JP3617826B2 - Information retrieval device - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to an information retrieval method and an information retrieval apparatus using an agent that retrieves information on a large-scale storage device in the apparatus or information on a large-scale storage device in a remote place by communication means.
[0002]
[Prior art]
An information retrieval apparatus using an agent is disclosed in, for example, Japanese Patent Laid-Open No. 9-292895.
[0003]
FIG. 30 shows a block diagram of an information retrieval apparatus using a conventional agent.
[0004]
This information retrieval apparatus using a conventional agent stores voice input means 3001, means 3003 for recognizing input voice, reliability judgment means 3004 for voice recognition results, and character screen data having a plurality of different facial expressions. Data storage means 3007, screen output means 3013, and CPU 3006 for controlling these means, and character screen data corresponding to the reliability level of the speech recognition result is read from the data storage means 3007 under the control of the CPU 3006. The screen output means outputs the data.
[0005]
[Problems to be solved by the invention]
However, in the conventional information search described above, the user has to set information search conditions in detail every time the information search is performed, and there is a problem that it takes time and effort.
[0006]
The present invention has been made to solve the above-described conventional problems, and performs information retrieval autonomously based on a simple instruction from a user, and can be easily applied from a wide range of information sources without taking time and effort. An object of the present invention is to provide an information search method and an information search apparatus using an agent capable of obtaining information.
[0007]
[Means for Solving the Problems]
The information retrieval method using the agent of the present invention Love Information search condition is In advance Set Double Number of agents To You from inside The Choice By agent Search information In this case, the preset information retrieval conditions are sequentially presented by voice by voice output means according to instructions from the user. It was decided.
[0008]
This way Information can be retrieved autonomously based on simple instructions from the user, and relevant information can be easily obtained from a wide range of information sources without time and effort. .
[0009]
Also, The agent that performs information retrieval according to the information retrieval condition and the agent that presents the information retrieval result are different agents. It was decided.
[0010]
This way The user's interest in the agent can be maintained .
[0011]
Also, In an information search method for performing an information search by an agent selected by a user from among a plurality of agents for which information search conditions are individually set, Previous Emotion Report search conditions When the information is additionally registered, the information search condition to be additionally registered is incorporated into the existing information search condition, and when the same information search condition as the existing information search condition exists, the additional registration is not performed. It was decided.
[0012]
This way Users can search for the information they want .
[0013]
Also, In an information search method for performing an information search by an agent selected by a user from among a plurality of agents for which information search conditions are individually set, Previous Emotion Report search conditions If the information search condition to be additionally registered is inconsistent with the existing information search condition, the registration is rejected, or the information search condition to be additionally registered and the existing information are checked. Decide which search condition to register It was decided.
[0014]
This way The user can easily determine that the selected agent was appropriate .
[0015]
Also, Use voice interaction between the user and the agent when performing the information retrieval It was decided.
[0016]
This way Users can reduce the burden of additional registration .
[0017]
Also, The agent searches for information on a plurality of predetermined information sources using the information search condition, and notifies the information search result at regular intervals. It was decided.
[0018]
This way Saves the user from having to call the agent .
[0019]
Also, The agent searches the plurality of predetermined information sources using the information search condition, and notifies when the information search result reaches a preset number of cases. It was decided.
[0020]
This way Saves the user from having to call the agent .
[0021]
Also, The agent searches the plurality of predetermined information sources using the information search condition, and notifies when the total amount of data obtained as a result of the information search reaches a preset limit capacity It was decided.
[0022]
This way Saves the user from having to call the agent .
[0023]
Also, Means for holding a plurality of predetermined agents; storage means for preliminarily storing information retrieval conditions for each of the plurality of agents; means for interpreting an instruction from a user; Pre-stored information And a means for reading out the information retrieval condition by a recorded voice or a synthesized voice.
[0024]
With this configuration, Information can be retrieved autonomously based on simple instructions from the user, and relevant information can be easily obtained from a wide range of information sources without time and effort. .
[0025]
Also, Means for operating an agent that interacts with the user and performs a search according to an inherent information search condition, and an agent that presents information by the search as different agents It is set as the structure provided with.
[0026]
With this configuration, The user's interest in the agent can be maintained .
[0027]
Also, A means for inputting the information search condition; a means for determining whether the information search condition stored in the storage means and the input information search condition are the same; and Means for outputting by voice that the same thing is excluded, except for the same thing. It is set as the structure provided with.
[0028]
With this configuration, Users can search for the information they want .
[0029]
Also, Means for inputting information search conditions to be additionally registered by the user, meaning understanding means for understanding the meaning of the information search conditions to be additionally registered by the user, and existing information stored in the storage means in the agent Means for detecting a contradiction between the meaning of the search condition and the meaning of the information search condition to be additionally registered, and when the contradiction is detected, the additional registration from the user is rejected or the input information Means for inquiring of the user whether to select a search condition or the existing information search condition, and re-registering in the storage area of the information search condition; It is set as the structure provided with.
