JP2015102957A - Information search system, information search device, information search method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an information search system that can provide a user with keywords (character strings) allowing the user to acquire unknown latest topics.SOLUTION: An information search system 100 includes sentence information acquisition means for acquiring pieces of sentence information from text data collected through search based on a keyword, character string selection means for selecting one or more character strings satisfying predetermined conditions from each of the pieces of sentence information and storing the selected character strings in character string storage means for each of the corresponding sentence information, and information output means for outputting information for displaying, to a user, the selected character strings for each of the corresponding sentence information.

Description

  The present invention relates to an information search system that provides a user with an information search function.

  Search words that have increased rapidly due to internet searches, etc. during a predetermined period, and words that have increased rapidly due to news, etc., during a predetermined period are stored as event words. Word) or a word analyzed in advance based on the frequency of appearance from the news containing the event word, etc., is stored as an event word related word, and in such a situation, one of the event words is input as a search word for net search etc In such a case, there is an information retrieval system configured to display a list of the above-described event word related words (see Patent Document 1).

JP 2007-34466 A

  However, such an information retrieval system is assumed to have the following problems. That is, when event word related words are obtained from AND search of event words in the net search, these event word related words are listed according to the user's event word input. Since it is information, it is often known biased information for users of the net search, and the association between the event word and the event word related word is also just the relationship considered by the input person. Therefore, it is difficult to acquire a new topic that is not known by using event word-related words obtained from AND search with event words in the net search.

  In addition, when the event word related word is analyzed in advance based on the appearance frequency or the like from the news including the event word, the event word related word is obtained by analyzing the past news. It is difficult to get the latest topic by word related words.

  The objective of this invention is providing the information search system which can solve the subject mentioned above.

Embodiments of the present invention
From text data collected by keyword-based search (for example, external log 502 (text data) acquired from the collected WEB page shown in FIG. 20), sentence information related to the keyword (for example, text hit by keyword search) Sentence information acquisition means (for example, an input information analysis unit 41 shown in FIG. 20) for acquiring a question sentence that is a part of the data;
One or a plurality of character strings satisfying a predetermined condition (for example, related verbs that are meaning-identifiable character strings) are selected from each of the sentence information, and the character strings are stored for each corresponding sentence information. A character string selection means (for example, the sentence analysis unit 43 shown in FIG. 20) stored in the means (for example, the related term dictionary 50 shown in FIG. 20);
Information for displaying the selected character string to the user for each of the corresponding sentence information (for example, a related term / co-occurrence word list display screen 650 as shown in FIG. 37 is displayed to the user) An information search system configured to include information output means (for example, the input information analysis unit 41 shown in FIG. 20) that outputs the input specific information including the related term / co-occurrence word data 52 shown in FIG. (For example, the information search system 100 shown in FIG. 20).

  With such a configuration of the present invention, the selected character string is obtained as information originating from the information sender, and a new topic that is not known can be acquired. In addition, since the selected character string (related term) is the latest information obtained from the search based on the keyword, the latest information can be obtained.

The feature of the embodiment of the present invention is further
The character string selection means is:
It is configured to select the character string without collating with character string data stored in advance (for example, a dictionary including morpheme data or the like).

  With such a configuration of the present invention, it is not necessary to create and maintain a dictionary including morpheme data in advance, and an information search system can be easily constructed.

The feature of the embodiment of the present invention is further
The character string selection means further includes:
Character string search means (for example, a character string search processing unit 43b shown in FIG. 21) for searching for the same character string from the text data;
For the same character string, it is an index indicating the degree of difference of the previous adjacent character (for example, how much the character appearing immediately before the searched “same character string” is different (there is a variation), Based on the number of patterns of characters appearing as adjacent characters of) and the degree of difference of the subsequent adjacent characters (for example, how much the character appearing immediately after the searched “same character string” is different (variation exists) A different degree determination means (for example, a different degree determination processing unit 43c shown in FIG. 21) for determining an index indicating the number of patterns of characters that appear as subsequent adjacent characters),
Specific character string determining means for determining whether or not the same character string is a specific character string (for example, a related term) based on the difference degree of the preceding adjacent character and the difference degree of the subsequent adjacent character. For example, a related term determination processing unit 43d) shown in FIG.
The character string selection means is configured to select the character string from the determined specific character string.

  With such a configuration of the present invention, related terms are determined according to the degree of difference between adjacent characters, and it is not necessary to perform comparison processing with a dictionary including morpheme data etc., and the processing can be speeded up. The display processing of the lyrics can be performed in real time.

The feature of the embodiment of the present invention is further
Scenario data storage means (for example, scenario data 28 and scenario data 55 shown in FIG. 20) for storing scenario data (for example, data consisting of statements as shown in FIG. 14) for defining response information related to the topic;
Response information determination means (for example, a response information determination unit 25 shown in FIG. 20) for determining the response information including the selected character string based on the scenario data;
Response information output means (for example, the output control unit 26 shown in FIG. 20) for outputting the response information determined by the response information determination means is further provided.

  With such a configuration of the present invention, it is possible to diversify the display mode when the selected character string (related term) is displayed to the user, and to easily execute and manage display editing.

The feature of the embodiment of the present invention is further
It further includes dictionary comparison means (for example, dictionary comparison processing unit 46c shown in FIG. 22),
When the character string selection unit stores the character string in the character string storage unit, each of the character string selection units stores a corresponding dictionary (for example, the related term dictionary 50 shown in FIG. 22) according to the collection condition of the text data. Remember,
The dictionary comparison means performs a comparison process for comparing a plurality of the dictionaries, stores the comparison result in a comparison result storage means (for example, comparison result data 54 shown in FIG. 22),
The response information determining means determines the response information including the comparison result based on the scenario data;
The response information output means outputs the response information determined by the response information determination means,
The dictionary comparison unit is further configured to perform the comparison process and automatically update the comparison result stored in the comparison result storage unit when at least one of the plurality of dictionaries is updated. That is.

  With such a configuration of the present invention, the selected character string (related term) can be automatically updated, and a change in the appearance status of the related term is grasped and displayed based on a comparison result at each update timing. Thus, it is possible to diversify the display mode when displaying the related words to the user.

The feature of the embodiment of the present invention is further
The information output means includes
When one of the character strings corresponding to one of the sentence information and one of the character strings corresponding to sentence information different from one of the sentence information are common, the character corresponding to the one sentence information It is configured to output information for displaying the set of columns in association with the set of character strings corresponding to the other sentence information.

The feature of the embodiment of the present invention is further
The information output means includes
Outputting information for displaying all of the set of character strings corresponding to the predetermined one or more sentence information;
The display order of the character strings is configured to be determined according to a usage mode of the user with respect to the character strings.

Further embodiments of the present invention are:
Keyword input means (for example, the input control unit 21 shown in FIG. 20) for inputting a keyword as a text data collection condition;
When one or more character strings satisfying a predetermined condition are selected from each of the sentence information related to the keyword acquired from the text data collected based on the keyword, the selected character string is An information search device (for example, FIG. 20) configured to include information output means (for example, the output control unit 26 shown in FIG. 20) that outputs information for display to the user for each corresponding sentence information. The conversation control terminal device 2 ″) shown in FIG.

Further embodiments of the present invention are:
A sentence information acquisition step of acquiring sentence information related to the keyword from text data collected by keyword-based search;
A character string selection step of selecting one or more character strings satisfying a predetermined condition from each of the sentence information, and storing the character string in a character string storage unit for each corresponding sentence information;
The information search method is configured to include an information output step of outputting information for displaying the selected character string to a user for each corresponding sentence information.

Further embodiments of the present invention are:
On the computer,
Sentence information acquisition means for acquiring sentence information relating to the keyword from text data collected by keyword-based search;
Character string selection means for selecting one or more character strings satisfying a predetermined condition from each of the sentence information, and storing the character strings in character string storage means for each corresponding sentence information, and
It is a program for causing the selected character string to function as information output means for outputting information for displaying to the user for each corresponding sentence information.

  An effect of the embodiment of the present invention is that it is possible to provide a keyword (character string) that can acquire the latest topic that is not known to a user who uses the information search system.

It is a figure which shows the outline | summary of a topic provision system. It is a figure which shows the outline | summary of a conversation control terminal device. It is a figure which shows the outline | summary of a maintenance apparatus. 1 is a block diagram showing an outline of a system configuration of a topic providing system 1. FIG. It is a flowchart which shows the specific process of the statement of scenario data. It is a flowchart which shows the specific process of the statement of scenario data. It is a flowchart which shows the specific process of the statement of scenario data. It is a flowchart which shows the specific process of the statement of scenario data. It is a flowchart which shows the specific process of the statement of scenario data. It is a flowchart which shows the specific process of the statement of scenario data. It is a flowchart which shows the specific process of the statement of scenario data. It is a flowchart which shows the specific process of the statement of scenario data. 6 is a diagram illustrating an example of output to an output unit 220. FIG. It is a figure which shows the specific example of the statement of scenario data. It is a figure which shows the process which produces | generates response information based on topic analysis, and outputs response information to an output part. It is a figure which shows the example of a structure of a topic introduction list. It is a figure which shows the process of the extraction of a topic, the production | generation of a related term dictionary, and the production | generation of a preference dictionary. The flow of processing from when a topic is input to the topic news setting screen of the maintenance device 3 until a topic introduction list is generated and output based on the related term dictionary and the topic list is shown. It is a figure for demonstrating the technical idea of an information search system. It is a figure which shows the outline | summary of an information search system. It is a figure which shows the outline | summary of the sentence analysis part of an information search system. It is a figure which shows the outline | summary of the information update part of an information search system. It is a figure which shows the screen transition of a FAQ search system. It is a flowchart showing the display process of FAQ candidate display screen. It is a figure which shows the outline | summary of the sentence analysis process of an information search system. It is a figure which shows an example of an external log. It is a figure which shows an example of a related term dictionary. It is a flowchart showing the character string search process of an information search system. It is a figure which shows the mechanism of the character string search using a suffix array and binary search. It is a figure which shows the mechanism of the character string search using a suffix array and binary search. It is a flowchart showing the process sequence of a different degree determination process of an information search system. It is a figure which shows the mechanism for determining the difference degree of the adjacent character before and behind. It is a flowchart showing the display process of a FAQ display screen. It is a flowchart showing the display processing of a related term / co-occurrence word list screen. It is a figure which shows the example of the screen of a FAQ search system. It is a figure which shows the example of the screen of a FAQ search system. It is a figure which shows the example of the screen of a FAQ search system. It is a figure which shows the example of preference data, and the example of the screen of FAQ search system. It is a figure which shows the process outline | summary of the information update part of an information search system. It is a flowchart showing the process sequence of the character string extraction process of the information update part of an information search system. It is a flowchart showing the process sequence of the dictionary comparison process of the information update part of an information search system. It is a figure which shows the character string extraction process and dictionary comparison process of the information update part of an information search system. It is a figure which shows the character string extraction process and dictionary comparison process of the information update part of an information search system. It is a figure which shows the character string extraction process and dictionary comparison process of the information update part of an information search system. It is a figure which shows the character string extraction process and dictionary comparison process of the information update part of an information search system with the content of a related term dictionary. It is a figure which shows the content of the comparison result data memorize | stored by the dictionary comparison process of the information update part of an information search system. It is a figure which shows the character string extraction process and dictionary comparison process of the information update part of an information search system with the content of a related term dictionary. It is a figure which shows the character string extraction process and dictionary comparison process of the information update part of an information search system with the content of a related term dictionary. It is a figure which shows the character string extraction process and dictionary comparison process of the information update part of an information search system with the content of a related term dictionary. It is a figure which shows the example of the hardware constitutions of the computer which comprises the topic provision server contained in the information search system of this invention. It is a block diagram which shows the outline of the other system configuration | structure of a topic provision system.

  Hereinafter, the present embodiment will be described with reference to the drawings.

  FIG. 1 is a diagram showing an overview of the topic providing system 1. FIG. 2 is a diagram showing an outline of the conversation control terminal device 2. FIG. 3 is a diagram showing an overview of the maintenance device 3.

<<< Overview of the topic providing system >>>
As shown in FIG. 1, the feature of the topic providing system 1 according to this embodiment is as follows.
An input unit for a user to input input information;
An input information analysis unit that analyzes the input information and generates input specific information;
A scenario data storage unit for extracting scenario data for defining response information on the topic;
A response information determination unit that determines the response information based on the scenario data and the input identification information;
And an output unit that outputs the response information determined by the response information determination unit.

  As shown in FIG. 1, the topic providing system 1 according to the present embodiment mainly includes an input unit, an input information analysis unit, a scenario data storage unit, a response information determination unit, and an output unit. In FIG. 1, these structures are indicated by solid-line squares. The transmission unit, the reception unit, and the switching input information input unit indicated by dotted-line squares will be described later. A portion surrounded by a broken line in FIG. 1 is the configuration of the conversation control terminal device 2 shown in FIG.

  The input unit is a member or a part for the user to input input information. The input part should just be what can input the information which a user desires as input information. For example, the input unit includes a keyboard, a touch panel, a microphone, a camera, and the like. The user can input text data, voice data, image data, and the like from the input unit. The input information input to the input unit is supplied to the input information analysis unit described below. The input information is preferably supplied to the input information analysis unit via a transmission unit described later.

  The input information analysis unit analyzes the input information and generates input specifying information. The input specifying information is information generated as a result of analyzing various types of information included in the input information. For example, there is a statistical analysis of the number and frequency of specific keywords (such as related terms described later) included in the input information. Furthermore, by analyzing the input information, it is possible to analyze the user's intention and preference from a question input by the user. Furthermore, a relative analysis result can also be acquired by comparison with other users. Furthermore, data such as an analysis dictionary can be generated in advance, and input information can be analyzed using the analysis dictionary. The input information analysis unit supplies the generated input specifying information to a response information determination unit described later.

  The scenario data storage unit is a member or part for extracting scenario data. The scenario data is data stored in advance in a scenario data storage unit (a plurality of scenario data) to be described later. Scenario data determined to be necessary based on the input specifying information generated by the input information analysis unit is extracted, and the extracted scenario data is stored in the scenario data storage unit. The scenario data extracted from the scenario data storage unit (a plurality of scenario data) is stored in the scenario data storage unit via a receiving unit and a response information determination unit described later.

  The scenario data is data for defining response information related to the topic provided to the user. That is, the scenario data includes topic information to be provided to the user.

  Further, the scenario data includes a topic introduction list including information on a plurality of topics. The topic introduction list is provided to the user. By selecting a topic included in the provided topic introduction list, the user can use the input information as alternative information. Since the user can advance the conversation by the selection operation, the user's input operation can be simplified and the conversation can be smoothly advanced as compared with the case of inputting characters.

  In addition, a plurality of topics can be provided to the user by the topic introduction list, and the user can learn various topics and can expand the range of interest.

  Further, the scenario data preferably includes information for greeting the user. By including not only information for providing a topic to the user but also information for greeting in the scenario data, it is possible to greet the user and make the conversation more natural.

  The scenario data is data created in advance including information that the subscriber of the topic providing system 1 wants to provide to the user. Information to be provided to the user can be defined by the scenario data.

  Furthermore, scenario data consists of a plurality of statements. The statement includes output information, output commands, control commands, and the like.

  The output information is information output by the output unit. The output information includes topic information and greeting information. Topic information and greeting information are information for providing a user with a conversation with the user.

  The output command is a command for controlling output specifications when topic information or greeting information is output to the output unit. For example, it is a command for erasing the screen, making a line break, controlling the output time, or displaying a predetermined image.

  The control command is a command for determining a statement, switching a topic name (for example, a theme), or changing a state control index. In particular, the determination includes a determination for branching according to time and time, and a determination for branching depending on the contents of the state control index. It is possible to make a transition to a predetermined statement by branching by judgment.

  In the present embodiment, when there is no need to distinguish each statement, the statement is synonymous with scenario data.

  Note that it is not necessary to include all of the output information, the output command, and the control command in a single statement. For example, a predetermined statement can be composed of only output information, can be composed of only output commands, or can be composed of only control commands.

  Thus, the statement includes not only information provided to the user but also various commands. As a result, topic information and greeting information can be output with various specifications in the output unit, and conversation can be naturally and smoothly advanced.

  As described above, scenario data (statements) includes output information, output commands, control commands, and the like. A topic control rule can be constructed by appropriately defining output information, output commands, and control commands. In particular, the topic control rules desired by the contractor can be constructed by including in the scenario data various information (topics) that the contractor of the topic providing system 1 wants to provide to the user.

  The scenario data only needs to be defined as appropriate for the information that the contractor wants to provide, so the topic control rules can be changed, added, modified, etc. without depending on the advanced and specialized knowledge and technology of the topic providing system 1 in general. The maintenance work can be performed separately.

  The response information determination unit determines response information. The response information is determined based on the scenario data and input specifying information supplied from the input information analysis unit described above. That is, the response information is determined using the input specifying information obtained by analyzing the input information input by the user. Therefore, the intention of the subscriber of the topic providing system 1 can be reflected in the response information by the scenario data, and the intention of the user can be reflected in the response information by the input specifying information. It is possible to reflect and generate response information. A natural response can be realized by smoothing the conversation by balancing the contractor and the user of the topic providing system 1.

  The response information includes a statement of scenario data. In addition to the output information provided to the user included in the statement, various commands such as an output command can be included in the response information. In this way, topic information and greeting information can be output from the output unit with various specifications.

  The output unit outputs the response information determined by the response information determination unit. The user is provided with the topic by recognizing the response information output from the output unit.

  As described above, the topic providing system 1 according to the present embodiment can provide various topics to the user based on the response information output to the output unit. That is, the topic providing system 1 according to the present embodiment generates input specifying information from input information, determines response information from scenario data and input specifying information, and provides various topics to the user by outputting response information. .

  The topic providing system 1 according to the present embodiment determines response information based on scenario data (for example, a statement and a topic introduction list described later) and input specific information analyzed by the input information analysis unit. Natural response that matches the flow of

  In addition, response information on topics can be defined based on scenario data, so topic control rules can be changed, added, modified, etc. without relying on advanced and specialized knowledge and technology throughout the topic control system. The maintenance work can be performed separately.

Further, as shown in FIG. 1, the feature of the topic providing system 1 according to the present embodiment is as follows.
A state control index storage unit for storing a state control index related to the input information and the response information;
The response information determination unit is to determine the response information by adding the state control index in addition to the scenario data and the input specifying information.

  The topic providing system 1 includes a state control index storage unit. The state control index storage unit stores a state control index. The state control index is an index related to input information and response information. The state control index is an index mainly based on the conversation history, and further indicates the user's emotion and personality that can be determined based on the conversation history. For example, there are an index defined based on input information input by the user in the past and an index defined based on response information provided to the user in the past. In addition, there is an index or the like indicating the user's emotion or personality obtained from the user's input to response information provided to the user in the past.

  The response information determination unit determines the response information by adding a state control index in addition to the scenario data and the input specifying information. In this way, response information is determined using the state control index, so it is necessary to provide topics or advance conversations based on past conversations with the user and the user's emotions and personality obtained from the conversation. Can do. Therefore, it is possible to prevent the same topic from being provided to the user in duplicate or to provide the user with a leap topic, and a smooth conversation can be promoted according to the user's emotion and personality.

  In the present embodiment, the state control index storage unit is provided in the conversation control terminal device 2. The state control index is preferably determined or changed by the response information determination unit. The state control index is preferably determined by the response information determination unit based on the scenario data and the input specifying information.

  The topic providing system 1 according to the present embodiment determines the response information using the state control index in addition to the scenario data and the input specific information, and thus realizes a natural response that more matches the topic and the flow of conversation. Can do.

Furthermore, as shown in FIG. 1, the feature of the topic providing system 1 according to this embodiment is as follows:
The scenario data includes information defining transition to a different topic (for example, topic switching information described later),
A topic switching unit that switches scenario data from scenario data for defining response information on a current topic to scenario data for defining response information on a different topic in accordance with information defining transition to the different topic Is further provided.

  In the present embodiment, the topic switching unit includes a switching input information input unit and an input information analysis unit. The topic switching unit determines whether to switch scenario data based on the scenario data and the input specifying information. Specifically, it is preferable to switch the scenario data based on the state control index. The switching input information input unit transmits the topic switching input information to a transmission unit (to be described later) and is supplied to the input information analysis unit. The input information analysis unit extracts the scenario data stored in the scenario data storage unit (a plurality of scenario data) based on the topic switching input information in addition to the input information.

  The scenario data includes information defining transition to a different topic (topic name). The topic switching unit switches scenario data. This switching is to switch from scenario data for defining response information on the current topic to scenario data for defining response information on a different topic.

  For example, all scenario data is stored in a server, etc., and scenario data is generated by recombining from all scenario data of the server based on information defining transition to a different topic. It is stored in the scenario data storage unit. This recombination of scenario data can be executed by determining a combination of a plurality of statements according to the topic name.

  Therefore, even when moving from one topic to another in a conversation with the user, it can be transitioned to another topic according to the information that defines the transition to a different topic, can correspond to any topic, It can cope with various users. Other topics can be provided to the user by the rearranged scenario data.

  Further, since scenario data should be prepared for each topic (topic name), maintenance of scenario data becomes easy. Specifically, when the scenario data needs to be changed, only the scenario data need be corrected. If a new topic is required, only the scenario data need be added. Furthermore, when it is no longer necessary due to an old topic, only the scenario data need be deleted.

  Scenario data can be specified for each topic (topic name) as appropriate for information that the contractor wants to provide, so even if the topic increases, advanced and specialized knowledge throughout the topic providing system 1 Maintenance work such as changing, adding, and correcting topic control rules can be performed for each topic without depending on the technology.

  Since it has information defining transition to a different topic, it is possible to easily match the transition of scenario data even when such scenario data is updated.

  For example, it is preferable to determine whether or not to switch topics based on a personality index described later among the state control indices. The personality index is an index indicating whether the user is active or reluctant to the topic.

  Since the topic providing system 1 according to this embodiment can switch topics using scenario data, it can realize a natural response according to the flow of topics and conversation.

  A transmission unit, a reception unit, and a switching input information input unit indicated by dotted squares in FIG. 1 will be described. The topic providing system 1 according to the present embodiment can include these transmission unit, reception unit, and switching input information input unit.

  Further, the transmission unit shown in FIG. 1 is a device or member for transmitting input information to the outside. Any device that transmits input information to the outside may be used. The outside can be, for example, a server, the conversation control terminal device 2, or the like.

  Further, the receiving unit shown in FIG. 1 is a device or member for receiving input specifying information. The input specifying information is generated externally. That is, the receiving unit is a device or member that receives input specifying information generated externally. Outside, the input information transmitted from the transmitting unit is analyzed to generate input specifying information, and the generated input specifying information is transmitted to the receiving unit.

  Furthermore, the switching input information input unit shown in FIG. 1 generates topic switching input information (for example, a personality index, which will be described later) according to information defining transition to a different topic. Information defining the transition to a different topic is information included in the scenario data, for example, topic switching information described later.

  The topic switching unit described above preferably includes an input information analysis unit and a switching input information input unit. Since topic switching input information is generated based on the input information, it is possible to transition to a topic reflecting the user's intention.

  Further, the scenario data storage unit (a plurality of scenario data) shown in FIG. 1 stores a plurality of scenario data. Here, the plurality of scenario data are all scenario data corresponding to the topic names necessary for talking with the user. Of all scenario data, scenario data determined to be necessary based on the input identification information is extracted.

<<< Overview of Conversation Control Terminal Device 2 >>>
As shown in FIG. 2, the feature of the conversation control terminal device 2 according to this embodiment is as follows.
An input unit for a user to input input information;
A scenario data storage unit for storing scenario data for defining response information on the topic;
A state control index storage unit that stores a state control index related to the input information and the response information;
A response information determination unit that determines the response information based on the scenario data and the state control index;
And an output unit that outputs the response information determined by the response information determination unit.

  As shown in FIG. 2, conversation control terminal apparatus 2 according to the present embodiment mainly includes an input unit, a scenario data storage unit, a state control index storage unit, a response information determination unit, and an output unit. In FIG. 2, these configurations are indicated by solid squares. In FIG. 2, a portion surrounded by a broken line is the configuration of the conversation control terminal device 2. Note that the scenario data storage unit (a plurality of scenario data) and the input information analysis unit indicated by dotted-line boxes are included in the topic providing server 4.

  The input unit is a member or a part for the user to input input information, similarly to the input unit of the topic providing system 1 according to the present embodiment. The input part should just be what can input the information which a user desires as input information. For example, the input unit includes a keyboard, a touch panel, a microphone, a camera, and the like. The user can input text data, voice data, image data, and the like from the input unit. The input information input to the input unit is supplied to the input information analysis unit described below. The input information is preferably supplied to the input information analysis unit via a transmission unit described later.

  The scenario data storage unit is a member or part for storing scenario data. The scenario data is data stored in advance in a scenario data storage unit (a plurality of scenario data) of the topic providing server 4 shown in FIG. Scenario data determined to be necessary based on the input specifying information generated by the input information analysis unit is extracted, and the extracted scenario data is stored in the scenario data storage unit. The scenario data extracted from the scenario data storage unit (a plurality of scenario data) is stored in the scenario data storage unit via a receiving unit and a response information determination unit described later.

