns on one Embodiment of this invention. It is a functional block diagram which shows each function part of the information update apparatus which concerns on one Embodiment of this invention. It is a figure which shows the example of the hardware constitutions of the computer which comprises the information update apparatus which concerns on one Embodiment of this invention.

<<< Outline of Technical Idea in Sentence Analysis Device of the Present Invention >>>
The sentence analysis apparatus of the present invention searches for the same character string from text data, and determines the degree of difference between the previous adjacent character and the degree of difference between the subsequent adjacent character for each of the searched character strings. Based on the degree of difference, it is determined whether or not the retrieved “same character string” is a specific character string that is highly important with respect to the topic and is capable of semantically identifying text data. The degree of difference between the previous adjacent characters is an index indicating how much the character appearing immediately before the searched “same character string” is different. Similarly, the degree of difference between subsequent adjacent characters is an index indicating how much the character appearing immediately after the searched “same character string” is different.

  Here, for example, among the searched “same character string”, a character string having a large difference between the preceding adjacent characters and a large difference between the subsequent adjacent characters is determined as the specific character string. One or more character strings determined in this way are stored in a predetermined storage unit as necessary.

  This kind of character string extraction is based on the fact that when you focus on multiple identical character strings included in text data, many variations of characters appear as characters that are located immediately before each character string. When the appearance characteristic that many variations of characters appear as the character positioned immediately after is recognized, the character string is based on the idea that the character string is an independent and frequently used term. Thus, in the sentence analysis apparatus of the present invention, a character string is extracted based on the idea based on kinematics of the character string.

  Here, assuming Japanese text data in which the character string “Iroha” appears 100 times, 100 character strings “Iroha” are searched, and for each character string “Iroha”, what is the immediately preceding character? Investigate. As a result, the fact that 30 characters including “A” and “I” appear appears. This indicates that, for example, expressions such as “... Airoha ...” and “... Airoha ...” exist in the above Japanese text data. On the other hand, for each character string “Iroha”, the character immediately after it is examined. As a result, the fact that 20 characters including “wa” and “n” appear can be obtained. This indicates that, for example, expressions such as “... Irohawa ...” and “... Irohan ...” exist in the Japanese text data.

  In this case, the degree of difference between the preceding adjacent characters is determined based on, for example, the number of variations of 30 types including “A” and “I”. Judgment is made based on the number of 20 variations including “n”. Here, when it is determined that the difference between the preceding adjacent character and the difference between the subsequent adjacent characters is large, the characters before and after the character string “Iroha” have changed with great diversity. It is determined that the column “Iroha” is an independent term and is highly likely to be a highly important word, is determined as a specific character string, and is stored in the storage unit as necessary. Whether the difference between the preceding adjacent characters and the difference between the subsequent adjacent characters is large is determined based on a common or individual determination criterion.

  The text data that is the input data may be any content data. Typical examples include WEB pages (homepages) and blog text data that have been created by individuals and published on the Internet, and TWITTER (registered trademark) tweet information. Further, in addition to an individual, it may be data generated and edited in advance by an arbitrary organization or text information in a database. Furthermore, various data such as text data acquired from a voice file / moving image file through voice recognition processing can be used.

  Text data is data collected according to collection conditions. For example, it may be text data described on a WEB page (homepage) shown as a search result of a keyword search, a sentence described on a user's blog having a certain attribute, tweet information in TWITTER, or the like. One text data may include a plurality of text files (for example, a plurality of WEB pages (HTML files) included in one WEB site), or one text file may be divided. (For example, one of the texts included in one file divided every 10,000 lines).

<<< Description of processing outline of sentence analysis apparatus according to one embodiment of the present invention >>>
With reference to FIG. 1, an outline of processing of the sentence analysis apparatus according to an embodiment of the present invention will be described. First, the sentence analysis apparatus acquires text data 200 (text data acquisition process 100). Text data 200 can be received from various data sources as described above. Further, the text data 200 can be acquired by accessing the received network address. Furthermore, when the acquired text data 200 or the text data 200 is acquired, a filtering process may be performed so as to acquire only specific text data, or grouping may be performed according to a specific classification.

  Next, the sentence analysis apparatus searches for the same (common) character string from the text data 200 acquired by the text data acquisition process 100 (character string search process 110). This process is, for example, a process of searching for and retrieving the same character string “Iroha” in the acquired text data 200 as described above. In the above example, there are 100 character strings “Iroha” in one text data, all of which are extracted. In text data, there may be a plurality of the same character strings other than “Iroha”. In this case, these character strings are similarly searched and extracted. For example, in addition to the character string “Iroha”, if a plurality of character strings “Nihoheto” are included, the character string is similarly extracted. In addition, even if there are multiple character strings that contain “Iroha” that has already been extracted as the same character string, such as the character string “Iroha ni”, the same character string is searched separately from the character string “Iroha”. Is done.

  The character string search processing 110 further stores the character strings searched as the same character string in the search result data 115 together with the adjacent character before and after the character string. The search result data 115 is stored in a main storage device such as a RAM, for example. The stored data is, for example, the character string “Iroha” in the above example, the character string “Iroha”, the adjacent character before “Iroha”, and “Iroha” It is data including the next adjacent character. In the case of the above-described example, the character string “Ihohani” and the character string “Irohani” are also stored in the search result data 115 in the same manner as those character strings, the previous adjacent character, and the subsequent adjacent character.

  As described above, when the same character string is searched in the character string search processing 110, the character string and the adjacent characters before and after the character string are stored. Finally, a specific character string having an important meaning is determined. For this reason, even if there are a plurality of the same character strings in the text data 200, if the appearance frequency does not reach a predetermined frequency, it can be determined as a specific character string at this point. It is possible to determine that there is no character and not to store data related to the character string in the search result data 115. This is because a word (character string) that appears only a few times in the text data 200 made up of many characters can be determined to be less important in the first place.

  In the character string search processing 110, in order to search and store the same character string from the text data 200, in the present embodiment, a search data structure called a suffix array is used. By searching by search (Binary Search), the same character string is searched at high speed. In the present embodiment, the character string search processing 110 is performed by the above method, but the same search processing can be performed by employing various other methods. The character string search processing 110 using the suffix array and binary search will be described in detail later.

  Next, the sentence analysis apparatus determines the degree of difference between the previous adjacent character and the degree of difference between the adjacent character from the character string stored in the search result data 115 by the character string search processing 110 and the content of the adjacent character before and after the character string. Determination (difference degree determination processing 120).

Here, one character is represented as s (i),
A character string m (i, j) composed of s (i) to s (j)
m (i, j) = (s (i), s (i + 1), s (i + 2),... s (j−2), s (j−1), s (j))
A character string m (i, j-1) composed of s (i) to s (j-1)
m (i, j−1) = (s (i), s (i + 1), s (i + 2),... s (j−2), s (j−1))
A character string m (i + 1, j) composed of s (i + 1) to s (j) is
m (i + 1, j) = (s (i + 1), s (i + 2),... s (j−2), s (j−1), s (j)).

In this case, the boundary condition for the previous adjacent character is
T (i-1) = {S (i-1) | m (i, j)}
T (i) = {S (i) | m (i + 1, j)}
Defined in
The boundary condition for the next adjacent character is
B (j) = {S (j) | m (i, j-1)}
B (j + 1) = {S (j + 1) | m (i, j)}
Defined by

  Here, for example, {S (i−1) | m (i, j)} means a set of characters appearing immediately before the character string m (i, j) in common. Here, s (i) εT (i) and s (j) εB (j) hold.

  For example, when the number of elements of T (i-1) is large and the number of elements of T (i) is 1, s (i) is likely to be the head of a specific character string, while B (j) When the number of elements is 1 and the number of elements of B (j + 1) is large, s (j) is likely to be the end of the specific character string. As a result, the character string m (i, j) Judged as a candidate column.

  In this way, the degree of difference regarding the adjacent character for the same character string is determined based on the appearance mode of the adjacent character before (or after) the same character string, that is, how many variations the adjacent character appears. judge. When the degree of difference regarding the adjacent characters before and after is determined, the determined degree of difference is stored as specific character string candidate data 125 together with the corresponding character string, for example, in a main storage device such as a RAM. The process of the difference degree determination process 120 will be described in detail later.

  Next, the sentence analysis device determines whether or not the same character string is a specific character string based on the degree of difference regarding the adjacent characters before and after the same character string determined by the difference degree determination process 120. When it is determined that the character string is a specific character string, the character string is stored in the specific character string data 135 (specific character string determination processing 130). The specific character string data 135 is stored in, for example, a main storage device such as a RAM or an external storage device such as a hard disk or a semiconductor memory. Further, the specific character string data 135 can take various data formats and data storage formats, and can be configured as, for example, a database.

  As described above, regarding the same character string, if there are variations in the adjacent characters before and after them, if the number of appearance elements of the adjacent character is small, the adjacent character and the “same character string” are combined. Can be considered to form another character string that is often used. On the other hand, if the number of appearance elements of the adjacent character is large, the adjacent character and the “same character string” are separated. The "column" is an independent term and is likely to be a highly important word. Further, whether or not the “same character string” is a specific character string can be determined in consideration of other factors in addition to the degree of difference between the preceding adjacent characters and the degree of difference between the subsequent adjacent characters. The specific character string determination process 130 will be described later in detail.

  Furthermore, in the specific character string determination process 130, when a plurality of specific character strings are determined, ranking can be performed among character strings determined as specific character strings. Such ranking is, for example, ranking related to the importance of a character string, and can be determined in consideration of other factors in addition to the degree of difference between adjacent characters in the character string. For example, ranking can be performed based on the character length, appearance frequency, etc. of the character string. In addition to ranking, ranking can also be performed numerically so that a relative degree of difference can be represented.

<< Description of Character String Search Processing of Sentence Analysis Device According to One Embodiment of the Present Invention >>
First, what kind of text data 200 is provided as an input of the character string search processing 110 by the text data acquisition processing 100 described above will be described with reference to FIG. FIG. 2 shows a WEB page displayed in the window 150 of the WEB browser. On the WEB page, an image display unit 160, a text display unit 170, and an image display unit 180 are shown. The WEB browser interprets the acquired HTML data and displays an image and text on each display unit described above. In the text data acquisition process 100, referring to the tag from such HTML data, only the text portion as shown in the text display unit 170 is extracted as the text data 200 and provided to the character string search process 110.

  Here, the text data 200 is acquired from data included in one WEB page (HTML data). However, as described above, the text data 200 can be collected and acquired by various methods. it can. In FIG. 2, the WEB page is displayed for convenience of explanation, but the text data 200 can be directly acquired from the HTML data with reference to the tag, so that FIG. 2 is displayed on the display of the sentence analysis device or other devices. It is not necessary to display the window 150 as shown in FIG.

  Next, the character string search processing 110 will be described with reference to FIGS. FIG. 3 is a flowchart showing the processing procedure of the character string search processing 110. 4 and 5 are diagrams showing a mechanism for character string search using a suffix array and binary search, and a part of text displayed on the text display unit 170 of FIG. 2 as a character string to be searched. A character string 171 “This code is in the code list” is set. When obtaining text data from a WEB page, all text parts of one or more WEB pages are usually searched, but here they are part of the text part for illustration purposes.

  First, a suffix array is created in order to search for the same character string from the character string “this code is in the code list”. In step S10 of FIG. 3, the suffix is expanded from the first character to the last character of the text data. Here, referring to FIG. 4, from the text data 200-1 to be searched (“this code is in the code list”) shown in FIG. 4A, as shown in FIG. Suffixes with indexes from 1 to 15 are expanded. Each suffix is a character string from the index position (start character position) to the end in the text data 200-1 to be searched. For example, for the index “1”, the text data 200-1 to be searched A character string “This code is in the code list” from the first character to the end (15th character) is shown. For the index “10”, the character string “in the list” from the 10th character to the end (15th character) of the text data 200-1 to be searched is shown. For the last index “15”, the last character “RU” is shown.