[0030]
With this configuration, The user can easily determine that the selected agent was appropriate .
[0031]
Also, Means for searching while switching a plurality of information sources in accordance with the information search condition inherent in the agent, means for storing information of the search result, and a predetermined time or a fixed time Means for notifying the result of the search every time It is set as the structure provided with.
[0032]
With this configuration, Saves the user from having to call the agent .
[0033]
Also, Means for searching while switching a plurality of information sources in accordance with the information search condition inherent in the agent; means for storing information of the search result; and when the number of stored cases reaches a preset number, Means for reporting results It is set as the structure provided with.
[0034]
With this configuration, Saves the user from having to call the agent .
[0035]
Also, Means for searching while switching a plurality of information sources in accordance with information search conditions inherent in the agent; means for storing information on the search result; and when the total amount of data reaches a preset upper limit, Means for reporting results It is set as the structure provided with.
[0036]
With this configuration, Saves the user from having to call the agent .
[0087]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, embodiments of the present invention will be described with reference to FIGS.
[0088]
FIG. 1 shows a flowchart of an information search method using an agent according to the first embodiment of the present invention.
[0089]
The operation of the information search method using this agent will be described with reference to FIG.
[0090]
First, in the information retrieval method using this agent, a list of images and characteristics of a plurality of agents acting on behalf of the information retrieval work for the user is presented (102). An agent who seems to have a tendency similar to the interest is selected (103). For example, in the case of “Oyaji Agent”, the image of an old man who seems to be stubborn and the characteristics such as “Slightly stubborn. Interested in political economy. Weak to grandchildren and wives” are presented. If you want to make a search request for information such as “Oyaji Agent”, you can expect to get almost the information you want.
[0091]
The user then selects that name or number. Only the selected agent remains and the other agents are deleted. As described above, each agent has a unique information search keyword (information search condition). For example, in the case of a businessman agent, words such as “salary”, “economy”, and “selling” are preset as information search keywords. When the user requests to present an information retrieval keyword unique to the agent, a list of keywords is displayed on the display. Depending on the case, it is also effective to read out the registered contents with synthesized speech or the like.
[0092]
When an agent is selected, an agent information search operation is started (111). When the user thinks that the presented information search keyword is insufficient, the user can additionally register the information search keyword.
[0093]
At that time, it is checked whether there is no overlap or contradiction with keywords registered in the past (107). If there is the same keyword in the past, the registration is canceled (108), and it is checked whether there is a semantic contradiction (109). If there is a contradiction, the one set by the user is preferentially registered (110), Conflicting past information search conditions are deleted.
[0094]
The information search condition need not be a word like a keyword, but may be a sentence. When the keyword set is finished, the information search operation is started (111), and the agent freely checks various channels of information sources (for example, Internet sites and text multiplex broadcasts) and includes the keyword. Find what you have and present it to the user.
[0095]
As described above, the information search method using the agent according to the first embodiment of the present invention has an excellent effect in that it can save the user from setting the information search condition.
[0096]
FIG. 2 shows a processing flow for inputting additional information search conditions by voice interaction in an information search method using an agent according to the second embodiment of the present invention.
[0097]
The operation of the information search method using this agent will be described with reference to FIG.
[0098]
When the user thinks that the presented information search keyword (condition) is insufficient, the user can make an additional registration request (201) for the information search keyword by voice interaction. Thereby, for example, the user can additionally register the information search condition even during driving.
[0099]
It should be noted that the keyword is checked for overlap or contradiction with those registered in the past (205). If there is the same keyword in the past, the registration is canceled (206), and it is checked whether there is a semantic contradiction (207). If there is a contradiction, the one set by the user is preferentially registered (208), Conflicting past information search conditions are deleted.
[0100]
Further, the information search condition need not be a word like a keyword, but may be a sentence. Once the additional keyword registration (209) is complete, the agent is free to check various channels of information sources (eg, Internet sites and text multiplex broadcasts) autonomously and search for those that contain the keyword. Present to the user.
[0101]
As described above, the information search method using the agent according to the second embodiment of the present invention has an excellent effect in that it can save time and effort for setting the information search condition of the user.
[0102]
FIG. 3 shows a processing flow for inputting an additional information search condition as a sentence in an information search method using an agent according to the third embodiment of the present invention.
[0103]
The operation of the information retrieval method using this agent will be described with reference to FIG.
[0104]
When the user thinks that the presented information search keyword is insufficient, the user can additionally register the information search keyword. First, the user inputs a sentence about information he / she wants to know from a remote controller or the like (303). For example, if "Yesterday, Prime Minister Mori Kaoru said," is input, the meaning of the input sentence is analyzed (304), the user really understands what he wants to do (305), and the information search keyword Is generated. At this time, it is checked whether there is no overlap or contradiction with keywords registered in the past (309). If there is the same keyword in the past, the registration is canceled (310), and it is checked whether there is a semantic contradiction (311). If there is a contradiction, the one set by the user is preferentially registered (312), Conflicting past information search conditions are deleted.