  The scenario data is data for defining response information related to the topic provided to the user. The scenario data includes topic information to be provided to the user. The configuration and functions of scenario data used in the conversation control terminal device 2 are the same as the scenario data of the topic providing system 1 according to this embodiment.

  The conversation control terminal device 2 according to the present embodiment includes a state control index storage unit. The state control index storage unit stores a state control index. The state control index is an index mainly based on the conversation history, and further indicates the user's emotion and personality that can be derived based on the conversation history. For example, there are an index defined based on input information input by the user in the past and an index defined based on response information provided to the user in the past. In addition, there is an index indicating the user's emotion and personality that can be derived from the user's input for response information provided to the user in the past.

  Thus, in the present embodiment, conversation control terminal device 2 includes a state control index storage unit. That is, it is not a configuration in which, for example, the topic providing server 4 or the like outside the conversation control terminal device 2 includes a state control index storage unit. Therefore, in the present embodiment, the conversation with the user is not controlled by an external device such as the topic providing server 4 but the conversation with the user is controlled by the conversation control terminal device 2.

  The response information determination unit determines response information based on the scenario data and the state control index supplied from the input information analysis unit of the topic providing server 4. The intention of the subscriber of the topic providing system 1 can be reflected in the response information by the scenario data.

  The response information includes a statement of scenario data. In addition to the output information provided to the user included in the statement, various commands such as an output command can be included in the response information. In this way, topic information and greeting information can be output from the output unit with various specifications.

  In addition, since response information is determined using a state control index, topics can be provided and conversations can be promoted based on past conversations with the user and the user's emotions and personality obtained from the conversation. . Therefore, it is possible to prevent the same topic from being provided to the user in duplicate or to provide the user with a leap topic, and a natural response can be realized by promoting a smoother conversation.

  The state control index is preferably determined or changed by the response information determination unit. The state control index is preferably determined by the response information determination unit based on the scenario data and the input specifying information.

  The output unit outputs the response information determined by the response information determination unit. The user is provided with the topic by recognizing the response information output from the output unit.

  Since the conversation control terminal device 2 according to the present embodiment provides both the scenario data storage unit and the state control index storage unit in the conversation control terminal device 2 and determines the response information, is it possible to have a conversation with the user? Can be determined and controlled by the conversation control terminal device 2, without significantly increasing the processing load in the conversation control terminal device 2, without increasing the load on the server, and also increase the network traffic Therefore, it is possible to smoothly advance the conversation according to the conversation flow with the user.

  Furthermore, since the conversation control terminal device 2 according to the present embodiment determines the response information based on the scenario data and the state control index, the response information can be determined according to the progress of the conversation with the user, and the load on the server It is possible to respond accurately according to the state of the user without increasing the value.

Furthermore, as shown in FIG. 2, the features of the conversation control terminal device 2 according to the present embodiment are as follows:
A transmission unit for transmitting the input information to the outside;
A receiving unit that receives the input specifying information generated by analyzing the transmitted input information, and
The response information determination unit determines the response information by adding the input specifying information to the scenario data and the state control index.

  The conversation control terminal device 2 according to the present embodiment further includes a transmission unit and a reception unit.

  The transmission unit transmits input information to the outside. What is necessary is just to transmit input information outside the conversation control terminal device 2. The outside can be, for example, a server or another conversation control terminal device 2.

  The receiving unit receives the input specifying information. The input specifying information is generated outside the conversation control terminal device 2. That is, the receiving unit is a device or member that receives input specifying information generated outside the conversation control terminal device 2. Outside the conversation control terminal device 2, the input information transmitted from the transmission unit is analyzed to generate input specification information, and the generated input specification information is transmitted to the reception unit of the conversation control terminal device 2.

  The response information determination unit determines the response information by adding input specifying information to the scenario data and the state control index. Response information is determined including input specifying information obtained by analyzing input information input by the user. Therefore, the intention of the subscriber of the topic providing system 1 can be reflected in the response information by the scenario data, and the user's intention can be reflected in the response information by the input specifying information. It is possible to reflect and generate response information. A natural response can be realized by smoothing the conversation by balancing the contractor and the user of the topic providing system 1.

  Since the conversation control terminal device 2 according to the present embodiment determines the response information by adding the input specific information, the response information can be determined including the input specific information that is the result of analysis performed outside the server or the like, The conversation can proceed smoothly according to the conversation flow.

Furthermore, as shown in FIG. 2, the features of the conversation control terminal device 2 according to the present embodiment are as follows:
The receiving unit receives scenario data extracted based on the input information,
The scenario data storage unit stores received scenario data.

  The receiving unit of the conversation control terminal device 2 according to the present embodiment receives the scenario data extracted based on the input information. That is, the scenario data is extracted outside the conversation control terminal device 2. Based on the input information transmitted to the outside of the conversation control terminal device 2, the scenario data is extracted based on the input information outside the conversation control terminal device 2. The extracted scenario data is transmitted to the reception unit of the conversation control terminal device 2.

  The scenario data storage unit stores scenario data received by the receiving unit of the conversation control terminal device 2. As described above, the configuration and functions of the scenario data used in the conversation control terminal device 2 are the same as the scenario data of the topic providing system 1 according to this embodiment.

  Since the conversation control terminal device 2 according to the present embodiment receives the scenario data extracted based on the input information, the scenario data can be switched based on the input information input by the user, and the conversation with the user The conversation can be smoothly conducted according to the flow of

Furthermore, as shown in FIG. 2, the features of the conversation control terminal device 2 according to the present embodiment are as follows:
The scenario data includes information defining transition to a different topic (for example, topic switching information described later),
A switching input information input unit that generates topic switching input information (for example, a personality index described later) according to information defining transition to the different topic,
The transmission unit transmits the topic switching input information to the outside,
The receiving unit is to receive scenario data based on the topic switching input information.

  The scenario data used in the conversation control terminal device 2 according to the present embodiment includes information defining transition to a different topic.

  The conversation control terminal device 2 according to the present embodiment includes a switching input information input unit. The switching input information input unit generates topic switching input information according to information defining transition to a different topic. Information defining the transition to a different topic includes, for example, topic switching information that is an element of a statement to be described later. The topic switching input information includes, for example, a personality index described later.

  The switching input information input unit determines whether to switch scenario data based on the scenario data and the input specifying information. Specifically, it is preferable to switch the scenario data based on the state control index. In the switching input information input unit, topic switching input information is transmitted to the transmission unit and supplied to the input information analysis unit. The input information analysis unit extracts the scenario data stored in the scenario data storage unit (a plurality of scenario data) of the topic providing server 4 based on the topic switching input information in addition to the input information.

  Furthermore, the transmission part of the conversation control terminal device 2 according to the present embodiment transmits the topic switching input information to the outside. The receiving unit receives scenario data based on the topic switching input information.

  It is possible to switch from scenario data for defining response information on the current topic to scenario data for defining response information on a different topic.

  For example, all scenario data is stored in a server or the like, scenario data is generated by rearranging all scenario data of the server based on topic switching input information, and the rearranged scenario data is the conversation control terminal device 2. Are stored in the scenario data storage unit.

  Therefore, even when moving from one topic to another in a conversation with the user, it can be transitioned to another topic according to the information that defines the transition to a different topic, can correspond to any topic, It can cope with various users.

  Further, since scenario data should be prepared for each topic (topic name), maintenance of scenario data becomes easy. Specifically, when the scenario data needs to be changed, only the scenario data need be corrected. If a new topic is required, only the scenario data need be added. Furthermore, when it is no longer necessary due to an old topic, only the scenario data need be deleted.

  It is preferable to determine whether or not to switch topics based on a personality index described later among the state control indices. The personality index is an index indicating whether the user is active or reluctant to the topic.

  According to the conversation control terminal device 2 according to the present embodiment, since the topic can be switched based on the state control index and the scenario data, the topic can be switched while viewing the state of the conversation with the user. The conversation can proceed smoothly according to the conversation flow.

  The input information analysis unit shown in FIG. 2 analyzes the input information and generates input specifying information. The input specifying information is information generated as a result of analyzing various types of information included in the input information. For example, there is a statistical analysis of the number and frequency of specific keywords (such as related terms described later) included in the input information.

  Further, the scenario data storage unit (a plurality of scenario data) shown in FIG. 2 stores a plurality of scenario data. Here, the plurality of scenario data are all scenario data corresponding to the topic names necessary for talking with the user. Of all scenario data, scenario data determined to be necessary based on the input identification information is extracted.

<<< Overview of Maintenance Device 3 >>>
As shown in FIG. 3, the features of the maintenance device 3 according to the present embodiment are as follows:
A scenario data storage unit that stores scenario data for defining response information related to a topic based on input specifying information generated by analyzing input information input by a user;
A receiving unit for receiving the input identification information;
A scenario data editing section for making the scenario data editable;
A scenario data verification unit that enables verification of a response of scenario data edited based on the input specific information received by the reception unit;
And a scenario data transmission unit that transmits the edited scenario data to the outside.

  As shown in FIG. 3, the maintenance device 3 according to the present embodiment mainly includes a scenario data storage unit, a reception unit, a scenario data editing unit, a scenario data verification unit, and a scenario data transmission unit. In FIG. 3, these configurations are indicated by solid-line squares. Note that the scenario data storage unit (a plurality of scenario data) and the input information analysis unit indicated by dotted-line boxes are included in the topic providing server 4 (see FIG. 2). As shown in FIG. 3, a scenario data verification unit plus a state control index storage unit constitutes a terminal device virtual construction unit to be described later. Information exchanged between these components is the same as that of the topic providing system 1 and the conversation control terminal device 2 described above.

  The topic providing system 1 and the conversation control terminal device 2 described above are mainly for a general user to have a conversation with the conversation control terminal device 2. On the other hand, the maintenance device 3 is mainly used by a contractor of the topic providing system 1, and the contractor of the topic providing system 1 performs maintenance of scenario data for providing a topic to a general user. It is a device for. Although the maintenance device 3 has such a difference, in FIG. 3, the same name is given to the configuration having the same function as the topic providing system 1 and the conversation control terminal device 2 and using the same data.

  The scenario data storage unit and the reception unit in the maintenance device 3 are functionally substantially the same as the scenario data storage unit and the reception unit in the topic providing system 1 and the conversation control terminal device 2 described above. It can be the same as the topic providing system 1 or the conversation control terminal device 2. For example, the scenario data storage unit and the reception unit of the maintenance device 3 may be mounted on the conversation control terminal device 2 assumed to be used by the user. Furthermore, as will be described later, the conversation control terminal device 2 may be virtually constructed in the maintenance device 3 and used as a scenario data storage unit and a reception unit of the virtual conversation control terminal device 2.

  The scenario data storage unit is a member or part for storing scenario data. The scenario data is data stored in advance in a scenario data storage unit (a plurality of scenario data) of the topic providing server 4 (see FIG. 2). Scenario data determined to be necessary based on the input specifying information generated by the input information analysis unit is extracted, and the extracted scenario data is stored in the scenario data storage unit. The scenario data extracted from the scenario data storage unit (a plurality of scenario data) is stored in the scenario data storage unit via a receiving unit and a response information determination unit described later.

  Scenario data is data for defining response information related to a topic based on input specifying information. The input specifying information is information generated by analyzing the input information. The input information is, for example, information input by the user in the conversation control terminal device 2.

  As described above, the maintenance device 3 is mainly used by the contractor of the topic providing system 1. In the maintenance device 3, the input information can be information virtually input by the user. The maintenance device 3 is for verifying scenario data before making the scenario data available to the user. Therefore, the user here may be a virtual user, and information assumed to be input by an actual user may be input information. Therefore, it is possible to generate input specifying information using various assumed input information, and to verify the response of the scenario data by the scenario data verification unit described later.

  The scenario data includes topic information to be provided to the user. The configuration and functions of scenario data used in the maintenance device 3 are the same as the scenario data of the topic providing system 1 according to the present embodiment and the scenario data of the conversation control terminal device 2 described above.

  The configuration and functions of the scenario data are the same as the scenario data in the topic providing system 1 and the conversation control terminal device 2, but as described above, the maintenance device 3 can use the scenario data for the user. It is for verifying scenario data before making it. Therefore, the scenario data targeted by the maintenance device 3 is scenario data for verification, and is data before the scenario data is made available to the user.

  The receiving unit receives the input specifying information. The input specifying information is generated outside the maintenance device 3. In other words, the receiving unit is a device or member that receives input specifying information generated outside the maintenance device 3. The input information is analyzed outside the maintenance device 3 to generate the input specification information, and the input specification information generated outside the maintenance device 3 is transmitted to the receiving unit of the maintenance device 3.

  As described above, the input information may be information virtually input by the user. Therefore, the input specifying information here can be information generated outside the maintenance apparatus 3 by using information that is assumed to be input by an actual user as input information. Thus, scenario data can be verified based on various types of input information by using information that is assumed to be input by an actual user as input information.

  The scenario data editing unit is a device or member for enabling editing of scenario data. The scenario data can be edited by the person in charge of the contractor of the topic providing system 1 operating the keyboard or the like. Editing includes adding, deleting, and changing scenario data. Specifically, editing is a process of adding, deleting, or changing a statement that constitutes scenario data. By editing the scenario data, the scenario data can be customized for each of a plurality of users.

  The scenario data verification unit is a device or member for enabling verification of a scenario data response. The scenario data here is edited scenario data. It is a device or member for verifying whether the response of scenario data edited by the scenario data editing unit is appropriate.

  As described above, the scenario data verification unit can generate input specifying information using various assumed input information, and can verify the response of the scenario data edited by the scenario data editing unit. For this reason, since it is possible to verify whether or not the response of the scenario data is appropriate for every user, it is possible to verify the custom scenario data applied to each of the plurality of users by the scenario data editing unit.

  The scenario data transmission unit transmits the edited scenario data to the outside. The outside can be, for example, a server or another conversation control terminal device 2. Thus, the verified scenario data can be made available to the user by transmitting the edited scenario data to the outside.

  As described above, the scenario data editing unit edits the scenario data or the scenario data verification unit verifies the scenario data using information input by the user as input information. Thus, a topic list can be generated by the topic analysis unit, and scenario data based on the topic list can be edited or verified. The topic analysis unit will be described later.

  The scenario data verification unit verifies whether the response of the scenario data edited by the scenario data editing unit is appropriate. By doing so, it is possible to confirm the contents and consistency of the scenario data before transmitting the scenario data to the outside such as a server. At least a part of the verified scenario data transmitted to the outside such as the server is finally transmitted to the conversation control terminal device 2 and used for conversation with the user.

  Data in the conversation control system includes both data for analyzing input information input by a user to generate input specifying information and scenario data for determining response information based on the input specifying information. This scenario data is data that can diversify response information that is an answer to the user. According to the configuration described above, the scenario data editing unit can edit the scenario data, and the scenario data verification unit can verify the response of the edited scenario data. By doing so, it is possible to customize the scenario data for each of a plurality of users who use the conversation control system without the need for highly specialized knowledge and technology throughout the conversation control system. it can.

Furthermore, as shown in FIG. 3, the features of the maintenance device 3 according to the present embodiment are as follows:
An input unit for a user to input input information;
A state control index storage unit that stores a state control index related to the input information and the response information;
A response information determination unit that determines the response information based on the scenario data and the state control index;
And an output unit that outputs response information determined by the response information determination unit, and a terminal device virtual construction unit that virtually constructs a conversation control terminal device.

  The maintenance device 3 according to the present embodiment has a terminal device virtual construction unit as shown in FIG. The conversation control terminal device 2 ′ is virtually constructed by the terminal device virtual construction unit.

  Furthermore, the maintenance device 3 according to the present embodiment has a scenario data verification unit as shown in FIG. The scenario data verification unit plus the state control index storage unit constitutes a terminal device virtual construction unit.

  Thus, the maintenance device 3 includes the conversation control terminal device 2 'as a function. The maintenance device 3 can have the function of the conversation control terminal device 2 ′ as a simulation package. Alternatively, the actual conversation control terminal device 2 can be obtained by omitting the maintenance function from the virtually constructed conversation control terminal device 2 ′. The virtually constructed conversation control terminal device 2 'may be realized as hardware or software. When realized as hardware, a separate device different from the actual conversation control terminal device 2 may be used as the conversation control terminal device 2 ′ virtually constructed. Further, in the case of realizing by software, the maintenance device 3 may realize the conversation control terminal device 2 ′ by emulation or the like.

  The maintenance device 3 is mainly used by a contractor of the topic providing system 1 and may be any device for maintaining scenario data for providing a topic to a general user.

  As illustrated in FIG. 3, the terminal device virtual construction unit and the scenario data verification unit mainly include an input unit, a response information determination unit, and an output unit. Furthermore, the terminal device virtual construction unit includes a state control index storage unit.

  The input unit is a member or a part for the user to input input information. The input part should just be what can input the information which a user desires as input information. For example, the input unit includes a keyboard, a touch panel, a microphone, a camera, and the like. The user can input text data, voice data, image data, and the like from the input unit.

  As described above, here, the input information may be information virtually input by the user. The user may also be a virtual user, and information that is assumed to be input by an actual user may be input information.

  The state control index storage unit stores a state control index. The state control index is an index related to input information and response information. The state control index is mainly an index related to history. For example, there are indicators relating to input information input by the user in the past and indicators relating to response information provided in the past to the user.

  The response information determination unit determines the response information by adding a state control index in addition to the scenario data and the input specifying information.

  The output unit outputs the response information determined by the response information determination unit.

  In this way, in the virtually constructed conversation control terminal device 2 ′, the edited scenario data can be used, or the verified scenario data can be used. Before that, you can check the contents and control of the scenario data. An appropriate topic can be provided to the user.

  The terminal device virtual construction unit can virtually construct and execute the conversation control terminal device 2 ′ in the maintenance device 3. Therefore, the maintenance device 3 can realize the same environment as the conversation control terminal device 2 used by general users. As a result, the content and operation of the scenario data can be checked in advance in an environment similar to the environment in which the user actually carries out the conversation, and the content of the scenario data can be verified before the conversation with the user. It is possible to verify in advance whether or not the custom made for each of a plurality of users connected to is appropriate.

Furthermore, as shown in FIG. 3, the features of the maintenance device 3 according to the present embodiment are as follows:
A topic analysis unit for generating a topic list to which the closeness and connection method of topics is given via a related word that relates topics,
The scenario data editing unit edits a topic introduction scenario for introducing a topic to a user and an input related scenario for responding to a user input as the scenario data by using the topic list and the related terminology. That is.

  The maintenance device 3 according to the present embodiment includes a topic analysis unit (not shown). The topic analysis unit is a device or member for generating a topic list. The topic list is data to which the closeness and connection method of the topics are given through the related words that relate the topics. The topic analysis unit accumulates related terms associated with the topic in the topic list. In the maintenance device 3, the topic list is data provided to the contractor of the topic providing system 1 and is used when generating scenario data.

  For example, a topic list is output to the output unit of the maintenance device 3 as shown in FIG. The contractor of the topic providing system 1 can construct topic introduction scenario data and input related scenario data to be provided to the user with reference to the topic list output to the output unit of the maintenance device 3. By doing in this way, the contractor of the topic providing system 1 can easily and easily construct topic introduction scenario data and input-related scenario data.

  The scenario data editing unit makes it possible to edit the topic introduction scenario and the input related scenario as scenario data. The topic introduction scenario and the input related scenario are made editable by the topic list and the related words. Since editing can be performed using a topic list and related terms, an input related scenario can be easily and easily constructed.

  The topic introduction scenario is a scenario for introducing a topic to a user. The user is provided with a topic by a topic introduction scenario. The input-related scenario is a scenario for responding to a user input. When the user inputs predetermined information, for example, information such as a greeting, the corresponding information such as a greeting is answered to the user by an input-related scenario.

  By this scenario data editing unit, the subscriber of the topic providing system 1 can edit the topic introduction scenario and the input related scenario to make them desired.

  The topic list can be updated based on various logs, for example, acquirable data such as Twitter and blog. That is, the latest information can be accumulated as related terms in the topic list. Therefore, when editing or verifying the topic introduction scenario and the input-related scenario based on the topic list, the subscriber of the topic providing system 1 knows the latest information from the topic list, and the topic introduction scenario. In addition, the input-related scenario can be edited, a topic including the latest information can be provided to the user, and a new user group can be cultivated by the latest information.

  Data in the conversation control system includes both data for analyzing input information input by a user to generate input specifying information and scenario data for determining response information based on the input specifying information. This scenario data is data that can diversify response information that is an answer to the user. According to the configuration described above, the scenario data editing unit can edit the scenario data in cooperation with the topic analysis unit, and the scenario data verification unit can verify the response of the edited scenario data. By doing so, it is possible to customize the scenario data for each of a plurality of users who use the conversation control system without the need for highly specialized knowledge and technology throughout the conversation control system. it can.

  Further, the transmission unit shown in FIG. 3 is a device or member for transmitting input information to the outside. Any device that transmits input information to the outside may be used. The outside can be, for example, the topic providing server 4 (see FIG. 2), the conversation control terminal device 2, or the like.

  Further, the input information analysis unit shown in FIG. 3 analyzes the input information and generates input specifying information. The input specifying information is information generated as a result of analyzing various types of information included in the input information. For example, there is a statistical analysis of the number and frequency of specific keywords (such as related terms described later) included in the input information.

  Furthermore, the scenario data storage unit (a plurality of scenario data) shown in FIG. 3 stores a plurality of scenario data. Here, the plurality of scenario data are all scenario data corresponding to the topic names necessary for talking with the user. Of all scenario data, scenario data determined to be necessary based on the input identification information is extracted.

<<< System configuration of topic providing system 1 >>>
FIG. 4 is a block diagram showing an outline of the system configuration of the topic providing system 1.

  The topic providing system 1 includes a Topiclet 20, iWA 30, and iWA Manager 40.

<< Topiclet 20 >>
In the present embodiment, Topiclet 20 corresponds to hardware such as a terminal device used by the user, for example. The Topiclet 20 corresponds to the conversation control terminal device 2 shown in FIG. The topic is provided to the user by the Topiclet 20. In this embodiment, “Topiclet” may be used synonymously with software executed by a terminal device to provide a topic to a user, or a topic providing environment that can be realized by the terminal device or these software.

  Specifically, the Topiclet 20 includes a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), a display, a keyboard (all not shown), and the like. The Topiclet 20 can be a personal computer or a mobile terminal device.

  The Topiclet 20 includes an input unit 210, an output unit 220, a transmission unit 230, a reception unit 240, a response information determination unit 250, a switching input information input unit 260, a scenario data storage unit 270, and a state control index storage unit 280.

<Input unit 210>
The input unit 210 is a device or member for a user to input input information. The input unit 210 includes a keyboard, a touch panel, a microphone, and the like. The input unit 210 may be any device or member that allows the user to input information such as questions.

<Output unit 220>
The output unit 220 outputs response information determined by a response information determination unit described later. The output unit 220 includes a display and a speaker. The output unit 220 only needs to output the response information so that the user can recognize it.

  Thus, the user can advance the conversation by inputting the input information to the input unit 210 and recognizing the response information output to the output unit 220.

<Transmitter 230 and Receiver 240>
The transmission unit 230 is a device or member for transmitting the input information input to the input unit 210 to the iWA 30. For example, the transmission unit 230 includes a communication interface.

  Note that the input information transmitted to the iWA 30 includes a user ID for identifying the user in addition to the input information from the input unit 210 by the user. The user ID may be information that can identify the user. Information assigned to each user may be used. Furthermore, the user ID may be information that can uniquely identify the topiclet 20 such as the serial number of the topicic 20. The user ID may be any information that can identify each user who uses the topic providing system 1 or the conversation control terminal device 2.

  The receiving unit 240 is a device or member for receiving input specifying information and scenario data transmitted from the iWA 30. For example, the transmission unit 230 includes a communication interface. Topiclet 20 is communicably connected to iWA 30 by transmission unit 230 and reception unit 240.

<Response information determination unit 250>
The response information determination unit 250 determines response information based on the input specifying information and scenario data. For example, the response information determination unit 250 includes the CPU, ROM, RAM, etc. of the Topiclet 20. As described above, the response information is determined using the input specifying information and the scenario data transmitted from the iWA 30.

  In the response information determination unit 250, the response information dynamically changes based on the scenario data regardless of the input.

  The response information determination unit 250 determines response information. The response information is determined based on the scenario data and the input specifying information. That is, the response information is determined using the input specifying information obtained by analyzing the input information input by the user. Therefore, the response information reflecting the user's intention can be generated, and the conversation with the user can be smoothly advanced by providing the topic desired by the user.

  The response information includes a statement of scenario data based on the input specifying information. In addition to the output information provided to the user included in the statement, various commands such as an output command can be included in the response information. In this way, topic information and greeting information can be output with various specifications in the output unit.

  The response information determination unit 250 determines the response information by adding a state control index in addition to the scenario data and the input specifying information. In this way, by determining the response information using the state control index, it is possible to provide a topic or advance the conversation based on the past conversation with the user. Therefore, it is possible to prevent the same topic from being provided to the user in duplicate or to provide the user with a jumping topic, and a smoother conversation can be promoted.

  Further, the response information determination unit 250 may determine the response information based on the scenario data and the state control index.

