JP2019149145A - Information search system - Google Patents

Abstract

To provide a more precise information search system which can detect a search target.SOLUTION: An information search system 10 includes: an input device 11 for receiving an input of a search phrase; a feature word generation unit 24 for generating a feature word related to a word indicating a search target from the search phrase; a search unit 25 for searching for the search target from a storage database storing feature words and search targets related to the feature words; and a display device 13 for displaying the search target, the search display 25 searching for the search target related to a feature word based on the feature word.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an information search system, and more particularly to an information search system that searches for a search target representing a specific point based on a search phrase.

  2. Description of the Related Art Conventionally, in map search, there is known an information search apparatus capable of performing map search not only on data in which coordinate information is explicitly registered but also on information included in the contents of atypical data (Patent Literature). 1).

  In the information search device of Patent Document 1, data including a plurality of words having attributes is input, a plurality of words included in the input data are extracted, and attribute-related words obtained by extracting a plurality of words for each attribute are converted. Searching is performed using data to which attribute information is added.

  For example, in the case of the word “Hokkaido” relating to the position attribute, the information search device of Patent Document 1 is based on the search keyword input by the user because the coordinate information of “Hokkaido” is added to the atypical data. The predetermined search result can be output.

JP 2014-191714 A

  However, in the configuration of the information search apparatus of Patent Document 1, a search result cannot be output unless the word has an attribute, and a search target with higher accuracy cannot be detected from the search phrase.

  An object of the present invention is to detect a search object with higher accuracy.

  The information search system according to the first aspect of the present disclosure includes an input device, a feature word generation unit, a search unit, and a display device. The search phrase is input to the input device. The feature word generation unit generates a feature word from a search phrase. The feature word is related to a word representing a search target. The search unit searches the search target from a storage database. The accumulation database accumulates the feature words and the search target. The search target corresponds to the feature word. The display device displays a search target. The search unit searches the search object corresponding to the feature word based on the feature word.

  The information search system of the first aspect can detect a search object with higher accuracy.

  According to the present invention, it is possible to detect a search object with higher accuracy.

It is a schematic block diagram of the information search system which concerns on this embodiment. It is a flowchart figure which shows the processing operation of the information search system which concerns on this embodiment. It is a flowchart figure which shows an example of the process which searches a spot based on a cluster. It is a figure which shows the specific example which determined the cluster from the search phrase. It is a figure which shows an example of the data table stored in the category database. It is a figure which shows an example of the data table stored in the spot database. It is a block diagram which shows an example of a principal part structure of an information storage device. It is a flowchart figure which shows the example of the process which produces | generates a spot database. It is a flowchart figure which shows the example of the process which produces | generates a category database. It is a block diagram which shows the deformation | transformation of the principal part structure of an information storage device. It is a flowchart figure which shows another example of the process which produces | generates an accumulation | storage database. It is the schematic diagram by which the example of a search was displayed on the display apparatus of the information processing terminal.

  Hereinafter, the information search system 10 of this embodiment will be described. As shown in FIG. 1, the information search system 10 includes an information processing terminal 1, an information search device 2, and an information storage device 3. The information search device 2 is configured to be able to communicate with the information processing terminal 1. The information storage device 3 is configured so that the information search device 2 can access it.

  The information processing terminal 1 includes an input device 11, a terminal communication device 12, and a display device 13. The input device 11 is configured to input a search phrase. The terminal communication device 12 is configured to be able to transmit a search phrase to the information search device 2. The terminal communication device 12 is configured to be able to receive the search target searched based on the search phrase from the information search device 2. The display device 13 is configured to display a search target.

  The information search device 2 includes a search communication device 21, a position information acquisition unit 22, a feature word generation unit 24, and a search unit 25. The search communication device 21 is configured to receive a search phrase from the information processing terminal 1. The search communication device 21 is configured to transmit a search target. The position information acquisition unit 22 is configured to acquire position information. The position information indicates the position on the map that is the starting point of the search. The feature word generation unit 24 generates a feature word from the search phrase. The feature word is related to a word representing the search target. The search unit 25 is configured to be able to search for a search target from the accumulated database.

  The search target has point information. The point information indicates a specific point. The search unit 25 is configured to be able to search for a search target corresponding to a feature word within a predetermined range from the position based on the position information and the feature word.

  The information storage device 3 includes a storage device 31. The accumulation storage device 31 stores an accumulation database. The accumulation database accumulates feature words and search targets. The search target corresponds to the feature word.

  The information search system 10 of this embodiment can detect a search target with higher accuracy.

  Hereinafter, each structure in the information search system 10 of this embodiment is demonstrated concretely.

  The information search system 10 according to the present embodiment is configured such that the information processing terminal 1 used by the user and the information search device 2 can communicate with each other. The information processing terminal 1 and the information search device 2 are connected by wireless communication via the public communication network 50, for example. In FIG. 1, the flow of information that is communicated via the public communication network 50 is illustrated by double arrows.

  As illustrated in FIG. 1, the information processing terminal 1 includes a terminal control device 14 and a terminal storage device 15 in addition to the input device 11, the terminal communication device 12, and the display device 13. The information processing terminal 1 is a terminal device used by a user. Examples of the terminal device include a mobile phone or a smartphone.

  The input device 11 is configured to input a search phrase. The search phrase is a word for searching for a search target. The search phrase is also a word arbitrarily input by the user. The search phrase may be a word, a combination of words, or a composed sentence including a subject and a predicate. The input device 11 is configured to instruct transmission of an input search phrase from the terminal communication device 12. Examples of the input device 11 include a touch panel integrated with the display device 13, a voice input device capable of inputting voice, or a physical key. The input device 11 is not limited to the configuration of the touch panel configured integrally with the display device 13, and may be configured only by the input unit.

  The terminal communication device 12 is configured to be able to communicate with the information search device 2. The terminal communication device 12 transmits search phrase information. The terminal communication device 12 receives the search target information. Since the search target has information indicating a specific point, it is also point information. The point information is POI (Point Of Interest) information. Specifically, the terminal communication device 12 is configured to be able to communicate with the search communication device 21 of the information search device 2 using the public communication network 50. The terminal communication device 12 may be configured not only for public communication using the public communication network 50 but also for wired communication, for example. Further, the terminal communication device 12 may be configured to be able to perform wireless communication corresponding to a communication standard of infrared communication, Wi-Fi (registered trademark), Bluetooth (registered trademark), or BLE (Bluetooth Low Energy).

  The display device 13 is configured to display various types of information. The display device 13 displays a search phrase, for example. The display device 13 may display a map. The display device 13 may display the spot indicated by the search target spot information searched by the information search apparatus 2 so as to overlap the map. For example, the display device 13 can visualize a plurality of pieces of point information and display the information on a map indicated by the map information stored in the terminal storage device 15. The display device 13 is not limited to the configuration of the touch panel configured integrally with the input device 11, and may be configured only by the display unit.

  The terminal control device 14 controls various information processing operations. The terminal control device 14 is electrically connected to the input device 11, the terminal communication device 12, the display device 13, and the terminal storage device 15. The terminal control device 14 is configured to control the input device 11, the terminal communication device 12, and the display device 13 based on a program stored in the terminal storage device 15. The terminal control device 14 is configured by, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit).

  The terminal storage device 15 has a volatile storage device whose information disappears when the power is turned off and a non-volatile storage device whose information does not disappear even when the power is turned off. The volatile storage device temporarily stores information processed by the terminal control device 14. The volatile storage device stores, for example, map information indicating a map and point information added to the map information. Examples of the volatile storage device include a RAM (Random Access Memory). The nonvolatile storage device is a storage capable of storing various information processing programs and various information. Examples of the nonvolatile storage device include a ROM (Read Only Memory). For example, a flash memory or an HDD (Hard Disk Drive) is used as the ROM.

  As shown in FIG. 1, the information search device 2 includes a search communication device 21 and a search control device 27. The information search device 2 includes a search storage device 28 in addition to the search communication device 21 and the search control device 27. The information search device 2 is configured by a server, for example. The search control device 27 includes a position information acquisition unit 22, a category determination unit 23, a feature word generation unit 24, a search unit 25, and a timer unit 26.

  The search communication device 21 is configured to be able to communicate with the information processing terminal 1. The search communication device 21 is configured to receive information on the search phrase from the information processing terminal 1. The search communication device 21 is configured to be able to transmit the search target information searched by the search control device 27 to the information processing terminal 1. That is, the search communication device 21 receives information on the search phrase. The search communication device 21 transmits information to be searched. Specifically, the search communication device 21 is configured to be able to communicate with the terminal communication device 12 of the information processing terminal 1 using the public communication network 50.

  The search communication device 21 is configured to be able to communicate with the information storage device 3. The search communication device 21 transmits information for searching for a search target. The search communication device 21 receives the searched search target information from the information storage device 3. Specifically, the search communication device 21 is configured to be able to communicate with the storage communication device 33 of the information storage device 3 using the public communication network 50. The search communication device 21 may be configured not only for public communication using the public communication network 50 but also for wired communication, for example. Further, the terminal communication device 12 may be configured to be able to perform wireless communication corresponding to a communication standard of infrared communication, Wi-Fi (registered trademark), Bluetooth (registered trademark), or BLE.