  Next, in step S11 of FIG. 3, the expanded suffixes are sorted in a predetermined order to create a suffix array. Here, referring to FIG. 4, the suffixes shown in FIG. 4B are sorted, and the suffix array after sorting is shown in FIG. 4C. Sorting is performed by, for example, a character code corresponding to each character (in this example, JIS code). From the first record to the fourth record, the first character is “-” (JIS code = 213C), “A”. It can be seen that the characters are sorted in the order of the character codes such as (JIS code = 2422) and “ga” (JIS code = 242C). The first and second records have the same first and second characters, but the third character differs between “GA” and “RE” (“GA” (JIS code = 242C), “RI” ( JIS code = 256A)), the first record is arranged first. Note that the index shown in FIG. 4B is attached as it is to the corresponding record.

  Next, in step S12 of FIG. 3, one search character string is sequentially determined from the text data. In this case, whether or not the same character string exists in the text data is searched, and all partial character strings in the text data are collated with the text data as search character strings. For example, regarding the text data 200-1 to be searched in FIG. 4, a search character string “ko” to “ru” of one character, a search character string “this”, “noko”,. ‘N’, ‘Yes’, 3 character search strings ‘Kon’, ‘No’, ・ ・ ・, ‘To’, ‘In’, etc. The search character string up to “This code is in the code list”. However, in this case, the search character string of 1 character or 15 characters can be omitted because it has no meaning to collate with the text data 200-1 to be searched. In addition, the character length of the search character string can be limited to a predetermined range.

  Next, in step S13 of FIG. 3, it is determined whether or not all the search character strings to be searched are completed. Here, when all the processes are completed, the character string search process ends. If all of them have not been completed, the suffix array is searched using the search character string as a search key in step S14. Here, referring to FIG. 5, as shown in FIGS. 5A and 5B, a character string “code” of three characters is determined from the text data 200-1 to be searched as a search character string. The search process in the case of being performed is shown. At this time, a binary search is performed on the suffix array of FIG. The suffix array in FIG. 5C is the same as the suffix array shown in FIG. 4C, and FIG. 5C shows a search process by binary search.

  Referring to FIG. 5C, the record (1) (index = 15, character string “RU”) in the center of the suffix array is compared with the search character string “code”. At this time, the JIS code of “ru” is 246B, the JIS code of “ko” is 2533, and “co” is larger, so the record (1) below the record array (1) located in the center of the lower half of the suffix array ( 2) Compare the search character string “code” with (index = 12, character string “is in”). At this time, the JIS code for “G” is 2548, the JIS code for “G” is 2533, and “C” is smaller, so the record (3) ( Index = 7, character string “is in code list”) and search character string “code” are compared.

  Then, since the first three characters of the record (3) match the search character string “code”, the same character string as the search character string is found in the search target text data 200-1. Thereafter, when compared with the upper and lower records of the record (3), the first three characters of the record (4) and the search character string “code” match, so the same character string as the search character string is the text data 200 to be searched. -1 is found. Such a binary search reveals that there are two character strings “code” in the text data 200-1 to be searched (one of which is extracted from the text data 200-1 to be searched). Search string "code" itself).

  Next, in step S15 of FIG. 3, it is determined whether or not a predetermined number of search character strings have been hit. If it is determined that the search character string does not hit the predetermined number, the process proceeds to step S12 in order to perform a search using the next search character string without setting the character string as a candidate for the specific character string. Here, the predetermined number can be determined based on various factors such as the number of characters in the search target text data 200-1 and the number of characters in the search character string. The fact that the predetermined number of hits does not occur indicates that the frequency of appearance of the search character string is low in the text data 200-1 to be searched and is not an important word. Note that at this stage, the appearance frequency may be stored as a specific character string candidate without being evaluated, and finally determined in a subsequent specific character string determination process or the like.

  If it is determined in step S15 that the search character string has been hit by a predetermined number, the process proceeds to step S16, where the character string that matches the search key (search character string) is set as a specific character string candidate, Along with characters, it is stored as one record in the main memory or the like. Here, referring to FIG. 5C, as a search result, the record (3) and the record (4) in which the character string matching the search character string “code” is found at the head are the same as the search character string, respectively. The character string “code” and adjacent characters before and after are stored as one record. For example, for record (3), “GA”, “CODE”, and “RE” are stored as one record. The preceding adjacent character is “GA”, and the subsequent adjacent character is “RE”. For record (4), “no”, “code”, and “ga” are stored as one record. The preceding adjacent character is “no” and the subsequent adjacent character is “ga”.

  As described above, the sentence analysis apparatus according to the present embodiment is configured to find the same character string in the text data at high speed using the suffix array and the binary search as described above. It is not limited to the processing method. It is possible to find the same character string in the text data by a method other than that described above.

<< Description of Difference Degree Determination Process of Sentence Analysis Device According to One Embodiment of Present Invention >>
Next, with reference to FIG. 6 and FIG. 7, the difference degree determination processing of the sentence analysis apparatus according to the embodiment of the present invention will be described in more detail.

  FIG. 6 is a flowchart showing the processing procedure of the difference degree determination processing 120. FIG. 7 is a diagram showing a mechanism for determining the degree of difference between adjacent characters before and after. A character string search process using a search character string “code” as shown in FIG. As a result of performing the search on the target character string, 26 search character strings “codes” are obtained as search results, and the corresponding 26 records are processed.

  First, in step S20 of FIG. 6, a character string search process 110 extracts a record related to one character string from the character string records (including adjacent characters before and after) stored in the search result data 115. Here, referring to FIG. 7A, a record (26 records in total) for the character string “code” stored in the search result data 115 is extracted and expanded in the memory.

  Next, when all the character string records stored in the search result data 115 are acquired in step S21 in FIG. 6 and it is determined that there is no data to be subjected to the different degree determination process, the different degree determination process in FIG. Ends. If all the processes have not been completed in step S21 and all the records have been acquired for one of the character strings stored in the search result data 115, the process proceeds to step S22.

  Next, in step S22 of FIG. 6, all records acquired for one of the character strings stored in the search result data 115 are sorted by the previous adjacent character, and the number of appearance character patterns related to the previous adjacent character is determined. Ask. Here, referring to FIG. 7A, the result of sorting the records (26 in total) acquired for the character string “code” stored in the search result data 115 by the previous adjacent character 211 is shown. . This sorting can be performed using a character code (for example, JIS code) as in the case of creating a suffix array in the character string search process described above. After performing such sorting, the number of appearance character patterns of the previous adjacent character 211 can be determined by counting the number of times the value of the previous adjacent character 211 has changed (breaked) between records. In the case of FIG. 7A, the preceding adjacent character 211 is “”, “(”, “,”, ““ ”,“ ga ”,“ ta ”,“ de ”,“ do ”,“ no ”, There are 13 patterns of “ha”, “be”, “mo”, and “ri”.

  As described above, in the sentence analysis apparatus according to the present embodiment, the previous adjacent character 211 is sorted, and the number of appearance character patterns related to the previous adjacent character is obtained based on whether or not the value has changed between records. The present invention is not limited to the processing method. The number of appearance character patterns can be obtained by various other methods. In addition, it is possible to flexibly set the handling of predetermined characters and character patterns according to specifications. For example, it is possible not to consider control characters such as line feeds and page breaks. You can also consider punctuation marks and punctuation marks, or ignore them. Furthermore, uppercase and lowercase letters can be treated as the same character, or they can be treated as different characters. As for sorting, for 1 byte code characters such as single-byte alphanumeric characters, the corresponding 1 byte is sorted, and for 2 byte code characters such as Kanji, the corresponding 2 bytes are sorted. Also, when sorting the previous adjacent character 211, in this embodiment, one adjacent character is sorted, but it is possible to sort two or more characters and determine the degree of difference between them. .

  Next, in step S23 of FIG. 6, the degree of difference with respect to the previous adjacent character 211 is determined. In this case, the degree of difference is an index indicating how much the adjacent character 211 is different (between the 26 records in FIG. 7A), and thus the appearance character related to the previous adjacent character described above. It is determined based on the number of patterns. The degree of difference may be the number of patterns itself, but can be determined in consideration of, for example, the appearance frequency of a character string (in the case of FIG. 7A, the appearance frequency of “code” is 26). . Also, the degree of difference can be evaluated in a plurality of stages (for example, three stages) using a predetermined threshold. Furthermore, when the adjacent character 211 is a specific character, it is possible to perform arbitrary weighting regarding the count of the character and the determination of the degree of difference.

  Next, in step S24 of FIG. 6, all records acquired for one of the character strings stored in the search result data 115 are sorted by the subsequent adjacent characters, and the number of appearance character patterns related to the subsequent adjacent characters is determined. Ask. Here, referring to FIG. 7B, the result of sorting the records (26 in total) acquired for the character string “code” stored in the search result data 115 by the subsequent adjacent characters 213 is shown. . By such sorting, the records 215 and 216 shown in FIG. 7A are arranged at positions indicated by dotted arrows.

  This sorting can be performed using a character code (for example, JIS code) as in the case of creating a suffix array in the character string search process described above. After performing such sorting, the number of characters appearing in the subsequent adjacent character 213 can be determined by counting the number of times the value of the subsequent adjacent character 213 has changed (breaked) between records. In the case of FIG. 7B, the subsequent adjacent characters 213 are “,”, ““ ”,“ ””, “GA”, “DE”, “TO”, “NI”, “NO”, “HA”. , “O”, “Li”, and “Branch”.

  As described above, in the sentence analysis apparatus according to the present embodiment, the subsequent adjacent characters 213 are sorted, and the number of appearance character patterns related to the subsequent adjacent characters is obtained based on whether or not the value has changed between the records. The present invention is not limited to the processing method. The number of appearance character patterns can be obtained by various other methods. Further, the predetermined character can be excluded from the count of the number of patterns. As for sorting, for 1 byte code characters such as single-byte alphanumeric characters, the corresponding 1 byte is sorted, and for 2 byte code characters such as Kanji, the corresponding 2 bytes are sorted. Further, when sorting the adjacent characters 213 later, in this embodiment, one adjacent character is sorted. However, two or more characters can be sorted and the degree of difference can be determined. .

  Next, in step S25 of FIG. 5, the degree of difference regarding the subsequent adjacent character 213 is determined. In this case, the degree of difference is an index indicating how much the adjacent character 213 is different (between the 26 records in FIG. 7B). It is determined based on the number of patterns. The degree of difference may be the number of patterns itself, but can be determined in consideration of, for example, the appearance frequency of a character string (in the case of FIG. 7B, the appearance frequency of “code” is 26). . Also, the degree of difference can be evaluated in a plurality of stages (for example, three stages) using a predetermined threshold. Furthermore, when the adjacent character 213 is a specific character, arbitrary weighting can be performed with respect to the count of the character and determination of the degree of difference.

  Next, in step S <b> 26 of FIG. 6, the character string to be determined, and the degree of difference related to the previous adjacent character and the degree of difference related to the subsequent adjacent character determined for the character string are stored in the specific character string candidate data 125. Remembered.

  When the process of step S26 in FIG. 6 ends, the process proceeds to step S20, and the next process related to “same character string” is performed.

<< Description of Specific Character String Determination Processing of Sentence Analysis Device According to One Embodiment of the Present Invention >>
In the specific character string determination process, the data stored in the specific character string candidate data 125 is sequentially read out by the different degree determination process, and the corresponding character string is determined based on the determined difference degree between adjacent characters. The determined specific character string is stored in the specific character string data 135. More specifically, it is determined whether or not the corresponding character string is a specific character string according to the degree of difference between the adjacent character characters.

  The degree of difference between the adjacent characters before and after can be determined based on a common or different determination criterion. When the degree of difference between the adjacent characters before and after is determined to be a predetermined size, the corresponding character string is an independent term and is determined as a specific character string that is an important word that identifies the topic. The That is, a score may be calculated based on the degree of difference between the adjacent characters before and after, and based on the score, it may be determined whether or not the corresponding character string is a specific character string.

  In addition, in the specific character string determination process, in addition to the degree of difference between the adjacent character before and after, the character length of the corresponding character string, the appearance frequency of the corresponding character string, the probability / frequency of appearance of the specific character as the previous adjacent character , Calculate the score in consideration of the probability and frequency that a specific character appears as a subsequent adjacent character, the probability and frequency that a specific character combination appears as the adjacent character before and after, and based on the calculated score, You may make it determine whether the corresponding character string is a specific character string.

  Furthermore, if there is a plurality of specific character string candidates in one text data (character string to be searched), it is determined as a specific character string according to the number of candidates and the score distribution calculated for each candidate. It is also possible to change the determination conditions for doing so.