<Switching input information input unit 260>
The switching input information input unit 260 includes the CPU, ROM, RAM, and the like of the Topiclet 20.

  The switching input information input unit 260 generates topic switching input information according to information defining transition to a different topic. Information defining transition to a different topic includes, for example, topic switching information described later. The topic switching input information includes, for example, a personality index described later.

<Scenario data storage unit 270>
The scenario data storage unit 270 extracts scenario data for defining response information related to the topic. For example, the scenario data storage unit 270 is composed of the ROM, RAM, etc. of the Topiclet 20.

  As will be described later, in this embodiment, the scenario data is composed of a plurality of statements. In Topiclet 20, it is possible to have a conversation with the user while providing a topic to the user by making a transition from one statement to another. The scenario data storage unit 270 stores a plurality of statements for proceeding with the conversation with the user. Specific examples of advancing a conversation with the user by transitioning statements will be specifically described with reference to FIGS.

  As will be described later, the iWA 30 also includes a scenario data storage unit 320. The scenario data storage unit 320 of the iWA 30 stores all scenario data. On the other hand, the scenario data storage unit 270 of the Topiclet 20 may be stored as a part of scenario data. What is necessary is just to transmit to Topiclet 20 as scenario data required for the conversation of the user who uses Topiclet20.

  In the present embodiment, when the user has a conversation with the Topiclet 20, information such as an answer is not transmitted from the iWA 30 to the Topiclet 20 every time the user has a conversation. When scenario data including a topic to be provided to the user is transmitted from the iWA 30, the scenario data is stored in the scenario data storage unit 270 of the Topiclet 20. When the user has a conversation with Topiclet 20, the scenario data already stored in scenario data storage unit 270 is used. In the present embodiment, since information such as an answer is not transmitted from iWA 30 to Topiclet 20 every time a conversation is made, a conversation with the user can be made smoothly.

  Note that all scenario data stored in the scenario data storage unit 320 of the iWA 30 may be transmitted to the Topiclet 20. The topic can be provided to the user more smoothly.

<State control index storage unit 280>
The state control index storage unit 280 stores a state control index. The state control index is an index related to input information and response information. The state control index storage unit 280 includes the ROM, RAM, and the like of the Topiclet 20.

  The Topiclet 20 has a state control index storage unit 280, and the state control index is stored in the state control index storage unit 280. In the present embodiment, the state control index is information that is not transmitted to the server (iWA 30 described later) but is stored in the Topiclet 20. The Topiclet 20 determines the response information with reference to the state control index stored in the state control index storage unit 280. By holding the state control index in the Topiclet 20, the amount of communication with the iWA 30 can be reduced. Further, since scenario data can be used by referring to the state control index in Topiclet 20, it is possible to perform processing quickly and to have a smooth conversation with the user.

<State control index>
In the present embodiment, the topic provided to the user is controlled using three types of indicators, that is, an input indicator, a progress indicator, and a personality indicator, as the state control indicators. Other indicators may be used.

  The input index is information indicating what input the user has made so far, that is, a history of user input. By using the input index, it is possible to guide to a situation where the user can easily ask a question. That is, by using the input index, it is possible to provide the user with a topic based on the user's previous input. Thereby, a user can be provided with a topic without making a useless question such as repeating a similar question.

  The progress index is information indicating what topic has been provided to the user so far, that is, a history of the topic provided to the user. A topic desired to be provided to the user can be maintained (stored) by the progress index. Thereby, a topic can be provided to a user, without making a user feel stress. By using the progress indicator, even when a series of explanations are provided as topics, even if the user asks questions on the way, the continuation of the series of explanations can be resumed.

  The personality index is information indicating what posture the user has input so far, that is, the history of the user's posture. For example, it is information indicating whether the user has made a positive input or a passive input for a certain topic. In the case of being active, it can be determined that it can continue to provide a topic on a certain theme. On the other hand, in a negative case, it can be determined that a topic must be provided by switching to a theme different from a certain theme.

  For example, it can be determined that a user who is interested in a car may continue to provide a topic about the car. On the other hand, it is possible to determine that a user who is not interested in a car must be provided with a topic related to food that is not related to the car.

  Thus, the topic name (theme) of the topic provided to the user can be switched by the personality index. The user can touch a topic belonging to the switched topic name without being aware of the topic name of the topic.

<IWA30>
In the present embodiment, the iWA 30 corresponds to hardware such as a server, for example. The iWA 30 corresponds to the topic providing server 4 shown in FIG. The iWA 30 is communicably connected to the Topiclet 20. This is hardware for executing processing related to a topic provided to a user in Topiclet 20.

  Specifically, the iWA 30 includes a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), an HDD (Hard Disk Drive), a display, a keyboard (all not shown), and the like.

  The iWA 30 includes an input information analysis unit 310 and a scenario data storage unit 320.

<Input Information Analysis Unit 310>
The input information analysis unit 310 analyzes the input information and generates input specifying information. The input information is information input from the input unit 210 by the user. The input specifying information includes a result obtained by statistically analyzing the input information and information necessary for providing a topic based on the result. For example, there is information such as the number and frequency of appearance of related terms in the input information. Moreover, scenario data (statement) determined to be necessary for providing topics according to the result is included.

  Furthermore, by analyzing the input information, it is possible to analyze the user's intention and preference from a question input by the user. Relative analysis results can also be obtained by comparison with input information of other users and input specific information. It is also possible to generate data such as an analysis dictionary in advance and analyze input information using the analysis dictionary.

  For example, the input specifying information includes various information such as related terms, scenario data, and the number of related terms included in the scenario data. The scenario data includes topic information provided to the user, greeting information necessary for conversation with the user, and the like.

<Related words>
Various data used in the topic providing system 1, the conversation control terminal device 2, and the maintenance device 3 according to the present embodiment are configured on the basis of data called related terms. Unlike normal keywords used in normal search processing and the like, various information such as history information and preferences can be associated with each other. The input information can be analyzed based on the related information held by the related words.

<Scenario data storage unit 320>
The scenario data storage unit 320 stores a plurality of scenario data. Here, the plurality of scenario data are all scenario data corresponding to topic names necessary for talking with the user on the Topiclet 20. Of all the scenario data, the scenario data determined to be necessary based on the input identification information is transmitted to the Topiclet 20. Therefore, when talking with the user in the Topiclet 20, the scenario data is not transmitted to the Topiclet 20 every time a conversation is made. As described above, the scenario data is composed of a plurality of statements. Therefore, a plurality of statements constituting scenario data determined to be necessary based on the input identification information are transmitted to the Topiclet 20.

  When it is determined that it is necessary based on the generated input specifying information, a statement is transmitted to the Topiclet 20 as scenario data. If it is determined that it is not necessary, the statement already transmitted to the Topiclet 20 is sufficient, and in this case, the statement is not transmitted to the Topiclet 20.

  Note that not all scenario data determined to be necessary based on the input identification information is transmitted to the Topiclet 20, but all scenario data stored in the scenario data storage unit 320 is transmitted to the Topiclet 20. Good. Since all the scenario data has already been transmitted to the Topiclet 20, the time required for transmitting / receiving the scenario data can be shortened, and the conversation with the user can be facilitated.

  Further, when switching the topic name, the scenario data stored in the scenario data storage unit 320 is rearranged and the scenario data corresponding to the topic name is transmitted to the Topiclet 20. That is, a statement corresponding to the scenario data corresponding to the topic name is transmitted to Topiclet 20. The rearranged scenario data is stored in the scenario data storage unit 270 of the Topiclet 20. This rearrangement of scenario data can be executed according to the topic name.

  As the conversation with the user progresses, it may be necessary to move from one topic name to another. In such a case, scenario data corresponding to one topic name cannot be sufficiently handled. For such a case, it is possible to switch to scenario data corresponding to other topic names.

<IWA Manager 40>
In the present embodiment, the iWA Manager 40 corresponds to hardware such as a server, for example. The iWA Manager 40 corresponds to the maintenance device 3 shown in FIG. iWA Manager 40 is communicably connected to iWA 30. The iWA Manager 40 is mainly hardware for executing processing related to scenario data used in the iWA 30.

  Specifically, the iWA Manager 40 includes a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), a HDD (Hard Disk Drive), a display, a keyboard (all not shown), and the like.

  The iWA Manager 40 includes a scenario data editing unit 410, a scenario data verification unit 420, and a scenario data transmission unit 430.

<Scenario data editing unit 410>
The scenario data editing unit 410 is a device or member that enables editing of scenario data. The scenario data can be edited by the person in charge of the contractor of the topic providing system 1 operating the keyboard or the like. Editing includes adding, deleting, and changing scenario data. Specifically, editing is a process of adding, deleting, or changing a statement that constitutes scenario data.

  Scenario data needs to be updated to accommodate the latest topics as new products are sold, new services are provided, various incidents occur, and the number of new users increases. . Therefore, the person in charge can acquire various types of information via the network and update the scenario data to the latest based on these information. By updating the scenario data, a topic corresponding to the latest information can be provided to the user.

  Further, by correcting inappropriate information such as typographical errors and omissions and incorrect information by the scenario data editing unit 410, a topic corresponding to appropriate information can be provided to the user.

<Scenario data verification unit 420>
The scenario data verification unit 420 is a device or member that enables verification of the response of scenario data edited based on the input specifying information generated by the input information analysis unit. That is, the scenario data verification unit 420 is a device or member for verifying whether the response of the scenario data edited by the scenario data editing unit 410 is appropriate.

  If the scenario data content is appropriate, the scenario data response is appropriate. Scenario data according to the present embodiment includes output information output from the output unit 220, output commands for controlling output specifications to the output unit 220, judgments for controlling statements, topic names Control commands for switching between and changing the state control index. For this reason, not only verifying whether the data output to the output unit 220 is appropriate, but also verifying whether the control of the output to the output unit 220 is appropriate and controlling the transition of scenario data, etc. It is necessary to verify whether it is appropriate.

  The scenario data verification unit 420 can generate input specifying information using various assumed input information, and can verify the response of the scenario data edited by the scenario data editing unit 410. For this reason, since it is possible to verify whether or not the response of the scenario data is appropriate for every user, it is possible to customize each of the users.

<Terminal device virtual construction unit>
The scenario data verification unit 420 can virtually construct an environment similar to Topiclet 20 by the terminal device virtual construction unit. By verifying scenario data in a virtual environment, it is possible to verify the output and operation of scenario data in an environment close to the environment actually used by the user, and it is easy to determine whether scenario data is appropriate. It is possible to judge accurately.

<Scenario data transmission unit 430>
The scenario data transmission unit 430 transmits the edited scenario data to the outside, for example, the iWA 30. In particular, the scenario data edited by the scenario data editing unit 410 and further verified by the scenario data verification unit 420 are transmitted to the iWA 30. Therefore, the scenario data transmission unit 430 transmits the verified scenario data to the iWA 30.

  By doing in this way, the scenario data transmitted from iWA30 to Topiclet 20 can always be kept in an appropriate state. Accordingly, a topic using appropriate scenario data can be provided to the user via the iWA 30.

<<< Data structure provided by topic providing server >>>
As shown in FIG. 15, scenario data, input specifying information, and a topic introduction list are output from the iWA 30. Hereinafter, an example of scenario data, an example of input specifying information, and an example of a topic introduction list will be described.

<<< Examples of scenario data >>>
FIG. 14 is an example of scenario data used in the topic providing system 1, the conversation control terminal device 2, and the maintenance device 3 of the present embodiment. Hereinafter, the scenario data shown in FIG. 14 will be described according to a specific processing procedure. The scenario data shown in FIG. 14 includes a plurality of first to thirteenth statements. 5 to 12 are flowcharts showing the processing procedure of these first to thirteenth scenario data. FIG. 13 is a diagram illustrating an example of output to the output unit 220 by processing the first to thirteenth scenario data.

  As described above, the scenario data (statement) used in the topic providing system 1, the conversation control terminal device 2, and the maintenance device 3 of the present embodiment includes output information, output commands, and control commands. The scenario data (statement) is composed of various elements such as output information, output commands, and control commands.

  FIG. 5 is a flowchart showing the processing of the first, second and third statements.

<First statement>
First, transition to the first statement. In FIG. 5, steps S511 to S521 correspond to the processing of the first statement.

  First, the progress index is set to −1 (step S511). This value indicates the state of progress. Next, the output unit 220 is temporarily erased (step S513), and “shift to a topic to resolve anxiety” is output to the output unit 220 (step S515). By this process, for example, as shown in FIG. 13A, the topic “I am worried about the earthquake” is input by the user's operation, and the text data display area of the output unit 220 displays “ Will shift "is displayed (1311 in FIG. 13).

  Next, a predetermined image is output (step S517), and it waits for 3 seconds (step S519). By this processing, as shown in FIG. 13A, a face image M1 of a predetermined color is displayed in the image data display area of the output unit 220 and waits for 3 seconds (1311 in FIG. 13).

  Next, the topic name “topic topic” is switched using the word “I worry” as input information (step S521). By this process, in this example, a transition is made to the second statement (1313 in FIG. 13).

<Second statement>
In FIG. 5, steps S523 to S525 correspond to the processing of the second statement.

  Transition to the second statement starts with monitoring whether or not the absolute time, for example, 12:00, has been reached (step S523). Next, it is determined whether or not the absolute time has come (step S525) (1315 in FIG. 13). If the absolute time has not come (NO), the process proceeds to the third statement. When the absolute time is reached (YES), the monitoring of the absolute time is canceled and a transition is made to the thirteenth statement (reference EE).

<Third statement>
In FIG. 5, steps S527 to S533 correspond to the processing of the third statement.

  When the process proceeds to the third statement, it is determined whether or not the progress index is −1 (step S527) (1317 in FIG. 13). When it is determined that the progress index is −1 (YES), the process proceeds to the fourth statement (reference E1).

  When it is determined that the progress index is not −1 (NO), it is determined whether or not the progress index is −2 (step S529). When it is determined that the progress index is −2 (YES), a transition is made to the fifth statement (reference E2).

  When it is determined that the progress index is not −2 (NO), it is determined whether or not the progress index is −3 (step S531). When it is determined that the progress index is −3 (YES), the process proceeds to the sixth statement (reference E3).

  When it is determined that the progress index is not −3 (NO), it is determined whether or not the progress index is −4 (step S533). When it is determined that the progress index is −4 (YES), a transition is made to another statement (sta: 200). When it is determined that the progress index is not -4 (NO), nothing is done.

  The second statement and the third statement described above consist only of control commands. As described above, the statement may not have output information for output to the output unit 220.

<4th statement and 7th statement>
FIG. 6 shows processing corresponding to the fourth statement and the seventh statement. The fourth statement corresponds to steps S611 to S621. The seventh statement corresponds to steps S623 to S629.

<4th statement>
When a transition is made to the fourth statement, measurement of relative time, for example, 120 seconds is started (step S611). Next, the input index is set to 1 (step S613), and the number of times the input index is set to 1 is counted (step S615).

  Next, it is determined whether or not the number of times the input index has been set to 1 has reached 5 (step S617) (1319 in FIG. 13). When the number of times that the input index is set to 1 has reached 5 (YES), a transition is made to the tenth statement (reference E11).

  If the number of times the input index is set to 1 has not reached 5 (NO), it is determined whether or not a relative time, for example, 120 seconds has elapsed (step S619) (1319 in FIG. 13). If the relative time has elapsed (YES), the measurement of the relative time is terminated (step S621), and a transition is made to the tenth statement (reference E11).

  If the relative time has not elapsed (NO), the process proceeds to the seventh statement.

<Seventh statement>
When the transition to the seventh statement is made, the output unit 220 is deleted (step S623), and the output unit 220 has a question about “I'm worried”. Is output (step S625). Next, a predetermined image (for example, a face image M1 of a predetermined color) is output (step S627) and waits for 10 seconds (step S629). By this processing, as shown in FIG. 13B, a face image M1 of a predetermined color is displayed in the image data display area of the output unit 220 and waits for 10 seconds. Next, a transition is made to the second statement (reference symbol ES).

<5th statement and 8th statement>
FIG. 7 shows processing corresponding to the fifth statement and the eighth statement. The fifth statement corresponds to steps S711 to S721. The eighth statement corresponds to steps S723-S729.

<5th statement>
When a transition is made to the fifth statement, measurement of a relative time, for example, 120 seconds is started (step S711). Next, the input index is set to 2 (step S713), and the number of times the input index is set to 2 is counted (step S715).

  Next, it is determined whether or not the number of times the input index is set to 2 has reached 5 (step S717) (1319 in FIG. 13). When the number of times that the input index is set to 2 has reached 5 (YES), a transition is made to the 11th statement (reference E12).

  If the number of times the input index is set to 2 has not reached 5 (NO), it is determined whether or not a relative time, for example, 120 seconds has elapsed (step S719) (1319 in FIG. 13). If the relative time has elapsed (YES), the measurement of the relative time is terminated (step S721), and the process proceeds to the eleventh statement (reference E12).

  If the relative time has not elapsed (NO), the process proceeds to the eighth statement.

<Eighth statement>
When the transition to the eighth statement is made, the output unit 220 is deleted (step S723), and the output unit 220 has a question about “OK”. Is output (step S725). Next, a predetermined image (for example, a face image M1 of a predetermined color) is output (step S727) and waits for 10 seconds (step S729). Next, a transition is made to the second statement (reference symbol ES).

<6th statement and 9th statement>
FIG. 8 shows processing corresponding to the sixth statement and the ninth statement. The sixth statement corresponds to steps S811 to S821. The ninth statement corresponds to steps S823 to S829.

<Sixth statement>
When a transition is made to the sixth statement, measurement of relative time, for example, 120 seconds is started (step S811). Next, the input index is set to 3 (step S813), and the number of times the input index is set to 3 is counted (step S815).

  Next, it is determined whether or not the number of times the input index is set to 3 has reached 5 (step S817) (1319 in FIG. 13). When the number of times that the input index is set to 3 has reached 5 (YES), a transition is made to the eleventh statement (reference E13).

  If the number of times the input index is set to 3 has not reached 5 (NO), it is determined whether or not a relative time, for example, 120 seconds has elapsed (step S819) (1319 in FIG. 13). If the relative time has elapsed (YES), the measurement of the relative time is terminated (step S821), and a transition is made to the twelfth statement (reference E13).

  If the relative time has not elapsed (NO), the process proceeds to the ninth statement.

<9th statement>
When the transition to the ninth statement is made, the output unit 220 is deleted (step S823), and the output unit 220 has a question about “it is dangerous”? Is output (step S825). Next, a predetermined image (for example, a face image M1 of a predetermined color) is output (step S827) and waits for 10 seconds (step S829). Next, a transition is made to the second statement (reference symbol ES).

<10th statement>
FIG. 9 shows a process corresponding to the tenth statement. Transition to the tenth statement is made by the above-described processing of FIG. 6 (reference numeral E11).

  When transitioning to the tenth statement, the progress index is set to -2 (step S911). Next, the output unit 220 is erased (step S913), and “shift to the next topic” is output to the output unit 220 (step S915). A predetermined image (for example, a face image M1 of a predetermined color) is output (step S917) and waits for 3 seconds (step S919). Next, the word “OK” is used as input information, and the topic name corresponding to this word is switched (step S921). Next, a transition is made to the second statement (reference symbol ES).

  As a result of the above-described processing, as shown in FIG. 13D, “Shift to next topic” is displayed in the text data display area of the output unit 220. In this way, it is possible to transition from scenario data with one topic name to scenario data with another topic name.

<Eleventh statement>
FIG. 10 shows processing corresponding to the eleventh statement. Transition to the eleventh statement is made by the above-described processing of FIG. 7 (reference numeral E12).

  When transitioning to the eleventh statement, the progress indicator is set to -3 (step S1011). Next, the output unit 220 is erased (step S1013), and “shift to the next topic” is output to the output unit 220 (step S1015). A predetermined image (for example, a face image M1 of a predetermined color) is output (step S1017) and waits for 3 seconds (step S1019). Next, using the word “dangerous” as input information, the topic name corresponding to this word is switched (step S1021). Next, a transition is made to the second statement (reference symbol ES).

<Twelfth statement>
FIG. 11 shows processing corresponding to the twelfth statement. Transition to the twelfth statement is made by the above-described processing of FIG. 8 (reference numeral E13).

  When transitioning to the twelfth statement, the progress indicator is set to -4 (step S1111). Next, the output unit 220 is erased (step S1113), and “time has come” is output to the output unit 220 (step S1115). A predetermined image (for example, a face image M1 of a predetermined color) is output (step S1117) and waits for 3 seconds (step S1119). Next, a transition is made to the thirteenth statement (reference EE).

<13th statement>
FIG. 12 shows processing corresponding to the thirteenth statement. The process transitions to the thirteenth statement by the process of FIG. 11 (reference EE) described above.

  When the transition is made to the thirteenth statement, the output unit 220 is deleted (step S1211), and “the explanation is finished” is output to the output unit 220 (step S1213) (1321 in FIG. 8). A predetermined image (for example, a face image M1 of a predetermined color) is output (step S1215) and waits for 3 seconds (step S1217). Next, a transition is made to another statement (sta: 200).

  In the state shown in FIG. 13B, when the user inputs “After all, I am worried about politics” (FIG. 13C), the text data display area of the output unit 220 displays “politician” Do not lie, so there is no need to worry ”(FIG. 13C), and the state again returns to the state shown in FIG. 13B.

<Configuration of scenario data>
As in the first to thirteenth statements described above, in this embodiment, the scenario data consists of a plurality of statements. After transitioning to one statement and executing processing based on that one statement, transitioning to another statement and executing processing based on that statement. It is possible to provide a topic to the user by repeating the transition of the statement and the processing in the statement. Thus, scenario data (a plurality of statements) is used in the topic providing system 1, the conversation control terminal device 2, and the maintenance device 3 in the present embodiment. Here, the structure of a single statement will be described.

  As in the first to thirteenth statements described above, the statement of the present embodiment is composed of various elements such as transition information and judgment. A statement can include elements necessary for providing a topic to the user and controlling a conversation with the user.

  The identification information is information attached to identify the statement. This identification information is referred to when transitioning statements. One statement includes transition destination information.

  That is, one statement includes both identification information and transition destination information. The identification information is identification information for identifying a statement and is information indicating the statement itself. On the other hand, the transition destination information is information for designating a statement to be transitioned next. The identification information and the transition destination information are information used when transitioning from one statement to another. That is, according to the transition destination information defined in another statement, an identification information statement that matches the transition destination information is searched, and a transition is made to the identification information statement (one statement) that matches the transition destination information. In this way, by using both the identification information and the transition destination information, it is possible to transition statements one after another.

  The judgment includes judgment based on an index and judgment based on time. The determination based on the index is a determination for determining whether the index satisfies a predetermined condition. If the index satisfies a predetermined condition, it can be determined to be true, and if the index does not satisfy the predetermined condition, it can be determined to be false and branched. The determination based on time is a determination for determining whether time satisfies a predetermined condition. If the time or time satisfies a predetermined condition, it can be determined to be true, and if the predetermined condition is not satisfied, it can be determined to be false and branched.

  The output information is text data to be output to the output unit 220. In addition, by including identification information (for example, a file name) specifying image data of output information, an image can also be output to the output unit 220 by the output information.

  The setting element is an element for setting a state index. A statement can be transitioned or branched based on a set state index.

  Other elements include, for example, line breaks and erasures. The line break is for outputting the text with a line break in the output unit 220. Erasing is for erasing the text or image output to the output unit 220.

  The output control element is an element for controlling the output of the output information described above. For example, it is possible to define a time for outputting the output information, or to define an image to be output together with the output of the output information.

  The transition destination information is information for designating the next transition destination statement. The identification information matching the transition destination information is searched for, and a transition is made to the statement of the identification information.

  Topic switching information is an element for switching topic names. The scenario data (a plurality of statements) of the present embodiment is defined for each of a plurality of topic names. That is, the scenario data is defined so that the scenario data corresponds to each of a plurality of topic names. That is, in this embodiment, the scenario data is defined so as to correspond to each of a plurality of topic names, and each scenario data is constituted by a plurality of statements.

  When a single topic name is sufficient for conversation with the user, it is only necessary to transition statements one after another using scenario data corresponding to the single topic name. However, there may be a case where it is necessary to move from one topic name to another as the conversation progresses with the user. In such a case, scenario data corresponding to one topic name cannot be sufficiently handled. For this reason, by defining scenario data corresponding to each of a plurality of topic names in advance, even when a topic needs to be transferred from one topic name to another topic name, it corresponds to another topic name. Switch to scenario data. Scenario data corresponding to other topic names is also composed of a plurality of statements. By sequentially switching statements of scenario data corresponding to other topic names, it is possible to advance conversation with the user on other topic names.

  When switching the topic name, all scenario data stored in the iWA 30 are rearranged to generate scenario data corresponding to the topic name. The rearranged scenario data is stored in the scenario data storage unit 270 of the Topiclet 20. This recombination of scenario data can be executed by determining a combination of a plurality of statements according to the topic name.

  Further, it is preferable to determine whether to switch the topic name based on the above-described personality index. The personality index is information indicating whether the user is active or passive about a certain topic. In the case of being active, it can be determined that the topic can be continuously provided without switching the topic name. On the other hand, in a negative case, it can be determined that the topic name must be switched to provide the topic.