  The search control device 27 is electrically connected to the search communication device 21 and the search storage device 28. The search control device 27 is configured such that the position information acquisition unit 22, the category determination unit 23, the feature word generation unit 24, the search unit 25, and the time measuring unit 26 function. The search control device 27 is driven to operate, for example, a position information acquisition program, a category determination program, a feature word generation program, a search program, and a time measurement program stored in the search storage device 28. The search control device 27 is composed of, for example, a CPU or MPU.

  The position information acquisition program functions as the position information acquisition unit 22 that acquires position information by being executed on the computer. The category discrimination program functions as a category discrimination unit 23 that discriminates the category of the search phrase by being executed on the computer. The feature word generation program functions as a feature word generation unit 24 that generates a feature word from a search phrase by being executed on a computer. The search program functions as a search unit 25 that searches a search target from a storage database stored in the information storage device 3 by being executed on a computer. The timekeeping program functions as the timekeeping unit 26 that can measure the year, month, day, and time by being executed on the computer.

  The position information acquisition unit 22 acquires position information. The position information is, for example, longitude information and latitude information. The position information may include altitude information in addition to longitude information and latitude information. The position information acquisition unit 22 can acquire position information transmitted from the information processing terminal 1, for example. The position information transmitted from the information processing terminal 1 includes, for example, position information input by the input device 11 of the information processing terminal 1. Further, the position information acquisition unit 22 can acquire position information from a search phrase transmitted from the information processing terminal 1.

  The search phrase is composed of text data. The search phrase includes a phrase. The phrase may be a single word or a group of a plurality of words. The phrase may be a written sentence. The search phrase is converted into a format in which text data can be handled mechanically. The search phrase is decomposed into a plurality of words by morphological analysis. Here, the morphological analysis can classify the search phrase into the smallest units that have meaning in natural language. In the morphological analysis, the part of speech information of the classified morphemes can also be acquired. In morphological analysis, for example, it is also possible to acquire information about whether a word included in a search phrase is a noun, an adjective, a verb, or an adverb.

  For the morphological analysis, for example, a morphological analysis engine such as MeCab can be used. MeCab can be used with a named entity dictionary. An example of the specific expression dictionary is a system dictionary such as Neologd. The position information acquisition unit 22 performs morphological analysis on the search phrase in order to obtain a word included in the search phrase. The position information acquisition unit 22 is not limited to a configuration that morphologically analyzes a search phrase in order to obtain a word included in the search phrase. The position information acquisition unit 22 may have a configuration in which, for example, the category discrimination unit 23, the feature word generation unit 24, the search unit 25, or a morpheme analysis unit (not shown) obtains a word obtained by morphological analysis of the search phrase. The position information acquisition unit 22 may perform a distributed expression in which a word subjected to morphological analysis is converted into a numerical expression. The position information acquisition unit 22 may collect utilization forms of words subjected to morphological analysis. For example, FastText may be used in order to summarize the utilization forms of words subjected to morphological analysis.

  When the word included in the search phrase is a place name, the position information acquisition unit 22 can obtain position information from a place name database in which the place name and the position information are associated with each other. The position information acquisition unit 22 compares, for example, a word obtained by decomposing the search phrase by morphological analysis with a place name database stored in the search storage device 28. If the word obtained by decomposing the search phrase by morphological analysis matches the place name in the place name database, the position information acquisition unit 22 may acquire position information corresponding to the matched place name.

  The place name database may be configured by associating names of prefectures, cities, wards, towns, villages, or facilities with location information, for example. Here, the place name includes not only the name representing the city, but also the name of the facility. In other words, the place name is a name indicating geographical information. In the place name database, for example, the name of the prefecture and the position information of the prefectural office, the name of the city and the position information of the city office, the name of the ward and the position information of the ward office, the name of the town and the position information of the town office, the name of the village and the village office The location information, the name of the facility, and the location information of the facility correspond to each other. Hereinafter, when the word included in the search phrase is a place name, obtaining the position information from the place name database in which the place name is directly associated with the position information is also referred to as obtaining position information by non-machine learning. When the position information acquisition unit 22 acquires position information by non-machine learning, the position information acquisition unit 22 performs a hard search as to whether or not it matches a word included in the database.

  When the word included in the search phrase does not include a place name, the position information acquisition unit 22 can acquire the position information from a database in which the search word and the position information are associated by machine learning. The position information acquisition unit 22 replaces the search phrase with a word that has been decomposed by morphological analysis and a search word having a high degree of similarity, for example, by machine learning. For example, the position information acquisition unit 22 can perform a morphological analysis on the search phrase and then select a desired search word based on the similarity between the word stored in advance and the search word. The position information acquisition unit 22 compares the search word with a place name database in which the position information is associated. If the search term matches the place name in the place name database, the position information acquisition unit 22 may acquire position information corresponding to the matched place name. In other words, the position information acquisition unit 22 uses a geocoding technique for converting a place name indicating geographical information into coordinate values of longitude and latitude.

  The position information acquisition unit 22 uses at least one of position information from the information processing terminal 1, a place name word included in the search phrase from the information processing terminal 1, and a search word based on the search phrase from the information processing terminal 1. Thus, position information indicating the position on the map can be acquired. The position information acquisition unit 22 uses the information from the information processing terminal 1 to acquire position information indicating the position on the map. In the information search device 2 according to the present embodiment, even when the position information cannot be acquired directly from the information processing terminal 1, the position information can be acquired indirectly. The information search device 2 can acquire position information with a lower processing load compared to a configuration that acquires position information only by machine learning.

  That is, in the information search device 2 according to the present embodiment, the position information acquisition unit 22 acquires position information. The position information is estimated from the words included in the search phrase by machine learning.

  The information search device 2 according to the present embodiment can estimate position information indirectly from words included in a search phrase by machine learning even if a word directly indicating position information is not included in the search phrase. it can.

The category determining unit 23 is configured to be able to determine the category of the search phrase. The category determination unit 23 determines the category of the search phrase transmitted from the information processing terminal 1. Categories include, for example, hot springs, parks, museums, shrines, live performances, shopping, amusements, outdoors, events, gourmet, ramen, and mountains. Categories are divided into appropriate types. The category type can be set to 300 types, for example.

  The category discrimination unit 23 performs morphological analysis on the search phrase. The category discriminating unit 23 is not limited to a configuration that performs morphological analysis of the search phrase in order to obtain a word included in the search phrase. For example, the category determination unit 23 may be configured to acquire a word obtained by morphological analysis of a search phrase by a position information acquisition unit 22, a feature word generation unit 24, a search unit 25, or a morpheme analysis unit (not shown). The category discriminating unit 23 may perform a distributed expression in which the words subjected to morphological analysis are expressed in numerical values. The category discriminating unit 23 may collect utilization forms of words subjected to morphological analysis.

  When the word included in the search phrase is a category name representing a category, the category determination unit 23 can directly determine the category from the category database in which the category name and the word are associated with each other. The category discriminating unit 23 compares, for example, a word obtained by disassembling the search phrase by morphological analysis with a category database stored in the search storage device 28. If the word obtained by decomposing the search phrase by morphological analysis matches the category name in the category database, the category determination unit 23 may store the matched category name in the search storage device 28 in association with the search phrase. Hereinafter, when the word included in the search phrase is a category name, determining the category from the category database is also referred to as category determination. That is, it can be said that the category determination unit 23 includes a category determination unit 231 that performs category determination by non-machine learning from a category database when a word included in a search phrase is a category name based on category determination.

  When the word included in the search phrase does not include the category name, the category determination unit 23 can estimate the category from the category database in which the search word is associated with the category name by machine learning. The category discriminating unit 23 replaces a word obtained by decomposing a search phrase by morphological analysis with a search word having a high degree of similarity with the word, for example, by machine learning. In this case, the category discriminating unit 23 may replace one word with a search word having a high similarity to the word among the words obtained by decomposing the search phrase by morphological analysis, or replace two or more words with those words. It may be replaced with a search term having a high similarity. For example, the category determination unit 23 may extract a co-occurrence word that co-occurs from two or more words, and replace the co-occurrence word with a search word having a high similarity to the words that are clustered in advance for each category. . Here, co-occurrence means that a predetermined word included in a search phrase appears simultaneously with another word in the search phrase. A co-occurrence word is another word that appears simultaneously with a predetermined word. Since categories often use different words depending on the classification, it is preferable that the category determination unit 23 performs category determination by machine learning using teacher data whose output corresponding to the input is known in advance.

  For example, the category determination unit 23 can select a desired search word based on the similarity between the word stored in advance and the co-occurrence word after performing morphological analysis on the search phrase. The desired search term is set to match the category name. The category discriminating unit 23 compares the search term that matches the category name with the category database. If the search term matches the category name in the category database, the category discriminating unit 23 may estimate that the matched category name is the category of the search phrase. That is, the category discriminating unit 23 includes a category estimation unit 232 that performs category estimation from the category database by machine learning when a category name is a search word similar to a word included in the search phrase based on category estimation. I can say that.

  The category determination unit 23 determines a category by using a word indicating a category included in the search phrase from the information processing terminal 1 or a search word based on a word included in the search phrase from the information processing terminal 1. Can do.

  In the information search device 2 according to the present embodiment, even when the category cannot be directly determined from the search phrase, the category can be indirectly determined based on the word included in the search phrase. The information search device 2 can determine the category more accurately when estimating the category by machine learning than when determining the category by non-machine learning.