  Furthermore, in the specific character string determination process, when there are a plurality of specific character strings determined for one text data (character string to be searched), ranking is performed among the character strings determined as the specific character strings. Can be. Such ranking is, for example, ranking related to the importance of a character string related to a topic. In addition to the above-described score calculated based on the degree of difference between adjacent characters and the degree of difference between adjacent characters before and after, It is determined on the basis of a score calculated taking into account various factors. Also, such ranking is not only for ordering the importance of character strings determined as specific character strings, but also for indicating the relative importance between specific character strings. Ranking can be performed by specific numerical values by using a score value or the like.

  Such ranking is performed when a plurality of specific character strings are determined. However, the ranking can be performed for a plurality of specific character strings determined with respect to one text data, or grouped according to a predetermined condition. It can also be performed for a plurality of specific character strings determined for a plurality of text data.

  For example, as a plurality of text data grouped according to a predetermined condition, text data of a WEB page group hit with an input search keyword, contents of a user's TWITTER corresponding to a predetermined attribute, and the like can be considered.

<<< Unit for grasping text data and specific character string data >>>
Here, referring to FIG. 8, the text data to be analyzed is understood in what unit, and the specific character string for identifying the topic is determined and ranked accordingly. An example will be described.

  In the example of FIG. 8, the text data 200 includes text data 200a, text data 200b-1, text data 200b-2, text data 200b-3, and text data 200c. It is assumed that the text data is obtained from each of the five WEB pages hit in the search of the WEB page using “setting”. The text data 200a is text data obtained from the WEB page of the site A, and the text data 200b-1, text data 200b-2, and text data 200b-3 are the text data obtained from the WEB page of the site B. It is assumed that the text data 200c is text data obtained from the WEB page of site C.

  The sentence analysis apparatus 400 acquires the text data 200 and determines a specific character string from these. In the first embodiment, the sentence analysis device 400 stores a specific character string as indicated by the specific character string data 135-1. In this example, the sentence analysis apparatus 400 grasps the text data 200a, the text data 200b-1, the text data 200b-2, the text data 200b-3, and the text data 200c as a group of text data, and there are four types of text data. Specific character strings (network, trouble, setting, MAC) were determined and ranked in this order. This is one in which text data to be analyzed for one sentence is extracted by the keyword “network setting”.

  In the second embodiment, the sentence analysis apparatus 400 stores a specific character string as indicated by the specific character string data 135-2. In this example, the sentence analysis apparatus 400 grasps the text data 200a, the text data 200b-1, the text data 200b-2, the text data 200b-3, and the text data 200c as separate text data, and these text data. A specific character string (for example, network, setting, trouble, address for the text data 200a) is determined and ranked for each (each address of the WEB page that is the original data of the text data). In this case, text data obtained with the keyword “network setting” is subjected to sentence analysis for each WEB page of the original data.

  In the third embodiment, the sentence analysis apparatus 400 stores a specific character string as indicated by the specific character string data 135-3. In this example, the sentence analysis apparatus 400 grasps the text data for each site of the WEB page, the text data 200a is group A, the text data 200b-1, the text data 200b-2, and the text data 200b-3 is group B. The text data 200c is group C, and is classified into such three groups. For each group, a specific character string (for example, network, setting, trouble, manual for group A) is determined, Ranked. In this case, text data obtained with the keyword “network setting” is subjected to sentence analysis for each site of the WEB page of the original data.

<<< Explanation of application example in sentence analysis apparatus according to one embodiment of the present invention >>>
Next, with reference to FIG. 9, in the sentence analysis apparatus 400 according to the embodiment of the present invention, the text data 200 is acquired from the search result of the WEB page, and the specific character string determined by the sentence analysis of the text data 200 is obtained. An application example for displaying is described.

  First, the user operates a general WEB browser operating on the search terminal 600 to search for a WEB page. This search is, for example, a generally available Internet search. When a user inputs a search keyword using the WEB browser and presses the search button, a search request is transmitted to the search server 610, where the search server 610 displays a WEB page related to the search keyword based on the received search keyword. The search is performed, and the obtained search result 620 is returned to the search terminal 600. The search result includes the address of the WEB page related to the search keyword (for example, Internet address identification information such as URL).

  When the search result 620 is transmitted to the search terminal 600, the application (application program) 601 operating on the search terminal 600 transmits the search result 620 to the sentence analysis apparatus 400 (for example, by API transmission). When the sentence analysis apparatus 400 receives the search result 620, the sentence analysis apparatus 400 accesses the address of the WEB page included in the search result 620, and acquires the text data 200 from each WEB page.

  Thereafter, the sentence analysis apparatus 400 performs the above-described character string search processing 110, the degree-of-difference determination processing 120, and the specific character string determination processing 130 on the acquired text data 200 to obtain an important specific character string for identifying the topic. It is determined and stored in the specific character string data 135. If a plurality of specific character strings are determined, ranking is performed.

  After determining the specific character string, the sentence analysis apparatus 400 transmits the specific character string display data 300 edited and generated to display the specific character string to the search terminal 600, and the WEB browser of the search terminal 600 Based on the received specific character string display data 300, the specific character string is displayed on the display 602 of the search terminal 600. When the text data 200 is grouped according to a predetermined condition, a ranked specific character string is displayed for each group.

  By such processing of the sentence analysis apparatus 400 and the like, the process from the time when the user inputs a search keyword at the search terminal 600 and instructs the search of the WEB page to the time when the specific character string is displayed on the display 602 is performed instantaneously. In this example, the determined specific character string is stored in the specific character string data 135, and the specific character string data 135 is stored in an external storage device such as a hard disk or a semiconductor memory in consideration of subsequent use. However, if the determined specific character string is merely displayed on the display 602 of the search terminal 600 instantaneously, the specific character string data 135 need only be temporarily stored in RAM, VRAM, or the like.

  In this example, in the search terminal 600, the WEB browser is configured to search the WEB page and display the specific character string display data 300, but the application 601 is configured to have these functions. You can also In addition, the application 601 or the sentence analysis apparatus 400 deletes the address of a part of the WEB page included in the search result 620 (for example, a WEB page having a low association with the search keyword (low rank)) as necessary. You can This is to prevent the extraction of a specific character string having a low relation.

  In this example, the search terminal 600 transmits the address of the WEB page related to the search keyword to the sentence analysis apparatus 400 as the search result 620. The search terminal 600 accesses these WEB pages and obtains the result. The received text data can be transmitted to the sentence analysis apparatus 400 as the search result 620.

  In addition, as described above, when the text data 200 is grouped according to a predetermined condition, a specific character string is displayed for each group. This is because a set of specific character strings (a plurality of characters are included in one group). It is shown that a set of specific character strings (a set of specific character strings exists for each group) is managed. By managing such a set of specific character strings as a set (for example, by finding a common specific character string in a set of different specific character strings), a set of a plurality of specific character strings You can find the connection of a specific character string in.

<<< Description of Configuration of Sentence Analysis Device According to One Embodiment of the Present Invention >>>
Next, with reference to FIG. 10, the structure of the sentence analysis apparatus 400 which concerns on one Embodiment of this invention is demonstrated. The sentence analysis apparatus 400 includes a text data acquisition processing unit 421, a character string search processing unit 422, a different degree determination processing unit 423, a specific character string determination processing unit 424, and a network interface (I / F) unit 425. Furthermore, the specific character string determination processing unit 424 includes a specific character string determination unit 424a and a ranking management unit 424b. In addition, the sentence analysis apparatus 400 stores the specific character string data 135 in a main storage device such as a RAM or an external storage device such as a hard disk or a semiconductor memory.

  The text data acquisition processing unit 421 acquires the text data 200 and provides it to the character string search processing unit 422 (text data acquisition processing 100 shown in FIG. 1). The character string search processing unit 422 performs the character string search processing 110 shown in FIG. The difference degree determination processing unit 423 performs a difference degree determination process 120 shown in FIG. Further, the specific character string determination processing unit 424 determines a specific character string, and stores the determined specific character string in the specific character string data 135 as necessary (specific character string determination processing 130 shown in FIG. 1). . A network interface (I / F) unit 425 controls access to other computers including the search terminal 600 shown in FIG. 9 and data transmission / reception with these computers via a network such as the Internet.

  Further, the specific character string determination unit 424a determines whether or not the same character is the specific character string from the degree of difference between the adjacent characters before and after the same character string included in the text data 200. When a plurality of specific character strings are determined in one text data 200, the ranking management unit 424b ranks the specific character strings.

<<< Description of Hardware Configuration of Sentence Analysis Device According to One Embodiment of the Present Invention >>>
Next, an example of a hardware configuration of a computer used as the sentence analysis apparatus 400 according to an embodiment of the present invention will be described with reference to FIG. However, the sentence analysis apparatus 400 illustrated in FIG. 10 only exemplifies a typical configuration.

  The sentence analysis apparatus 400 includes a CPU (Central Processing Unit) 401, a RAM (Random Access Memory) 402, a ROM (Read Only Memory) 403, a network interface 404, an audio control unit 405, a microphone 406, a speaker 407, a display controller 408, a display. 409, an input device interface 410, a keyboard 411, a mouse 412, an external storage device 413, an external recording medium interface 414, and a bus 415 for connecting these components to each other.

  The CPU 401 controls the operation of each component of the sentence analysis apparatus 400, and under the control of the OS, the text data acquisition process 100, the character string search process 110, the difference degree determination process 120, and the specific character string determination according to the present invention. The execution of the process 130 is controlled.

  The RAM 402 temporarily stores programs for executing the specific character string determination process 130 and the like executed by the CPU 401 and data used during the execution of these programs. The search result data 115, the specific character string candidate data 125, and the specific character string data 135 shown in FIG. 1 can also be temporarily stored in the RAM 402. The ROM 403 stores a program that is executed when the sentence analysis apparatus 400 is activated.

  The network interface 404 is an interface for connecting to the network 500. The network 500 is, for example, a network between the search terminal 600 and the sentence analysis apparatus 400 illustrated in FIG. 9 or a network such as the Internet.

  The audio control unit 405 controls the microphone 406 and the speaker 407 to control audio input / output. The display controller 408 is a dedicated controller for actually processing a drawing command issued by the CPU 401. The display 409 is a display device configured by, for example, an LCD (Liquid Crystal Display) or a CRT (Cathode Ray Tube).

  The input device interface 410 receives signals input from the keyboard 411 and the mouse 412 and transmits a predetermined command to the CPU 401 according to the signal pattern.

  The external storage device 413 is a storage device such as a hard disk or a semiconductor memory, for example. The above-described program and data are recorded in this device, and are loaded from the RAM 402 into the RAM 402 when necessary. For example, the specific character string data 135 shown in FIG. 1 can also be stored in such a storage device.

  The external recording medium interface 414 accesses the external recording medium 510 and reads data recorded therein. The external recording medium 510 is, for example, a portable flash memory, a CD (Compact Disc), a DVD (Digital Versatile Disc), or the like. A program executed by the CPU 401 and realizing each function of the present invention can be provided from the external recording medium 510 via the external recording medium interface 414. Further, as another distribution form of the program for realizing each function of the present invention, a route that is stored in the external storage device 413 or the RAM 402 via a network 500 and a network interface 404 from a predetermined server on the network. Etc. are also conceivable.

  Up to this point, an example of the hardware configuration of the sentence analysis apparatus according to the embodiment of the present invention has been described. However, the hardware configuration of the search terminal 600 illustrated in FIG. 9 is basically the same as the configuration illustrated in FIG. It is. However, regarding the sentence analysis apparatus 400, the audio control unit 405, the microphone 406, the speaker 407, the display controller 408, the display 409, the input device interface 410, the keyboard 411, and the mouse 412 are not essential components. Regarding the search terminal 600, the display 602 corresponds to the display 409, and the audio control unit 405, the microphone 406, and the speaker 407 are not essential components.

  So far, the sentence analysis apparatus according to an embodiment of the present invention has been described with reference to some examples that can implement the present invention. However, these examples are examples for explaining the present invention. However, the scope of rights of the present invention is not limited to these examples. The technical idea of the present invention can be realized by various methods and configurations other than these embodiments.