<< Example of input specific information >>
Identification information corresponding to the input information or information for identifying the identification information is added to the input specifying information, and scenario data can be activated by this information.

  In FIG. 15, the input specifying information in FIGS. 1 to 4 includes a topic introduction list described below.

<< Example of topic introduction list >>
FIG. 16 is a diagram illustrating an example of the configuration of a topic introduction list.

<Composition of topic introduction list>
The topic introduction list is a list of pairs of related terms and topics. The related term set is a set of related terms included in the topic. The vicinity of the related term is a set of related terms including the related term A when attention is given to a certain related term A. A neighborhood system of related terms is a set of neighborhoods of related terms. The number of neighbors of the related term is the number of elements in the neighborhood system of the related term. The phase of the related term can be understood by looking at the neighborhood system of the related term. By performing the topic analysis, the neighborhood system can be displayed for all sets of related terms. By performing the preference analysis, it is possible to display the neighborhood system of related terms in the order of preference. A scenario related to topic introduction is a scenario that can be configured based on the proximity or connection of topics based on the neighborhood system of related terms.

  A topic is text that is assigned an action and an index. An action is a change that is activated by clicking a text or the like. A set of related terms as an index is added to the topic. Clicking on the index displays the related term companions that are included in the index.

<Use of topic introduction list>
FIG. 17 shows that topics in the topic introduction list are connected by a related terminology in which a related term structure such as a related term dictionary or a preference dictionary is introduced. The user can detect a topic by paying attention to how the topics in the topic introduction list are connected.

  Further, the user can detect a topic from various viewpoints by performing topic switching based on the related terminology while referring to the related term structure in the topic introduction list.

<Topic switching with related words>
In scenario data defining response information related to a topic, it is necessary to introduce not only the topic switching by topic name but also the topic itself. Topic analysis provides "related terms and related term structure" necessary for switching the topic itself in the scenario data via the topic introduction list.

  As shown in FIG. 17, it is possible to see the closeness and connection of topics by using related words. Therefore, by using related words in scenario data, it is possible to perform topic switching of the topic itself. For example, for the current topic, topic switching to a topic having a similar content or topic switching to a topic having a connected content can be performed.

  Also, by using a related phrase structure in the related phrase, variable related phrases (for example, the most frequent related phrases, the most popular related phrases, etc.) can be used in the scenario data. Makes it possible to introduce various topics.

  Since the topic can be switched by using related terms, the topic providing system 1 can reproduce the manual operation in which the user detects the topic using the topic introduction list as the topic providing service using the scenario data.

<<< Topic Analysis >>>
Next, the topic analysis unit provided in the maintenance device 3 in FIG. 4 will be described again based on FIGS. 15 to 18. As described above, the maintenance device 3 constitutes a scenario data verification unit for creating in advance including information that the subscriber of the topic providing system 1 wants to provide to the user. And although it is not necessary to create the information (topic introduction list) that the user wants to provide, the maintenance device 3 of this embodiment adds the state control index storage unit described above to the scenario data verification unit. The terminal device virtual construction unit is configured to function as the conversation control terminal device 2 virtually. That is, a terminal device virtual construction unit is configured by adding the state control index storage unit to the scenario data verification unit, and this terminal device virtual construction unit corresponds to the above-described Topiclet 20 and iWA Manager 40.

  As shown in FIG. 15, according to the topic analysis unit, it is possible to analyze the topic and to output for visualizing the topic introduction list. In other words, the topic analysis unit is configured to generate a topic list to which the closeness of the topics and how to connect the topics are connected via the related words that relate the topics. In addition to the topic analysis unit, the maintenance device 3 uses a topic list and the related terms to introduce a topic introduction list (equivalent to the topic list in FIG. 17) for introducing a topic to the user, It is also characterized by having a scenario data editing section for making it possible to edit an input related scenario for responding to an input as the scenario data. In the case of the maintenance device 3, since it is virtually constructed in the conversation control terminal device 2, the user input here corresponds to the input of the simulator (person in charge).

  Hereinafter, topic analysis in the topic analysis unit, generation of a topic introduction list, and scenario data editing by the scenario data editing unit will be described.

<<< Response output based on topic analysis >>>
FIG. 15 is a diagram illustrating a process of generating response information based on topic analysis and outputting the response information to an output unit. FIG. 16 is a diagram illustrating an example of the configuration of a topic introduction list. FIG. 17 is a diagram illustrating a process of topic extraction, generation of a related term dictionary, and generation of a preference dictionary. Topic analysis is executed by the topic analysis unit, and a preference dictionary and related term dictionary of iWA30 as a server are constructed. The control unit configured by the CPU of the maintenance device 3 uses these dictionaries to assign a plurality of related terms included in the topic to each of a plurality of topics (topic topics) input by the person in charge of the contractor. Grant automatically.

  FIG. 15 is a diagram illustrating a process of generating response information based on topic analysis and outputting the response information to an output unit.

  As a result of the topic analysis, scenario data is generated by the iWA 30 from the input-related scenario and the topic introduction scenario. The iWA 30 generates input specific information from elements such as identification information. The topic list is generated from the set of related terms and topics by iWA30.

  Then, response information is generated based on the generated scenario data, input identification information, and topic introduction list, and the response information is output from the output unit 220.

  In this way, response information can be generated from topic analysis and the response information can be output. By generating response information by topic analysis, the response information used in the conversation with the user can be made appropriate for each user, and the conversation with the user can be made smoother.

<Composition of topic introduction list>
FIG. 16 is a diagram illustrating an example of the configuration of a topic introduction list.

  The topic introduction list is a list of pairs of related terms and topics. The related term set is a set of related terms included in the topic. The vicinity of the related term is a set of related terms including the related term A when attention is given to a certain related term A. A neighborhood system of related terms is a set of neighborhoods of related terms. The number of neighbors of the related term is the number of elements in the neighborhood system of the related term. The phase of the related term can be understood by looking at the neighborhood system of the related term. By performing the topic analysis, the neighborhood system can be displayed for all sets of related terms. By performing the preference analysis, it is possible to display the neighborhood system of related terms in the order of preference. A scenario related to topic introduction is a scenario that can be configured based on the proximity or connection of topics based on the neighborhood system of related terms.

  A topic is text that is assigned an action and an index. An action is a change that is activated by clicking a text or the like. A set of related terms as an index is added to the topic. Clicking on the index displays the related term companions that are included in the index.

<Topic extraction, generation of related term dictionary, generation of preference dictionary>
FIG. 17 is a diagram illustrating creation of a topic introduction list and profiling of a user using a preference dictionary.

  The topic introduction list is visualized in a display form as shown on the screen (reference numerals 1813 and 1811) of the display device provided in the maintenance device 3 in FIG. 17, and obtained from the related term dictionary F or an external news source. The topic list G is automatically extracted by controlling the maintenance device 3 based on the topic list G consisting of topic data input by the person in charge and the topic data group taken from outside while extracting the topic list G from the iWA 30 It will be built.

  The input source of the content that is input and displayed as the topic (topic item setting field on the screens 1813 and 1811) in the topic introduction list is as follows. First, the person in charge of the contractor uses the input keyboard as the input device of the maintenance device 3 The person in charge at the input device of the maintenance device 3 from the first form in which the topic material is directly input and set from the log data collected by the iWA 30 from the outside, for example, data that can be collected via a network such as Twitter or blog There is a second form in which the iWA 30 automatically extracts the topic material based on the topic input by (1811). From the extracted topic, topic browsing list data that is a candidate for the topic introduction list is generated. The iWA 30 refers to the related term dictionary F in order to display the topic manually input by the person in charge through the maintenance device 3 on the screen 1815, and to the topic in which a plurality of related terms are input under the control of the iWA 30. The iWA 30 refers to a topic list G consisting of general news groups collected from the outside by using the related term dictionary associated with the topic manually entered by the person in charge as a key, and the person in charge The iWA 30 automatically extracts an external topic related to the topic inputted by the user, and the maintenance device 3 receives the extracted data and displays it as shown on a screen 1811.

  Then, the person in charge repeats the topic input using a direct input device such as an input keyboard and the topic obtained from the database of the topic list in which iWA 30 previously stores information from outside while automatically reducing or adding topics. Build a referral list.

  On the other hand, in the maintenance apparatus 3 of the present embodiment, in addition to the generation of the topic introduction list described above, the input topic is referred to based on the related dictionary dictionary F while referring to the preference dictionary E obtained from the iWA 30. The related terms displayed in the linked screen 1815, the user IDs and user types generated from the response histories of other users, and the related terms in the user type list data associated with the related terms are compared. By this comparison, for example, as shown in a screen 1817, what kind of “most scary” extracted as a related term for a certain topic is referred to the preference dictionary E constructed by other past user histories. Visualization can be performed by analyzing and displaying whether similar related terms are associated with information input by a user of the user type.

  This analysis result is stored together with a user ID for identifying a user who has input the same related term, a user type (for example, yesterday's customer), and related terms common to all users, and based on this stored data. And can be used to analyze user preferences. As a method of use, for example, a user who is considered to have the same preference, a specific service that is considered to match the preference can be identified from the user ID, such as the user's email address, It can be used to specify and deliver a delivery destination, or to provide a topic that suits the taste other than the service to the specified delivery destination.

  FIG. 18 shows iWA 30 as a server by generating a topic introduction list from the related term dictionary and the topic list when a topic is input to the topic story setting screen by manual input according to the first form of the maintenance device 3 described above. The flow of processing until output is shown. In FIG. 17, the process of performing the user profile from the topic input using the preference dictionary has been described. However, the process of performing this profile is a process different from the topic introduction list generation. A description of the process of performing the user profile from the topic is omitted.

  Referring to FIG. 18, the control unit of maintenance device 3 displays a topic story setting screen on the display screen of maintenance device 3, and waits for topic input to be executed by the person in charge (S2000).

  Next, when a topic is input to the input screen via an input device such as a keyboard and it is determined that a switch for topic topic setting is input (S2001: YES), the topic topic for the iWA 30 serving as a server. The set topic material is transmitted, and one or more related terms are extracted from the related term dictionary F under the control of the CPU of the iWA 30 in accordance with the content of the transmitted topic content data. In the case of the screen 1813 in FIG. 17, “panic discussion material” is transmitted from the maintenance device 3 to the iWA 30 as the topic material, and the content of this “panic discussion material” is called “panic” under the control of the CPU of the iWA 30. Related terms are extracted. Then, when the related topic is extracted from the data of the topic list G existing in the iWA 30 database in advance using the related term “panic” as a key, the topic list (number of selected topics) is displayed as shown in a screen 1813. : 1424 Total number of topics 1424) Through Butt: 17.25 is displayed. From this screen 1813, 1424 topics are extracted under the control of the CPU of the iWA 30 using the related word “panic” as a key, and there is a possibility that a topic introduction list may eventually be constructed. The topic and a plurality of related terms associated with the topic are received by the maintenance device 3 and displayed on the screen 1813. Briefly, list data in which a plurality of topics and a plurality of representative related terms are associated with each topic using the related term “panic” as a key to display the screen 1813 in FIG. 17. Is received from the iWA 30 (S2002).

  Such input is generated and displayed so that 1424 topics can be provided as topic introduction list candidates using the first related word “panic” as a key. If this number is large, it is visualized. The person in charge can determine the content of the topic, and can narrow down the topic so that it becomes a topic to be adopted in the target topic introduction list. That is, referring to the flow of FIG. 18, without confirming the list data of the topic introduction list in step S2004, a time-out occurs after a certain time has elapsed, and the input of additional topic material in step S2001 is executed again. Can do. For example, on the screen 1815, by inputting a topic topic “I am relieved” for the second time, the input representative related verbs and the received data as the topic are displayed. Number of topics 136 Total number of topics 1424) Throughput: 16.54 is displayed. That is, the list data being generated as the topic provision list has been reduced from 1424 to 136. As a result, it has been modified to a form close to the topic provision list according to the intention of the person in charge.

  Furthermore, when the person in charge cannot come up with a new topic, the display form can be changed to a display form centered on related terms. In this display mode, as shown in a screen 1815, “condition setting: priority related terminology” is input by operating the input device, so that the related terms can be displayed in a priority list format. . In other words, a plurality of related terms given to the second topic under the control of the CPU of the iWA 30 are 136 topics (1, 2, 3,...) As shown in a screen 1815 in FIG. .., 136) It is possible to switch to a display form in which a plurality of related terms are displayed in a plurality of columns in each row. As described above, this display mode switching is performed by the control unit (not shown) of the maintenance device 3 listing the related terms for each topic displayed in each row in the column direction according to the screen switching input of the input device. Change display to form. The person in charge can determine from this display form a related terminology suitable for introducing the topic he / she wants to create from a plurality of related terms displayed on the screen 1815, and input the related terminator with the input device. (S2001: YES). The screen 1811 shows this input state. In this case, the related term “most scary” is input as a new topic topic. Then, the related term “most scary” is referred to the topic list database under the control of the CPU of the iWA30, and a new topic introduction list comprising a plurality of related terms and topics based on the topic topic inputted. The list data as candidates is received (S2002) and displayed (S2003).

  The topic list G is a list made up of information collected by an external information collecting means such as the Internet from the outside by the iWA 30 as a server. A plurality of related terms are associated with each topic in the topic list G in advance and stored in the iWA 30 database. As described above, in this embodiment, there is a possibility that variations in setting a topic may become obsolete due to lack of knowledge or ability of the person in charge, and other related topics obtained from the iWA30 topic list as a server. And by displaying the topic itself and a plurality of related terms related to the topic on the screen of the maintenance device 3, as described above based on the topics obtained from these topic lists This increases the possibility of abundant variations of topics that transition to.

  The modification of the candidate of the topic provision list as described above is timed out after a predetermined time until the input completion is input (S2004: YES), and an input screen for inputting the above-mentioned topic is displayed. Waiting for the next topic, the processes of S200 to S2003 are repeated sequentially.

  When input completion is input (S2004: YES), data as a topic introduction list is output to the iWA 30 as a server (S2005).

<<< Outline of Technical Thought in Information Retrieval System >>>
The information search system of the present invention provides a user with a keyword (character string) that can acquire the latest unknown topic using the mechanism of the topic providing system 1 as shown in FIG. First, an outline of the technical idea in the information search system of the present invention will be described with reference to FIG.

  In the information search system of the present invention, an important character string (related) that can identify a topic from an external log 502 including narrative information generated by an individual, through a sentence analysis process 511, a preference analysis process 512, and a topic analysis process 513. The relationship (distribution)) and the distribution situation are displayed, and the user can grasp the topic (topic) by viewing this display. From the input of the external log 502 to the provision of the display of related terms is performed instantaneously.

  For example, if a result of searching a web page on the Internet is regarded as topic information, a topic dictionary that is a summary of topic information can be obtained by compressing and summarizing the topic information. In the information retrieval system of the present invention, the topic dictionary is compressed before the sentence analysis process 511 described above. For example, only text data that can be topic information, excluding tags and script sentences, is extracted from the result of searching a WEB page and the like, and the extracted text data is a processing target of the sentence analysis process 511. .

  In a more specific example, the company information (topic information) is information related to the company, which is text data generated by an individual, and this is a knowledge space related to the company. This knowledge space is compressed and summarized without using a dictionary related to the language by the above-described processing, and converted into a partial knowledge space. As a result of such processing, a dictionary (partial knowledge space related to the company) consisting of a set of decomposed text data (related terms) that can identify the company information is obtained. As will be described later, this partial knowledge space includes information representing the connection between related terms.

  In the conversation control terminal device 2 ″, a condition for collecting the external log 502 is given (for example, from the user of the conversation control terminal device 2 ″), and the above-described processing (sentence analysis processing 511, preference analysis processing 512, In addition, as a result of the topic analysis processing 513), a related term is provided to the conversation control terminal device 2 ''. The conversation control terminal device 2 ″ is, for example, a device such as a PC (personal computer), a smartphone, or a robot. If the conversation control terminal device 2 ″ is a PC, the related term of the processing result is the conversation control terminal device 2. They are displayed on the display of '' and provided to the user of the conversation control terminal device 2 '' as information for instantly grasping the topic. The conversation control terminal device 2 "is configured as a modification of the above-described conversation control terminal device 2 or conversation control terminal device 2 '.

  The sentence analysis process 511, the preference analysis process 512, and the topic analysis process 513 described above are performed by the topic providing server 4 '. The topic providing server 4 ′ is configured as a modification of the topic providing server 4 described above.

<< Summary of sentence analysis process >>
The sentence analysis process 511 analyzes sentence information included in the external log 502 based on the appearance characteristic of the character string, and selects a related term 503.

  The sentence analysis process 511 selects (extracts) a related verb that can identify a topic from the external log 502 without using dictionary data stored and prepared in advance such as morpheme data. That is, a common character string appearing in the external log 502 is searched, and related terms are extracted according to the degree of difference between the adjacent characters immediately before and the degree of difference between the adjacent characters immediately after those character strings.

  The external log 502 includes narrative information created by an individual as described above (for example, data stored in a predetermined log format, WEB page (homepage) or blog text data published on the Internet, and TWITTER (registration). Trademark information), data generated and edited in advance by an arbitrary organization, and text information in a database. Also, various data such as text data acquired from a voice file / moving image file through voice recognition processing may be used.

  The external log 502 is data collected according to collection conditions. For example, it may be text data described in a WEB page (homepage) 501 shown as a search result of keyword search, a sentence described in a user's blog having a certain attribute, tweet information in TWITTER, or the like. . A search condition or the like in the keyword search can be specified by the user from the conversation control terminal device 2 ″. One external log 502 may include a plurality of text files (for example, one including a plurality of WEB pages (HTML files) included in one WEB site) or one text file. It may be a divided part (for example, one of texts included in one file divided every 10,000 lines).

<< Overview of preference analysis process >>
The preference analysis processing 512 captures how the related terms extracted by the sentence analysis processing 511 are used based on the internal log 506 and determines their importance.

  The internal log 506 is data indicating preferences of the user (including the organization or organization to which the user belongs), and is data stored in a predetermined log format, for example. The internal log 506 includes, for example, data indicating what related terms tend to be used by the user. In this specification, the related terminology associated with the importance according to the user's preference is referred to as a topic key (cluster) 504 in this specification.

<< Summary of topic analysis processing >>
The topic analysis processing 513 captures the distribution of the topic key 504 generated by the preference analysis processing 512 based on the topic material 507 and provides the user with the distribution of related terms associated with each other.

  As described above, the topic topic 507 is set when the person in charge of the contractor directly inputs and sets with the input device of the maintenance device 3 as described above, and when the topic providing server 4 ′ is the input device of the maintenance device 3 In some cases, the external log 502 collected from outside (for example, data that can be collected via a network such as TWITTER or a blog) is automatically extracted based on the input keyword.

  By such topic analysis processing 513, it is possible to show how related terms are distributed in the topic, and it is also possible to recommend related terms according to the user of the conversation control terminal device 2 ''.

<<< Overview of Information Retrieval System >>>
Next, an overview of the information search system will be described with reference to FIG. An information search system 100 shown in FIG. 20 includes a conversation control terminal device 2 ″ and a topic providing server 4 ′. Between the conversation control terminal device 2 ″ and the topic providing server 4 ′, a predetermined network (LAN, Internet, WAN, wireless communication, etc.).

<< Overview of Conversation Control Terminal 2 ">>
The conversation control terminal device 2 ″ includes an input control unit 21, a search control unit 22, a transmission control unit 23, a reception control unit 24, a response information determination unit 25, an output control unit 26, and a network interface (I / F) unit 27. including. The scenario data 28 is stored in a main storage device such as a RAM or an external storage device such as a hard disk or a semiconductor memory.

  The input control unit 21 receives an input by the user of the conversation control terminal device 2 ″ using a keyboard, a mouse, or the like, and passes input data or the like to a corresponding function unit according to the input content. For example, the user inputs a search keyword using a keyboard, or clicks a display area of an interesting related term using a mouse.

  The search control unit 22 includes a general WEB browser that operates on the conversation control terminal device 2 ″. The conversation control terminal device 2 ″ is connected to the Internet, for example, and when the user operates the WEB browser to search a WEB page (generally available Internet search), the search control unit 22 The obtained search result is transmitted to the transmission control unit 23. The search result includes the address of the WEB page related to the search keyword (for example, Internet address identification information such as URL).

  Upon receiving the search result from the search control unit 22, the transmission control unit 23 transmits this as input information to the input information analysis unit 41 of the topic providing server 4 ′ by API transmission, for example.

  The reception control unit 24 receives the input specifying information transmitted from the input information analysis unit 41 of the topic providing server 4 ′ and supplies it to the response information determination unit 25.

  The response information determination unit 25 determines response information based on the scenario data 28 and the input specifying information. Response information is determined from the input information analysis unit 41 based on input specifying information (for example, data for displaying the distribution of related terms) and scenario data determined to be necessary for the display.

  The output control unit 26 performs control so that the response information determined by the response information determination unit 25 is displayed on the conversation control terminal device 2 ″.

  The network interface unit 27 includes access to the topic providing server 4 ′ connected via the network, data transmission / reception, and other computers (for example, a server including an Internet search engine connected via the Internet). To control access and data transmission / reception.

  The scenario data 28 is data for defining response information related to topics provided to the user as shown in FIG. The scenario data 28 is data stored in advance in scenario data 55 of the topic providing server 4 ′ described later. Scenario data determined to be necessary based on the input specifying information generated by the input information analysis unit 41 of the topic providing server 4 ′ is extracted from the scenario data 55, and the extracted scenario data is the conversation control terminal device. 2 ″ scenario data 28 is stored. The scenario data extracted from the scenario data 55 is stored in the scenario data 28 by the processes of the reception control unit 24 and the response information determination unit 25.

  All scenario data is stored in the scenario data 55 of the topic providing server 4 ′, and scenario data that is rearranged from the scenario data of the scenario data 55 is generated and rearranged based on the information that defines the transition to a different topic. Only the corrected scenario data can be stored in the scenario data 28 of the conversation control terminal device 2 ″.

<< Overview of Topic Providing Server 4 '>>
The topic providing server 4 ′ includes an input information analysis unit 41 and a network interface (I / F) unit 47. In addition, the search result data 48, the related term candidate data 49, the related term dictionary 50, the preference data 51, the related term / co-occurrence data are stored in a main storage device such as a RAM or an external storage device such as a hard disk or a semiconductor memory. 52, topic data 53, comparison result data 54, and scenario data 55 are stored. These data can take various data formats and data storage formats.

  The input information analysis unit 41 analyzes the input information received from the conversation control terminal device 2 ″ to generate input specifying information. The input specifying information is information generated as a result of analyzing various types of information included in the input information, and includes, for example, the distribution of related terms described later. The input information analysis unit 41 further includes an external log acquisition control unit 42, a sentence analysis unit 43, a preference analysis unit 44, a topic analysis unit 45, and an information update unit 46.

  In the external log acquisition control unit 42, the input information received from the conversation control terminal device 2 ″ is identification information for identifying the external log 502 (for example, a search result including the address of the WEB page 501 related to the search keyword). In this case, for example, the identification information is accessed via the Internet, and the corresponding HTML data is acquired. In addition, when the input information received from the conversation control terminal device 2 ″ includes text data itself that is a target for extracting related terms, the data is provided to the sentence analysis unit 43 as an external log 502.

  Further, when information identifying the external log 502 (for example, a search result including the address of the WEB page 501 related to the search keyword) is received from a crawler (see FIG. 39) that is automatically started at a predetermined interval, The external log 502 is accessed, the corresponding data is acquired, and the acquired data is provided to the information update unit 46 for comparison with the related term dictionary.

  The sentence analysis unit 43 acquires the text data from the external log 502 acquired by the external log acquisition control unit 42, extracts important related terms included in the text data according to the appearance characteristics of the character string, and the related terms Store in dictionary 50.

  The preference analysis unit 44 determines the importance of the related terms stored in the related term dictionary 50 by the sentence analysis unit 43 based on the preference data 51 and stores the determination result in the related term / co-occurrence word data 52. The preference data 51 is data including an internal log 506 that stores the usage of the related terms by the user.

  The topic analysis unit 45 captures the distribution of the related terms stored in the related term / co-occurrence word data 52 generated by the preference analysis unit 44 based on the topic data 53 and associates the related terms with each other. Update the co-occurrence word data 52. The topic data 53 is data including a topic material 507 that is input and set by the person in charge of the contractor or is automatically extracted.

  Based on the text data collected under different collection conditions, the information updating unit 46 selects a related term to generate a related term dictionary, compares the generated related term dictionaries, and compares the comparison result with comparison result data. 54.

  The network interface unit 47 is used to access and transmit / receive data to / from the conversation control terminal device 2 ″ connected via the network, and other computers (for example, a server having an Internet search engine connected via the Internet, etc. ) And access data transmission / reception.

  In this embodiment, the information search system 100 has been described as a system including the conversation control terminal device 2 ″ and the topic providing server 4 ′. However, the conversation control terminal device 2 ″ and the topic providing server 4 ′ are It can also be configured as one integrated computer. Conversely, the same function can also be realized by distributing it to three or more computers connected to the network.