  In other words, the information search device 2 according to the present embodiment further includes a category determination unit 23 and a search storage device 28. The category determination unit 23 determines the category of the search phrase. The search storage device 28 stores words corresponding to categories. The category determination unit 23 includes a category determination unit 231 and a category estimation unit 232. The category determination unit 231 determines a category based on whether or not a word included in the search phrase matches a word stored in the search storage device 28 in advance. The category estimation unit 232 estimates a category from words included in a search phrase that is not determined by the category determination unit 231 by machine learning.

  The information search apparatus 2 according to the present embodiment can indirectly estimate a category from words included in a search phrase by machine learning even if a word indicating a category directly is not included in the search phrase. By including the category determination unit 231 and the category estimation unit 232, the information search device 2 can determine a category with a lower processing load than a configuration in which a category is determined only by machine learning.

  The feature word generation unit 24 is configured to generate a feature word related to a word representing a search target. The feature word generation unit 24 generates a feature word from the search phrase transmitted from the information processing terminal 1. The feature word generation unit 24 performs morphological analysis on the search phrase in order to generate a feature word from the search phrase. For example, the feature word generation unit 24 acquires a word obtained by morphological analysis of the search phrase by the position information acquisition unit 22, the category determination unit 23, the search unit 25, or a morpheme analysis unit (not shown), and generates a feature word. It may be configured. The feature word generation unit 24 performs distributed expression in which the morpheme-analyzed words are expressed in numerical values. The feature word generation unit 24 summarizes the utilization forms of words subjected to morphological analysis. The “feature word” may be a single word or a group of a plurality of words. “Generating feature words” includes determining a feature word or selecting a feature word.

  For example, the feature word generation unit 24 replaces a word obtained by decomposing a search phrase by morphological analysis with a feature word having high similarity with the word by machine learning. The feature word generation unit 24 may replace one word with a feature word having a high degree of similarity among the words decomposed by the morphological analysis of the search phrase, or replace two or more words with those words having a similarity degree. It may be replaced with a high feature word. The feature word generation unit 24 generates a feature word having a higher similarity to the word representing the search target from the words included in the search phrase by machine learning. For example, the feature word generation unit 24 can select a desired feature word based on the similarity between the word and the feature word stored in advance after performing morphological analysis on the search phrase. More specifically, the feature word generation unit 24 can determine how far away the feature word is by measuring the feature vector of the feature word with cosine similarity. In other words, the feature word generation unit 24 can determine the similarity by measuring the feature vector of the feature word with cosine similarity.

  The feature vector can be obtained, for example, by an algorithm such as word2vec using, as input data, data obtained by numerically expressing a word subjected to morphological analysis. The algorithm such as word2vec used here is machine-learned so that the feature vector of the input word can be output. In cosine similarity, the cosine of two vectors is calculated, and the cosine value is used as the similarity. The cosine similarity represents the closeness of the angle formed by the vectors, and the closer to 1, the more similar. The cosine similarity indicates that the closer to 0, the less similar. The feature word generation unit 24 may calculate statistical data of search phrases according to the similarity. The feature word generation unit 24 is preferably configured to preferentially output a feature word having a higher frequency based on statistical data among a plurality of feature words.

  The feature word generation unit 24 extracts co-occurrence words from words included in the search phrase. In this case, the feature word generation unit 24 may use co-occurrence words as feature words, and the search unit 25 may search for a search target from the feature words. By using the co-occurrence words, the feature word generation unit 24 can effectively derive the search object even if it is a word that does not seem to be meaningful to express the search object and does not have a correlation. In other words, the feature word generation unit 24 generates a feature word, which is a feature vector that can more easily represent a search target, from the feature vector by machine learning.

  That is, the feature word generation unit 24 generates a feature word related to the word representing the search target from the search phrase. In the information search device 2 according to the present embodiment, the feature word generation unit 24 generates a feature word having a higher similarity to the word representing the search target from words including nouns, adjectives, verbs, and adverbs in the search phrase. To do.

  The information search device 2 can detect a search target with higher accuracy by generating a feature word having a higher degree of similarity to the word representing the search target. In particular, when the word included in the search phrase is an adjective, the information search device 2 generates a feature word from a word including at least the adjective, and therefore can search for a search target including a subjective or emotional meaning. .

  The search unit 25 is configured to be able to search for a search target from the accumulated database. In the accumulation database, feature words are classified into categories. The search target has point information indicating a specific point. The specific point represents the position of the search target on the map. The point information is, for example, longitude information and latitude information. The point information may include altitude information in addition to longitude information and latitude information. The search unit 25 acquires position information from the position information acquisition unit 22. The search unit 25 acquires category information from the category determination unit 23. The search unit 25 acquires a feature word from the feature word generation unit 24. The search unit 25 searches for a search target from the accumulation database based on the position information, the category, and the feature word. The search target searched by the search unit 25 corresponds to a feature word in a predetermined range and a determined category from the position indicated by the position information. In other words, the search unit 25 searches for a search object corresponding to the feature word in a predetermined range and a determined category from the position indicated by the position information, based on the position information, the category, and the feature word. It is configured to be able to.

  The timer unit 26 is configured to be able to measure the year, date, and time. The timer unit 26 may be configured so as to be able to measure time by counting the number of clocks of the CPU, for example. For example, the time measuring unit 26 can specify the date and time when the search communication device 21 received the search phrase from the information processing terminal 1. The timer 26 can discriminate the search phrase received by the search communication device 21 for each predetermined period. The timer 26 can store the date and time when the search phrase is received in the search storage device 28 in association with the statistical data.

  The search storage device 28 has a volatile storage device whose information disappears when the power is turned off and a non-volatile storage device whose information does not disappear even when the power is turned off. The volatile storage device temporarily stores information processed by the search control device 27. An example of a volatile storage device is a RAM.

  The nonvolatile storage device is a storage capable of storing a position information acquisition program, a category determination program, a feature word generation program, a search program, and a time measurement program. An example of the nonvolatile storage device is a ROM. The non-volatile storage device may store a place name database, a category database, statistical data, or a system dictionary.

  In the information search system 10 according to the present embodiment, the feature word generation unit 24 uses, for example, a “night view”, “beautiful”, “restaurant” using morphological analysis when the content of the search phrase is “beautiful restaurant with night view”. Get the word. The feature word generation unit 24 determines the similarity of the feature words co-occurring with “night view”, “beautiful”, or “restaurant” by machine learning, and the search unit 25 stores the accumulated database based on the determined feature words. The location information of “restaurant” whose search target is ambiguous can be searched.

  The information storage device 3 includes a storage control device 32 and a storage communication device 33 in addition to the storage device 31. The information storage device 3 is constituted by a database server, for example.

  The storage device 31 stores a storage database in which search targets to be searched by the information search device 2 are stored. In the accumulation database, search objects are classified for each category. In the storage database, search objects are stored in association with feature words.

  The storage device 31 has a volatile storage device whose information disappears when the power is turned off and a non-volatile storage device whose information does not disappear even when the power is turned off. The volatile storage device temporarily stores information processed by the accumulation control device 32. Examples of the volatile storage device include a RAM. The nonvolatile storage device is a storage capable of storing various information processing programs and various information. An example of the nonvolatile storage device is a ROM. The non-volatile storage device stores an accumulation database. The non-volatile storage device may store map information indicating a map and point information added to the map information.

  The storage control device 32 is electrically connected to the storage device 31 and the storage communication device 33. The storage control device 32 is configured to control the storage device 31 and the storage communication device 33. The accumulation control device 32 can be configured using a CPU or MPU. The accumulation control device 32 is configured to be able to implement a predetermined program based on a program stored in advance in the accumulation storage device 31, for example.

  The storage communication device 33 is configured so that the information search device 2 can access it. The storage communication device 33 is configured to receive information for searching for a search target from the information search device 2. The storage communication device 33 is configured to transmit information to be searched to the information search device 2.

  Further, the information storage device 3 may be configured such that a storage database can be constructed from an SNS (Social Networking Service) provided by an external information processing device (not shown). The information storage device 3 constructs a storage database from the generated feature words in the same manner as the information search device 2 generates a feature word from the search phrase based on the posted article information published externally by the external information processing device. can do. The posted article information is, for example, information on posted articles posted by the user to the external information processing apparatus.

  Next, the operation of the entire information search system 10 according to the present embodiment will be described.

  First, the relationship between the information processing terminal 1 and the information search device 2 will be described. In the information search system 10 according to the present embodiment, the user inputs a search phrase with the input device 11 of the information processing terminal 1. When the input device 11 receives an instruction to transmit a search phrase, the information processing terminal 1 transmits the search phrase from the terminal communication device 12 to the information search device 2.

  In addition, the information processing terminal 1 transmits position information indicating the selected position from the terminal communication device 12 to the information search device 2 when the user selects a position on the map displayed on the display device 13. It may be configured. In the information search device 2, when the position information from the information processing terminal 1 is received, the position information can be set as a starting point on the search map.

  Next, operation | movement of the information search device 2 which received the search phrase from the information processing terminal 1 is demonstrated using FIG. In the following, each step in the figure is indicated by S.

  In the flowchart shown in FIG. 2, among the steps performed by the information search device 2, the information search device 2 receives a search phrase from the information processing terminal 1 (S 101). The information search device 2 stores the received search phrase in the search storage device 28.

  The information search device 2 performs a position information acquisition step of acquiring position information by a position information acquisition program whose operation is controlled by the search control device 27 (S102). The location information acquisition program acquires location information when location information is transmitted from the information processing terminal 1 in the location information acquisition step. When there is no position information that can be acquired in the position information acquisition step, the position information acquisition program acquires position information from the search phrase.