<<< Outline of Technical Idea in Information Updating Device of the Present Invention >>>
The information update device of the present invention extracts character strings that can be distinguished from text data collected under different collection conditions, stores the extracted character strings in a dictionary corresponding to the text data, and about these dictionaries The comparison result obtained by performing the comparison process is updated. The comparison process is automatically performed when the dictionary is updated.

  In the present specification, a character string that is extracted from text data and that can be identified is referred to as a “related term”. A related term is a character string having a concept different from that of a keyword used for search. Moreover, it is possible to determine the closeness of topics and how to connect them using related words. With such a configuration, the information updating apparatus of the present invention can be applied to more various response systems.

  Text data associated with different dictionaries is text data collected under different collection conditions. These text data are, for example, a plurality of text data collected at different timings for the same target or data source. Or a plurality of text data collected according to different subjects and search conditions at the same timing.

  The above comparison process compares a plurality of dictionaries, and in addition to newly appearing related terms, disappeared related terms, commonly appearing related terms, (in a dictionary corresponding to three or more time-series text data) ) Determine the appearance status of a related term such as a related term that appears again, and store the related term as a comparison result when the related term is one of such appearance statuses.

  Further, when a plurality of related terms are extracted from one text data, these related terms can be associated as one set (as a co-occurrence related term) and stored in a corresponding dictionary. With this configuration, when it is determined in the comparison process that there is a related term common to a plurality of dictionaries, the co-occurrence related terms of the related terms can be compared and further determination can be performed.

  In this way, by capturing the history of the appearance of related terms, the meaning of the related terms can be found out. In other words, by repeating such processing, the topic name to which the related term belongs becomes clear, and the usual related term can be distinguished from the new arrival related term (newly appeared). By the comparison process, it is possible to determine the similarity or difference between topics. Such a function is referred to as a related term learning function. It can be expected that end-user input identification means will be diversified by the related term learning function.

  Further, the text data collected and the related terms extracted from may be any content data. Typical examples include text data of homepages and blogs created on the Internet and published on the Internet, and tweet information of TWITTER (registered trademark). Further, in addition to an individual, it may be data generated and edited in advance by an arbitrary organization or text information in a database. Furthermore, various data such as text data acquired from a voice file / moving image file through voice recognition processing can be used.

  The text data may be data selected from the original data according to a predetermined condition. For example, it may be text data described on a WEB page (homepage) shown as a search result of a keyword search, a sentence described on a user's blog having a certain attribute, tweet information in TWITTER, or the like. One text data may include a plurality of text files (for example, a plurality of WEB pages (HTML files) included in one WEB site), or one text file may be divided. (For example, one of the texts included in one file divided every 10,000 lines).

<<< Description of processing outline of information updating apparatus according to one embodiment of the present invention >>>
With reference to FIG. 12, an outline of processing of the information updating apparatus according to the embodiment of the present invention will be described. First, the information updating apparatus acquires text data 1200 (text data acquisition process 1100). Text data 1200 can be received from various data sources, as described above. Further, the text data 1200 can be acquired by accessing the received network address. Furthermore, when the acquired text data 1200 or the text data 1200 is acquired, a filtering process may be performed so as to acquire only specific text data, or grouping may be performed according to a specific classification.

  Next, the information updating apparatus extracts a character string that can be distinguished from the text data 1200 acquired by the text data acquisition process 1100, and stores the extracted character string in the related term dictionary 1115 (character string extraction process). 1110). The character strings extracted in this way correspond to the above-mentioned related terms, and these related terms are respectively stored in the related terms dictionary 1 to 3 corresponding to the text data 1200 from which the related terms are extracted. Remembered.

  Various methods are conceivable as a method for extracting related terms from the text data 1200. For example, the same character string is searched from the text data 1200, and the character according to the degree of difference between adjacent characters before and after the character string (the number of patterns of the preceding adjacent character and the subsequent adjacent character related to the same character string). There is a way to determine if a sequence is a related term. In addition, morpheme analysis using morpheme data, which has been widely used, can be used.

  In the character string extraction process 1110, related terms are extracted from the plurality of text data 1200 and stored in the corresponding related term dictionary 1115, respectively. For example, the plurality of text data 1200 may be text data collected at different timings for the same target or data source, or may be a plurality of text data collected by different subjects or search conditions at the same timing. . Detailed processing of the character string extraction processing 1110 will be described later.

  Next, the information updating apparatus compares a plurality of related terminology dictionaries 1115 each storing a related term by character string extraction processing 1110 and stores the comparison result in the comparison result data 1125 according to the appearance status of the related term. (Dictionary comparison process 1120).

  For example, when comparing two related terminology dictionaries (related term dictionary 1 and related term dictionary 2) collected at different timings, if there is a related term that does not exist in the related term dictionary 1 but exists in the related term dictionary 2 This is stored in the comparison result data 1125 as a newly-arrived new related term, and conversely, if there is a related term that exists in the related term dictionary 1 but does not exist in the related term dictionary 2, this is deleted. And stored in the comparison result data 1125 as a related term.

  Also, for example, when comparing three related terminology dictionaries (related terms 1 to 3) collected at the same timing for different subjects, if there are related terms existing in all the related terminators dictionaries 1 to 3, And stored in the comparison result data 1125 as a common related term.

  It should be noted that, in a plurality of related terminology dictionaries, the appearance status of the related term is stored in the comparison result data 1125 in a flexible manner according to the response system to which the information updating apparatus of the present invention is applied. can do. Detailed processing of the dictionary comparison processing 1120 will be described in detail later.

<< Description of Character String Extraction Processing of Information Updating Device According to One Embodiment of the Present Invention >>
The character string extraction process 1110 will be described with reference to FIG. FIG. 13 is a flowchart showing the processing procedure of the character string extraction processing 1110. First, in step S110, text data that is a target for extracting related terms is read. As described above, the text data may be any data as long as the text data can be acquired.

  Next, in step S111, a related term which is a character string whose meaning can be identified is extracted from the text data read in step S110. As described above, there are various methods for extracting a related term from text data, including a method based on the degree of difference between adjacent characters and a method using morphological analysis.

  Next, in step S112, when a plurality of related terms are extracted for one text data 1200 in step S111, the plurality of related terms are ranked according to a predetermined criterion. For example, ranking can be performed according to the importance of the related term in the text data 1200, and ranking can be performed according to the character length and appearance frequency of the related term. In the case where the related terms are extracted by a method based on the degree of difference between the adjacent characters before and after, ranking is performed according to the degree of difference between the adjacent characters before and after. The ranking can be performed by various factors in addition to such criteria and combinations thereof. Such “rank” indicates relevance to a topic. Further, even when a plurality of related terms are extracted, it is possible not to perform such ranking.

  Next, in step S113, the related terms ranked in step S112 are stored in the related term dictionary corresponding to the text data 1200. For example, related terms extracted from one text data 1200 are collectively stored in one record, and each related term is stored in a storage position (array entry) according to ranking. By storing the related terms in this way, a plurality of related terms are defined as a set associated with one text data 1200 (text data from which the related terms are extracted). Ranking is to rank related terms in the set.

  In the character string extraction process, when there are a plurality of text data 1200 to be processed, the processes from step S110 to step S113 described above are repeated for each text data 1200.

<< Description of Dictionary Comparison Processing of Information Updating Device According to One Embodiment of the Present Invention >>
The dictionary comparison process 1120 will be described with reference to FIG. FIG. 14 is a flowchart showing the processing procedure of dictionary comparison processing 1120. In this embodiment, related terms are extracted from two text data (text data 1, text data 2) collected as time series data, and the corresponding related terms dictionary (i-1) and related terms dictionary (i) are extracted. It is assumed that the comparison process is performed in the situation stored in.

  First, in step S120, the related terms stored in the related term dictionary (i-1) and the related term dictionary (i) are read. Next, in step S121, the related terms in the related term dictionary (i-1) and the related term dictionary (i) are compared. Among them, the related term dictionary (i-1) does not exist and the related term dictionary (i-1) is not present. ) Are stored in the comparison result data 1125 as newly appearing related terms (new arrival related terms). Each related term dictionary is associated with, for example, a topic name, and the dictionary comparison process 1120 can perform comparison using the topic name. The new arrival related terminology includes the topic name that can represent the corresponding related terminology dictionary, the appearance status (in this case, “new arrival” character indicating that it has newly appeared, a code corresponding thereto, and the like) and comparison result data 1125. Is remembered.

  Next, in step S122, the related terms in the related term dictionary (i-1) and the related term dictionary (i) are compared with each other. Is stored in the comparison result data 1125 as an extinct related term (an extinct related term). Each related terminology dictionary is associated with, for example, a topic name, and an extinction related terminology corresponds to the topic name, appearance status (in this case, “disappearance” indicating new appearance and this) Are stored in the comparison result data 1125.

  Thereafter, in step S123, the contents of the related term dictionary (i-1) are copied to the related term dictionary (i). This is because, at the next timing, the character string extraction process 1110 prepares a related term dictionary (i-1) for storing related terms, and thereafter, this new related term dictionary (i-1) and The related term dictionary (i) to which the content of the related term dictionary (i-1) is copied is compared by the dictionary comparison processing 1120.

  As described above, the character string extraction processing 1110 and the dictionary comparison processing 1120 are repeatedly executed at a predetermined timing, and detailed description thereof will be described later. In addition, by repeatedly performing the dictionary comparison process 1120, the comparison result data 1125 stores the comparison results at the processing timing. When the comparison results are stored, the comparison results are stored before that. Whether the comparison result is erased or stored cumulatively is determined according to the specifications of the applied response system or the like. Further, the comparison result data 1125 may be prepared separately for each dictionary comparison process 1120.

  Although omitted in this example, the related term dictionary (i-1) and the related term dictionary (i) can be compared, and a common related term (common related term) can be stored in the comparison result data 1125. In this case, for example, other related terms (co-occurrence related terms) stored together with the common related term in the related term dictionary (i-1) and others stored together with the common related term in the related term dictionary (i) It is possible to further compare whether or not there is commonality with other related terms (co-occurrence related terms), and to store information regarding the commonality in the comparison result data 1125.

  Further, when comparing the co-occurrence related terms as described above, information on the commonality may be determined in consideration of the ranks associated with the co-occurrence related terms. For example, when co-occurrence related terms having high rank (high importance for the topic indicated by those related terms) are common in the related term dictionary (i-1) and the related term dictionary (i), Commonality can be appreciated more.

<<< Description of Character String Extraction Processing and Dictionary Comparison Processing of Information Updating Device According to One Embodiment of the Present Invention >>>
FIG. 15 shows that the related terms are extracted at different timings by the character string extraction processing 1110 from the five text data (text data 1 to 5) collected in time series from the same WEB page. Are stored in the corresponding related term dictionary (i-1) or the related term dictionary (i), and then the related term dictionary (i-1) and the related term dictionary when the related term dictionary (i) is updated. A dictionary comparison process 1120 is performed for (i), and these processes are periodically performed from time (T = t1) to (T = t5) (time (T = T = It was omitted after t6).

  First, at time (T = t1), a related term is extracted by the character string extraction processing 1110a from the text data 1 collected from a predetermined WEB page at this time, and the extracted related term is related to the related term dictionary (i -1). This character string extraction process 1110a corresponds to the character string extraction process 1110 described with reference to FIG.

  At the next time (T = t2), as in the case of T = t1, a related phrase is extracted from the text data 2 collected from the same WEB page by the character string extraction process 1110b. It is stored in the related term dictionary (i). Here, if there is a change in the topic or description content in the target WEB page, the extracted related terminology also changes accordingly. When a related term is stored in the related term dictionary (i) (updated), the dictionary comparison process 1120a compares the related term dictionary (i-1) with the related term dictionary (i), and In accordance with the appearance status, for example, newly-arrived related words that have newly appeared are stored in the comparison result data 1125. When the comparison process is completed, the contents of the related term dictionary (i) are copied to the related term dictionary (i-1).

  This dictionary comparison process 1120a corresponds to the dictionary comparison process 1120 described with reference to FIG. In this figure, the dictionary comparison processing 1120a is described as being performed at the timing of T = t2, but is performed after the related term dictionary (i) is updated.