<Outline of sentence analysis department>
Next, an outline of the sentence analysis unit 43 will be described with reference to FIG. The sentence analysis unit 43 retrieves the same character string from the text data, and determines the degree of difference between the previous adjacent character and the degree of difference between the subsequent adjacent character for each of the retrieved character string, and the determined difference Based on the degree, it is determined whether or not the retrieved “same character string” is a related verb that has high importance with respect to the topic and can semantically identify the text data. The degree of difference between the previous adjacent characters is an index indicating how much the character appearing immediately before the searched “same character string” is different. Similarly, the degree of difference between subsequent adjacent characters is an index indicating how much the character appearing immediately after the searched “same character string” is different.

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

  This kind of character string extraction is based on the fact that when you focus on multiple identical character strings included in text data, many variations of characters appear as characters that are located immediately before each character string. When the appearance characteristic that many variations of characters appear as the character positioned immediately after is recognized, the character string is based on the idea that the character string is an independent and frequently used term. As described above, the sentence analysis unit 43 of the present invention extracts character strings based on the idea based on kinematics of character strings.

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

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

  The sentence analysis unit 43 includes a text data acquisition processing unit 43a, a character string search processing unit 43b, a different degree determination processing unit 43c, and a related term determination processing unit 43d. Furthermore, the related term determination processing unit 43d includes a related term determination unit 43d-1 and a ranking management unit 43d-2.

  The text data acquisition processing unit 43a acquires the external log 502 (text data to be processed) and provides it to the character string search processing unit 43b (text data acquisition processing 520 shown in FIG. 25 described later). The character string search processing unit 43b performs a character string search process 530 shown in FIG. The difference degree determination processing unit 43c performs a difference degree determination process 540 shown in FIG.

  The related term determination processing unit 43d determines a related term, and stores the determined related term in the related term dictionary 50 as necessary (related term determination processing 550 shown in FIG. 25).

  Also, the related term determining unit 43d-1 determines whether or not the same character is a related term from the degree of difference between adjacent characters before and after the same character string included in the external log 502. When a plurality of related terms are determined in one external log 502, the ranking management unit 43d-2 ranks the related terms as necessary.

<Outline of information update unit>
Next, an overview of the information update unit 46 will be described with reference to FIG. The information update unit 46 includes a text data acquisition processing unit 46a, a character string extraction processing unit 46b, a dictionary comparison processing unit 46c, and a comparison result output unit 46d.

  The text data acquisition processing unit 46a acquires the external log 502 (text data to be processed) and provides it to the character string extraction processing unit 46b (text data acquisition processing 700 shown in FIG. 39, which will be described later). The character string extraction processing unit 46b extracts a related term from the external log 502 and stores it in the corresponding related term dictionary 50 (character string extraction processing 710 shown in FIG. 39). The character string extraction processing unit 46b is, for example, the same processing as the processing by the sentence analysis unit 43 described above.

  The dictionary comparison processing unit 46c compares a plurality of related terminology dictionaries 50 and stores the comparison result in the comparison result data 54 (dictionary comparison processing 720 shown in FIG. 39).

  The comparison result output unit 46e acquires a comparison result to be displayed from the comparison result data 54, and transmits input specifying information including the comparison result to the conversation control terminal device 2 ''.

<<< Explanation of an embodiment in which the information search system of the present invention is applied to FAQ search >>>
Next, the FAQ search system that displays the result of the FAQ search according to the user's instruction using the information search system according to the embodiment of the present invention will be described.

<< Screen transition of FAQ search system >>
FIG. 23 shows the screen transition of the FAQ search system. First, the user gives a predetermined instruction on the conversation control terminal device 2 ″, displays the FAQ search screen 600 on the display, and inputs a desired search keyword (using a keyboard or the like) there. The FAQ search screen 600 is an input instruction screen as shown in FIG. 35A, for example, and a search keyword input unit 601 and a “FAQ search” button 602 are displayed on the FAQ search screen 600.

  When the user inputs a search keyword (“network” in the example of FIG. 35A) to search keyword input unit 601 and clicks “FAQ search” button 602 with a mouse or the like, FAQ candidate display screen 610 is displayed. Is displayed. The FAQ candidate display screen 610 is, for example, a display screen as shown in FIG. 35B, and displays a related term index display portion 611, a candidate question sentence display portion 612, and a “return to FAQ search screen” button 613. ing. The questions shown in the candidate question sentence display unit 612 are all related to “network”, and the search results based on the search keyword input by the user are displayed. The set of related terms shown in the related term index display unit 611 is a set of related terms included in the corresponding question. When the user clicks a “return to FAQ search screen” button 613 here, the display on the display of the conversation control terminal device 2 ″ returns to the FAQ search screen 600.

  In the FAQ candidate display screen 610, when the user selects one of the candidate question sentences displayed in the candidate question sentence display unit 612 by clicking the mouse or the like (arrow (1)), the FAQ display screen 630 is displayed. . The FAQ display screen 630 is, for example, a display screen as shown in FIG. 36, and displays a question display portion 631, a related term index display portion 632, an answer display portion 633, and a “return to FAQ candidate display screen” button 634. ing. When the user clicks a “return to FAQ candidate display screen” button 634 here, the display on the conversation control terminal device 2 ″ returns to the FAQ candidate display screen 610.

  When the user selects one of the related term indexes displayed on the related term index display unit 611 by clicking the mouse on the FAQ candidate display screen 610 (arrow (2)), the related term / co-occurrence word list is displayed. A screen 650 is displayed. The related term / co-occurrence word list display screen 650 is, for example, a display screen as shown in FIG. 37, and includes a NO display unit 651, a related term display unit 652, a neighborhood related term display unit (653-656), and “FAQ”. A “return to candidate display screen” button 657 is displayed. Here, when the user clicks a “return to FAQ candidate display screen” button 657, the display on the conversation control terminal device 2 ″ returns to the FAQ candidate display screen 610.

  On the related term / co-occurrence word list display screen 650, when the user selects one of the related terms displayed on the related term display unit 652 or the neighborhood related term display unit (653-656) by clicking a mouse or the like, The FAQ search screen 660 is displayed. The FAQ search screen 660 is a display screen as shown in FIG. 38B, for example, which is substantially the same as the FAQ search screen 600 shown in FIG. It shows that it has returned to. In the search keyword input unit 661 of the FAQ search screen 660, as a search keyword, the related term (for example, “SNS” in the example of FIG. 37) selected on the related term / co-occurrence word list display screen 650 is automatically displayed. Is set automatically.

  When the user clicks the “FAQ search” button 662 in this situation, the FAQ candidate display screen 610 is displayed again, and the question sentence regarding “SNS” is displayed in the candidate question sentence display unit 612 this time.

<< Explanation regarding display processing of FAQ candidate display screen >>
Next, the display process of the FAQ candidate display screen will be described with reference to FIG. FIG. 24 is a flowchart showing the processing for displaying the FAQ candidate display screen, and shows what processing is performed in each of the conversation control terminal device 2 ″ and the topic providing server 4 ′. In the conversation control terminal device 2 ″, for example, each process is performed by the above-described Topiclet 20, and the screen display on the display of the conversation control terminal device 2 ″ shown in FIGS. Or a WEB browser that operates under the control of the Topiclet 20.

  First, in step S <b> 11, it is determined whether or not the user has clicked the “FAQ search” button 602 on the FAQ search screen 600. While the “FAQ search” button 602 is not clicked (NO), this determination is repeated. When the “FAQ search” button 602 is clicked (YES), in step S12, the search result based on the search keyword input to the search keyword input unit 601 by the user is transmitted as input information to the topic providing server 4 '. In this embodiment, the search result is a result of keyword search on a general Internet search site, and the Topiclet 20 controls the search on this Internet search site, and the topic providing server 4 transmits the search result by API transmission. Send to '. The search result is, for example, the address of the WEB page that hits the keyword search.

  When the topic providing server 4 ′ receives the input information from the conversation control terminal device 2 ″, in step S13, the input information is analyzed, the address of the WEB page included in the input information is accessed, and the HTML corresponding to the WEB page is accessed. The external log 502 as the target text data is acquired from the data or the like.

  Next, in step S <b> 14, the topic providing server 4 ′ executes sentence analysis processing on the acquired external log 502 and extracts related terms from the external log 502. The sentence analysis process will be described later in detail.

  Thereafter, in step S15, the topic providing server 4 'generates a related term dictionary 50 from the related terms extracted from the external log 502 in step S14. The related term dictionary 50 includes a related term index 50 a for each sentence information in the external log 502.

  Next, in step S16, the topic providing server 4 ′ acquires the related term index 50a and the like from the related term dictionary 50 to be displayed on the FAQ candidate display screen 610, and uses the information as input specific information to control the conversation control terminal. Send to device 2 ''.

  When receiving the input specifying information from the topic providing server 4 ′ (step S 17), the conversation control terminal device 2 ″ determines response information based on the received input specifying information and the scenario data 28 in step S 18. The topic providing server 4 ′ transmits the scenario data 55 to the conversation control terminal device 2 ″ as necessary, and the conversation control terminal device 2 ″ stores this in the scenario data 28.

  Next, in step S19, the response information determined in step S18 is displayed on the display of the conversation control terminal device 2 ''. For example, a FAQ candidate display screen 610 as shown in FIG. 35 (B) is displayed. In this embodiment, for example, a part of the collected question sentences (Q1, Q8, Q13, Q24, Q25) is displayed as a list of candidate question sentences on the candidate question sentence display unit 612. The related term index display unit 611 shows related term indexes corresponding to the question sentences displayed as candidate question sentences.

<< Detailed explanation of sentence analysis process >>
Next, with reference to FIG. 25, an outline of sentence analysis processing executed by the sentence analysis unit 43 (see FIGS. 20 and 21) of the topic providing server 4 ′ will be described. First, the sentence analysis unit 43 acquires the external log 502 that is text data (text data acquisition processing 520). The external log 502 can be received from various data sources as described above. In this embodiment, each WEB page is accessed based on the address of the WEB page received from the conversation control terminal device 2 ″, and the text data is obtained from the corresponding HTML data or the like. Further, when acquiring the acquired external log 502 or the external log 502, it is possible to perform a filtering process so as to acquire only specific text data, or group by a specific classification.

  Next, the sentence analysis unit 43 searches for the same (common) character string from the external log 502 acquired by the text data acquisition process 520 (character string search process 530). This processing is, for example, processing for searching for and retrieving the same character string “Iroha” in the acquired external log 502. If 100 character strings “Iroha” exist in one text data, all of them are extracted. In text data, there may be a plurality of the same character strings other than “Iroha”. In this case, these character strings are similarly searched and extracted. For example, in addition to the character string “Iroha”, if a plurality of character strings “Nihoheto” are included, the character string is similarly extracted. In addition, even if there are multiple character strings that contain “Iroha” that has already been extracted as the same character string, such as the character string “Iroha ni”, the same character string is searched separately from the character string “Iroha”. Is done.

  The character string search process 530 further stores the character strings searched as the same character string in the search result data 48 together with the adjacent character after the character string and the adjacent character after the character string. The data stored in the search result data 48 is, for example, the character string “Iroha” in the above example, the character string “Iroha”, the adjacent character before “Iroha”, for each of the 100 “Iroha”, And the data including the adjacent character after “Iroha”. In the case of the above-described example, the character string “Ihohani” and the character string “Irohani” are also stored in the search result data 48 in the same manner as those character strings, the previous adjacent character, and the subsequent adjacent character.

  As described above, when the same character string is searched in the character string search processing 530, storing the character string and the adjacent characters before and after it ultimately determines an associated verb having an important meaning. For this reason, even if there are a plurality of the same character strings in the external log 502, if the appearance frequency does not reach the predetermined frequency, there is a possibility that it will be determined as a related term at this point. It is possible to determine that the character string is not stored as search result data 48. This is because a word (character string) that appears only a small number of times in the external log 502 composed of many characters can be determined to be less important in the first place.

  In the character string search processing 530, in order to search for and store the same character string from the external log 502, in the present embodiment, a search data structure called a suffix array (Suffix Array) is used. By searching by search (Binary Search), the same character string is searched at high speed. In the present embodiment, the character string search processing 530 is performed by the method as described above, but the same search processing can be performed by employing various other methods. The processing of the character string search processing 530 using the suffix array and binary search will be described in detail later.

  Next, the sentence analysis unit 43 uses the character string stored in the search result data 48 by the character string search processing 530 and the contents of adjacent characters before and after the character string to determine the degree of difference between the previous adjacent character and the degree of difference between the subsequent adjacent characters. (Difference degree determination processing 540).

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

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

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

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

  In this way, the degree of difference regarding the adjacent character for the same character string is determined based on the appearance mode of the adjacent character before (or after) the same character string, that is, how many variations the adjacent character appears. judge. When the degree of difference regarding the adjacent characters before and after is determined, the determined degree of difference is stored in the related term candidate data 49 together with the corresponding character string. Note that the process of the difference degree determination process 540 will be described in detail later.

  Next, the sentence analysis unit 43 determines whether or not the same character string is a related term based on the degree of difference regarding the adjacent characters before and after the same character string determined by the difference degree determination processing 540. If it is determined to be a related term, the character string is stored in the related term dictionary 50 (related term determination process 550).

  As described above, regarding the same character string, if there are variations in the adjacent characters before and after them, if the number of appearance elements of the adjacent character is small, the adjacent character and the “same character string” are combined. Can be considered to form another character string that is often used. On the other hand, if the number of appearance elements of the adjacent character is large, the adjacent character and the “same character string” are separated. The "column" is an independent term and is likely to be a highly important word. Further, whether or not the “same character string” is a related term can be determined in consideration of other factors in addition to the degree of difference between the preceding adjacent characters and the degree of difference between the subsequent adjacent characters. Such a related term determination process 550 will be described in detail later.

  Further, in the related term determining process 550, when a plurality of related terms are determined, ranking can be performed among character strings determined as related terms. Such ranking is, for example, ranking related to the importance of a character string, and can be determined in consideration of other factors in addition to the degree of difference between adjacent characters in the character string. For example, ranking can be performed based on the character length, appearance frequency, etc. of the character string. In addition to ranking, ranking can also be performed numerically so that a relative degree of difference can be represented.

<Description of sentence analysis processing for specific external log examples>
FIG. 26 shows an external log 502 a that is an example of the external log 502. As shown in FIG. 26A, the external log 502a is a collection of only sentence information including “network” in the description part of the question sentence as a search result based on the search keyword. This is text data for solving problems written by various users on various servers on the Internet. Typical examples of these text data include WEB page (homepage) and blog text data published on the Internet, and TWITTER tweet information. Further, data generated and edited in advance by an arbitrary organization or text information in a database may be included. In the original data, it is assumed that the question sentence (Q (question)) and the answer sentence (A (answer)) correspond to each other on a one-to-one basis. Here, only the sentence information in which the character string “network” is included in the description part of the question sentence is extracted from the original data, but the character string “network” is included in the description part of the question sentence and the answer sentence. Various variations such as extracting sentence information can be considered.

  Here, when the sentence analysis process by the sentence analysis unit 43 is performed, the external log 502a shown in FIG. 26A is acquired by the text data acquisition process 520, and then the above-described character string search process 530, difference degree determination When the processing 540 and the related term determination processing 550 are performed, a plurality of related terms are extracted for each question sentence of the extracted sentence information, as shown in FIG. For example, in the question sentence, “network”, “trouble”, “response”, and “setting” are selected for Q1. In the description of the question of Q1, “the network” corresponding to the search keyword is underlined, and other related terms are surrounded by a rectangle. Further, {network, setting, trouble, correspondence} is shown as a set of extracted related terms corresponding to the description of the question of Q1. This set of related terms is described in the ranking order described above with respect to the related term determination process 550.

  Similarly, for Q8, “network”, “setting”, and “by event” are selected. In the description of the question of Q8, the “network” corresponding to the search keyword is underlined, and other related terms are surrounded by a rectangle. Also, {by network, setting, event} is shown as a set of extracted related terms corresponding to the description of the question of Q8. Here, it is possible to extract not only the question sentence but also related contents of the answer sentence so as to be included in the related term index.

  An example of the related term dictionary 50 generated by the related term determining process 550 is shown in FIG. As a related term index 50a, a set of related terms related to each question shown in FIG. 26B is stored as it is. In some cases, it is sufficient to store only the related term index 50a as the related term dictionary 50. However, in this embodiment, the question sentence corresponding to the related term index is stored in the question sentence 50b. The answer corresponding to the question sentence 50b is stored in the answer sentence 50c.

  As shown in FIG. 27A, the related term index 50a stored in the related term dictionary 50 is stored in association with corresponding sentence information, so that one set of related terms and other related terms are stored. The related terms belonging to the other set are associated with each other through the related terms common to the set. For example, as shown in FIG. 27B, {network, setting, trouble, correspondence} is grasped as a set of related terms for the question Q1 in the question sentence, and the question Q8 in the question sentence. If {network, setting, event} is grasped as a set of related terms, there is a common related term “setting” (except for the related keyword “network” that is the search keyword). , It is understood that the related term (also known as co-occurrence related term) is related to the related term “setting”, and is related to the related terms “trouble” and “correspondence”. It is understood that they have a relationship in that they are related to the verb “by event”, that is, they have a common point that they co-occur with the related term “setting”.

  In this embodiment, the relationship between the related terms is seen among the sentence information of the external log 502a collected by the search keyword “network”, but is collected by a completely different search keyword. In some cases, it is possible to find such a relationship among related terms in the sentence information. In this case, a potential topical relationship can also be found.

<Detailed description of character string search processing in sentence analyzer>
The character string search processing 530 will be described with reference to FIGS. FIG. 28 is a flowchart illustrating the processing procedure of the character string search processing 530. FIGS. 29 and 30 are diagrams showing a mechanism for character string search using a suffix array and binary search. As a character string to be searched, for example, “this code is a part of a character string of the external log 502”. Text data 502-1 “is in the code list” is set. Normally, the entire text portion of the external log 502 is a search target, but here it is a part of the text portion for illustration.

  First, a suffix array is created in order to search for the same character string from the character string “this code is in the code list”. In step S21 in FIG. 28, the suffix is expanded from the first character to the last character of the text data. Here, referring to FIG. 29, from the text data 502-1 to be searched ("this code is in the code list") shown in FIG. 29A, as shown in FIG. Suffixes with indexes from 1 to 15 are expanded. Each suffix is a character string from the index position (start character position) to the end in the text data 502-1 to be searched. For example, for the index “1”, the text data 502-1 to be searched A character string “This code is in the code list” from the first character to the end (15th character) is shown. For the index “10”, the character string “in the list” from the 10th character to the end (15th character) of the text data 502-1 to be searched is shown. For the last index “15”, the last character “RU” is shown.

  Next, in step S22 of FIG. 28, the expanded suffixes are sorted in a predetermined order to create a suffix array. Here, referring to FIG. 29, the suffixes shown in FIG. 29 (B) are sorted, and the suffix array after sorting is shown in FIG. 29 (C). Sorting is performed by, for example, a character code corresponding to each character (in this example, JIS code). From the first record to the fourth record, the first character is “-” (JIS code = 213C), “A”. It can be seen that the characters are sorted in the order of the character codes such as (JIS code = 2422) and “ga” (JIS code = 242C). The first and second records have the same first and second characters, but the third character differs between “GA” and “RE” (“GA” (JIS code = 242C), “RI” ( JIS code = 256A)), the first record is arranged first. Note that the index shown in FIG. 29B is attached to the corresponding record as it is.

  Next, in step S23 of FIG. 28, one search character string is sequentially determined from the text data. In this case, whether or not the same character string exists in the text data is searched, and all partial character strings in the text data are collated with the text data as search character strings. For example, regarding the text data 502-1 to be searched in FIG. 29, a search character string “ko” to “ru” of one character, a search character string “this”, “noco”,. ‘N’, ‘Yes’, 3 character search strings ‘Kon’, ‘No’, ・ ・ ・, ‘To’, ‘In’, etc. The search character string up to “This code is in the code list”. However, in this case, the search character string of 1 character or 15 characters can be omitted because it is meaningless to collate with the text data 502-1 to be searched. In addition, the character length of the search character string can be limited to a predetermined range.

  Next, in step S24 of FIG. 28, it is determined whether or not all the search character strings to be searched are completed. Here, when all the processes are completed, the character string search process ends. If all have not been completed yet, the suffix array is searched using the search character string as a search key in step S25. Here, referring to FIG. 30, as shown in FIGS. 30A and 30B, a character string “code” of three characters is determined from the text data 502-1 to be searched as a search character string. The search process in the case of being performed is shown. At this time, a binary search is performed on the suffix array of FIG. The suffix array in FIG. 30C is the same as the suffix array shown in FIG. 29C, and FIG. 30C shows a search process by binary search.

  Referring to FIG. 30C, the record (1) in the center of the suffix array (index = 15, the character string “RU”) is compared with the search character string “code”. At this time, the JIS code of “ru” is 246B, the JIS code of “ko” is 2533, and “co” is larger, so the record (1) below the record array (1) located in the center of the lower half of the suffix array ( 2) Compare the search character string “code” with (index = 12, character string “is in”). At this time, the JIS code for “G” is 2548, the JIS code for “G” is 2533, and “C” is smaller, so the record (3) ( Index = 7, character string “is in code list”) and search character string “code” are compared.

  Then, since the first three characters of the record (3) match the search character string “code”, the same character string as the search character string is found in the search target text data 502-1. After that, when compared with the upper and lower records of the record (3), the first three characters of the record (4) and the search character string “code” match, so the same character string as the search character string is the text data 502 to be searched. -1 is found. Such a binary search reveals that there are two character strings “code” in the text data 502-1 to be searched (one of which is extracted from the text data 502-1 to be searched). Search string "code" itself).

  Next, in step S26 of FIG. 28, it is determined whether or not a predetermined number of search character strings have been hit. If it is determined that a predetermined number of search character strings do not hit, the process proceeds to step S23 in order to perform a search by the next search character string without using the character string as a candidate for a related term. Here, the predetermined number can be determined based on various factors such as the number of characters in the text data 502-1 to be searched and the number of characters in the search character string. The fact that the predetermined number of hits does not occur means that the frequency of appearance of the search character string is low in the search target text data 502-1 and is not an important word. It should be noted that at this stage, the appearance frequency can be stored as a related term candidate without being evaluated, and finally determined in a subsequent related term determination process or the like.

  If it is determined in step S26 that the search character string has been hit by a predetermined number, the process proceeds to step S27, where the character string that matches the search key (search character string) is set as a related term candidate, At the same time, it is stored in the related term candidate data 49 as one record. Here, referring to FIG. 30C, as a search result, the record (3) and the record (4) in which the character string matching the search character string “code” is found at the head are the same as the search character string, respectively. The character string “code” and adjacent characters before and after are stored as one record. For example, for record (3), “GA”, “CODE”, and “RE” are stored as one record. The preceding adjacent character is “GA”, and the subsequent adjacent character is “RE”. For record (4), “no”, “code”, and “ga” are stored as one record. The preceding adjacent character is “no” and the subsequent adjacent character is “ga”.

  As described above, the sentence analysis unit 43 in this embodiment is configured to find the same character string in the text data at high speed using the suffix array and the binary search as described above. It is not limited to the said processing method. It is possible to find the same character string in the text data by a method other than that described above.

<Detailed description of the degree of difference determination process in the sentence analysis unit>
Next, with reference to FIG. 31 and FIG. 32, the different degree determination processing of the sentence analysis unit 43 in this embodiment will be described in more detail.

  FIG. 31 is a flowchart showing the processing procedure of the degree-of-difference determination processing 540. FIG. 32 is a diagram showing a mechanism for determining the degree of difference between the adjacent characters before and after, and the character string search process using the search character string “code” as shown in FIG. As a result of performing the search on the target character string, 26 search character strings “codes” are obtained as search results, and the corresponding 26 records are processed.

  First, in step S31 of FIG. 31, a character string search process 530 extracts a record relating to one character string from the character string records (including preceding and following adjacent characters) stored in the search result data 48. Here, referring to FIG. 32A, a state is shown in which records (26 records in total) for the character string “code” stored in the search result data 48 are extracted and expanded in the memory.

  Next, if all the character string records stored in the search result data 48 are acquired in step S32 in FIG. 31 and it is determined that there is no more data to be subjected to the different degree determination process, the different degree determination process in FIG. Ends. If all the processes have not been completed in step S32 and all the records have been acquired for one of the character strings stored in the search result data 48, the process proceeds to step S33.

  Next, in step S33 of FIG. 31, all records acquired for one of the character strings stored in the search result data 48 are sorted by the previous adjacent character, and the number of appearance character patterns related to the previous adjacent character is determined. Ask. Here, referring to FIG. 32A, the result of sorting the records (26 in total) acquired for the character string “code” stored in the search result data 48 by the previous adjacent character 561 is shown. . This sorting can be performed using a character code (for example, JIS code) as in the case of creating a suffix array in the character string search process described above. After performing such sorting, the number of appearance character patterns of the previous adjacent character 561 can be determined by counting the number of times the value of the previous adjacent character 561 has changed (breaked) between records. In the case of FIG. 32A, the previous adjacent characters 561 are “”, “(”, “,”, ““ ”,“ ga ”,“ ta ”,“ de ”,“ do ”,“ no ”, There are 13 patterns of “ha”, “be”, “mo”, and “ri”.