  Next, the information search device 2 performs a category determination step of determining the category of the search phrase by the category determination program whose operation is controlled by the search control device 27 (S103). The category determination program determines a category name from the category database when a word indicating a place name is included in the search phrase. When the search phrase does not include a word indicating the place name, the category determination program generates a search word from the search phrase by machine learning. The category discrimination program estimates a category name from the category database based on a search word having a high similarity among the generated search words.

  Subsequently, the information search device 2 performs a feature word generation step of generating a feature word related to the word representing the search target from the search phrase by the feature word generation program whose operation is controlled by the search control device 27 (S104).

  Next, the information search device 2 performs a search execution step of searching for a search target from the stored database by a search program whose operation is controlled by the search control device 27 (S105).

  Finally, the information search device 2 may be terminated if the search target is searched.

  According to the information search system 10 of the present embodiment, even if a user inputs a search phrase based on an ambiguous image to the information processing terminal 1, the information search device 2 performs a soft search using the user's subjective words or emotion words. It can be carried out. For example, the information search device 2 displays on the display device 13 of the information processing terminal 1 the location of a shop where the hot spicy ramen may be eaten on the display device 13 even if the search phrase “hot spicy ramen” is input. Can be displayed with a marker of a color corresponding to the category of ramen on the map.

  That is, in the information search system 10 of the present embodiment, the information processing terminal 1 further includes a terminal storage device 15. The terminal storage device 15 stores map information. The display device 13 displays a specific point indicating the search target on the map of the map information.

  The information search system 10 of the present embodiment can display a search target point with higher accuracy on a map.

  Moreover, in the information search system 10 of this embodiment, the feature word generation part 24 calculates the statistical data of a search phrase. The information storage device 3 associates the search phrase received by the search communication device 21 within the period set in advance from the information processing terminal 1 with the statistical data and stores it in the storage database.

  The information search system 10 of this embodiment can detect a search object with higher accuracy based on a search phrase within a preset period.

  Furthermore, in the information search system 10 of the present embodiment, the feature word generation unit 24 generates a feature word having a higher degree of similarity with the word representing the search target from the words included in the search phrase. The feature word generation unit 24 is configured to preferentially output feature words with higher frequency based on statistical data.

  The information search system 10 of this embodiment can detect a search target with higher accuracy.

  In the information search system 10 of the above-described embodiment, for example, in the case where the information processing terminal 1 has a touch panel, the map displayed on the display device 13 is enlarged or reduced, and the user searches as an area to be searched. By tapping a place to be designated, position information can be input to the input device 11.

  Further, the information processing terminal 1 displays the search target on the display device 13 so as to display the search target as a marker on the map. An example of the marker is a balloon in which a pictogram representing a category is displayed at the center. For example, the information processing terminal 1 may display a map including the marker on the display device 13 by changing the color or shade of the marker for each category. For example, the information processing terminal 1 may display the map including the marker on the display device 13 by changing the size of the marker according to the similarity between the word included in the search phrase and the feature word.

  Furthermore, in the information search system 10 of the above-described embodiment, the information processing terminal 1 may have a navigation function. Since the information processing terminal 1 has a navigation function, the user can be guided to the point information on the map displayed on the display device 13. The navigation function is stored in the terminal storage device 15 of the information processing terminal 1 and controlled by the terminal control device 14. The navigation function may be stored in the search storage device 28 of the information search device 2 and controlled by the search control device 27. The information search system 10 may be equipped with a navigation function in either the information processing terminal 1 or the information search device 2 as long as the map and navigation can be displayed on the display device 13 of the information processing terminal 1.

  Specifically, the navigation function may be stored in one of the information search device 2 and the information processing terminal 1, and the navigation function may be controlled by the other device. Alternatively, the navigation function may be divided and stored in both the information search device 2 and the information processing terminal 1, and either one device or both devices may cooperate to control the navigation function. Good.

  Each process or each function of the above embodiment may be realized by centralized processing by a single device or a single system, or may be distributedly processed by a plurality of devices or a plurality of systems. It may be realized with. In addition, each component in the above embodiment may be configured by dedicated hardware. Each component of the above embodiment may be realized by executing a program for components that can be realized by software.

  Each component of the above embodiment may be realized, for example, by a CPU executing a software program recorded on a recording medium. The program may be executed by being downloaded from a server, or may be executed by reading a program recorded on a predetermined recording medium. Further, the computer that executes the program may be singular or plural. The above embodiment may be configured to perform centralized processing or may be configured to perform distributed processing.

  It should be noted that the present invention can be implemented in various other forms without departing from the spirit, gist, or main features. The above embodiment is merely an example in all respects, and should not be interpreted in a limited manner. That is, taking the above embodiment as an example, the present invention is an information search apparatus or an information search system.

  [Summary of Embodiment]

(1: About feature words)
According to the information search device 2 described above, it is assumed that the search phrase input by the user performing the search does not directly indicate the spot that the user wants to search due to the function of each unit included in the search control device 27. In addition, a valid spot can be detected and presented to the user. Here, the spot is also a search target.

  Specifically, the search control device 27 includes a feature word generation unit 24 and a search unit 25. Among these, the feature word generation unit 24 generates a feature word from a word obtained by morphological analysis of the search phrase. Hereinafter, a word obtained by morphological analysis of a search phrase may be referred to as an input word. In the present specification, the word “generation” is used in the meaning of “specific”, “determination”, “detection”, or “selection” with respect to the feature word.

  Here, the feature word generated by the feature word generation unit 24 may be a similar word having a high similarity with the input word, or may be a co-occurrence word of the input word. The feature words generated by the feature word generator 24 may be both similar words and co-occurrence words. In the following, a word whose similarity to an input word is higher than a predetermined threshold may be called a similar word.

  When using a similar word as a feature word, the feature word generation unit 24 generates feature information indicating the feature of the input word. The feature information only needs to indicate the feature of the input word. For example, the feature information may be a feature vector of an input word. The feature vector can be calculated by using, for example, GloVe, WordNet, or fastText algorithm in addition to word2vec. The feature word generation unit 24 calculates the similarity between the feature vector of each feature word associated with the spot in the accumulation database and the calculated feature vector, and identifies words whose similarity is equal to or greater than a threshold value. Thereby, the feature word production | generation part 24 can pinpoint the similar word similar to the input word among the feature words matched with the spot in the accumulation | storage database. The method for calculating the similarity is not particularly limited, and can be calculated by cosine similarity, for example.

  When a co-occurrence word is used as a feature word, the feature word generation unit 24 specifies a co-occurrence word of the input word. The co-occurrence word can be extracted by, for example, TF-IDF (Term Frequency-Inverse Document Frequency). The feature word generation unit 24 may use a co-occurrence word of similar words as a feature word.

  Then, the search unit 25 searches the storage database stored in the storage device 31 using the generated feature word. The search unit 25 searches the storage database to detect spots associated with feature words in the storage database. “Spot” means, for example, a place or place, or a building installed at a specific place or place. In the accumulation database, each spot is associated with position information indicating the geographical position of the spot. Since the feature word used for the search is a similar word or co-occurrence word of the input word, even if the search phrase does not directly indicate the spot that the user wants to search, a valid spot is detected to the user. Can be presented.

  Note that the feature word generation unit 24 may use a word with a predetermined part-of-speech among the words obtained by morphological analysis of the search phrase. As the predetermined part of speech, for example, a noun, an adjective, a verb, and an adverb may be used. Accordingly, it is difficult to generate a significant feature word. For example, a part of a word such as a conjunction, a moving verb, a particle, or an auxiliary verb can be excluded to generate a highly relevant feature word.

(2: About location information)
The search control device 27 may include the position information acquisition unit 22. The position information acquisition unit 22 acquires position information serving as a reference for determining a spot search range based on information received from the information processing terminal 1 used by the user. The search unit 25 sets a predetermined range based on the position indicated by the acquired position information, and detects spots within the set range. As a result, the information search system 10 can search for a spot that is narrowed down to an area in which the user performing the search is interested.

  The position information acquisition unit 22 may acquire position information from words obtained by morphological analysis of the search phrase. For example, if the word obtained by morphological analysis of the search phrase includes a word indicating the position, the position information acquisition unit 22 uses a place name database in which the word indicating the position is associated with the position information. Position information may be acquired. In addition, as a word which shows a position, a place name is mentioned, for example.

  Further, the position information acquisition unit 22 may acquire position information using a position information database for specifying position information. The position information database is a database in which a word and position information indicating a position corresponding to the word are associated with each other. When the position information acquisition unit 22 acquires position information using the position information database, the position information acquisition unit 22 uses at least one of a word obtained by morphological analysis of the search phrase, a word similar word, and a word co-occurrence word. Search the information database. Thereby, the positional information acquisition part 22 can acquire the positional information relevant to the word obtained by carrying out the morphological analysis of the search phrase. Similar words and co-occurrence words may be specified using a machine-learned model. In this case, the position information acquisition unit 22 acquires position information estimated by machine learning from words included in the search phrase.

  Further, the information processing terminal 1 may acquire position information indicating the position of the information processing apparatus 1 using, for example, GPS (Global Positioning System), and transmit the acquired position information to the information search apparatus 2. In this case, the position information acquisition unit 22 may acquire position information using GPS transmitted from the information processing terminal 1. The information search system 10 can also detect spots around the current location of the information processing terminal 1 by using position information acquired using GPS.