  At the next time (T = t3), as in the case of T = t1 and t2, a related term is extracted from the text data 3 collected from the same WEB page by the character string extraction processing 1110c, and the extracted relation The lyrics are stored in the related dictionary (i). Here, if there is a change in the topic or description content in the target WEB page, the extracted related terminology also changes accordingly. When a related term is stored in the related term dictionary (i) (updated), the dictionary comparison process 1120b compares the related term dictionary (i-1) with the related term dictionary (i), and In accordance with the appearance status, for example, newly-arrived related words that have newly appeared are stored in the comparison result data 1125. When the comparison process is completed, the contents of the related term dictionary (i) are copied (saved) to the related term dictionary (i-1).

  Thereafter, the character string extraction processing (1110d, 1110e) and the dictionary comparison processing (1120c, 1120d) are repeated in the same manner, so that the comparison result data 1125 includes the related term dictionary (i-1) and the related term dictionary (i). It is updated at each timing (T = t2 to t5) with the related term obtained as a result of the comparison. Whether only the latest related terms as comparison results are stored or cumulatively stored depends on the specifications of the applied system or the like as described above.

  FIG. 16 shows that the related terms are extracted at different timings by the character string extraction processing 1110 from the five text data (text data 1 to 5) collected in time series from the same WEB page. Are stored in the corresponding related term dictionary (i-1), the related term dictionary (i), or the related term dictionary (i + 1), and then the related term dictionary (i + 1) is updated. Dictionary comparison processing 1120 is performed on i-1), the related term dictionary (i), and the related term dictionary (i + 1), and these processings are performed periodically from time (T = t1) to (T = t5). (The time after time (T = t6) is omitted). The difference from FIG. 15 is that three related terminology dictionaries are used cyclically.

  First, at time (T = t1), a related term is extracted from text data 1 collected from a predetermined WEB page at this time by a character string extraction process 1110f, and the extracted related term is a related term dictionary (i -1).

  At the next time (T = t2), as in the case of T = t1, a related term is extracted from the text data 2 collected from the same WEB page by the character string extraction processing 1110g. It is stored in the related term dictionary (i). Here, if there is a change in the topic or description content in the target WEB page, the extracted related terminology also changes accordingly. Thereafter, at time (T = t3), as in the case of T = t1 and t2, the related terms are extracted from the text data 3 collected from the same WEB page by the character string extraction processing 1110h, and the extracted related terms Is stored in the related term dictionary (i + 1). Here, if there is a change in the topic or description content in the target WEB page, the extracted related terminology also changes accordingly.

  When a related term is stored (updated) in the related term dictionary (i + 1) at time (T = t3), three related term dictionaries (related term dictionary (i-1), related) are compared by the dictionary comparison process 1120f. The dictionary of words (i) and the dictionary of related words (i + 1) are compared, and the related words are stored in the comparison result data 1125 according to the appearance status of the related words. In this embodiment, comparisons are made with respect to three related dictionaries, so as related words to be stored based on changes related to the two related word dictionaries, for example, newly appearing related words and disappearing related words, Some related terms are determined to be stored based on changes across the three related term dictionary. For example, it is a resurrection related verb that once disappeared in the related term dictionary (i) and reappears in the related term dictionary (i + 1). In addition, it is a condition that the frequency of appearance of the related term is memorized in the related term dictionary, but the related term that has rapidly increased in the short term (in the three related term dictionary), Maintains a certain range of appearance frequency as the frequency of appearance of related verbs (in the dictionary dictionary), related verbs in the frequency of appearance again (in the three related terminology dictionaries), and changes in the frequency of appearance of other related terms It is also possible to grasp related terms.

  In the dictionary comparison process 1120f, when the comparison process is completed, the contents of the related term dictionary (i) are copied to the related term dictionary (i-1), and the contents of the related term dictionary (i + 1) are copied to the related term dictionary (i). i) is copied. In this figure, the dictionary comparison process 1120f is described as being performed at the timing of T = t3, but the related term dictionary (i-1) and the related term dictionary (i) are updated. It will be done later.

  At the next time (T = t4), as in the case of T = t1 to t3, a related term is extracted from the text data 4 collected from the same WEB page by the character string extraction processing 1110i, and the extracted relation The lyrics are stored in the related dictionary (i + 1). Here, if there is a change in the topic or description content in the target WEB page, the extracted related terminology also changes accordingly. When a related term is stored in the related term dictionary (i + 1) (updated), three related term dictionaries (the related term dictionary (i-1), the related term dictionary (i), the related terminology) are processed by the dictionary comparison process 1120g. Dictionary (i + 1)) is compared, and related terms are stored in the comparison result data 1125 according to the appearance status of related terms. When the comparison process is completed, the contents of the related term dictionary (i) are copied to the related term dictionary (i-1), and the contents of the related term dictionary (i + 1) are copied to the related term dictionary (i). Is done.

  Thereafter, the character string extraction processing 1110j and the dictionary comparison processing 1120h are similarly repeated, and the comparison result data 1125 compares the related term dictionary (i-1), the related term dictionary (i), and the related term dictionary (i + 1). It is updated at each timing (T = t3 to t5) with the related term obtained as a result. Whether only the latest related terms as comparison results are stored or cumulatively stored depends on the specifications of the applied system or the like as described above.

  The comparison result data 1125 is stored / updated using two related terminology dictionaries in the embodiment of FIG. 15 and three related terminology dictionaries (cyclically) in the example of FIG. You may perform a dictionary comparison process using a related term dictionary. As a result, the appearance status of the related term at more timings can be grasped, and when the appearance status satisfies a predetermined condition, the related term can be stored in the comparison result data 1125.

  FIG. 17 shows the relations extracted from the three text data (text data A to C) collected at the same timing from different WEB pages (WEB pages related to different subjects) by the character string extraction processing 1110. The lyrics are stored in the corresponding related term dictionary A, related term dictionary B, or related term dictionary C, respectively, and then a dictionary comparison process 1120 is performed for these three related term dictionaries. An example in which the period is periodically performed from time (T = t1) to (T = t3) is shown (the time (T = t4) and thereafter are omitted).

  First, at time (T = t1), character string extraction processing 1110k, character string extraction processing 1110m, character from three text data (text data A to C) respectively collected from predetermined different WEB pages at this time The related terminology is extracted by the column extraction process 1110n, and the extracted related terms are stored in the related term dictionary A, the related term dictionary B, and the related term dictionary C, respectively.

  After that, the dictionary comparison process 1120k compares the three related terminology dictionaries (related term dictionary A, related term dictionary B, and related term dictionary C), and the related term etc. is compared with the comparison result data according to the appearance status of the related term. 1125 is stored. In this embodiment, for example, related terms existing in common in three related terms dictionaries are stored in the comparison result data 1125. In this case, the text data A to C are text data collected from WEB pages related to different subjects, and it is better to focus on related terms (common related terms) common to the three related terms dictionaries rather than different related terms. It becomes possible to discover a common topic, and it is often meaningful in that respect.

  In addition, other related terms (co-occurrence related terms) stored together with the common related term in the related term dictionary A, other related terms (co-occurrence related terms) stored together with the common related term in the related term dictionary B, And other related terms (co-occurrence related terms) stored together with the common related term in the related term dictionary C, and further comparing the information on the commonality with the comparison result data. 1125 can be stored.

  Further, when comparing the co-occurrence related terms as described above, information on the commonality may be determined in consideration of the ranks associated with the co-occurrence related terms. For example, if co-occurrence related terms with high rank (high importance for the topic indicated by those related terms) are common in the three related term dictionaries, the commonness of the common related terms can be evaluated more highly.

  Such comparison of the three related term dictionaries at time (T = t1) can be repeatedly performed at time (T = t2). By performing such processing, the comparison result data 1125 can be updated in time series.

  At time (T = t2), similarly to time (T = t1), character string extraction processing is performed from three text data (text data A ′ to C ′) respectively collected from predetermined different WEB pages at this time. 1110k ′, character string extraction processing 1110m ′, and character string extraction processing 1110n ′ extract related terms, and the extracted related terms are stored in the related term dictionary A ′, the related term dictionary B ′, and the related term dictionary C ′, respectively. Is done. In this embodiment, the text data A 'is assumed to be the same WEB page as the text data A or the same subject WEB page. Similarly, the text data B 'is the same WEB page as the text data B or the same WEB page, and the text data C' is the same WEB page as the text data C or the same WEB page.

  After that, the dictionary comparison process 1120k ′ compares three related terminology dictionaries (related term dictionary A ′, related term dictionary B ′, and related term dictionary C ′), and the related terms etc. Is stored in the comparison result data 1125. In this embodiment, for example, related terms existing in common in three related terms dictionaries are stored in the comparison result data 1125.

  Furthermore, at time (T = t3), as with time (T = t1, t2), three text data (text data A ″ to C ″) respectively collected from predetermined different WEB pages at this time. Are extracted by the character string extraction process 1110k ″, the character string extraction process 1110m ″, and the character string extraction process 1110n ″, and the extracted related verbs are the related term dictionary A ″ and the related term dictionary, respectively. B ″ is stored in the related term dictionary C ″. In this embodiment, the text data A ″ is assumed to be the same WEB page as the text data A, the text data A ′, or the same subject WEB page. Similarly, the text data B ″ is the same WEB page as the text data B and text data B ′ or the WEB page of the same subject, and the text data C ″ is the same WEB as the text data C and text data C ′. Page, or WEB page of the same subject.

  Thereafter, the three comparison terms dictionaries (related term dictionary A ″, related term dictionary B ″, and related term dictionary C ″) are compared by the dictionary comparison process 1120 k ″, and according to the appearance status of the related terms. , Related terms and the like are stored in the comparison result data 1125. In this embodiment, for example, related terms existing in common in three related terms dictionaries are stored in the comparison result data 1125.

  In the example of FIG. 17, related terms are extracted based on three text data collected from different WEB pages (WEB pages related to different subjects) at the same timing. Extraction of the lyrics may be performed, or the related lyrics may be extracted from four or more text data.

<< Detailed Description of Character String Extraction Processing and Dictionary Comparison Processing of Information Updating Device According to One Embodiment of the Present Invention >>
Next, an example of the character string extraction process 1110 and the dictionary comparison process 1120 shown in FIG. 16 will be described in more detail with reference to FIG. In FIG. 18, character string extraction processing (1110f, 1110g, 1110h) is performed on three text data (text data 1 to 3), respectively, and the corresponding related term dictionary (i-1) and related term dictionary (i ), A dictionary comparison process 1120f is performed on the related term dictionary (i + 1).

  In this example, the three text data were collected from the same WEB page related to the common subject “stock trading”. For example, a search keyword “stock transaction” is input by WEB search, and three WEB pages obtained as a result are handled as one text data. In FIG. 18, the text data 1 includes text data 1-1 obtained from the first WEB page, text data 1-2 obtained from the second WEB page, and third data at time (T = t1). The text data 1-3 obtained from the WEB page is included. Similarly, the text data 2 includes text data 2-1 obtained from the first WEB page, text data 2-2 obtained from the second WEB page, and third WEB at time (T = t2). The text data 3 is obtained from the second WEB page, the text data 3-1 obtained from the first WEB page at time (T = t3), including the text data 2-3 obtained from the page. Text data 3-2 and text data 3-3 obtained from the third WEB page are included. Here, the URLs of the first WEB page are all the same, the URLs of the second WEB page are all the same, and the URLs of the third WEB page are all the same.

  The character string extraction process 1110f extracts a related term from the text data 1 by a predetermined method at time (T = t1), and stores it in the related term dictionary (i-1). In this embodiment, four related terms are extracted, and each is arranged in order of rank and stored as one record in the related term dictionary (i-1). The ranking of related terms can be determined based on, for example, the appearance frequency. The extracted four related terms (related terms 1 to 4) are “○ company”, “△ bank”, “application” and “account” in order of rank. In morphological analysis, etc., the character string is ascertained by dividing it into the smallest meaningful unit (morpheme), but in other methods, a unit larger than the morpheme (eg sentence or part of sentence) is extracted as a related term sell. A character string composed of a noun and a particle, such as the above-mentioned “Application”, is also extracted as a related particle.

  In this embodiment, four related terms are extracted for each text data, but this is for convenience of explanation (the same applies to the following embodiments). Actually, any number of related terms may be extracted, and the number varies depending on the text data. In the character string extraction process, when a character string is determined as a related term when a threshold is exceeded according to a certain criterion, the number of related terms extracted is changed according to the determination. Also, the number of related terms to be extracted can be fixed, or can be set according to the number of characters of text data.