  As described above, the sentence analysis unit 43 of this embodiment sorts the previous adjacent characters 561 and obtains the number of appearance character patterns related to the previous adjacent characters depending on whether or not the value has changed between the records. However, the present invention is not limited to the processing method. The number of appearance character patterns can be obtained by various other methods. In addition, it is possible to flexibly set the handling of predetermined characters and character patterns according to specifications. For example, it is possible not to consider control characters such as line feeds and page breaks. You can also consider punctuation marks and punctuation marks, or ignore them. Furthermore, uppercase and lowercase letters can be treated as the same character, or they can be treated as different characters. As for sorting, for 1 byte code characters such as single-byte alphanumeric characters, the corresponding 1 byte is sorted, and for 2 byte code characters such as Kanji, the corresponding 2 bytes are sorted. Also, when sorting the previous adjacent character 561, in this embodiment, one adjacent character is sorted. However, it is possible to sort two or more characters and determine the degree of difference between them. .

  Next, in step S34 of FIG. 31, the degree of difference regarding the previous adjacent character 561 is determined. In this case, the degree of difference is an index indicating how much the adjacent character 561 is different (between the 26 records in FIG. 32A), and thus the appearance character related to the previous adjacent character described above. It is determined based on the number of patterns. The degree of difference may be the number of patterns itself, but can be determined in consideration of, for example, the appearance frequency of a character string (in the case of FIG. 32A, the appearance frequency of “code” is 26). . Also, the degree of difference can be evaluated in a plurality of stages (for example, three stages) using a predetermined threshold. Furthermore, when the adjacent character 561 is a specific character, arbitrary weighting can be performed with respect to the count of the character and determination of the degree of difference.

  Next, in step S35 of FIG. 31, all records acquired for one of the character strings stored in the search result data 48 are sorted by the subsequent adjacent character, and the number of appearance character patterns related to the subsequent adjacent character is determined. Ask. Here, referring to FIG. 32 (B), the result obtained by sorting the records (26 in total) acquired for the character string “code” stored in the search result data 48 by the subsequent adjacent characters 563 is shown. . By such sorting, the records 565 and 566 shown in FIG. 32A are arranged at the positions indicated by dotted arrows.

  This sorting can be performed using a character code (for example, JIS code) as in the case of creating a suffix array in the character string search process described above. After performing such sorting, the number of characters appearing in the subsequent adjacent character 563 can be determined by counting the number of times the value of the subsequent adjacent character 563 has changed (breaked) between records. In the case of FIG. 32B, the subsequent adjacent characters 213 are “,”, ““ ”,“ ””, “ga”, “de”, “to”, “ni”, “no”, “ha”. , “O”, “Li”, and “Branch”.

  As described above, the sentence analysis unit 43 of this embodiment sorts the subsequent adjacent characters 563, and obtains the number of appearance character patterns related to the subsequent adjacent characters depending on whether or not the value has changed between the records. However, the present invention is not limited to the processing method. The number of appearance character patterns can be obtained by various other methods. Further, the predetermined character can be excluded from the count of the number of patterns. As for sorting, for 1 byte code characters such as single-byte alphanumeric characters, the corresponding 1 byte is sorted, and for 2 byte code characters such as Kanji, the corresponding 2 bytes are sorted. Further, when the subsequent adjacent characters 563 are sorted, in this embodiment, one adjacent character is sorted. However, two or more characters can be sorted and the degree of difference can be determined. .

  Next, in step S36 in FIG. 31, the degree of difference regarding the subsequent adjacent character 563 is determined. In this case, the degree of difference is an index indicating how much the adjacent character 563 is different (between the 26 records in FIG. 32B). It is determined based on the number of patterns. The degree of difference may be the number of patterns itself, but can be determined in consideration of, for example, the appearance frequency of a character string (in the case of FIG. 32B, the appearance frequency of “code” is 26). . Also, the degree of difference can be evaluated in a plurality of stages (for example, three stages) using a predetermined threshold. Furthermore, when the adjacent character 563 is a specific character, arbitrary weighting can be performed with respect to the count of the character and determination of the degree of difference.

  Next, in step S37 of FIG. 31, the character string to be determined and the degree of difference regarding the previous adjacent character and the degree of difference regarding the subsequent adjacent character determined for the character string are stored in the related term candidate data 49. Is done.

  When the process of step S37 in FIG. 31 is completed, the process proceeds to step S31, and the process for the next “same character string” is performed.

<Detailed explanation of related term decision processing in sentence analysis section>
In the related term determination process 550, the data stored in the related term candidate data 49 by the difference degree determination process 540 is sequentially read out, and the corresponding character string is a related term based on the determined difference degree between adjacent characters. Whether or not, the determined related term is stored in the related term dictionary 50 in the form of the related term index, for example, and sentence information corresponding to the related term index (for example, in the above example, question Sentence and answer sentence) are stored in the related term dictionary 50. The related term determination process 550 determines whether or not the corresponding character string is a related term, for example, according to the degree of difference between the adjacent character before and after.

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

  In addition, in the related term determination process 550, in addition to the degree of difference between the adjacent characters before and after, the character length of the corresponding character string, the appearance frequency of the corresponding character string, the probability / frequency of appearance of a specific character as the previous adjacent character , Calculate the score in consideration of the probability and frequency that a specific character appears as a subsequent adjacent character, the probability and frequency that a specific character combination appears as the adjacent character before and after, and based on the calculated score, You may make it determine whether the corresponding character string is a related term.

  Furthermore, when there are a plurality of related term candidates in one text data (character string to be searched), in order to determine as a related term according to the number of candidates and the distribution of scores calculated for each candidate. It is also possible to change the determination conditions.

  Furthermore, in the related term determination process 550, when there are a plurality of related terms determined for each of the external log 502 or sentence information included in the external log 502, ranking is performed among character strings determined as related terms. Can be done. Such ranking is, for example, ranking related to the importance of a character string related to a topic. In addition to the above-described score calculated based on the degree of difference between adjacent characters and the degree of difference between adjacent characters before and after, It is determined on the basis of a score calculated taking into account various factors. In addition, such ranking is not only used to order the importance of strings determined as related terms, but also to indicate the relative importance between related terms, for example, the above-mentioned score Ranking can be performed by specific numerical values by using values or the like.

  Such ranking is performed when a plurality of related terms are determined, but can also be performed for a plurality of related terms determined with respect to one text data, or a plurality of grouped groups according to a predetermined condition. It can also be performed for a plurality of related terms determined for text data.

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

<< Explanation regarding display processing of FAQ display screen >>
Next, the FAQ display screen display process will be described with reference to FIG. FIG. 33 is a flowchart showing the display processing of the FAQ display screen, and shows what processing is performed in the conversation control terminal device 2 ″ and the topic providing server 4 ′. In the conversation control terminal device 2 ″, for example, each process is performed by the above-described Topiclet 20.

  First, in step S41, the user selects one of the candidate question sentences displayed on the candidate question sentence display unit 612 on the FAQ candidate display screen 610 shown in FIG. 35B by clicking the mouse or the like. It is determined whether or not. While one of the candidate question sentences is not selected (NO), this determination is repeated. When one of the candidate question sentences is selected (YES), in step S42, the selected candidate question sentence is transmitted as input information to the topic providing server 4 '. The input information can include the selected question text itself, but it is sufficient if the input information includes an identifier that can identify the question text. Note that the user can select a plurality of question sentences of interest simultaneously.

  When the topic providing server 4 ′ receives the input information from the conversation control terminal device 2 ″, in step S43, the input information is analyzed, and an answer sentence corresponding to the question sentence included in the input information is acquired from the related term dictionary 50. To do. In this embodiment, as shown in FIG. 27A, a question sentence 50b and an answer sentence 50c corresponding to the question sentence 50b are stored in the related term dictionary 50. The sentence 50c can be stored in another file while being associated with the related term index 50a of the related term dictionary 50.

  Next, in step S44, the topic providing server 4 ′ displays information including the answer sentence 50c corresponding to the question sentence 50b acquired from the related term dictionary 50 to be displayed on the FAQ display screen 630 as a related term / co-occurrence word. The information is stored in the data 52 and transmitted to the conversation control terminal device 2 ″ as input specifying information.

  When receiving the input specifying information from the topic providing server 4 ′ (Step S 45), the conversation control terminal device 2 ″ determines response information based on the received input specifying information and the scenario data 28 in Step S 46. The topic providing server 4 ′ transmits the scenario data 55 to the conversation control terminal device 2 ″ as necessary, and the conversation control terminal device 2 ″ stores this in the scenario data 28.

  Next, in step S47, the response information determined in step S46 is displayed on the display of the conversation control terminal device 2 ''. For example, on the FAQ candidate display screen 610 as shown in FIG. 35B, one of the question sentences listed in the candidate question sentence display unit 612 (for example, the question Q24 indicated by the arrow (1)) is selected. Then, an FAQ display screen 630 as shown in FIG. 36 is displayed, where the question display unit 631 displays the question Q24 which is the selected question sentence, and the related term index display unit 632 displays Q24. The related term index corresponding to the question is displayed, and further, the answer corresponding to the question of Q24 (the answer of A24) is displayed on the answer display unit 633.

  By such a screen transition from the FAQ search screen 600 to the FAQ display screen 630, the user can search the FAQ with the search keyword designated by the user and display a plurality of question sentence candidates as search results. Furthermore, it is possible to easily grasp what important keywords appear in each candidate question sentence (that is, what matters are related) by looking at the related index. it can.

  Further, in this embodiment, the FAQ candidate display screen 610 does not display the answer sentence corresponding to the question sentence, but the corresponding answer sentence is displayed at the stage where the candidate question sentence is displayed as a list. You can also.

<< Explanation about display processing of related term / co-occurrence word list screen >>
Next, with reference to FIG. 34, display processing of the related term / co-occurrence word list screen will be described. FIG. 34 is a flowchart showing the display processing of the related term / co-occurrence word list screen, and shows what processing is performed in the conversation control terminal device 2 ″ and the topic providing server 4 ′. In the conversation control terminal device 2 ″, for example, each process is performed by the above-described Topiclet 20.

  First, in step S51, the user selects one of the related term indexes displayed on the related term index display unit 611 on the FAQ candidate display screen 610 shown in FIG. 35B by clicking the mouse or the like. It is determined whether or not. While one of the related term indexes is not selected (NO), this determination is repeated. When one of the related term indexes is selected (YES), in step S52, the selected related term index is transmitted as input information to the topic providing server 4 '. The input information may include the selected related term index itself, but it is sufficient if the input information includes an identifier that can identify this related term index. Note that the user can select a plurality of related terminology indexes of interest simultaneously.

  When the topic providing server 4 ′ receives the input information from the conversation control terminal device 2 ″, in step S53, the input information is analyzed, and all the related terms including the related term index included in the input information are analyzed from the related term dictionary 50. Get the index.

  Next, in step S54, the topic providing server 4 'performs preference analysis for all related terms included in the related term index acquired in step S53 based on the internal log 506 such as the preference data 51. The preference data 51 is a log file that stores data indicating usage modes, such as what related terms have been used so far by each user, for example, as shown in FIG. In addition, for each user ID 51a, which related words 51b the user has input as a reference or search keyword is stored. In addition, as the preference data 51, the usage date and time and detailed usage contents of the related terms can be stored, and the preference analysis can be performed in consideration of the information.

  The topic providing server 4 ′ performs preference analysis on all the related terms included in the conjunction index based on the preference data 51 and determines the importance of each related term. For example, with reference to the preference data 51, the importance level of the related term is set so that the more frequently used related term is, the higher the importance level is for the same user. The related terms associated with such importance correspond to the topic key (cluster) 504 described above.

  Next, in step S55, the topic providing server 4 'further performs topic analysis on the related terms whose importance is set in step S54 based on the topic material 507 such as the topic data 53. The topic data 53 may be a topic input by the person in charge of the contractor or a topic automatically extracted from the external log 502 based on the topic input by the person in charge. Based on such topic data 53, the distribution is captured, and the distribution of related terms associated with each other is provided to the user. For example, it is possible to associate a related term that is a topic in the FAQ with its co-occurrence word and express how the related term is distributed in the topic. Moreover, in the input of topic material or automatic extraction, it is possible to make adjustments for each user of the conversation control terminal device 2 ″ and recommend related terms according to the user. For example, the topic can be adjusted so as to limit the target question sentence to a predetermined range.

  Next, in step S56, the topic providing server 4 ′ displays information including the related terms finally associated in step S55 as input specific information for display on the related term / co-occurrence word list display screen 650. It is transmitted to the conversation control terminal device 2 ″.

  When the conversation control terminal device 2 ″ receives the input specifying information from the topic providing server 4 ′ (step S 57), it determines response information based on the received input specifying information and the scenario data 28 in step S 58. The topic providing server 4 ′ transmits the scenario data 55 to the conversation control terminal device 2 ″ as necessary, and the conversation control terminal device 2 ″ stores this in the scenario data 28.

  Next, in step S59, the response information determined in step S58 is displayed on the display of the conversation control terminal device 2 ''. For example, a related term / co-occurrence word list display screen 650 as shown in FIG. 37 is displayed on the display of the conversation control terminal device 2 ″. On the related term / co-occurrence word list display screen 650, a NO display unit 651, a related term display unit 652, a neighborhood related term display unit (653-656), and a “return to FAQ candidate display screen” button 657 are displayed. Related terms are displayed in the form of a two-dimensional matrix.

  With respect to the vertical axis direction of the matrix, the related term display unit 652 extracts all related terms that are extracted as related terms regarding the FAQ search of this embodiment and appear in the related term index of the related term dictionary 50 in order without duplication. Yes. The display order is set according to the importance of each related term determined by preference analysis. In this embodiment, the lower the number shown in the NO display unit 651 (the higher the number displayed in the upper part of FIG. 37). The importance of the corresponding related terms is high. In FIG. 37, the numbers shown in the NO display portion 651 are 1 to 17, but the sliders on the related term / co-occurrence word list display screen 650 are operated to move downward. Allows you to browse more related terms.

  Regarding the horizontal axis direction of the matrix, a neighborhood related term display unit 653 to a neighborhood related term display unit 656 are shown on the right side of the related term displayed on the related term display unit 652, and here, a related term display unit 652 is displayed. The neighborhood related verbs related to the related verbs displayed in are displayed. As described with reference to FIG. 16, the neighborhood is a set of related terms including the related term A when the attention is given to a related term A, and such a related term is referred to as a neighborhood here. It is a related verb. The related term set is a set of related terms included in a certain topic, and here, the related term index corresponds to this.

  In FIG. 37, there are only four neighborhood related terms from neighborhood related terms 1 to 4; however, the slider bar on the related terms / co-occurrence word list display screen 650 is operated to the right. By moving to, more neighborhood related terms can be browsed. The neighborhood related terminology can be said to be a related term co-occurring with the related term displayed in the related term display unit 652 (co-occurrence related terminology: that is, a related term appearing together in the same topic). The display order of the neighborhood related terms (in the horizontal direction) is displayed in the related term display unit 652 as the co-occurrence relationship is strong, that is, the frequency of appearance with the related term displayed in the related term display unit 652 is higher. It is adjusted to be displayed at a position close to the related verb. Further, the display order in the horizontal direction can be determined in consideration of ranking of related terms, setting by a user or an information search system, and the like.

  Also, on the related term / co-occurrence word list display screen 650, among the related terms displayed on the related term display unit 652, the FAQ candidate display screen 610 shown in FIG. 35B displays on the related term index display unit 611. When one of the related related term indexes is selected by clicking the mouse or the like, the related terms included in the related term index (in this embodiment, for example, “network”, “connection”, “router”). "And" modem ") are highlighted so that the user can easily recognize them.

  The user originally paid attention by the matrix display of the related terms displayed in the related term display unit 652 and the neighborhood related term display unit (653-) of the related term / co-occurrence word list display screen 650. To see another related terminology related to the related terminology (search keyword) in terms of how it has used the related terminology and whether it is close to the topic that the user or information retrieval system is focusing on or recommending Yes, you can be given “awareness” about new related terms. For example, in the related term / co-occurrence word list display screen 650 in FIG. 37, the related term matrix display is performed by the search keyword “network”, but the numbers displayed on the NO display unit 651 are 1 to 13, In the case of No. 15 and No. 15, it can be seen from the set of displayed related terms that the topic is generally related to the communication network. However, when the numbers displayed on the NO display unit 651 are 14, 16, and 17, It is a topic related to social networks, and it can be seen that a different topic has appeared.

  When the user selects one of the related terms displayed on the related term display unit 652 or the neighboring related term display unit (653-) on the related term / co-occurrence word list display screen 650 (FIG. 37). ), The screen automatically transitions to a FAQ search screen 660 as shown in FIG. 38 (B), where the selected related term (in this example, the neighborhood related term “SNS”) is It is automatically set in the search keyword input part 661 of the FAQ search screen 660. When the user clicks the “FAQ search” button 662 in this situation, the FAQ candidate display screen 610 is displayed again, and the question sentence regarding “SNS” is displayed in the candidate question sentence display unit 612 this time.

<<< Description of processing outline in information update unit >>>
The information updating unit 46 extracts a character string that can be distinguished from the external log 502 (text data) collected under different collection conditions, and stores the extracted character string in a related term dictionary corresponding to the text data. The comparison result obtained by performing the comparison process on these related terminology dictionaries is stored in the comparison result data 54 and updated. The comparison process is automatically performed when the related term dictionary is updated.

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

  The above comparison process compares a plurality of related terminators, and in addition to newly appearing related terms, disappeared related terms, commonly appearing related terms, (corresponding to three or more time-series text data) The appearance status of a related term such as a related term that has reappeared is determined, and if the related term is one of such appearance statuses, the related term is stored as a comparison result.

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

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

  With reference to FIG. 39, the processing outline of the information update unit 46 will be described. First, the information update unit 46 acquires the external log 502 that is text data (text data acquisition processing 700). The external log 502 is collected by the crawler 730, for example. When the crawler 730 returns the network address (URL or the like) of the WEB page, the external log 502 can be acquired by accessing the network address. Furthermore, when acquiring the acquired external log 502 or the external log 502, it is possible to perform a filtering process so as to acquire only specific text data, or to perform grouping according to a specific classification.

  For example, the crawler 730 is automatically activated and performs topic analysis on a topic name determined at a predetermined time (that is, performs a search and periodically collects topics). The topic name is stored in, for example, a service (an area assigned to a service ID corresponding to each topic handled by the user) that holds the related term dictionary 50. If the user wants to handle 10 topics, the topic name is 10 These services are handled using individual services. In addition, for each of the services described above, corresponding topic chips are set, each topic chip always collects information on the corresponding topic, and the related topic chips are linked and integrated according to user input. It is also possible to realize more diverse topic providing services.

  In the search by the crawler 730, for example, an existing Internet search site on the Internet is accessed, and a search keyword is specified there, thereby receiving a search result from a search server of the Internet search site. The search result includes, for example, the address of a WEB page that includes content that matches or is similar to the search keyword (the address of WEB page 1, the address of WEB page 2, the address of WEB page 3,..., The address of WEB page X. ) Is included.

  In this embodiment, the crawler 730 acquires a search result by executing a search on an existing Internet search site. However, the crawler 730 acquires a web page address that satisfies a predetermined condition by various other methods. can do. The search target is not limited to WEB pages on the Internet, but TWITTER tweet information, data (database or local) generated and edited in advance by any organization or organization, and text in the database It may be information.

  In an existing Internet search site, a search engine provided in a search server used by the Internet search site allows an address of a WEB page that matches or is similar to a search keyword from a data source on the Internet in response to a search request. Collect (or through pre-periodic collection activities).

  When the search result is transmitted from the search server, the crawler 730 transmits the search result to the topic providing server 4 ′ (for example, by API transmission) from the computer on which the crawler 730 operates. In addition, the crawler 730 can be configured to exclude a search result that satisfies a predetermined condition using a filter.

  In this embodiment, the crawler 730 is automatically activated at a predetermined time, but the operation of the crawler 730 is controlled in accordance with the operation control of the topic providing server 4 ′ and the search result is acquired. Good. Further, the crawler 730 acquires search results at predetermined intervals, holds the search results in a computer on which the crawler 730 operates, and the topic providing server 4 ′ accesses the computer at a necessary timing to perform a search. You can also get the result. Further, the crawler 730 may be configured to be executed by the topic providing server 4 '.

  In this embodiment, the computer on which the crawler 730 operates transmits the address of the WEB page related to the search keyword as a search result to the topic providing server 4 ′. In the computer on which the crawler 730 operates, these WEB pages And the text data obtained as a result can be transmitted as the external log 502 to the topic providing server 4 ′.

  Next, the information update unit 46 extracts a character string whose meaning can be identified from the external log 502 acquired by the text data acquisition process 700, and stores the extracted character string in the related term dictionary 50 (character string extraction). Process 710). The character strings thus extracted correspond to the above-mentioned related terms, and these related terms are respectively stored in the related term dictionary 1 to 3 corresponding to the external log 502 from which the related terms are extracted. Remembered.

  Various methods can be considered as a method for extracting a related term from the external log 502. For example, the related words can be extracted by the method by the sentence analysis unit 43 described above.

  In the character string extraction process 710, related terms are extracted from the plurality of external logs 502 and stored in the corresponding related term dictionary 50, respectively. For example, the plurality of external logs 502 may be text data collected at different timings for the same target or data source, or may be a plurality of text data collected by different subjects or search conditions at the same timing. . Detailed processing of the character string extraction processing 710 will be described later.

  Next, the information updating unit 46 compares a plurality of related terminology dictionaries 50 each storing a related term by character string extraction processing 710, and compares the comparison result into the comparison result data 54 according to the appearance status of the related term. Store (dictionary comparison process 720).

  For example, when comparing two related terminology dictionaries (related term dictionary 1 and related term dictionary 2) collected at different timings, if there is a related term that does not exist in the related term dictionary 1 but exists in the related term dictionary 2 This is stored in the comparison result data 54 as a newly arrived related term, and if there is a related term that exists in the related term dictionary 1 but does not exist in the related term dictionary 2, it is erased. And stored in the comparison result data 54.

  Also, for example, when comparing three related terminology dictionaries (related terms 1 to 3) collected at the same timing for different subjects, if there are related terms existing in all the related terminators dictionaries 1 to 3, And stored in the comparison result data 54 as a common related term.

  It should be noted that, in a plurality of related terminology dictionaries, what kind of appearance state of the related term is stored in the comparison result data 54 can be flexibly defined according to the use mode of the information updating unit 46. Detailed processing of the dictionary comparison processing 720 will be described later in detail.

  When the user requests the conversation control terminal device 2 ″ to display the comparison result data 54 comparing the predetermined relational dictionary directly or according to the response scenario, the topic providing server 4 ′ displays the comparison result. The input specific information including the data 54 is transmitted to the conversation control terminal device 2 ″. When the conversation control terminal device 2 ″ receives the input specific information, it determines response information based on the input specific information and the scenario data 28. Then, control is performed so that the response information is displayed on the display of the conversation control terminal device 2 ″.

  On the display of the conversation control terminal device 2 ″, for example, a topic name and a change in a related term in this topic are displayed. The display of the change of the related term includes, for example, the appearance status of the related term and the corresponding related term.

  For the comparison result data 54 of FIG. 46 to be described later, for example, for the topic name “October 10, 2013, topic of“ stock trading ”at t2,” the related term “tax rate” whose appearance status is “new arrival related terminology”. ”And the related term“ account ”whose appearance status is“ annihilation related term ”. This display corresponds to the record 54a of the comparison result data 54 shown in FIG. The user looks at the contents displayed on the display, and in the topic related to the topic name, a new related term “tax rate” appears at the timing t2, and at the same time, the related term “account” disappears. You can get notice.

<< Description of Character String Extraction Processing in Information Update Unit >>
The character string extraction process 710 will be described with reference to FIG. FIG. 40 is a flowchart showing the processing procedure of the character string extraction processing 710. First, in step S61, an external log 502 (text data) that is a target for extracting related terms is read. As described above, the text data may be any data as long as the text data can be acquired.

  Next, in step S62, a related term which is a character string whose meaning can be identified is extracted from the text data read in step S61. As described above, there are various methods for extracting related terms from text data, including a method based on the degree of difference between adjacent characters by the sentence analysis unit 43 and a method using morphological analysis.

  Next, in step S63, when a plurality of related terms are extracted for one text data in step S62, the plurality of related terms are ranked according to a predetermined criterion. For example, ranking can be performed according to the importance of related terms in text data, and ranking can be performed according to the character length and appearance frequency of related terms. In the case where the related terms are extracted by a method based on the degree of difference between the adjacent characters before and after, ranking is performed according to the degree of difference between the adjacent characters before and after. The ranking can be performed by various factors in addition to such criteria and combinations thereof. Such “rank” indicates relevance to a topic. Further, even when a plurality of related terms are extracted, it is possible not to perform such ranking.

  Next, in step S64, the related terms ranked in step S63 are stored in the related term dictionary corresponding to the text data. For example, the related terms extracted from one text data are collectively stored in one record, and each related term is stored in a storage position (array entry) corresponding to the ranking. By storing the related terms in this way, a plurality of related terms are defined as a set associated with one text data (text data from which the related terms are extracted). Ranking is to rank related terms in the set.