(3: About categories)
The search control device 27 may include a category determination unit 23. The category determination unit 23 may include a category determination unit 231 and a category estimation unit 232. The category discriminating unit 23 determines a category of words obtained by morphological analysis of the search phrase. In this case, in the accumulation database, each spot category is associated with each spot. Thereby, the search part 25 can detect the spot of the category which the category discrimination | determination part 23 determined among the spots according to the search phrase.

  For example, the category determination unit 231 can determine a category corresponding to a word obtained by morphological analysis of a search phrase by using a category database in which a word is associated with a category corresponding to the word.

  The category estimation unit 232 uses a machine-learned algorithm to specify a category corresponding to a word obtained by morphological analysis of the search phrase. The algorithm may be, for example, machine-learned correspondence between word feature information and categories. The word feature information is, for example, a feature vector. When using an algorithm obtained by machine learning of the correspondence between word feature information and categories, the category estimation unit 232 obtains word feature information obtained by morphological analysis of the search phrase, and uses the obtained feature information as the algorithm. By inputting, a category can be specified. The category estimation unit 232 may specify at least one of a word similar word obtained by morphological analysis of the search phrase and a word co-occurrence word obtained by morphological analysis of the search phrase. The category estimation unit 232 may specify a category by searching the category database using at least one of the specified similar word and co-occurrence word. Similar words and co-occurrence words may be specified using a machine-learned model. In this case, the category estimation unit 232 estimates the category from the words included in the search phrase by machine learning. For example, the category estimation unit 232 may calculate the similarity between a feature vector of a word belonging to a certain category and a word feature vector obtained by morphological analysis of the search phrase. In this case, if the calculated similarity is equal to or greater than a predetermined threshold, the category estimation unit 232 determines that a word obtained by morphological analysis of the search phrase belongs to a certain category.

  The determined category may be used for weighting described later. The determined category may be used to narrow down the search range of the search unit 25. When the search unit 25 is used to narrow down the search range, the feature word generated by the feature word generation unit 24 uses, as search targets, spots belonging to the category determined by the category determination unit 23 among the spots stored in the storage database. Detect spots associated with words. For example, let us consider a case where the category determination unit 23 determines that the category of the word “landscape” included in the search phrase is “sightseeing spot”. In this case, the search unit 25 searches for spots associated with the category “sightseeing spot” among spots stored in the storage database, using feature words generated from “landscape”. Thereby, the information search system 10 can narrow down a search range appropriately, and can obtain a reasonable search result rapidly.

(4: Priority in search)
When a plurality of feature words can be generated, the feature word generation unit 24 may generate only a feature word having a high priority among the plurality of feature words. For example, in the information search system 10, the priority is calculated based on the cumulative number of times used in the past, the frequency used in the past search for a predetermined period, and / or the cumulative number and usage frequency. It may be at least one of the following. For example, if “landscape” and “restaurant” can be generated as feature words, the feature word generation unit 24 can search for “restaurant” in the most recent week higher than the search frequency for “landscape” in the most recent week. For example, “restaurant” may be a characteristic word.

  Note that the feature word generation unit 24 calculates information indicating the number of times or information indicating the frequency for the search phrase received from the information processing terminal 1 within a preset period, and stores it as statistical data. That's fine. The stored statistical data is associated with the search phrase received from the information processing terminal 1.

  When the feature word generation unit 24 generates a plurality of feature words, the search unit 25 may perform a search using a feature word having a high priority among the plurality of feature words. Further, the search unit 25 may output the search result by the feature word having a higher priority in preference to the search result by the feature word having a lower priority. For example, the search unit 25 may sequentially output the search results using feature words with high priority. The statistical data can also be used for weighting described later.

(5: Construction of storage database)
The information storage device 3 can acquire various information related to the search target spot and construct a storage database. For example, the information storage device 3 may generate a feature word from an article posted to the SNS. For example, the information storage device 3 may generate a feature word from an article posted on a website introducing a spot or a site posting word-of-mouth information on a spot. Hereinafter, an article posted on the SNS or an article posted on a site posting word-of-mouth information on a spot is also referred to as a comment. Moreover, a website may be abbreviated as a site.

  For example, when the information storage device 3 obtains a comment “view is the best” posted on the word-of-mouth site about the spot “observation platform X”, the information storage device 3 performs a morphological analysis on the obtained comment to obtain “view” or “best”. Get the word. Next, the information storage device 3 calculates a feature vector of a word obtained by morphological analysis, and generates a feature word similar to each word and the feature vector using the calculated feature vector. Then, the information storage device 3 adds the spot “observation platform X” to the storage database, and records the words obtained by the morphological analysis in association with the feature words generated from the words. In addition, if the spot “observation platform X” is already recorded in the storage database, the information storage device 3 adds a word obtained by morphological analysis and a feature word generated from the word to the already recorded spot. Record in association with.

  The information storage device 3 may record a co-occurrence word or a later-described cluster in association with the feature word instead of or in addition to the feature word. Also, on the site, spots may be evaluated by points or the number of stars. When the spot is evaluated by the score or the number of stars, the information storage device 3 may also record the evaluation of the spot in the storage database. In addition to this, the information storage device 3 may record, for example, the number of accesses to the site, the number of accesses to the spot page, the number of comments to the spot, the date and time of comment posting, and the site name in the storage database. Good. The site name may be a service name, for example. Such information can be used, for example, for weighting spots, and for example, the information search system 10 can also preferentially search for spots with high evaluation.

  As described above, the information storage device 3 can expand the storage database based on the word-of-mouth information and can search for new spots. The information search system 10 can perform a search based on the impression of a person who actually visited a spot. For example, if the feature word is recorded based on the comment “view is the best” for the spot “observation platform X”, the information search system 10 can start from an ambiguous search phrase such as “the feeling of liberation is highest”. The spot “observation platform X” can also be detected.

  Moreover, the information search system 10 can detect a spot according to the user's intention even when an ambiguous search phrase is input by constructing a storage database based on information related to the spot. .

[Search using clusters]
As described in the above embodiment, the feature word generation unit 24 may set one word as a “feature word”, or may set a word group including a plurality of words as a “feature word”. In the following, the latter case will be described in more detail based on FIG.

  When a word group consisting of a plurality of words is used as a feature word, a feature word group consisting of a plurality of feature words having similar feature information indicating the feature of the word is associated with a spot to be searched in the accumulation database. . The feature information is, for example, a feature vector. Hereinafter, the feature word group is also referred to as a cluster. When a search phrase is input, the feature word generation unit 24 determines a cluster corresponding to the word based on the feature information of the word included in the input search phrase. Then, the search unit 25 detects spots associated with the clusters determined by the feature word generation unit 24 from the accumulation database.

  According to this configuration, the information search system 10 can detect a valid spot in accordance with the intention of the user who performs the search even when a search phrase that is not directly associated with the spot is input. . For example, when a cluster A composed of similar feature words such as “landscape” and “landscape” is associated with a spot A in the accumulation database, a search phrase including the word “scenery” is input. To do. In this case, in the information retrieval system 10, “scenery” is similar to “scenery” and “scenery”, and therefore “scenery” is determined to belong to cluster A, so spot A is detected from the accumulation database. be able to. Note that whether or not the feature information is similar can be determined based on, for example, whether or not the similarity is equal to or higher than a predetermined threshold.

  Also, in the information retrieval system 10, when a word group composed of a plurality of words is used as a feature word, a category database in which clusters composed of a plurality of feature words having similar feature information indicating the feature of the word and categories are associated is created. It may be used. In this case, the category determination unit 23 detects, from the category database, the category associated with the cluster determined based on the feature information of the word included in the search phrase. According to this configuration, even when a search phrase that is not directly associated with a category is input, the information search system 10 can determine an appropriate category in accordance with the intention of the user who performs the search. .

  Below, the specific example of the spot search according to the flow of FIG. 3 is demonstrated based on FIGS. Note that the category database and the spot database correspond to the accumulation database. Also, the acquisition of the search phrase and position information (S201, S202) in FIG. 3 is the same as in FIG.

  In S203, the feature word generation unit 24 calculates a feature vector of each word obtained by morphological analysis of the search phrase. FIG. 4 shows an example in which four search phrases of “Scenery is beautiful” as Example 1, “Scenery is beautiful” as Example 2, “Scenery is beautiful” as Example 3, and “Fun Dating” as Example 4 are input. ing. For example, when the search phrase of Example 1 is input, in S203, “Scenery” and “Pretty” are excluded from the words obtained by performing morphological analysis on “Scenery is beautiful” except for the particle “Ga”. A feature vector is calculated. In the illustrated example, an n-dimensional feature vector is calculated. n may be a natural number, for example, n = 300.

  Next, the feature word generation unit 24 determines a cluster of each word obtained by morphological analysis of the search phrase (S204). Specifically, the feature word generation unit 24 inputs each of the feature vectors calculated in S203 to a predetermined clustering model, whereby each word obtained by morphological analysis of a cluster corresponding to the feature vector, that is, a search phrase. Get the output of the cluster. For example, in the example of FIG. 4, both “scenery” and “scenery” are determined to belong to the cluster having the cluster ID “15”. Further, both “beautiful” and “beautiful” are determined to belong to the cluster having the cluster ID “8”. The clustering model is a model that is machine-learned so as to output a cluster corresponding to a word using a feature vector of the word as input data. A cluster corresponding to a word is a cluster that includes a feature word having a feature vector similar to that word as a constituent element. A clustering model generation method will be described later.