  The character string extraction process 1110g extracts a related term from the text data 2 by a predetermined method at time (T = t2) and stores it in the related term dictionary (i). In this embodiment, four related terms are extracted, and each is arranged in order of rank and stored as one record in the related term dictionary (i). The ranking of related terms can be determined based on, for example, the appearance frequency. The extracted four related terms (related terms 1 to 4) are “tax rate”, “○ company”, “△ bank”, and “application” in order of rank.

  Similarly, the character string extraction process 1110h extracts a related term from the text data 3 by a predetermined method at time (T = t3) and stores it in the related term dictionary (i + 1). In this embodiment, four related terms are extracted, and each is arranged in order of rank, and is stored as one record in the related term dictionary (i + 1). The ranking of related terms can be determined based on, for example, the appearance frequency. The four extracted related terms (related terms 1 to 4) are “○ company”, “account”, “△ bank”, and “application” in the rank order.

  Next, dictionary comparison processing 1120f is performed on the related term dictionary (i-1), the related term dictionary (i), and the related term dictionary (i + 1). In this embodiment, the dictionary comparison process 1120f detects newly appearing related terms (new arrival related terms), disappeared related terms (disappearing related terms), and again appearing related terms (resurrection related terms). It is assumed that the comparison result data 1125 is stored.

  For example, when the related term dictionary (i-1) and the related term dictionary (i) are compared, the related term “tax rate” has newly appeared in the related term dictionary (i). It has disappeared. Therefore, as shown in the record 1125a in FIG. 19, the relative result “tax rate” and “account” are stored in the comparison result data 1125. Further, the comparison result data 1125 has the same data indicating the appearance status (in this embodiment, “new arrival” for a newly appearing related term and “annihilation” for a disappearing related term in this example). Stored in the record. Furthermore, in this embodiment, “topic name” data for identifying a related term dictionary is stored in order to indicate the timing at which the appearance situation is reached. Each related term dictionary is associated with a topic name and date, and the related term dictionary (i) is associated with a topic name such as “topic of“ stock trading ”on October 10, 2013, t2”. It has been.

  Next, when the related term dictionary (i) and the related term dictionary (i + 1) are compared, the related term “tax rate” disappears in the related term dictionary (i + 1), and the related term “account” is restored. (It exists in the related term dictionary (i-1) and disappears in the related term dictionary (i)). Accordingly, as shown in the record 1125b in FIG. 19, the relative result “account” and “tax rate” are stored in the comparison result data 1125. The comparison result data 1125 includes data indicating the appearance status together with these related terms (in this example, “resurrection” in the case of related terms that reappeared (resurrected), and “disappear” in the case of related terms that have disappeared). ) Is stored in the same record. Furthermore, in this embodiment, “topic name” data for identifying a related term dictionary is stored in order to indicate the timing at which the appearance situation is reached. Each related term dictionary is associated with a topic name and date, and the related term dictionary (i + 1) is associated with a topic name such as “topic of“ stock trading ”on October 10, 2013 at t3”. It has been.

  Next, an example of the character string extraction process 1110 and the dictionary comparison process 1120 shown in FIG. 17 will be described in more detail with reference to FIG. In FIG. 20, character string extraction processing (1110k, 1110m, 1110n) is performed on three text data (text data A to C) at time (T = t1), and the corresponding related term dictionary A and related A dictionary comparison process 1120k is performed for the lyrics dictionary B and the related dictionary dictionary C.

  In this example, the three text data were collected from WEB pages related to different subjects at the same time (T = t1). That is, the text data A is based on a WEB page whose theme is “Technology of Company A”, and the text data B is based on a WEB page whose theme is “Technology of Company B”. C is based on a WEB page whose theme is “AI (artificial intelligence) related technology”.

  For example, regarding the text data A, a search keyword “Technology of Company A” is input by WEB search, and three WEB pages obtained as a result are handled as one text data. Similarly, for the text data B, the search keyword “Technology of company B” is input by WEB search, and the resulting three WEB pages are treated as one text data. For text data C, the WEB search is performed. Thus, the search keyword “AI (artificial intelligence) related technology” is input, and the three WEB pages obtained as a result are handled as one text data.

  In FIG. 20, the text data 1 is related to the subject “Technology of Company A”, the text data A-1 obtained from the first WEB page, the text data A-2 obtained from the second WEB page, The text data A-3 obtained from the third WEB page is included. Similarly, the text data 2 includes text data B-1 obtained from the first WEB page, text data B-2 obtained from the second WEB page, Text data B-3 obtained from three WEB pages, the text data 3 including text data C-1 obtained from the first WEB page related to the subject “AI (Artificial Intelligence) related technology”, It includes text data C-2 obtained from the second WEB page and text data C-3 obtained from the third WEB page.

  The character string extraction process 1110k extracts a related term from the text data A by a predetermined method and stores it in the related term dictionary A. In this embodiment, four related terms are extracted, and each is arranged in order of rank and stored as one record in the related term dictionary A. The ranking of related terms can be determined based on, for example, the appearance frequency. The extracted four related terms (related terms 1 to 4) are “Company A”, “Voice”, “Voice Recognition”, and “Sales” in order of rank.

  The character string extraction process 1110m extracts a related term from the text data B by a predetermined method and stores it in the related term dictionary B. In this embodiment, four related terms are extracted, and each is arranged in order of rank and stored in the related term dictionary B as one record. The ranking of related terms can be determined based on, for example, the appearance frequency. The extracted four related terms (related terms 1 to 4) are “voice”, “research and development”, “business achievements of company B”, and “voice recognition” in order of rank.

  Similarly, the character string extraction process 1110n extracts a related term from the text data C by a predetermined method and stores it in the related term dictionary C. In this embodiment, four related terms are extracted, and each is arranged in order of rank and stored as one record in the related term dictionary C. The ranking of related terms can be determined based on, for example, the appearance frequency. The extracted four related terms (related terms 1 to 4) are “AI”, “robot”, “voice recognition”, and “agent” in order of rank.

  Next, a dictionary comparison process 1120k is performed on the related term dictionary A, the related term dictionary B, and the related term dictionary C. In this embodiment, the dictionary comparison process 1120k detects related terms common to the three dictionaries (common related terms) and stores them in the comparison result data 1125.

  When the related term dictionary A, the related term dictionary B, and the related term dictionary C are compared, it is recognized that the above-mentioned related terms are stored, and “speech recognition” exists as a common related term. Therefore, this “voice recognition” is stored in the comparison result data 1125.

  By grasping such common related terms, it is possible to effectively realize analysis of related information between companies. For example, a related terminology frequently used in the description about the technology of company A is extracted by the character string extraction process 1110k based on the text data A, and a related terminology frequently used in the description about the technology of company B is extracted into the text data B. A and B companies are extracted by a character string extraction process 1110m based on text data C, and extracted by a character string extraction process 1110n based on text data C. However, it is possible to objectively understand what AI-related technologies may have commonality.

  In the embodiment shown in FIG. 20, at the same time (T = t1), the related terminology dictionaries based on the text data collected from the WEB pages related to different subjects are compared. Although it was collected by intentional WEB search, as a result of comparing the related terminology dictionaries obtained from WEB pages collected by chance, there may be cases where common related terms are found by chance. .

  Next, another example of character string extraction processing 1110 and dictionary comparison processing 1120 in the information updating apparatus according to an embodiment of the present invention will be described with reference to FIG. FIG. 21 shows a modification of the character string extraction process 1110 and the dictionary comparison process 1120 shown in FIG. In FIG. 21, character string extraction processing 1110 is performed for two text data (text data 1 and text data 2), and the corresponding related term dictionary (i-1) and related term dictionary (i) are processed. In this manner, the dictionary comparison process 1120 is performed. The display related to the text data 3 shown in FIG. 18 is omitted.

  In this example, the two text data were collected from the same WEB page associated with the common subject "stock trading". For example, a search keyword “stock transaction” is input by WEB search, and three WEB pages obtained as a result are set as one text data, but related terms are extracted for each WEB page unit. As a result, related terms are managed for each WEB page, but three text data based on three WEB pages may be prepared, and related terms may be extracted for each text data. Here, it is important that the related terms are extracted from a plurality of text data.

  In FIG. 21, text data 1 includes text data 1-1 obtained from the first WEB page, text data 1-2 obtained from the second WEB page, and third data at time (T = t1). The text data 1-3 obtained from the WEB page is included. Similarly, the text data 2 includes text data 2-1 obtained from the first WEB page, text data 2-2 obtained from the second WEB page, and third WEB at time (T = t2). It includes text data 2-3 obtained from the page. Here, the URLs of the first WEB page are all the same, the URLs of the second WEB page are all the same, and the URLs of the third WEB page are all the same.

  The character string extraction process 1110 extracts related terms from the text data 1 by a predetermined method at time (T = t1). As described above, this is performed for each text data included in the text data 1. For example, a related term is extracted from the text data 1-1 by a predetermined method, and related text is extracted from the text data 1-2 by a predetermined method. The lyrics are extracted, and the related words are extracted from the text data 1-3 by a predetermined method. In this embodiment, four related terms are extracted for each, and each related term is arranged in rank order. The ranking of related terms can be determined based on, for example, the appearance frequency. Regarding the text data 1-1, the extracted four related terms (related terms 1 to 4) are “○ company”, “account”, “application procedure”, and “Δ bank” in rank order. Regarding the text data 1-2, the extracted four related terms (related terms 1 to 4) are “account”, “Δ bank”, “application”, and “◇ sha” in order of rank. Regarding the text data 1-3, the extracted four related terms (related terms 1 to 4) are “buy stock”, “Δ bank”, “limit”, and “○ company” in order of rank.

  Next, the character string extraction process 1110 obtains neighborhood related terms for each of the related terms extracted in this way, and stores them in the related term dictionary (i-1). A neighborhood related terminator is a related term that appears (co-occurs) with a related term when a particular related term is focused. In each text data (1-1, 1-2, 1-3), the set of related terms included in the topic corresponding to the text data is a set of related terms. A set of related terms including related terms is referred to as a neighborhood of related terms, and a set of neighborhoods of related terms is referred to as a neighborhood system of related terms. In the related term dictionary (i-1), a neighborhood system of related terms is stored for each related term.

  For example, focusing on the related term “○ Company”, this related term is extracted for the text data 1-1, and the neighborhood of the related term is {○ Company, Account, Application Procedure, ΔBank}. Similarly, this related term is extracted for the text data 1-3, and the neighborhood of the related term is {stock purchase, Δbank, limit, ○ company}. From these, for the related term “○ Company”, the neighborhood system of the related term is {○ Company, account, stock purchase, △ bank, application procedure, limit}} (the neighborhood of the related term for text data 1-1) And only one related term “Δ bank” is duplicated in the vicinity of the related term for the text data 1-3).

  The relative system of the related terms thus obtained is the related terms “○ Company”, “Account”, “△ Bank”, “Application procedure”, “Stock purchase”, “Application is”, “Limit price”, “ ◇ Company ”is stored in the related term dictionary (i-1). For each related terminology, the related system of the related terms (neighboring related terms 1 to 7) is stored, and the order of these is determined by the ranking performed by the character string extraction processing 1110, the high co-occurrence, etc. Determined in consideration of

  Further, the character string extraction process 1110 similarly extracts related terms from the text data 2 by a predetermined method at time (T = t2). As described above, this is performed for each text data included in the text data 2, and for example, related words are extracted from the text data 2-1 by a predetermined method, and related by a predetermined method from the text data 2-2. The lyrics are extracted, and the related words are extracted from the text data 2-3 by a predetermined method. In this embodiment, four related terms are extracted for each, and each related term is arranged in rank order. The ranking of related terms can be determined based on, for example, the appearance frequency. Regarding the text data 2-1, the extracted four related terms (related terms 1 to 4) are "○ company", "account", "new system", and "application procedure" in order of rank. Regarding the text data 2-2, the extracted four related terms (related terms 1 to 4) are “account”, “Δ bank”, “◇ company”, “buy stock” in order of rank. Regarding the text data 2-3, the extracted four related terms (related terms 1 to 4) are “stock purchase”, “Δ bank”, “○ company”, and “new system” in order of rank.