  In the character string extraction process, when there are a plurality of text data to be processed, the processes from step S61 to step S64 described above are repeated for each text data.

<< Description of Dictionary Comparison Processing in Information Update Unit >>
The dictionary comparison process 720 will be described with reference to FIG. FIG. 41 is a flowchart showing the processing procedure of dictionary comparison processing 720. In this embodiment, related terms are extracted from two text data (text data 1, text data 2) collected as time series data, and the corresponding related terms dictionary (i-1) and related terms dictionary (i) are extracted. It is assumed that the comparison process is performed in the situation stored in.

  First, in step S71, related terms stored in the related term dictionary (i-1) and the related term dictionary (i) are read. Next, in step S72, the related terms in the related term dictionary (i-1) and the related term dictionary (i) are compared with each other. ) Are stored in the comparison result data 54 as newly appearing related terms (new arrival related terms). Each related term dictionary is associated with, for example, a topic name, and the dictionary comparison process 720 can perform comparison using the topic name. The new arrival related terminology is a comparison result data 54 together with a topic name that can represent the corresponding related terminology dictionary and an appearance status (in this case, a “new arrival” character that represents a new appearance, a code corresponding thereto, and the like). Is remembered.

  Next, in step S73, the related terms in the related term dictionary (i-1) and the related term dictionary (i) are compared, and among them, the related term dictionary (i-1) exists, and the related term dictionary (i). Is stored in the comparison result data 54 as an extinct related term (an extinct related term). Each related terminology dictionary is associated with, for example, a topic name, and an extinction related terminology corresponds to the topic name, appearance status (in this case, “disappearance” indicating new appearance and this) Are stored in the comparison result data 54.

  Thereafter, in step S74, the contents of the related term dictionary (i-1) are copied to the related term dictionary (i). This is because, at the next timing, the character string extraction process 710 prepares a related term dictionary (i-1) for storing related terms, and thereafter, this new related term dictionary (i-1) and The related term dictionary (i) to which the content of the related term dictionary (i-1) is copied is compared by the dictionary comparison processing 720.

  As described above, the character string extraction processing 710 and the dictionary comparison processing 720 are repeatedly executed at a predetermined timing, and detailed description thereof will be described later. Further, by repeatedly performing the dictionary comparison process 720, the comparison result is stored in the comparison result data 54 at the processing timing. However, when the comparison result is stored, it is stored before that. Whether the comparison result is deleted or stored cumulatively is determined according to the specification of the information search system 100 according to the present invention. Further, the comparison result data 54 may be prepared separately for each dictionary comparison process 720.

  Although omitted in this example, the related term dictionary (i-1) and the related term dictionary (i) can be compared, and a common related term (common related term) can be stored in the comparison result data 54. In this case, for example, other related terms (co-occurrence related terms) stored together with the common related term in the related term dictionary (i-1) and others stored together with the common related term in the related term dictionary (i) It is possible to further compare whether or not there is a commonality with other related terms (co-occurrence related terms), and to store information on the commonality in the comparison result data 54.

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

<<< Description of Character String Extraction Processing and Dictionary Comparison Processing in Information Update Unit >>>
In FIG. 42, the related terms are extracted at different timings by the character string extraction processing 710 from the five text data (text data 1 to 5) collected in time series from the same WEB page. Are stored in the corresponding related term dictionary (i-1) or the related term dictionary (i), and then the related term dictionary (i-1) and the related term dictionary when the related term dictionary (i) is updated. A dictionary comparison process 720 is performed for (i), and these processes are periodically performed from time (T = t1) to (T = t5) (time (T = T = It was omitted after t6).

  First, at time (T = t1), a related term is extracted by the character string extraction processing 710a from the text data 1 collected from a predetermined WEB page at this time, and the extracted related term is stored in the related term dictionary (i -1). This character string extraction process 710a corresponds to the character string extraction process 710 described with reference to FIG.

  At the next time (T = t2), as in the case of T = t1, a related phrase is extracted from the text data 2 collected from the same WEB page by the character string extraction processing 710b. It is stored in the related term dictionary (i). Here, if there is a change in the topic or description content in the target WEB page, the extracted related terminology also changes accordingly. When a related term is stored in the related term dictionary (i) (updated), the dictionary comparison process 720a compares the related term dictionary (i-1) with the related term dictionary (i), and Depending on the appearance status, for example, newly-arrived related words that have newly appeared are stored in the comparison result data 54. When the comparison process is completed, the contents of the related term dictionary (i) are copied to the related term dictionary (i-1).

  This dictionary comparison process 720a corresponds to the dictionary comparison process 720 described with reference to FIG. In this figure, the dictionary comparison process 720a is described as being performed at the timing of T = t2, but is performed after the related term dictionary (i) is updated.

  At the next time (T = t3), as in the case of T = t1, t2, the related term is extracted by the character string extraction processing 710c from the text data 3 collected from the same WEB page, and the extracted relation The lyrics are stored in the related dictionary (i). Here, if there is a change in the topic or description content in the target WEB page, the extracted related terminology also changes accordingly. When a related term is stored in the related term dictionary (i) (updated), the dictionary comparison process 720b compares the related term dictionary (i-1) with the related term dictionary (i), Depending on the appearance status, for example, newly-arrived related words that have newly appeared are stored in the comparison result data 54. When the comparison process is completed, the contents of the related term dictionary (i) are copied (saved) to the related term dictionary (i-1).

  Thereafter, the character string extraction processing (710d, 710e) and the dictionary comparison processing (720c, 720d) are repeated in the same manner, so that the comparison result data 54 is obtained from the related term dictionary (i-1) and the related term dictionary (i). It is updated at each timing (T = t2 to t5) with the related term obtained as a result of the comparison. Whether only the latest related terms as comparison results are stored or cumulatively stored depends on the specifications of the applied system or the like as described above.

  In FIG. 43, related words are extracted at different timings by the character string extraction processing 710 from five text data (text data 1 to 5) collected in time series from the same WEB page. Are stored in the corresponding related term dictionary (i-1), the related term dictionary (i), or the related term dictionary (i + 1), and then the related term dictionary (i + 1) is updated. i-1), a dictionary comparison process 720 is performed on the related term dictionary (i) and the related term dictionary (i + 1), and these processes are performed periodically from time (T = t1) to (T = t5). (The time after time (T = t6) is omitted). The difference from FIG. 41 is that three related terminology dictionaries are used cyclically.

  First, at time (T = t1), a related term is extracted by the character string extraction processing 710f from the text data 1 collected from a predetermined WEB page at this time, and the extracted related term is stored in the related term dictionary (i -1).

  At the next time (T = t2), as in the case of T = t1, a related phrase is extracted from the text data 2 collected from the same WEB page by the character string extraction processing 710g. It is stored in the related term dictionary (i). Here, if there is a change in the topic or description content in the target WEB page, the extracted related terminology also changes accordingly. Thereafter, at time (T = t3), as in the case of T = t1 and t2, the related terms are extracted from the text data 3 collected from the same WEB page by the character string extraction processing 710h. Is stored in the related term dictionary (i + 1). Here, if there is a change in the topic or description content in the target WEB page, the extracted related terminology also changes accordingly.

  When a related term is stored (updated) in the related term dictionary (i + 1) at time (T = t3), three related term dictionaries (related term dictionary (i-1), A comparison is made between the lyrics dictionary (i) and the related words dictionary (i + 1), and the related words are stored in the comparison result data 54 according to the appearance status of the related words. In this embodiment, comparisons are made with respect to three related dictionaries, so as related words to be stored based on changes related to the two related word dictionaries, for example, newly appearing related words and disappearing related words, Some related terms are determined to be stored based on changes across the three related term dictionary. For example, it is a resurrection related verb that once disappeared in the related term dictionary (i) and reappears in the related term dictionary (i + 1). In addition, it is a condition that the frequency of appearance of the related term is memorized in the related term dictionary, but the related term that has rapidly increased in the short term (in the three related term dictionary), Maintains a certain range of appearance frequency as the frequency of appearance of related verbs (in the dictionary dictionary), related verbs in the frequency of appearance again (in the three related terminology dictionaries), and changes in the frequency of appearance of other related terms It is also possible to grasp related terms.

  In the dictionary comparison process 720f, when the comparison process ends, the contents of the related term dictionary (i) are copied to the related term dictionary (i-1), and the contents of the related term dictionary (i + 1) i) is copied. In this figure, the dictionary comparison process 720f is described as being performed at the timing of T = t3, but the related term dictionary (i-1) and the related term dictionary (i) are updated. It will be done later.

  At the next time (T = t4), as in the case of T = t1 to t3, a related term is extracted from the text data 4 collected from the same WEB page by the character string extraction processing 710i, and the extracted relation The lyrics are stored in the related dictionary (i + 1). Here, if there is a change in the topic or description content in the target WEB page, the extracted related terminology also changes accordingly. When a related term is stored in the related term dictionary (i + 1) (updated), three related terms dictionaries (related term dictionary (i-1), related term dictionary (i), related term) are compared by dictionary comparison processing 720g. Dictionary (i + 1)) is compared, and related terms are stored in the comparison result data 54 according to the appearance status of the related terms. When the comparison process is completed, the contents of the related term dictionary (i) are copied to the related term dictionary (i-1), and the contents of the related term dictionary (i + 1) are copied to the related term dictionary (i). Is done.

  Thereafter, the character string extraction processing 710j and the dictionary comparison processing 720h are similarly repeated, and the comparison result data 54 compares the related term dictionary (i-1), the related term dictionary (i), and the related term dictionary (i + 1). It is updated at each timing (T = t3 to t5) with the related term obtained as a result. Whether only the latest related terms as comparison results are stored or cumulatively stored depends on the specifications of the applied system or the like as described above.

  In the embodiment of FIG. 42, the comparison result data 54 is stored / updated using two related terminology dictionaries and in the example of FIG. 43 (cyclically), the comparison result data 54 is stored / updated. You may perform a dictionary comparison process using a related term dictionary. As a result, the appearance status of the related term at more timings can be grasped, and when the appearance status satisfies a predetermined condition, the related term can be stored in the comparison result data 54.

  FIG. 44 shows the relations extracted from the three text data (text data A to C) collected at the same timing from different WEB pages (WEB pages related to different subjects) by the character string extraction processing 710 and extracted. The lyrics are stored in the corresponding related term dictionary A, related term dictionary B, or related term dictionary C, respectively, and then a dictionary comparison process 720 is performed on these three related term dictionaries. An example in which the period is periodically performed from time (T = t1) to (T = t3) is shown (the time (T = t4) and thereafter are omitted).

  First, at time (T = t1), character string extraction processing 710k, character string extraction processing 710m, characters from three text data (text data A to C) respectively collected from predetermined different WEB pages at this time A related term is extracted by the column extraction processing 710n, and the extracted related term is stored in the related term dictionary A, the related term dictionary B, and the related term dictionary C, respectively.

  After that, the dictionary comparison processing 720k compares the three related terminology dictionaries (related term dictionary A, related term dictionary B, and related term dictionary C). 54. In this embodiment, for example, related terms existing in common in the three related term dictionaries are stored in the comparison result data 54. In this case, the text data A to C are text data collected from WEB pages related to different subjects, and it is better to focus on related terms (common related terms) common to the three related terms dictionaries rather than different related terms. It becomes possible to discover a common topic, and it is often meaningful in that respect.

  In addition, other related terms (co-occurrence related terms) stored together with the common related term in the related term dictionary A, other related terms (co-occurrence related terms) stored together with the common related term in the related term dictionary B, And other related terms (co-occurrence related terms) stored together with the common related term in the related term dictionary C, and further comparing the information on the commonality with the comparison result data. 54 can be stored.

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

  Such comparison of the three related term dictionaries at time (T = t1) can be repeatedly performed at time (T = t2). By performing such processing, the comparison result data 54 can be updated in time series.

  At time (T = t2), similarly to time (T = t1), character string extraction processing is performed from three text data (text data A ′ to C ′) respectively collected from predetermined different WEB pages at this time. 710k ′, character string extraction processing 710m ′, and character string extraction processing 710n ′ extract related terms, and the extracted related terms are stored in the related term dictionary A ′, the related term dictionary B ′, and the related term dictionary C ′, respectively. Is done. In this embodiment, the text data A 'is assumed to be the same WEB page as the text data A or the same subject WEB page. Similarly, the text data B 'is the same WEB page as the text data B or the same WEB page, and the text data C' is the same WEB page as the text data C or the same WEB page.

  After that, the dictionary comparison process 720k ′ compares the three related terminology dictionaries (the related term dictionary A ′, the related term dictionary B ′, the related term dictionary C ′), and the related terms etc. according to the appearance status of the related term. Is stored in the comparison result data 54. In this embodiment, for example, related terms existing in common in the three related term dictionaries are stored in the comparison result data 54.

  Furthermore, at time (T = t3), as with time (T = t1, t2), three text data (text data A ″ to C ″) respectively collected from predetermined different WEB pages at this time. Are extracted by the character string extraction processing 710k ″, the character string extraction processing 710m ″, and the character string extraction processing 710n ″, and the extracted related verbs are the related term dictionary A ″ and the related term dictionary, respectively. B ″ is stored in the related term dictionary C ″. In this embodiment, the text data A ″ is assumed to be the same WEB page as the text data A, the text data A ′, or the same subject WEB page. Similarly, the text data B ″ is the same WEB page as the text data B and text data B ′ or the WEB page of the same subject, and the text data C ″ is the same WEB as the text data C and text data C ′. Page, or WEB page of the same subject.

  Thereafter, three related terminology dictionaries (related term dictionary A ″, related term dictionary B ″, and related term dictionary C ″) are compared by dictionary comparison processing 720k ″, and according to the appearance status of the related terminology. , Related terms and the like are stored in the comparison result data 54. In this embodiment, for example, related terms existing in common in the three related term dictionaries are stored in the comparison result data 54.

  In the example of FIG. 44, related terms are extracted based on three text data collected from different WEB pages (WEB pages related to different subjects) at the same timing. Extraction of the lyrics may be performed, or the related lyrics may be extracted from four or more text data.

<< Detailed Description of Character String Extraction Processing and Dictionary Comparison Processing in Information Update Unit >>
Next, an example of the character string extraction processing 710 and the dictionary comparison processing 720 shown in FIG. 43 will be described in more detail with reference to FIG. In FIG. 45, character string extraction processing (710f, 710g, 710h) is performed on three text data (text data 1 to 3), respectively, and the corresponding related term dictionary (i-1) and related term dictionary (i ), A dictionary comparison process 720f is performed on the related term dictionary (i + 1).

  In this example, the three text data were collected from the same WEB page related to the common subject “stock trading”. For example, a search keyword “stock transaction” is input by WEB search, and three WEB pages obtained as a result are handled as one text data. In FIG. 45, text data 1 includes text data 1-1 obtained from the first WEB page, text data 1-2 obtained from the second WEB page, and third data at time (T = t1). The text data 1-3 obtained from the WEB page is included. Similarly, the text data 2 includes text data 2-1 obtained from the first WEB page, text data 2-2 obtained from the second WEB page, and third WEB at time (T = t2). The text data 3 is obtained from the second WEB page, the text data 3-1 obtained from the first WEB page at time (T = t3), including the text data 2-3 obtained from the page. Text data 3-2 and text data 3-3 obtained from the third WEB page are included. Here, the URLs of the first WEB page are all the same, the URLs of the second WEB page are all the same, and the URLs of the third WEB page are all the same.

  Here, the text data (text data 1-1, text data 1-2, text data 1-3) corresponding to three WEB pages included in one text data is respectively converted into a question sentence as shown in FIG. It can be considered in association. For example, the text data 1-1 is a Q1 question, the text data 1-2 is a Q8 question, and the text data 1-3 is a Q13 question.

  The character string extraction process 710f extracts a related term from the text data 1 by a predetermined method at time (T = t1), and stores it in the related term dictionary (i-1). In this embodiment, four related terms are extracted, and each is arranged in order of rank and stored as one record in the related term dictionary (i-1). The ranking of related terms can be determined based on, for example, the appearance frequency. The extracted four related terms (related terms 1 to 4) are “○ company”, “△ bank”, “application” and “account” in order of rank. In morphological analysis, etc., the character string is ascertained by dividing it into the smallest meaningful unit (morpheme), but in other methods, units larger than the morpheme (for example, sentences or parts of sentences) are extracted as related terms. sell. A character string composed of a noun and a particle, such as the above-mentioned “Application”, is also extracted as a related particle.

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

  The character string extraction processing 710g extracts a related term from the text data 2 by a predetermined method at time (T = t2), and stores it in the related term dictionary (i). In this embodiment, four related terms are extracted, and each is arranged in order of rank and stored as one record in the related term dictionary (i). The ranking of related terms can be determined based on, for example, the appearance frequency. The extracted four related terms (related terms 1 to 4) are “tax rate”, “○ company”, “△ bank”, and “application” in order of rank.

  Similarly, the character string extraction process 710h extracts a related term from the text data 3 by a predetermined method at time (T = t3), and stores it in the related term dictionary (i + 1). In this embodiment, four related terms are extracted, and each is arranged in order of rank, and is stored as one record in the related term dictionary (i + 1). The ranking of related terms can be determined based on, for example, the appearance frequency. The four extracted related terms (related terms 1 to 4) are “○ company”, “account”, “△ bank”, and “application” in the rank order.

  Next, dictionary comparison processing 720f is performed on the related term dictionary (i-1), the related term dictionary (i), and the related term dictionary (i + 1). In this embodiment, the dictionary comparison process 720f detects newly appearing related terms (new arrival related terms), disappeared related terms (disappearing related terms), and again appearing related terms (resurrection related terms). It is assumed that the comparison result data 54 is stored.

  For example, when the related term dictionary (i-1) and the related term dictionary (i) are compared, the related term “tax rate” has newly appeared in the related term dictionary (i). It has disappeared. Therefore, as shown in the record 54a in FIG. 46, the relative result “tax rate” and “account” are stored in the comparison result data 54. In addition, the comparison result data 54 has the same data indicating the appearance status together with these related terms (in this embodiment, “new arrival” for newly appearing related terms, “annihilation” for disappearing related terms). Stored in the record. Furthermore, in this embodiment, “topic name” data for identifying a related term dictionary is stored in order to indicate the timing at which the appearance situation is reached. Each related term dictionary is associated with a topic name and date, and the related term dictionary (i) is associated with a topic name such as “topic of“ stock trading ”on October 10, 2013, t2”. It has been.

  Next, when the related term dictionary (i) and the related term dictionary (i + 1) are compared, the related term “tax rate” disappears in the related term dictionary (i + 1), and the related term “account” is restored. (It exists in the related term dictionary (i-1) and disappears in the related term dictionary (i)). Therefore, as shown in the record 54b in FIG. 46, the comparison result data 54 stores the related terms “account” and “tax rate”. In addition, the comparison result data 54 includes data indicating the appearance status together with these related terms (in this embodiment, “resurrection” in the case of related terms that have reappeared (resurrected), and “disappear” in the case of related terms that have disappeared). ) Is stored in the same record. Furthermore, in this embodiment, “topic name” data for identifying a related term dictionary is stored in order to indicate the timing at which the appearance situation is reached. Each related term dictionary is associated with a topic name and date, and the related term dictionary (i + 1) is associated with a topic name such as “topic of“ stock trading ”on October 10, 2013 at t3”. It has been.

  Next, an example of the character string extraction process 710 and the dictionary comparison process 720 shown in FIG. 44 will be described in more detail with reference to FIG. In FIG. 47, at time (T = t1), the character string extraction processing (710k, 710m, 710n) is performed on each of the three text data (text data A to C), and the corresponding related dictionary dictionary A, related This shows that dictionary comparison processing 720k is performed on the lyrics dictionary B and the related dictionary dictionary C.

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

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

  In FIG. 47, text data 1 includes text data A-1 obtained from the first WEB page, text data A-2 obtained from the second WEB page, related to the subject “Technology of company A”. The text data A-3 obtained from the third WEB page is included. Similarly, the text data 2 includes text data B-1 obtained from the first WEB page, text data B-2 obtained from the second WEB page, Text data B-3 obtained from three WEB pages, the text data 3 including text data C-1 obtained from the first WEB page related to the subject “AI (Artificial Intelligence) related technology”, It includes text data C-2 obtained from the second WEB page and text data C-3 obtained from the third WEB page.

  The character string extraction process 710k extracts a related term from the text data A by a predetermined method and stores it in the related term dictionary A. In this embodiment, four related terms are extracted, and each is arranged in order of rank and stored as one record in the related term dictionary A. The ranking of related terms can be determined based on, for example, the appearance frequency. The extracted four related terms (related terms 1 to 4) are “Company A”, “Voice”, “Voice Recognition”, and “Sales” in order of rank.

  The character string extraction process 710m extracts a related term from the text data B by a predetermined method and stores it in the related term dictionary B. In this embodiment, four related terms are extracted, and each is arranged in order of rank and stored in the related term dictionary B as one record. The ranking of related terms can be determined based on, for example, the appearance frequency. The extracted four related terms (related terms 1 to 4) are “voice”, “research and development”, “business achievements of company B”, and “voice recognition” in order of rank.

  Similarly, the character string extraction process 710n extracts a related term from the text data C by a predetermined method and stores it in the related term dictionary C. In this embodiment, four related terms are extracted, and each is arranged in order of rank and stored as one record in the related term dictionary C. The ranking of related terms can be determined based on, for example, the appearance frequency. The extracted four related terms (related terms 1 to 4) are “AI”, “robot”, “voice recognition”, and “agent” in order of rank.

  Next, a dictionary comparison process 720k is performed on the related term dictionary A, the related term dictionary B, and the related term dictionary C. In this embodiment, the dictionary comparison process 720k detects related terms common to the three dictionaries (common related terms) and stores them in the comparison result data 54.

  When the related term dictionary A, the related term dictionary B, and the related term dictionary C are compared, it is recognized that the above-mentioned related terms are stored, and “speech recognition” exists as a common related term. Therefore, this “voice recognition” is stored in the comparison result data 54.

  By grasping such common related terms, it is possible to effectively realize analysis of related information between companies. For example, a related terminology frequently used in the description about the technology of the company A is extracted by the character string extraction processing 710k based on the text data A, and a related terminology frequently used in the description about the technology of the company B is extracted into the text data B A and B companies are extracted by a string extraction process 710n based on text data C and extracted by a string extraction process 710n based on text data C. However, it is possible to objectively understand what AI-related technologies may have commonality.

  In the embodiment shown in FIG. 47, the related dictionary is based on text data collected from WEB pages related to different subjects at the same time (T = t1). Although it was collected by intentional WEB search, as a result of comparing the related terminology dictionaries obtained from WEB pages collected by chance, there may be cases where common related terms are found by chance. .

  Next, another embodiment of the character string extraction process 710 and the dictionary comparison process 720 in the information update unit 46 will be described with reference to FIG. FIG. 48 shows a modification of the character string extraction process 710 and the dictionary comparison process 720 shown in FIG. In FIG. 48, character string extraction processing 710 is performed on each of two text data (text data 1 and text data 2), and the corresponding related term dictionary (i-1) and related term dictionary (i) are processed. Thus, the dictionary comparison process 720 is performed. The display related to the text data 3 shown in FIG. 45 is omitted.

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

  In FIG. 48, text data 1 includes text data 1-1 obtained from the first WEB page, text data 1-2 obtained from the second WEB page, and third data at time (T = t1). The text data 1-3 obtained from the WEB page is included. Similarly, the text data 2 includes text data 2-1 obtained from the first WEB page, text data 2-2 obtained from the second WEB page, and third WEB at time (T = t2). It includes text data 2-3 obtained from the page. Here, the URLs of the first WEB page are all the same, the URLs of the second WEB page are all the same, and the URLs of the third WEB page are all the same.

  The character string extraction processing 710 extracts related terms from the text data 1 by a predetermined method at time (T = t1). As described above, this is performed for each text data included in the text data 1. For example, a related term is extracted from the text data 1-1 by a predetermined method, and related text is extracted from the text data 1-2 by a predetermined method. The lyrics are extracted, and the related words are extracted from the text data 1-3 by a predetermined method. In this embodiment, four related terms are extracted for each, and each related term is arranged in rank order. The ranking of related terms can be determined based on, for example, the appearance frequency. Regarding the text data 1-1, the extracted four related terms (related terms 1 to 4) are “○ company”, “account”, “application procedure”, and “Δ bank” in rank order. Regarding the text data 1-2, the extracted four related terms (related terms 1 to 4) are “account”, “Δ bank”, “application”, and “◇ sha” in order of rank. Regarding the text data 1-3, the extracted four related terms (related terms 1 to 4) are “buy stock”, “Δ bank”, “limit”, and “○ company” in order of rank.

  Next, the character string extraction processing 710 obtains neighborhood related words for each of the extracted related words and stores them in the related word dictionary (i-1). A neighborhood related terminator is a related term that appears (co-occurs) with a related term when a particular related term is focused. In each text data (1-1, 1-2, 1-3), the set of related terms included in the topic corresponding to the text data is a set of related terms. A set of related terms including related terms is referred to as a neighborhood of related terms, and a set of neighborhoods of related terms is referred to as a neighborhood system of related terms. In the related term dictionary (i-1), a neighborhood system of related terms is stored for each related term.