  Next, the category determination unit 23 determines the category of each word obtained by morphological analysis of the search phrase based on the cluster determined in S204 (S205). For category determination, a category database in which cluster IDs, feature words, weights, and categories are associated as shown in FIG. 5 can be used. Specifically, first, the category determination unit 23 extracts a category associated with the cluster determined in S204 from the category database. For example, in the example 1 “Scenery is beautiful” in FIG. 4, the cluster is determined to be the cluster ID “15” and the cluster ID “8” in S204. The “historic sites” and the category “restaurant” are extracted.

  Next, the category determination unit 23 calculates the similarity between each word obtained by morphological analysis of the search phrase and each feature word of the category corresponding to the word, and multiplies the calculated similarity by a weight. For calculating the similarity, a fast text inter-word similarity estimation model may be used. Then, the calculated values are totaled for each category, and the extracted categories are ranked in descending order of the total value. Hereinafter, the total value totaled for each category is also referred to as a score.

  For example, in the case of Example 1 “Beautiful scenery” in FIG. 4, the word “landscape” obtained by morphological analysis of the search phrase and the characteristic word “landscape” registered in the category database for the category “sights / historic sites”. The similarity is calculated. The same applies to the word “beautiful”. Then, the calculated similarity is multiplied by the weight registered in the category database. For example, if the similarity between the word “landscape” and the feature word “landscape” is 0.8, and the similarity between the word “beautiful” and the feature word “beautiful” is 0.7, the category “sights / historic sites” Is calculated as follows.

About the word “scenery”: similarity “0.8” × weight “0.88” = 0.704
About the word “beautiful”: similarity “0.7” × weight “0.76” = 0.532
Score of category “Historic sites / historic sites”: 0.704 + 0.532 = 1.236
In other words, the score is calculated by multiplying the similarity value and the weight value for each word, and adding the multiplied values.

  When a plurality of feature words with the cluster ID “15” are registered in the category database, the calculation of similarity for each feature word is performed by multiplying the weights in the same manner as described above. The same applies to the cluster ID “8”. And the category discrimination | determination part 23 totals the value obtained by multiplication for every category, calculates a score, and ranks the category extracted in order with a big score.

  Next, the search unit 25 searches for spots based on the clusters determined in S204 (S206). For spot search, a spot database in which a cluster ID, a feature word, a weight, and a spot ID are associated with each other as shown in FIG. 6 can be used. Specifically, first, the search unit 25 extracts spots associated with the clusters determined in S204 from the spot database. For example, in the example 1 “Scenery is beautiful” in FIG. 4, the cluster is determined to be the cluster ID “15” and the cluster ID “8” in S204. The spot “Restaurant” is extracted.

  Next, the search unit 25 calculates the similarity between each word obtained by morphological analysis of the search phrase and each feature word of the spot corresponding to the word, and multiplies the calculated similarity by a weight. For calculating the similarity, a fast text inter-word similarity estimation model may be used. Then, the calculated values are totaled for each spot, and the extracted spots are ranked in descending order of the total value. Hereinafter, the total value obtained by adding the calculated values for each spot is also referred to as a score.

  For example, in the case of Example 1 “Scenery is beautiful” in FIG. 4, the word “landscape” obtained by morphological analysis of the search phrase and the feature word “ The similarity of “landscape” is calculated. Since the word “beautiful” matches the feature word “beautiful” registered in the spot database, the similarity is 1. Then, the calculated similarity is multiplied by the weight registered in the spot database. For example, if the similarity between the word “landscape” and the feature word “landscape” is 0.9, the score of the spot “sights A” is calculated as follows.

About the word “scenery”: similarity “0.9” × weight “0.53” = 0.477
About the word “beautiful”: similarity “1.0” × weight “0.46” = 0.46
The score of the spot “Sightseeing A”: 0.477 + 0.46 = 0.937
In other words, the score is calculated by multiplying the similarity value and the weight value for each word, and adding the multiplied values.

  When a plurality of feature words with the cluster ID “15” are registered in the spot database, the calculation of the similarity similar to the above is performed for each feature word and multiplication by weight. The same applies to the cluster ID “8”. Then, the values obtained by multiplication are summed for each spot, and the extracted spots are ranked in descending order of the score which is the total value.

  Next, the search unit 25 gives a final ranking to the spots detected in S206 in consideration of the category determination result in S205 (S207). For example, in the category determination of S205, the search unit 25 may rank spots belonging to the category having the highest score in descending order of the score calculated in S206. Note that the category to which each spot belongs is determined in advance.

  Then, the search unit 25 ranks all the spots belonging to the category having the highest score, and then ranks all spots belonging to the category having the next highest score. It may be repeated until is determined. Note that the search unit 25 may end the repetitive processing when it is determined to a predetermined rank. Examples of the predetermined rank include the top 20 ranks.

  Note that the ranking method based on the category and spot scores is not limited to the above example. For example, for each spot detected in S206, the search unit 25 may calculate the total value of the score of the spot and the score of the category to which the spot belongs, and rank the spots in the order of the total value. In this case, it can be said that the category score is used for weighting the spot score. Further, the above-described statistical data may be added to the ranking in S207. In this case, for example, the ranking of spots with high evaluation can be increased.

  Finally, the search communication device 21 notifies the information processing terminal 1 of the search result (S209). Thereby, the terminal control device 14 of the information processing terminal 1 displays the search result on the display device 13. When the search communication device 21 displays the search result on the display device 13, the search communication device 21 may notify the information processing terminal 1 only of a predetermined number of the search results ranked higher in S208. As the upper predetermined number, for example, the upper 10 items are included in the search results.

  The search communication device 21 may also notify the information processing terminal 1 of the order determined in S208. In this case, the terminal control device 14 can display the search result on the display device 13 in a display mode according to the order. For example, when displaying a search result on a map, a marker with a larger rank may be displayed on a map. Thereby, the information search system 10 can make a user recognize which of the detected spots is high.

  As described above, the information search system 10 can detect an appropriate spot from various search phrases by determining a cluster corresponding to the search phrase and searching for a spot using the determined cluster. For example, even if the search phrase is Example 1 “Scenery is beautiful” in FIG. 4, Example 2 “Scenery is beautiful” in FIG. 4, and Example 3 “Scenery is beautiful” in FIG. Spots can be detected. In addition, when the search phrase is Example 4 “fun date” in FIG. 4 that is completely different from Examples 1 to 3, a cluster different from Example 1 to Example 3 is determined, and a different spot is determined accordingly, for example, an amusement park F is detected.

  The cluster can also be used to specify a category. By specifying a category, spots in the category can be detected. Further, by setting a higher weight for a combination of a spot and a feature word or a combination of a category and a feature word for a combination having higher relevance, it is possible to preferentially detect a spot with high validity.

(Modification of category judgment / spot search)
In the category determination of S205, the similarity between the word obtained by morphological analysis of the search phrase and the feature word registered in the category database is calculated, but this process can be omitted. In this case, in S205, the category determination unit 23 may calculate the sum of the weight values of each cluster ID associated with the category, and use the calculated value as the score of the category.

  Similarly, the calculation of similarity can be omitted in the spot search in S206. In this case, in S206, the search unit 25 may calculate the sum of the weight values of each cluster ID associated with the spot, and use the calculated value as the score of the category.

  [Generation of category database and spot database]

(1: Configuration to achieve)
The information search system 10 may have a category database and a spot database generation function. The components for realizing this function may be provided in the information search device 2 or the information storage device 3, for example. Further, a device having this function may be added to the information search system 10 separately.

  Below, the example in which the information storage device 3 is provided with the production | generation function of a category database and a spot database is demonstrated based on FIG. FIG. 7 is a block diagram illustrating an example of a main configuration of the information storage device 3. As illustrated, the accumulation control device 32 includes a clustering model generation unit 321, a feature word extraction unit 322, a cluster determination unit 323, a spot database generation unit 324, a category classification unit 325, and a category database generation unit 326. Hereinafter, the database may be abbreviated as DB. The functions of these units can also be realized by a program, for example. In addition, word-of-mouth information written in a predetermined site is used to generate the category database and the spot database. Further, it is assumed that at least one sentence is included in one word of mouth. Here, the predetermined site may be a plurality of sites or an SNS. In the following, word of mouth information may be simply abbreviated as word of mouth.

  The clustering model generation unit 321 generates a clustering model for clustering words. Clustering may be performed based on, for example, the similarity of feature vectors, whereby roughly similar word groups can be handled as a cluster. Note that the “roughly similar word group” can be said to be a rough synonym group. For example, a fastText vectorization model may be used to calculate a feature vector of a word. The generated clustering model is used for determining a cluster in S204 of FIG. By performing clustering, a search can be performed in cluster units, so that the search can be made efficient and the search can be speeded up.

  The feature word extraction unit 322 extracts feature words in the input sentence. For example, co-occurrence word analysis can be used to extract feature words. Specifically, the feature word extraction unit 322 calculates a TF-IDF value for each word included in the word group obtained by performing morphological analysis on the input sentence. Then, the feature word extraction unit 322 ranks words included in the word group based on the calculated TF-IDF value, and extracts words ranked higher as feature words. Further, since the TF-IDF value is a numerical value indicating the likelihood of the feature word, the feature word extraction unit 322 sets the TF-IDF value of the extracted feature word as the weight value of the feature word.

  The cluster determination unit 323 determines a cluster of feature words extracted by the feature word extraction unit 322 using the clustering model generated by the clustering model generation unit 321. The determined cluster includes a plurality of feature words having similar feature information as components.