  Next, the character string extraction process 1110 obtains the neighborhood related words for each of the related words extracted in this way, and stores them in the related word dictionary (i). For example, paying attention to the related term “○ Company”, this related term is extracted for the text data 2-1, and the neighborhood of the related term is {○ Company, account, new system, application procedure}. Similarly, this related term is extracted for the text data 2-3, and the neighborhood of the related term is {stock purchase, Δbank, ○ company, new system}. From these, for the related term "○ Company", the neighborhood system of the related term is {○ Company, account, stock purchase, new system, application procedure, △ bank} (the related terms for Text Data 2-1 Only one related term “new system” that overlaps the neighborhood and the neighborhood of the related term for the text data 2-3 is included).

  The related system of the related terms obtained in this way is the related terms “○ Company”, “Account”, “△ Bank”, “Application Procedure”, “Stock Purchase”, “New System”, “◇ Company”. Are stored in the related term dictionary (i). For each related terminology, the related system of the related terms (neighboring related terms 1 to 6) is stored, and the order of these is determined by the ranking performed by the character string extraction processing 1110, the high co-occurrence, etc. Determined in consideration of

  Next, the related term dictionary (i-1) and the related term dictionary (i) are compared by the dictionary comparison processing 1120. As a result, the related terms “limit” and “application” are disappearing related terms that have disappeared at time (T = t2) (see reference numeral 1133 in FIG. 21), and the related term “new system” is time (T = t2), which are new arrival related terms (see reference numeral 1132 in FIG. 21), and these related terms are compared result data 1125 as changes between the related term dictionary (i-1) and the related term dictionary (i). Is remembered.

  Further, the dictionary comparison process 1120 is performed for the related terms “○ Company”, “Account”, “△ Bank”, “Application procedure”, “Stock purchase”, and “◇ Company”, with time (T = t1) and time. Although it is a related term which exists in both (T = t2), it compares also about the neighborhood related terminator of each related term. Then, it can be seen that the neighborhood related terms (or the order of the neighborhood related terms) are changed (see reference numeral 1131 in FIG. 21). This indicates that the relationship and position of the related terminology in the topic are changing. When a response system or the like to which the information updating apparatus is applied tries to visualize such a change in the neighborhood related terms, the information is also stored in the comparison result data 1125.

  Next, another example of character string extraction processing 1110 and dictionary comparison processing 1120 in the information updating apparatus according to an embodiment of the present invention will be described with reference to FIG. FIG. 22 shows a modification of the character string extraction process 1110 and the dictionary comparison process 1120 shown in FIG. In FIG. 22, a character string extraction process 1110 is performed for each of the three text data (text data A to C), and the corresponding related term dictionary A, related term dictionary B, and related term dictionary C are compared with the dictionary. The comparison process 1120 is shown.

  In this example, the three text data were collected from the same WEB page associated with different subjects at the same time (T = t1). That is, the text data A is based on a WEB page whose theme is “Technology of Company A”, and the text data B is based on a WEB page whose theme is “Technology of Company B”. C is based on a WEB page whose theme is “AI (artificial intelligence) related technology”.

  For example, for text data A, a search keyword “Technology of Company A” is input by WEB search, and two text data (text data A-1 and text data A-2 are obtained from two WEB pages obtained as a result. ) And are individually handled in the character string extraction process 1110. Similarly, for text data B, a search keyword “Technology of company B” is input by WEB search, and two text data (text data B-1, text data B-) are obtained from the two WEB pages obtained as a result. 2) are acquired and handled individually in the character string extraction processing 1110. Similarly, with respect to the text data C, a search keyword “AI (artificial intelligence) related technology” is input by WEB search, and two text data (text data C-1, text) are obtained from two WEB pages obtained as a result. Data C-2) is acquired and handled individually in the character string extraction processing 1110. In FIG. 20, text data A, text data B, and text data C each include three text data. In this embodiment, it is assumed that each text data includes two text data.

  The character string extraction process 1110 extracts related terms from the text data A by a predetermined method at time (T = t1). As described above, this is performed for each text data included in the text data A. For example, related words are extracted from the text data A-1 by a predetermined method, and related text is extracted from the text data A-2 by a predetermined method. The lyrics are extracted. In this embodiment, four related terms are extracted for each, and each related term is arranged in rank order. The ranking of related terms can be determined based on, for example, the appearance frequency. Regarding the text data A-1, the extracted four related terms (related terms 1 to 4) are “Company A”, “speech”, “speech recognition”, and “robot” in order of rank. Regarding the text data A-2, the extracted four related terms (related terms 1 to 4) are “compression technology”, “speech recognition”, “sales”, and “speech” in order of rank.

  Next, the character string extraction processing 1110 obtains the neighborhood related words for each of the related words extracted in this way, and stores them in the related word dictionary A. A neighborhood related terminator is a related term that appears (co-occurs) with a related term when a particular related term is focused. In each text data (A-1, A-2), a set of related terms included in a topic corresponding to the text data is a related term set. A set of related terms is called a neighborhood of related terms, and a set of neighborhoods of related terms is called a neighborhood system of related terms. In the related term dictionary A, a neighborhood system of related terms is stored for each related term.

  For example, paying attention to the related term “speech recognition”, this related term is extracted for the text data A-1, and the neighborhood of the related term is {Company A, speech, speech recognition, robot}. Similarly, this related term is extracted for the text data A-2, and the neighborhood of the related term is {compression technology, speech recognition, sales, speech}. From these, for the related term “speech recognition”, the neighborhood system of the related term is {speech recognition, company A, compression technology, speech, robot, business} (the neighborhood of the related term for the text data A-1 and Only one related terminology “speech” that overlaps with the neighborhood of the related term for the text data A-2 is included).

  The neighborhood system of the related terms thus obtained is stored in the related term dictionary A for the related terms “Company A”, “speech recognition”, “speech”, “compression technology”, “sales”, and “robot”. The For each related terminology, the neighborhood system of the related terms (neighboring related terms 1 to 5) is stored, and the order of these is determined by the ranking performed by the character string extraction processing 1110, the high co-occurrence, etc. Determined in consideration of

  Further, the character string extraction process 1110 extracts related terms from the text data B by a predetermined method at time (T = t1). As described above, this is performed for each text data included in the text data B. For example, related words are extracted from the text data B-1 by a predetermined method, and related words are extracted from the text data B-2 by a predetermined method. The lyrics are extracted. In this embodiment, four related terms are extracted for each, and each related term is arranged in rank order. The ranking of related terms can be determined based on, for example, the appearance frequency. Regarding the text data B-1, the extracted four related terms (related terms 1 to 4) are “voice”, “business achievements of B company”, “voice recognition”, and “research and development” in order of rank. Regarding the text data B-2, the extracted four related terms (related terms 1 to 4) are “research and development”, “speech”, “speech recognition”, and “authentication technology” in order of rank.

  Next, the character string extraction processing 1110 obtains the neighborhood related words for each of the related words extracted in this way, and stores them in the related word dictionary B. For example, focusing on the related term “speech”, this related term is extracted for the text data B-1, and the neighborhood of the related term is {speech, achievement of company B, speech recognition, research and development}. Similarly, this related term is extracted for the text data B-2, and the neighborhood of the related term is {R & D, speech, speech recognition, authentication technology}. From these, for the related term “speech”, the neighborhood system of the related term is {speech, research and development, achievement of company B, speech recognition, authentication technology} (the neighborhood of the related term for the text data B-1, Only one of the related terms “speech recognition” and “research and development” that overlap in the vicinity of the related term for the text data B-2 is included).

  The related system of the related terms thus obtained is stored in the related term dictionary B for the related terms “speech”, “research and development”, “business achievements of company B”, “speech recognition”, and “authentication technology”. . For each related terminology, the neighborhood system of the related terms (neighboring related terms 1 to 4) is stored, and the order of these is determined by the ranking performed by the character string extraction processing 1110, the high co-occurrence, etc. Determined in consideration of

  Furthermore, the character string extraction process 1110 extracts a related term from the text data C by a predetermined method at time (T = t1). As described above, this is performed for each text data included in the text data C. For example, a related term is extracted from the text data C-1 by a predetermined method, and related text is extracted from the text data C-2 by a predetermined method. The lyrics are extracted. In this embodiment, four related terms are extracted for each, and each related term is arranged in rank order. The ranking of related terms can be determined based on, for example, the appearance frequency. Regarding the text data C-1, the extracted four related terms (related terms 1 to 4) are “AI”, “agent”, “robot”, and “voice recognition” in rank order. Regarding the text data C-2, the extracted four related terms (related terms 1 to 4) are “robot”, “voice recognition”, “AI”, and “learning function” in order of rank.

  Next, the character string extraction processing 1110 obtains the neighborhood related words for each of the extracted related words, and stores them in the related word dictionary C. For example, focusing on the related term “AI”, this related term is extracted for the text data C-1, and the neighborhood of the related term is {AI, agent, robot, speech recognition}. Similarly, this related term is extracted for the text data C-2, and the neighborhood of the related term is {robot, voice recognition, AI, learning function}. From these, for the related term “AI”, the neighborhood system of the related term is {AI, robot, agent, speech recognition, learning function} (the neighborhood of the related term for the text data C-1 and the text data C− Only one of the related terms “robot” and “speech recognition” that overlap in the vicinity of the related term for 2 is included).

  The neighborhood system of the related terms thus obtained is stored in the related term dictionary C for each of the related terms “AI”, “robot”, “speech recognition”, “agent”, and “learning function”. For each related terminology, the neighborhood system of the related terms (neighboring related terms 1 to 4) is stored, and the order of these is determined by the ranking performed by the character string extraction processing 1110, the high co-occurrence, etc. Determined in consideration of

  Next, the dictionary comparison process 1120 compares the related term dictionary A to C. As a result, the related term “speech recognition” is a related term (common related term) common to three related term dictionaries at time (T = t1) (see reference numerals 1135, 1135 ′, 1135 ″ in FIG. 22). This is stored in the comparison result data 1125. By grasping such common related terms, common topics can be found from different themes, and setting the subject as in this embodiment also leads to analysis of related information between companies.

  In addition, the dictionary comparison process 1120 compares the common related terms with the neighboring related terms of each related term. Then, it is possible to grasp the commonality of neighboring related terms, the commonality of the order of neighboring related terms, and the like, thereby determining the level of commonality between the common related terms.

  Note that “speech” can be grasped as a common related terminology in the related term dictionary A and the related term dictionary B (see reference numerals 1136 and 1136 ′ in FIG. 22). Since it may be important information, it can be stored in the comparison result data 1125.

<<< Overview of Information Updating System Including Information Updating Device According to One Embodiment of the Present Invention >>>
Next, with reference to FIG. 23, an example of a series of processes by the information update system including the information update apparatus according to the embodiment of the present invention will be described.

  An information update system 1300 illustrated in FIG. 23 includes an information update device 1400, a search processing device 1600, and a user terminal 1700. The information update device 1400 stores the related term dictionary 1115 and the comparison result data 1125 in the storage means. The crawler 1601 that operates in the search processing device 1600 is automatically activated, for example, and performs topic analysis on a topic name determined at a predetermined time (performs a search and collects topics regularly). The topic name is stored in, for example, a service (an area assigned to a service ID corresponding to each topic handled by the user) that holds the related term dictionary 1115, and the user wants to handle ten topics. These services will be handled using 10 services. In addition, for each of the services described above, a corresponding topic chip is set, each topic chip always collects information on the corresponding topic, and related topic chips are linked and integrated according to user input. It is also possible to realize more diverse topic providing services.

  The search by the crawler 1601 is performed by, for example, accessing an existing Internet search site on the Internet and specifying a search keyword there to receive a search result 1620 from the search server 1610 of the Internet search site. The search result 1620 includes, for example, the address of a WEB page that includes content that matches or is similar to the search keyword (the address of WEB page 1, the address of WEB page 2, the address of WEB page 3,..., WEB page X Address).

  In this embodiment, the crawler 1601 acquires a search result 1620 by executing a search on an existing Internet search site. However, by using various other methods, the address of a WEB page that satisfies a predetermined condition can be obtained. Can be acquired. The search target is not limited to the WEB page on the Internet. It can be tweet information from TWITTER, data generated and edited in advance by any institution (network or local) and text information in the database. There may be.