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

  The relative system of the related terms thus obtained is the related terms “○ Company”, “Account”, “△ Bank”, “Application procedure”, “Stock purchase”, “Application is”, “Limit price”, “ ◇ Company ”is stored in the related term dictionary (i-1). For each related terminology, the related system of the related terms (neighboring related terms 1 to 7) is stored, and the order of these is determined by the ranking performed by the character string extraction processing 710, the high co-occurrence, etc. Determined in consideration of

  Furthermore, the character string extraction processing 710 similarly extracts related terms from the text data 2 by a predetermined method at time (T = t2). As described above, this is performed for each text data included in the text data 2, and for example, related words are extracted from the text data 2-1 by a predetermined method, and related by a predetermined method from the text data 2-2. The lyrics are extracted, and the related words are extracted from the text data 2-3 by a predetermined method. In this embodiment, four related terms are extracted for each, and each related term is arranged in rank order. The ranking of related terms can be determined based on, for example, the appearance frequency. Regarding the text data 2-1, the extracted four related terms (related terms 1 to 4) are "○ company", "account", "new system", and "application procedure" in order of rank. Regarding the text data 2-2, the extracted four related terms (related terms 1 to 4) are “account”, “Δ bank”, “◇ company”, “buy stock” in order of rank. Regarding the text data 2-3, the extracted four related terms (related terms 1 to 4) are “stock purchase”, “Δ bank”, “○ company”, and “new system” in order of rank.

  Next, the character string extraction processing 710 obtains neighborhood related words for each of the extracted related words, and stores them in the related word dictionary (i). For example, paying attention to the related term “○ Company”, this related term is extracted for the text data 2-1, and the neighborhood of the related term is {○ Company, account, new system, application procedure}. Similarly, this related term is extracted for the text data 2-3, and the neighborhood of the related term is {stock purchase, Δbank, ○ company, new system}. From these, for the related term "○ Company", the neighborhood system of the related term is {○ Company, account, stock purchase, new system, application procedure, △ bank} (the related terms for Text Data 2-1 Only one related term “new system” that overlaps the neighborhood and the neighborhood of the related term for the text data 2-3 is included).

  The related system of the related terms obtained in this way is the related terms “○ Company”, “Account”, “△ Bank”, “Application Procedure”, “Stock Purchase”, “New System”, “◇ Company”. Are stored in the related term dictionary (i). For each related terminology, a neighborhood system of the related terms (neighboring related terms 1 to 6) is stored, and the order of these is determined by the ranking performed by the character string extraction processing 710, the high co-occurrence, etc. Determined in consideration of

  Next, by the dictionary comparison process 720, the related term dictionary (i-1) and the related term dictionary (i) are compared. As a result, the related terms “limit” and “application” are disappearing related terms that disappeared at time (T = t2) (see reference numeral 753 in FIG. 48), and the related term “new system” is time (T = new related words appearing newly at t2) (see reference numeral 752 in FIG. 48), and these related words are compared result data 54 as changes in the related word dictionary (i-1) and the related word dictionary (i). Is remembered.

  Further, the dictionary comparison processing 720 performs the time (T = t1) and time for the related terms “○ Company”, “Account”, “△ Bank”, “Application procedure”, “Stock purchase”, and “◇ Company”. Although it is a related term which exists in both (T = t2), it compares also about the neighborhood related terminator of each related term. Then, it can be seen that the neighborhood related terms (or the order of neighborhood related terms) are changed (see reference numeral 751 in FIG. 48). This indicates that the relationship and position of the related terminology in the topic are changing. When the information search system 100 according to the present invention attempts to visualize such changes in the neighborhood related terms, these information are also stored in the comparison result data 54.

  Next, with reference to FIG. 49, another embodiment of the character string extraction process 710 and the dictionary comparison process 720 in the information update unit 46 will be described. FIG. 49 shows a modification of the character string extraction process 710 and the dictionary comparison process 720 shown in FIG. In FIG. 49, character string extraction processing 710 is performed for each of the three text data (text data A to C), and the corresponding related term dictionary A, related term dictionary B, and related term dictionary C are compared with the dictionary. It shows where the comparison process 720 is performed.

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

  For example, for text data A, a search keyword “Technology of Company A” is input by WEB search, and two text data (text data A-1 and text data A-2 are obtained from two WEB pages obtained as a result. ) And are individually handled in the character string extraction processing 710. Similarly, for text data B, a search keyword “Technology of company B” is input by WEB search, and two text data (text data B-1, text data B-) are obtained from the two WEB pages obtained as a result. 2) are acquired, and these are handled individually in the character string extraction processing 710. Similarly, with respect to the text data C, a search keyword “AI (artificial intelligence) related technology” is input by WEB search, and two text data (text data C-1, text) are obtained from two WEB pages obtained as a result. Data C-2) is acquired, and these are handled individually in the character string extraction processing 710. In FIG. 48, text data A, text data B, and text data C each include three text data. In this embodiment, it is assumed that each text data A, text data B, and text data C includes two text data.

  The character string extraction processing 710 extracts a related term from the text data A by a predetermined method at time (T = t1). As described above, this is performed for each text data included in the text data A. For example, related words are extracted from the text data A-1 by a predetermined method, and related text is extracted from the text data A-2 by a predetermined method. The lyrics are extracted. In this embodiment, four related terms are extracted for each, and each related term is arranged in rank order. The ranking of related terms can be determined based on, for example, the appearance frequency. Regarding the text data A-1, the extracted four related terms (related terms 1 to 4) are “Company A”, “speech”, “speech recognition”, and “robot” in order of rank. Regarding the text data A-2, the extracted four related terms (related terms 1 to 4) are “compression technology”, “speech recognition”, “sales”, and “speech” in order of rank.

  Next, the character string extraction processing 710 obtains neighborhood related words for each of the extracted related words and stores them in the related word dictionary A. A neighborhood related terminator is a related term that appears (co-occurs) with a related term when a particular related term is focused. In each text data (A-1, A-2), a set of related terms included in a topic corresponding to the text data is a related term set. A set of related terms is called a neighborhood of related terms, and a set of neighborhoods of related terms is called a neighborhood system of related terms. In the related term dictionary A, a neighborhood system of related terms is stored for each related term.

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

  The neighborhood system of the related terms thus obtained is stored in the related term dictionary A for the related terms “Company A”, “speech recognition”, “speech”, “compression technology”, “sales”, and “robot”. The For each related terminology, the neighborhood system of the related terms (neighboring related terms 1 to 5) is stored. The order of these is determined by the ranking performed by the character string extraction process 710, the high co-occurrence, etc. Determined in consideration of

  Further, the character string extraction processing 710 extracts a related term from the text data B by a predetermined method at time (T = t1). As described above, this is performed for each text data included in the text data B. For example, related words are extracted from the text data B-1 by a predetermined method, and related words are extracted from the text data B-2 by a predetermined method. The lyrics are extracted. In this embodiment, four related terms are extracted for each, and each related term is arranged in rank order. The ranking of related terms can be determined based on, for example, the appearance frequency. Regarding the text data B-1, the extracted four related terms (related terms 1 to 4) are “voice”, “business achievements of B company”, “voice recognition”, and “research and development” in order of rank. Regarding the text data B-2, the extracted four related terms (related terms 1 to 4) are “research and development”, “speech”, “speech recognition”, and “authentication technology” in order of rank.

  Next, the character string extraction processing 710 obtains neighborhood related terms for each of the related terms extracted in this way, and stores them in the related term dictionary B. For example, focusing on the related term “speech”, this related term is extracted for the text data B-1, and the neighborhood of the related term is {speech, achievement of company B, speech recognition, research and development}. Similarly, this related term is extracted for the text data B-2, and the neighborhood of the related term is {R & D, speech, speech recognition, authentication technology}. From these, for the related term “speech”, the neighborhood system of the related term is {speech, research and development, achievement of company B, speech recognition, authentication technology} (the neighborhood of the related term for the text data B-1, Only one of the related terms “speech recognition” and “research and development” that overlap in the vicinity of the related term for the text data B-2 is included).

  The related system of the related terms thus obtained is stored in the related term dictionary B for the related terms “speech”, “research and development”, “business achievements of company B”, “speech recognition”, and “authentication technology”. . For each related terminology, the related system of the related terms (neighboring related terms 1 to 4) is stored. The order of these is determined by the ranking performed by the character string extraction processing 710, the high co-occurrence, etc. Determined in consideration of

  Further, the character string extraction processing 710 extracts a related term from the text data C by a predetermined method at time (T = t1). As described above, this is performed for each text data included in the text data C. For example, a related term is extracted from the text data C-1 by a predetermined method, and related text is extracted from the text data C-2 by a predetermined method. The lyrics are extracted. In this embodiment, four related terms are extracted for each, and each related term is arranged in rank order. The ranking of related terms can be determined based on, for example, the appearance frequency. Regarding the text data C-1, the extracted four related terms (related terms 1 to 4) are “AI”, “agent”, “robot”, and “voice recognition” in rank order. Regarding the text data C-2, the extracted four related terms (related terms 1 to 4) are “robot”, “voice recognition”, “AI”, and “learning function” in order of rank.

  Next, the character string extraction processing 710 obtains neighborhood related words for each of the extracted related words and stores them in the related word dictionary C. For example, focusing on the related term “AI”, this related term is extracted for the text data C-1, and the neighborhood of the related term is {AI, agent, robot, speech recognition}. Similarly, this related term is extracted for the text data C-2, and the neighborhood of the related term is {robot, voice recognition, AI, learning function}. From these, for the related term “AI”, the neighborhood system of the related term is {AI, robot, agent, speech recognition, learning function} (the neighborhood of the related term for the text data C-1 and the text data C− Only one of the related terms “robot” and “speech recognition” that overlap in the vicinity of the related term for 2 is included).

  The neighborhood system of the related terms thus obtained is stored in the related term dictionary C for each of the related terms “AI”, “robot”, “speech recognition”, “agent”, and “learning function”. For each related terminology, the related system of the related terms (neighboring related terms 1 to 4) is stored. The order of these is determined by the ranking performed by the character string extraction processing 710, the high co-occurrence, etc. Determined in consideration of

  Next, the dictionary comparison process 720 compares the related term dictionaries A to C. As a result, the related term “speech recognition” is a related term (common related term) common to the three related term dictionaries at time (T = t1) (see reference numerals 755, 755 ′, and 755 ″ in FIG. 49). This is stored in the comparison result data 54. By grasping such common related terms, common topics can be found from different themes, and setting the subject as in this embodiment also leads to analysis of related information between companies.

  In addition, the dictionary comparison process 720 also compares the related related terms with respect to the related related terms. Then, it is possible to grasp the commonality of neighboring related terms, the commonality of the order of neighboring related terms, and the like, thereby determining the level of commonality between the common related terms.

  Note that “speech” can be grasped as a common related terminology in the related terminology dictionary A and the related terminology dictionary B (see reference numerals 756 and 756 ′ in FIG. 49). Since it may be important information, it can be stored in the comparison result data 54.

<<< Switching between context learning function and service ID >>>
In the information search system 100 according to an embodiment of the present invention, as described above, the input index, the progress index, etc. are learned in the dialogue between the conversation control terminal device 2 ″ and the user who uses this device. Thus, it is possible to realize a dialogue according to the input index and the progress index. Such a function is a context learning function. The input index is information indicating what input the user has made so far, that is, a history of user input. The progress index is information indicating what topic has been provided to the user so far, that is, a history of the topic provided to the user.

  Furthermore, in the information retrieval system 100, the information update unit 46 of the topic providing server 4 ′ can capture the history of the appearance of related terms by the information update unit 46, thereby clarifying the topic name to which the related term belongs, and the usual related information. Related words learning that can distinguish between words and new arrival related words (newly appearing), and can make judgments on similarities and differences between topics through comparison processing of related words Functions can be realized. With this related term learning function, the user of the conversation control terminal device 2 ″ can handle input types related to many topic names, and the user's input identification means can be diversified.

  The scenario data is controlled so as to switch the service ID based on the input type determined from the input situation in the user's conversation control terminal device 2 ″. For example, the related word dictionary 50 provided by the sentence analysis unit 43, the preference analysis unit 44, and the topic analysis unit 45 of the topic providing server 4 ′ in the information search system 100, the related term / co-occurrence word list display screen 650, and the like are provided. The service ID corresponding to the function to be performed and the service ID corresponding to the function providing the display of the related term dictionary 50 and the comparison result data 54 provided by the information updating unit 46 of the topic providing server 4 ′ are automatically determined by the scenario data. Switch automatically.

The statement of the corresponding scenario data is set so as to transition to the service with the corresponding service ID as an action when a predetermined input type is input, for example. When this is represented by scenario data as shown in FIG. 14, the following statement is obtained.
<sto: $ IDN $: <sta: $ num $>: $ input $>
Here, “sto” is a description to shift the state (shift to), “$ IDN $” is the identification number of the destination service, and “<sta: $ num $>” is the destination "<$ Input $>" is a user input sentence.

<<< Description of Hardware Configuration of Topic Providing Server According to One Embodiment of the Present Invention >>>
Next, with reference to FIG. 50, an example of a hardware configuration of a computer constituting the topic providing server 4 ′ according to the embodiment of the present invention will be described. However, the configuration of the topic providing server 4 ′ illustrated in FIG. 50 is merely an example of the typical configuration.

  The topic providing server 4 ′ includes a CPU (Central Processing Unit) 801, a RAM (Random Access Memory) 802, a ROM (Read Only Memory) 803, a network interface 804, an audio control unit 805, a microphone 806, a speaker 807, a display controller 808, A display 809, an input device interface 810, a keyboard 811, a mouse 812, an external storage device 813, an external recording medium interface 814, and a bus 815 for connecting these components to each other are included.

  The CPU 801 controls the operation of each component of the topic providing server 4 ′, and under the control of the OS, processes in the sentence analysis unit 43, the preference analysis unit 44, the topic analysis unit 45, the information update unit 46 according to the present invention, and the like. Control the execution of

  The RAM 802 temporarily stores programs for executing each process executed by the CPU 801 and data used during the execution of these programs. Further, as described above, the related term dictionary 50, the comparison result data 54, and the like can also be stored. The ROM 803 stores a program executed when the topic providing server 4 'is started.

  The network interface 804 is an interface for connecting to the network 900. The network 900 is, for example, a network between the conversation control terminal device 2 ″ shown in FIG. 20 and a computer on which the crawler 730 operates, or a network such as the Internet.

  The audio control unit 805 controls the microphone 806 and the speaker 807 to control audio input / output. The display controller 808 is a dedicated controller for actually processing a drawing command issued by the CPU 801. The display 809 is a display device configured by, for example, an LCD (Liquid Crystal Display) or a CRT (Cathode Ray Tube).

  The input device interface 810 receives a signal input from the keyboard 811 or the mouse 812, and transmits a predetermined command to the CPU 801 according to the signal pattern.

  The external storage device 813 is, for example, a storage device such as a hard disk or a semiconductor memory. The above-described program and data are recorded in this device, and are loaded from there to the RAM 802 as necessary at the time of execution. For example, as described above, the related term dictionary 50, the comparison result data 54, and the like can also be stored.

  The external recording medium interface 814 accesses the external recording medium 910 and reads data recorded therein. The external recording medium 910 is, for example, a portable flash memory, a CD (Compact Disc), a DVD (Digital Versatile Disc), or the like. A program executed by the CPU 801 and realizing each function of the present invention can be provided from the external recording medium 910 via the external recording medium interface 814. Further, as another distribution form of the program for realizing each function of the present invention, a route in which the program is stored in the external storage device 813 or the RAM 802 via a network 900 and a network interface 804 from a predetermined server on the network. Etc. are also conceivable.

  An example of the hardware configuration of the topic providing server 4 ′ according to the embodiment of the present invention has been described. However, the conversation control terminal device 2 ″ and the crawler 730 included in the information search system 100 of the present invention The hardware configuration is basically the same as that shown in FIG. However, regarding the computer on which the topic providing server 4 ′ and the crawler 730 operate, the audio control unit 805, the microphone 806, the speaker 807, the display controller 808, the display 809, the input device interface 810, the keyboard 811, and the mouse 812 It is not an essential component.

  Further, the information search system 100 described so far responds to the control by the scenario data 28 (or the scenario data 55) between the Topiclet 20 operating on the conversation control terminal device 2 ″ and the topic providing server 4 ′. By transmitting and receiving data, information such as related terms is displayed on the display of the conversation control terminal device 2 ″. The Topiclet 20 is downloaded to the conversation control terminal device 2 ″ at a predetermined timing and activated, for example, and the Topiclet 20 communicates with the topic providing server 4 ′ via a network such as the Internet. Can be configured as a system based on

  However, the information search system 100 according to the present invention can effectively realize the technical idea of the present invention by various other configurations and methods. For example, each function of the topic providing server 4 ′ described above is configured by a WEB server, an ASP (Active Server Pages) server, etc., and a general WEB browser operating on the conversation control terminal device 2 ″ controls the scenario data. (Or under the control of scenario data), information such as related terms is displayed on the display of the conversation control terminal device 2 ″ in response to a user instruction, a topic, a related term dictionary, The comparison result data can be switched. In this case, a WEB server, an ASP server, or the like that functions as the topic providing server 4 ′ displays data (for example, HTML data) for the display in order to display the screen on the display of the conversation control terminal device 2 ″. Edit and generate.

<<< Other system configuration of topic providing system >>>
Next, an outline of another system configuration of the topic providing system will be described with reference to FIG.

  51 includes a conversation control terminal device 1002 (Topiclet 1020), a topic providing server 1004 (iWA 1030), a maintenance device 1003 (iWA Manager 1040), and a topic analysis device 1005. In the topic providing system 1 shown in FIG. 4, it is shown that the result of topic analysis processing (to the scenario data editing unit 410) is provided in the maintenance device 3 (iWA Manager 40), but is shown in FIG. In the topic providing system 1 ′, it is shown that the topic analysis processing itself is executed by a topic analysis device 1005, which is a device separate from the maintenance device 1003 (iWA Manager 1040). Can also be realized.

  The topic providing system 1 and the topic providing system 1 ′ are the same in other configurations, and detailed description thereof is omitted. The conversation control terminal device 1002 includes a reception unit 1240 and a transmission unit 1230. The reception unit 1240 corresponds to the reception unit 240 of the conversation control terminal device 2, and the transmission unit 1230 corresponds to the transmission unit 230 of the conversation control terminal device 2. The conversation control terminal device 1002 is basically the same as the conversation control terminal device 2 of FIG. 4, and the display of other components is omitted. The topic providing server 1004 includes an input information analysis unit 1310 and a scenario data storage unit 1320, and the maintenance device 1003 includes a scenario data transmission unit 1430, a scenario data editing unit 1410, and a terminal device virtual construction unit 1420. The topic analysis device 1005 includes a topic analysis unit 1510.

  In the topic providing system 1 ′ shown in FIG. 51, the topic analyzing unit 1510 of the topic analyzing apparatus 1005 is connected to the topic providing server 1004 via a network, and receives scenario data and other data obtained by topic analyzing processing. And provided to the input information analysis unit 1310 of the topic providing server 1004. Further, the topic analysis unit 1510 of the topic analysis device 1005 is connected to the maintenance device 1003 via a network (or indirectly connected via the topic providing server 1004), and is a scenario obtained by topic analysis processing. Data and other data are provided to the scenario data editing unit 1410 of the maintenance device 1003.

  The topic analysis unit 1510 of the topic analysis device 1005 generates a topic list and edits or verifies scenario data based on the topic list. The topic list is data to which the closeness and connection method of the topics are given through the related words that relate the topics. The topic analysis unit 1510 accumulates related terms associated with the topic in the topic list. The topic list provided to the maintenance device 1003 is data provided to the contractor of the topic providing system 1 ′, and these data are used, for example, when generating scenario data.

  Further, the topic analysis unit 1510 of the topic analysis device 1005 may be configured to realize the processing of the sentence analysis unit 43 of the topic providing server 4 ′ illustrated in FIG. 20, and each process of the input information analysis unit 41 may be performed. It may be configured to be realized.

  Further, a plurality of topic analysis units 1510 of the topic analysis apparatus 1005 can be arranged so as to be associated with each contractor of the topic providing system 1 ′. In that case, information acquired by each topic analysis device 1005 can be used (or used after being organized and integrated), and data can be provided to the corresponding maintenance device 1003 and the topic providing server 1004. The timing at which data is provided by the topic analysis unit 1510 of the topic analysis device 1005 and the content of the data may differ depending on the provision destination (that is, between the maintenance device 1003 and the topic provision server 1004).

  Also, the contractor (or the person in charge belonging to the contractor) can use the maintenance device 1003 to build a topic list or edit / create scenario data using data provided from the topic analysis device 1005. However, with the configuration of the topic providing system 1 ′ shown in FIG. 51, the maintenance device 1003 uses a mechanism such as PaaS (Platform as a Service) or SaaS (Software as a Service) that can be used remotely as a service on the Internet. Functions can also be realized.

  So far, the information search system 100 according to an embodiment of the present invention has been described with reference to some examples that can implement the present invention. These examples are for explaining the present invention. The scope of right of the present invention is not limited to these examples. The technical idea of the present invention can be realized by various methods and configurations other than these embodiments.

1, 1 'Topic providing system 2, 1002 Conversation control terminal device (Topiclet 20, Topiclet 1020)
2 ′, 2 ″ conversation control terminal device 3, 1003 maintenance device (iWA Manager 40, iWA Manager 1040)
4, 4 ', 1004 Topic providing server (iWA30, iWA1030)
DESCRIPTION OF SYMBOLS 10 Topic storage device 21 Input control part 22 Search control part 23 Transmission control part 24 Reception control part 25 Response information determination part 26 Output control part 41 Input information analysis part 42 External log acquisition control part 43 Sentence analysis part 44 Preference analysis part 45 Topic Analysis unit 46 Information update unit 100 Information retrieval system 1005 Topic analysis device

Claims (10)

Sentence information acquisition means for acquiring sentence information related to the keyword from text data collected by keyword-based search;
Character string selection means for selecting one or more character strings satisfying a predetermined condition from each of the sentence information, and storing the character strings in character string storage means for each corresponding sentence information;
An information search system comprising: information output means for outputting information for displaying the selected character string to a user for each corresponding sentence information. The character string selection means is:
2. The information search system according to claim 1, wherein the character string is selected without performing collation with character string data stored in advance. The character string selection means further includes:
A character string search means for searching for the same character string from the text data;
For the same character string, a different degree determination means for determining a difference degree of a preceding adjacent character and a difference degree of a subsequent adjacent character;
Specific character string determining means for determining whether or not the same character string is a specific character string based on the difference degree of the preceding adjacent character and the difference degree of the subsequent adjacent character;
The information search system according to claim 2, wherein the character string selection unit selects the character string from the determined specific character string. Scenario data storage means for storing scenario data for defining response information on the topic;
Response information determining means for determining the response information including the selected character string based on the scenario data;
The information search system according to claim 1, further comprising response information output means for outputting the response information determined by the response information determination means. A dictionary comparison means;
The character string selection means, when storing the character string in the character string storage means, respectively, according to the collection condition of the text data, stored in a corresponding dictionary,
The dictionary comparison means performs a comparison process for comparing a plurality of the dictionaries, stores a comparison result in the comparison result storage means,
The response information determining means determines the response information including the comparison result based on the scenario data;
The response information output means outputs the response information determined by the response information determination means,
The dictionary comparison unit further performs the comparison process when at least one of the plurality of the dictionaries is updated, and automatically updates the comparison result stored in the comparison result storage unit. The information retrieval system according to claim 1. The information output means includes
When one of the character strings corresponding to one of the sentence information and one of the character strings corresponding to sentence information different from one of the sentence information are common, the character corresponding to the one sentence information 6. The information search system according to claim 1, wherein information for displaying a set of columns in association with the set of character strings corresponding to the other sentence information is output. The information output means includes
Outputting information for displaying all of the set of character strings corresponding to the predetermined one or more sentence information;
The information search system according to claim 1, wherein the display order of the character strings is determined according to a usage mode of the user with respect to the character strings. A keyword input means for inputting a keyword as a text data collection condition;
When one or more character strings satisfying a predetermined condition are selected from each of the sentence information related to the keyword acquired from the text data collected based on the keyword, the selected character string is And an information output means for outputting information for display to the user for each corresponding sentence information. A sentence information acquisition step of acquiring sentence information related to the keyword from text data collected by keyword-based search;
A character string selection step of selecting one or more character strings satisfying a predetermined condition from each of the sentence information, and storing the character string in a character string storage unit for each corresponding sentence information;
An information search method comprising: an information output step of outputting information for displaying the selected character string to a user for each corresponding sentence information. On the computer,
Sentence information acquisition means for acquiring sentence information relating to the keyword from text data collected by keyword-based search;
Character string selection means for selecting one or more character strings satisfying a predetermined condition from each of the sentence information, and storing the character strings in character string storage means for each corresponding sentence information, and
A program for causing the selected character string to function as information output means for outputting information for displaying to the user for each corresponding sentence information.

Images