  The spot DB generation unit 324 generates a spot database as shown in FIG. 6 by associating spots, feature words, clusters thereof, and weight values. The feature word and the weight value are extracted and calculated by the feature word extraction unit 322. The cluster is determined by the cluster determination unit 323.

  The category classification unit 325 classifies the input sentence into a plurality of predetermined categories. For classification, a classification model constructed by supervised machine learning may be used. As the classification model, for example, a fastText text classification model may be used. In machine learning, a sentence with a known category is used as teacher data. In the teacher data, for example, categories of each word of mouth written on a predetermined site may be associated manually.

  The category DB generation unit 326 generates a category database as shown in FIG. 5 by associating the categories, feature words, clusters, and weight values. The feature word and the weight value are extracted and calculated by the feature word extraction unit 322. The cluster is determined by the cluster determination unit 323.

(2: Process flow)
In the following, an example of the flow of processing for generating a spot database will be described with reference to FIG. When the clustering model generation unit 321 starts the process of generating the spot database, the clustering model generation unit 321 generates a clustering model (S301). For example, the clustering model generation unit 321 calculates feature vectors for all words obtained by morphological analysis of all the reviews written on a predetermined site. The clustering model generation unit 321 can generate a clustering model based on the calculated feature vector. In this case, the generated clustering model is a model that classifies the input words into clusters in which the feature vectors of the input words are similar to the feature vectors. For example, fastText can be used to generate the model.

  Next, the feature word extraction unit 322 extracts feature words and weights from each word of mouth (S302). The feature word and the weight can be extracted using, for example, a TF-IDF value. The correspondence between each word of mouth and the spot is specified in advance according to which spot the word of mouth is written for. For example, if the word of mouth is written on a page introducing the famous place A in a predetermined site, the feature word extracting unit 322 stores the word of mouth in association with the famous place A so that the word of mouth is the word of mouth of the famous place A. Can be identified.

  Next, the cluster determination unit 323 determines a cluster of feature words extracted in S302 using the clustering model generated in S301 (S303). A feature word, a weight, and a cluster are determined for each word of mouth written for each spot by the processing of S302 and the processing of S303.

  Next, the spot DB generation unit 324 stores the determined feature words, weights, and clusters in the spot database in association with the spots (S304). Thereby, for each spot, a record in which the feature word, the cluster, and the weight are associated is added to the spot database. If the spot database has not been generated, a spot database is generated in S304.

  Next, an example of processing for generating a category database will be described with reference to the flowchart shown in FIG. When the category classification unit 325 starts the process of generating the category database, the category classification unit 325 classifies each word of mouth written in a predetermined site into categories (S401).

  Next, the feature word extraction unit 322 extracts feature words and weights from the reviews of each category (S402). The feature word and the weight can be extracted using, for example, a TF-IDF value. In S402, the feature words and weights extracted in S302 may be used.

  Next, the cluster determination unit 323 determines a cluster of feature words extracted in S402 using the clustering model generated in S301 (S403). For each word of mouth of each category, feature words, weights, and clusters are determined by the processing of S302 and the processing of S403.

  Finally, the category DB generation unit 326 stores the determined feature words, weights, and clusters in the category database in association with the corresponding categories (S404). Thereby, for each category, a record in which a feature word, a cluster, and a weight are associated is added to the category database. If the category database has not been generated, the category database is generated in S404.

(3: Summary)
As described above, the clustering model generation unit 321 calculates a feature vector for each word obtained by morphological analysis of the word of mouth, and generates a clustering model based on the calculated feature vector. According to the generated clustering model, search phrases including expressions similar to word-of-mouth can be clustered with high accuracy. In addition, the clustering model can be generated only from word of mouth.

  A spot database and a category database can be generated by using the built clustering model and word-of-mouth. The spot database and the category database can be generated only from reviews. Moreover, these databases can be expanded by acquiring the latest reviews as needed. And since word-of-mouth reflects the latest terms used when evaluating or expressing spots and categories, it is also possible to support searches using the latest terms by using each database generated. Can do.

  Further, the cluster determination unit 323 determines a cluster of feature words using the clustering model, and the spot DB generation unit 324 stores the clusters and spots determined by the cluster determination unit 323 in association with each other. Thereby, even if it is a case where the search phrase which consists of the word which is not matched with the spot directly is input, the search part 25 can detect an appropriate spot by using the cluster corresponding to a word. .

  Similarly, the category DB generation unit 326 stores the clusters determined by the cluster determination unit 323 and the categories classified by the category classification unit 325 in association with each other. Thereby, even if the category discrimination | determination part 23 is a case where the search phrase which consists of the word which is not matched with the category directly is input, it can determine an appropriate category by using the cluster corresponding to a word. it can.

  Further, the feature word extraction unit 322 extracts feature words and calculates their weights, and the spot DB generation unit 324 stores spots, clusters, feature words, and weights in association with each other. As a result, each feature word included in one cluster can be identified by the weight value of the degree of relevance with the spot. Therefore, the search unit 25 can rank the search results according to the magnitude of the relevance between the feature word corresponding to the search phrase and the spot.

  Similarly, the category DB generation unit 326 stores categories, clusters, feature words, and weights in association with each other. As a result, for each feature word associated with one category, the magnitude of relevance with the category can be specified by the weight value. Therefore, the category determination unit 23 can rank the category determination results according to the degree of relevance between the feature word corresponding to the search phrase and the category.

(About relearning)
When using a model generated by supervised machine learning in the search, teacher data corresponding to the search result of the search may be generated, and the generated model may be updated by performing machine learning again with the teacher data. For example, it is assumed that a certain search phrase is input, category determination (S204) and spot search (S206) are performed, and one of the spots notified to the information processing terminal 1 is selected by the user. In this case, it is considered that the selected spot was a spot along the user's will. Therefore, the search phrase or the words constituting the search phrase, the feature vector thereof, and the spot or the category thereof can be associated with each other and used as teacher data. For example, it is good also as teacher data for updating the classification model which a category classification | category part uses by matching a search phrase and the category of the selected spot. By updating the classification model by re-learning using teacher data, the classification accuracy in S401 can be improved.

  [Modification of Category Database and Spot Database Generation]

(1: Configuration to achieve)
Below, based on FIG. 10, the modification provided with the function which produces | generates the category database and spot database different from FIG. 7 in the information storage device 3 is demonstrated. The information storage device 3 includes a timing device 34 in addition to the storage device 31, the storage control device 32, and the storage communication device 33. The function of each part can also be realized by a program, for example. In other words, the information storage device 3 shown in FIG. 7 and the information storage device 3 shown in FIG. 10 have the same configuration except that the timing device 34 is connected to the storage control device 32. Below, the description which overlaps with the description of FIG. 7 is abbreviate | omitted. In addition, in generating the category database and the spot database, word-of-mouth information is used as posted article information posted on a predetermined site of the external information processing apparatus 4. For example, the information storage device 3 and the external information processing device 4 are connected by wireless communication via the public communication network 50. In FIG. 10, the flow of information that is communicated via the public communication network 50 is illustrated by double arrows.

  In the information storage device 3 shown in FIG. 10, the storage control device 32 is electrically connected to the time measuring device 34. The accumulation control device 32 is configured to acquire time information from the time measuring device 34. The spot DB generation unit 324 generates a spot database by associating time information in addition to spots, feature words, clusters, and weight values. The category DB generation unit 326 generates a category database by associating time information with the category, feature word, cluster, and weight value. The time information is, for example, information on the time measured by the time measuring device 34. The time measuring device 34 is configured to be able to measure the year, month, day, and time by executing a time measuring program on the computer, like the time measuring unit 26 of the information search device 2.

(2: Process flow)
FIG. 11 shows an example of processing for updating the spot database and the category database when the information storage device 3 acquires word-of-mouth information from the external information processing device 4. In the information storage device 3, the storage communication device 33 acquires word-of-mouth communication from the external information processing device 4 at predetermined time intervals (S111). More specifically, the information storage device 3 collects word-of-mouth information via the SNS WebAPI.

  Moreover, the information storage device 3 analyzes a new word of word in the acquired word of mouth information. The information storage device 3 discriminates whether or not the new word of mouth is written within a predetermined period in order to analyze the new word of mouth. The predetermined period may be, for example, a time that is a predetermined time after the current time measured by the time measuring device 34. Next, the information storage device 3 analyzes a new word of mouth by machine learning (S112). The analysis of a new word of mouth can be performed in the same manner as the processing in FIGS.

  The information storage device 3 counts the number of times a new spot is detected within a predetermined period as a result of analyzing a new word of mouth. The information storage device 3 can determine whether or not the spot analyzed from the word-of-mouth information is a new spot by comparing with a spot database 311 in which spots are registered in advance. In order to count the number of times a new spot has been detected, the information storage device 3 stores the number of new spot detections in the temporary database 312 shown in FIG. In the information storage device 3, the temporary database 312 may be stored in the storage device 31, for example. In the information storage device 3, if the number of new spot detections is greater than a predetermined threshold number or the threshold number, the spot database generating unit 324 adds the new spot to the spot database 311 (S113). For example, the spot database 311 may be stored in the storage device 31.

  In the information storage device 3, if the number of new spot detections is less than a predetermined threshold number in a predetermined unit time, the spot database generating unit 324 deletes the new spot from the temporary database 312 (S114). The predetermined unit time may be the same as or different from the predetermined period.