  An existing Internet search site uses a search engine provided in the search server 1610 to search for an address of a WEB page that matches or is similar to a search keyword from a data source on the Internet in response to a search request (or in advance on a regular basis). Collect by collection activity).

  When the search result 1620 is transmitted from the search server 1610, the crawler 1601 transmits the search result 1620 (for example, by API transmission) to the information update device 1400 by the application running on the crawler 1601 or the search processing device 1600. To do. Further, the crawler 1601 can be configured to exclude a search condition 1620 that satisfies a predetermined condition using a filter.

  In this embodiment, the crawler 1601 is automatically activated at a predetermined time, but the search result 1620 may be acquired in accordance with the operation control of the information update device 1400. In addition, the crawler 1601 acquires the search result 1620 at a predetermined interval, holds the search result 1620 in the storage unit of the search processing device 1600, and the information update device 1400 stores the storage unit of the search processing device 1600 at a necessary timing. To obtain a search result 1620. Further, the information update device 1400 and the search processing device 1600 can be configured by one server.

  In this embodiment, the search processing device 1600 transmits the address of the WEB page related to the search keyword to the information update device 1400 as the search result 1620. The search processing device 1600 accesses these WEB pages, The text data obtained as a result can be transmitted to the information update device 1400 as a search result 1620.

  Upon receiving the search result 1620, the information updating apparatus 1400 accesses the address of the WEB page included in the search result 1620, and each WEB page (WEB page 1, WEB page 2, WEB page 3,..., WEB Text data 1200 is acquired from page X). The search result 1620 may include a plurality of WEB page addresses that satisfy the search conditions. If these are ranked according to the satisfaction of the search conditions, the text data 1200 for WEB pages of a predetermined rank or higher is included. You can also get

  Upon obtaining the text data 1200, the information update device 1400 extracts related terms from the text data 1200 by a character string extraction process 1110, and stores them in the corresponding related term dictionary 1115. Thereafter, the information update device 1400 performs a dictionary comparison process 1120 on two or more related terminology dictionaries 1115 and stores the comparison results in the comparison result data 1125. The dictionary comparison process 1120 is automatically started when, for example, all of the related terms are stored in the related term dictionary 1115 to be compared.

  The user terminal 1700 is a computer used by the user of the information update system 1300. Here, a response system that automatically responds to user input includes an application 1701 that operates on the user terminal 1700 and an information update device 1400. Built between.

  When the user terminal 1700 requests display of a comparison result obtained by comparing predetermined related terminology dictionaries directly or according to a response scenario selected by the application 1701, the user terminal 1700 updates the information. A comparison result display request is transmitted to the device 1400. When the information update apparatus 1400 receives this comparison result display request, the information update apparatus 1400 acquires corresponding comparison result data from the comparison result data 1125 and transmits it to the user terminal 1700 accordingly.

  The user terminal 1700 receives the comparison result data 1125 transmitted from the information update device 1400, edits the data to be displayed on the display 1702 of the user terminal 1700 (for example, an HTML file configured to display the display result) Edit) to generate comparison result display data 1150. The comparison result display data 1150 may be generated by the information update device 1400 and received by the user terminal 1700 for display.

  Thereafter, in the user terminal 1700, the application 1701 or WEB browser that has received the comparison result display data 1150 interprets the comparison result display data 1150, and displays the comparison result requested by the comparison result display request on the display 1702. This display indicates, for example, a topic name and a change in related terms in the topic. As the display of the change of the related term, the appearance state of the related term and the corresponding related term are displayed.

  In the example of FIG. 23, the topic name “October 10, 2013, topic of“ stock trading ”at t2”, the related term “tax rate” whose appearance status is “new arrival related term”, and the appearance status are The related term “account” which is the “annihilation related term” is displayed. This display corresponds to the record 1125a of the comparison result data 1125 shown in FIG. The user looks at the content displayed on the display 1702, and in the topic related to the topic name, a new related term “tax rate” appears at the timing t2, and at the same time, the related term “account” disappears. Can be noticed.

<<< Description of Configuration of Information Updating Device According to One Embodiment of the Present Invention >>>
Next, with reference to FIG. 24, the structure of the information update apparatus 1400 which concerns on one Embodiment of this invention is demonstrated. The information update apparatus 1400 includes a text data acquisition processing unit 1421, a character string extraction processing unit 1422, a dictionary comparison processing unit 1423, a comparison result display control unit 1424, and a network interface (I / F) unit 1425.

  The information update device 1400 stores the related term dictionary 1115 and the comparison result data 1125 in a main storage device such as a RAM or an external storage device such as a hard disk or a semiconductor memory. The related term dictionary 1115 and the comparison result data 1125 can take various data formats and data storage formats.

  The text data acquisition processing unit 1421 receives the search result 1620 in the Internet search site acquired by the crawler 1601 shown in FIG. Text data 1200 is acquired from the address of the WEB page included in the search result 1620 and provided to the character string extraction processing unit 1422 (text data acquisition processing 1100 shown in FIG. 12). The character string extraction processing unit 1422 extracts a related term from the text data 1200 and stores it in the corresponding related term dictionary 1115 (character string extraction processing 1110 shown in FIG. 12). The dictionary comparison processing unit 1423 compares the plurality of related terminology dictionaries 1115 and stores the comparison results in the comparison result data 1125 (dictionary comparison processing 1120 shown in FIG. 12).

  In response to a comparison result display request from the user terminal 1700, the comparison result display control unit 1424 acquires a corresponding comparison result from the comparison result data 1125, generates comparison result display data 1150, and transmits the comparison result display data 1150 to the user terminal 1700. A network interface (I / F) unit 1425 controls access to other computers including the search processing device 1600 and the user terminal 1700 shown in FIG. 23 and data transmission / reception with these computers via a network such as the Internet. To do.

<<< Description of Hardware Configuration of Information Updating Device According to One Embodiment of the Present Invention >>>
Next, an example of a hardware configuration of a computer used as the information update device 1400 according to an embodiment of the present invention will be described with reference to FIG. However, the information update device 1400 illustrated in FIG. 25 merely illustrates a typical configuration.

  The information updating apparatus 1400 includes a CPU (Central Processing Unit) 1401, a RAM (Random Access Memory) 1402, a ROM (Read Only Memory) 1403, a network interface 1404, an audio control unit 1405, a microphone 1406, a speaker 1407, a display controller 1408, a display. 1409, an input device interface 1410, a keyboard 1411, a mouse 1412, an external storage device 1413, an external recording medium interface 1414, and a bus 1415 for connecting these components to each other.

  The CPU 1401 controls the operation of each component of the information update device 1400, and under the control of the OS, the text data acquisition process 1100, the character string extraction process 1110, the dictionary comparison process 1120, the comparison result display control, etc. according to the present invention. Control execution.

  The RAM 1402 temporarily stores programs for executing the dictionary comparison process 1120 and the like executed by the CPU 1401 and data used during the execution of these programs. Further, as described above, the related term dictionary 1115, the comparison result data 1125, and the like can also be stored. The ROM 1403 stores a program that is executed when the information updating apparatus 1400 is activated.

  The network interface 1404 is an interface for connecting to the network 1500. The network 1500 is, for example, a network between the search processing device 1600 and the user terminal 1700 and the information update device 1400 shown in FIG. 23, or a network such as the Internet.

  The audio control unit 1405 controls the microphone 1406 and the speaker 1407 to control audio input / output. A display controller 1408 is a dedicated controller for actually processing a drawing command issued by the CPU 1401. The display 1409 is a display device configured by, for example, an LCD (Liquid Crystal Display) or a CRT (Cathode Ray Tube).

  The input device interface 1410 receives a signal input from the keyboard 1411 or the mouse 1412 and transmits a predetermined command to the CPU 1401 according to the signal pattern.

  The external storage device 1413 is, for example, a storage device such as a hard disk or a semiconductor memory. The above-described program and data are recorded in this device, and are loaded from there into the RAM 1402 as necessary at the time of execution. For example, as described above, the related term dictionary 1115, the comparison result data 1125, and the like can also be stored.

  The external recording medium interface 1414 accesses the external recording medium 1510 and reads data recorded therein. The external recording medium 1510 is, for example, a portable flash memory, a CD (Compact Disc), a DVD (Digital Versatile Disc), or the like. A program executed by the CPU 1401 and realizing each function of the present invention can be provided from the external recording medium 1510 via the external recording medium interface 1414. Further, as another distribution form of the program for realizing each function of the present invention, a route in which the program is stored in the external storage device 1413 or the RAM 1402 from a predetermined server on the network via the network 1500 and the network interface 1404. Etc. are also conceivable.

  An example of the hardware configuration of the information updating apparatus according to the embodiment of the present invention has been described, but the hardware configuration of the search processing apparatus 1600 and the user terminal 1700 illustrated in FIG. 23 is basically the same as that illustrated in FIG. It is the same. However, regarding the information update device 1400 and the search processing device 1600, the audio control unit 1405, the microphone 1406, the speaker 1407, the display controller 1408, the display 1409, the input device interface 1410, the keyboard 1411, and the mouse 1412 are essential components. It is not an element. Regarding the user terminal 1700, the display 1702 corresponds to the display 1409, and the audio control unit 1405, the microphone 1406, and the speaker 1407 are not essential components.

  So far, the information updating apparatus according to an embodiment of the present invention has been described with reference to some examples that can implement the present invention, but these examples are examples for explaining the present invention. However, the scope of rights of the present invention is not limited to these examples. The technical idea of the present invention can be realized by various methods and configurations other than these embodiments.

DESCRIPTION OF SYMBOLS 100 Text data acquisition process 110 Character string search process 120 Difference degree determination process 130 Specific character string determination process 200 Text data 400 Sentence analysis apparatus 421 Text data acquisition process part 422 Character string search process part 423 Difference degree determination process part 424 Specific character string Decision processing unit 1100 Text data acquisition processing 1110 Character string extraction processing 1120 Dictionary comparison processing 1200 Text data 1300 Information update system 1400 Information update device 1421 Text data acquisition processing unit 1422 Character string extraction processing unit 1423 Dictionary comparison processing unit 1424 Comparison result display control Part

Claims (4)

A character string search means for searching for the same character string from text data;
For the same character string, a different degree determination means for determining a difference degree of a preceding adjacent character and a difference degree of a subsequent adjacent character;
The degree of importance of the same character string is determined based on the degree of difference between the preceding adjacent characters, the degree of difference between the subsequent adjacent characters, and the appearance frequency of the same character string in the text data, and the same character string is identified. Specific character string determining means for determining whether or not the character string,
The specific character string determining means includes
In group including a plurality of different text data, if included is a plurality of specific character strings, based on the importance for each specific character string, performs the ranking of a specific character string in the previous Kigu the loop, the a plurality of the specific character string, before sentence analyzing unit and to store in association with Kigu loop. The specific character string determining means further includes
The sentence according to claim 1, wherein importance of the same character string is determined based on a character length of the same character string, and whether or not the same character string is a specific character string is determined. Analysis device. A string search step for searching for the same string from text data;
For the same character string, a different degree determination step for determining a difference degree of a preceding adjacent character and a difference degree of a subsequent adjacent character;
The degree of importance of the same character string is determined based on the degree of difference between the preceding adjacent characters, the degree of difference between the subsequent adjacent characters, and the appearance frequency of the same character string in the text data, and the same character string is identified. A specific character string determining step for determining whether the character string is a character string,
The specific character string determining step includes:
In group including a plurality of different text data, if included is a plurality of specific character strings, based on the importance for each specific character string, performs the ranking of a specific character string in the previous Kigu the loop, the sentence analyzing method characterized in that in association plurality of specific character strings, before Kigu loop. On the computer,
String search means for searching for the same string from text data,
For the same character string, a different degree determination means for determining a difference degree of a preceding adjacent character and a difference degree of a subsequent adjacent character, and
The degree of importance of the same character string is determined based on the degree of difference between the preceding adjacent characters, the degree of difference between the subsequent adjacent characters, and the appearance frequency of the same character string in the text data, and the same character string is identified. A program that functions as a specific character string determining means for determining whether or not a character string,
The specific character string determining means includes
In group including a plurality of different text data, if included is a plurality of specific character strings, based on the importance for each specific character string, performs the ranking of a specific character string in the previous Kigu the loop, the a program characterized by a plurality of specific character string, in association previously Kigu loop.

Images