  Next, the information storage device 3 analyzes the word-of-mouth information for the existing spot. The information storage device 3 discriminates whether or not the spot analyzed from the word-of-mouth information is an existing spot by comparing with a spot database 311 in which spots are registered in advance. The information storage device 3 analyzes word-of-mouth on an existing spot using machine learning (S115). Analysis of word-of-mouth for an existing spot can be performed in the same manner as the processing in FIGS.

  Note that the step of analyzing the comment of a new word of mouth and the step of analyzing the word of mouth to the existing spot may not be the order of the new analysis step of S112 and the existing analysis step of S115. A new analysis step may be performed after the step. In the information storage device 3, a new analysis step for analyzing a new word of mouth and an existing analysis step for analyzing a word of mouth to an existing spot may be performed in parallel.

  (3: Summary)

[Other variations]
Below, the modification of the information processing terminal 1 is explained in full detail. In the information processing terminal 1, when a user inputs a character into a search box for inputting a character string to be searched, the information search device 2 searches for a search phrase related to the input character, and information search is performed at the bottom of the search box. Search result candidates searched by the apparatus 2 are displayed.

  The information processing terminal 1 is configured so that a bookmark can be attached to a place that the user wants to go to or a place that the user has visited. In the information processing terminal 1, the user can check the check box to see whether or not the user has performed, so that the user can go to the checked place. The place where the user bookmarks the user wants to go or the place where the user went is the basis of the recommendation. In the information processing terminal 1, the user may go to a predetermined place using the position information.

  The information processing terminal 1 displays a standard word that the user often uses and a hot word that the user recommends on the display device 13. The information processing terminal 1 is configured to be able to perform a search from a standard word and a hot word in addition to the search phrase input by the user in the search box of the information processing terminal 1.

  The information processing terminal 1 is configured to reflect a new comment if there is a new comment in an existing spot. The information processing terminal 1 can access the information storage device 3 via the information search device 2, detect spots in the information storage device 3 within a predetermined period, and cause the display device 13 to display a new spot. As illustrated in FIG. 12, the information processing terminal 1 causes the display device 13 to display a count value that is incremented for each predetermined reference value at the lower right of the icon 151 on the map 150. The count value is, for example, a numerical value that increases the count for each predetermined reference value when a predetermined number of users or more leave a favorable comment on the word of mouth. The information processing terminal 1 may display an existing spot or a new spot by changing the color of the icon 151. For example, the information processing terminal 1 may illustrate a heart mark 153 that indicates a spot that the user wants to go to the upper left of the icon 151. The information processing terminal 1 may illustrate a star mark 154 indicating recommendation on the upper right of the icon 151, for example.

  The information processing terminal 1 is not limited to the configuration in which the map information is stored in the terminal storage device 15 in advance. The information processing terminal 1 may have a configuration in which map information is stored in the terminal storage device 15 by communication from the information search device 2. As map information, for example, topographic maps, topographic maps, geological maps, land use maps, housing maps, route maps, road maps, guide maps, aerial photographs, satellite photographs, or old maps can be used. The map information may be raster data or vector data, for example.

  The information processing terminal 1 may have a navigation function. When the information processing terminal 1 has a navigation function, the information processing terminal 1 may be configured to display a recommendation on a map if it is close to a checkpoint on the route. The check point may be, for example, a POI that the user wants to recommend, a treasure buried spot in a treasure hunting game, or an electric vehicle charging station. When the information processing terminal 1 obtains information from a plurality of SNSs, the information processing terminal 1 may register another ID that links the login IDs of the plurality of SNSs.

  Below, the modification of the information search device 2 is explained in full detail. The information search device 2 searches for a search phrase by estimating that a word that frequently appears in a word-of-mouth during a predetermined period collected from the SNS or the Web is most related to the search history, the hot word, and the standard word. The information search device 2 may be configured to search for any combination of a search history, a hot word, and a standard word. A hot word is a word statistically processed per unit time. A hot word is a word that frequently appears in word of mouth per unit time. In addition to the words that have been statistically processed per unit time, the hot word may be a word of a spot within a predetermined range from the search point. Thus, the hot ward can include events such as local festivals. In other words, the hot word can be said to be a word recommended to the user. The standard word is a word estimated to be frequently used by the user.

  Hereinafter, a hot spot is also called a hot spot. When searching for a hot spot, the information search device 2 only needs to be configured so as to be searched from information within a predetermined period from the current time in the storage database stored in the storage device 31.

  The information search device 2 may perform a search based on hot spot information and usage history information in addition to a search phrase, for example, when the user operates the information processing terminal 1. The hot spot information includes, for example, a new spot newly registered in the spot database 311 in the storage storage device 31 of the information storage device 3. Examples of the usage history information include search history information searched by the user in the past and registration information registered by the user in the past. In other words, the usage history information can be said to be operation history information that the user operated the information processing terminal 1.

  Since the information search device 2 searches from the information storage device 3 using the use history information of the user, the searched search target is optimized for each user. In other words, the information search device 2 uses the usage history as a parameter to the user even if a large amount of user attribute information indicating the user attribute is not stored in the storage device 31 of the information storage device 3 in advance. It is configured to be able to provide recommended words. The information search device 2 may acquire position information acquired from a sensor that acquires position information from a public communication base station, in addition to the GPS in which the information processing terminal 1 is a satellite positioning system. When the new spot is registered in the storage device 31 of the information storage device 3, the information search device 2 displays the hot spot on the display device 13 of the information processing terminal 1 so that the terminal communication device 12 of the information processing terminal 1 can display the hot spot. It may be configured to be able to make a push notification.

  Below, the modification of the information storage device 3 is explained in full detail. The information storage device 3 may acquire word-of-mouth information from a plurality of external information processing devices 4. The information storage device 3 is preferably configured to extract only Japanese from the word-of-mouth information in advance or delete spaces or symbols when analyzing word-of-mouth. Word-of-mouth is often not in accurate Japanese. In addition, the word of mouth may include a symbol. The word-of-mouth information may not be able to perform a desired morphological analysis if the word-of-mouth is not in correct Japanese or contains a symbol. When analyzing word-of-mouth, the information storage device 3 can perform a more accurate search by extracting only Japanese from word-of-mouth information in advance or deleting spaces or symbols.

  For example, when more than a predetermined number of users leave favorable comments on word-of-mouth, the information storage device 3 can increase the count for each predetermined reference value to a number greater than the predetermined count. The new spot is registered in the spot database 311. The information storage device 3 determines the category of whether the registered new spot is, for example, a cafe, a restaurant, or a landscape. The information storage device 3 registers the new spot in the category database together with the determined category. In other words, the information storage device 3 stores hot words or standard words in the storage device 31.

  As described above, even if the user does not know the name of “Tonkotsu Ramen Shop” that the user has performed before, when the user inputs “Ramen” in the search box, the information retrieval system 10 uses the usage history information associated with the individual user. You can search for “Name of Tonkotsu Ramen Shop”.

  In addition, even if the information search system 10 replaces the information processing terminal 1 and the user's search history disappears from the information processing terminal 1, the information search system 10 replaces the information using the use history information registered in the information search device 2 or the information storage device 3. A similar search can be performed on the information processing terminal 1.

  The information storage device 3 of the information search system 10 determines what the user has based on the list of places where the user wants to go or the list of places where the user has visited, and the search history that the search results have been viewed down to the detailed screen. Create a search seed for each user who is interested in The information search device 2 can discriminate the search type of the user and other users of a similar type by machine learning. The information processing terminal 1 can perform it with respect to the user who searched for the recommendation of the other spot which the other user performed. That is, for example, if the frequency of use of the user increases, the information search system 10 searches for a list of places where the user wants to go or a list of places where the user wants to go and a search result to see a detailed screen. Based on the above, it is configured to recommend a place recommended to the user.

  The information search system 10 determines, for example, by machine learning whether it is a valid comment recommending something from a word of mouth added by SNS, such as “I went to lunch today”. In the case of a valid comment that is recommended, the information processing terminal 1 outputs a recommended location on the map displayed on the display device 13. In other words, the information storage device 3 selects a positive comment that is newly recommended to everyone from word-of-mouth of SNS by machine learning, and displays a spot related to the comment on a map.

DESCRIPTION OF SYMBOLS 10 Information search system 11 Input device 13 Display device 22 Position information acquisition part 24 Feature word generation part 25 Search part

Claims (4)

An input device for inputting a search phrase;
A feature word generation unit that generates a feature word related to a word representing a search target from the search phrase;
A search unit that searches the search target from a storage database that stores the feature word and the search target corresponding to the feature word;
A display device for displaying the search object,
The search unit is configured to search for the search target corresponding to the feature word based on the feature word. It further includes a position information acquisition unit that acquires position information indicating a position on the map as a search starting point,
The search target has point information indicating a specific point,
The information search system according to claim 1, wherein the search unit searches the search target corresponding to the feature word within a predetermined range from the position based on the feature word and the position information. In the accumulation database, a feature word group consisting of a plurality of feature words having similar feature information indicating a feature of a word is associated with the search target,
The feature word generation unit determines the feature word group corresponding to the word based on the feature information of the word included in the search phrase,
The information search system according to claim 1, wherein the search unit detects the search target associated with the feature word group determined by the feature word generation unit from the accumulation database. The information search system according to any one of claims 1 to 3, wherein the storage database is generated based on word-of-mouth information acquired from an external information processing device within a predetermined period from a current time.