[0105]
Further, the information search condition need not be a word like a keyword, but may be a sentence. When the additional registration of the keyword is completed (313), the agent freely checks various channels of information sources (for example, Internet sites and text multiplex broadcasting, etc.) and searches for the one containing the keyword, Present to the user.
[0106]
As described above, the information search method using the agent according to the third embodiment of the present invention has an excellent effect in that it can save the user from setting the information search condition.
[0107]
FIG. 4 shows a processing flow in which the agent that reads the searched information and the agent that performs the dialogue are separated in the information search method using the agent according to the fourth embodiment of the present invention.
[0108]
The operation of the information search method using this agent will be described with reference to FIG.
[0109]
First, an agent automatically appears when a restriction condition such as a call from a user (401) or the possibility of exceeding its own memory capacity is satisfied (403). When the agent is presented from the beginning, it starts to move actively when the above conditions are met. The agent autonomously checks various channels of information sources (for example, Internet sites and text multiplex broadcasts) and searches for ones that contain keywords, but the meaning of the search results prior to presentation to the user Understand (404) and find the words that are in focus.
[0110]
The meaning of the focused word is found in the language dictionary on the agent's memory, and a sentence expressing the corresponding impression is generated. Since the sentence expressing this impression can be set in advance, it is not always necessary to be a text-to-speech synthesis, and a recorded / reproduced voice may be used. For example, when the focus of “dropping out” has been extracted, an impression according to the meaning of “Hey, ask me this. After this, the agent switches to an agent specializing in reading (406). A read-only agent reads the retrieved information using text-to-speech synthesis. This change is continued until there is no information retrieved.
[0111]
As described above, the information search method using the agent according to the fourth embodiment of the present invention is also excellent in that the user's interest can be maintained.
[0112]
FIG. 5 shows a processing flow for selecting a dialogue strategy based on user's emotion estimation for smooth dialogue with the user in the information search method using the agent according to the fifth embodiment of the present invention.
[0113]
The operation of the information search method using this agent will be described with reference to FIG.
[0114]
First, after a one-turn dialogue with the user (503), the success or failure of the dialogue is recorded (504), a pattern of the dialogue result is extracted (505), and the state of the user is estimated from the dialogue history (506). To do.
[0115]
For example, whether the user is “joyful” or “angry” can be easily estimated (506) based on the record (504) of whether the dialogue has succeeded or failed in the past several turns. This is because if there is much success, it will be “joy”, and if there is little success, it will be “anger”. If the user is “joyful”, the conversation proceeds efficiently with a simple expression, but if it is “anger”, switch to a polite expression, change the expression of the agent to something that seems to be apologetic, and the estimated user The user selects an utterance method and dialogue strategy that matches his emotion (507).
[0116]
As described above, the information search method using the agent according to the fifth embodiment of the present invention is also excellent in that the user's interest can be maintained.
[0117]
FIG. 6 shows a processing flow for selecting a dialogue strategy based on user emotion estimation for facilitating dialogue with the user in the information search method using the agent according to the sixth embodiment of the present invention.
[0118]
The operation of the information search method using this agent will be described with reference to FIG.
[0119]
First, after a one-turn dialogue with the user (603), the user's voice situation analysis (604) is performed, the user's estimated emotion is extracted (605), and the current user's emotional state is estimated from the user's voice quality. (606).
[0120]
For example, if the average pitch frequency is slightly higher and the duration of the ending is longer, the user is often happier. Conversely, if the average pitch frequency is lower, the overall power increases, and the duration of the ending is shorter There are many cases of “anger”. Such estimation is performed for each dialogue turn, and the estimation results are accumulated and used for emotion estimation. If the user is “joyful”, the conversation proceeds efficiently with a simple expression, but if it is “anger”, switch to a polite expression, change the expression of the agent to something that seems to be apologetic, and the estimated user Utterance method and dialogue strategy are selected in accordance with the emotion (607).
[0121]
As described above, the information search method using the agent according to the sixth embodiment of the present invention is also excellent in that the user's interest can be maintained.
[0122]
FIG. 7 shows a processing flow for selecting a dialogue strategy based on a user's facial expression for facilitating dialogue with the user in the information search method using the agent according to the seventh embodiment of the present invention.
[0123]
The operation of the information search method using this agent will be described with reference to FIG.
[0124]
First, after a one-turn dialogue with the user (703), the user's facial expression is analyzed (704), the user's estimated emotions are extracted (705), and the emotional state of the user is estimated from the user's facial expressions. (706).
[0125]
For example, when both eyes are narrow and both ends of the mouth are raised, it is often “joy”, and when the distance between the eyebrows is shortened and the mouth is slightly opened, it is often “angry”. . Such estimation is performed for each dialogue turn, and the estimation results are accumulated and used for emotion estimation. If the user is “joyful”, the conversation proceeds efficiently with a simple expression, but if it is “anger”, switch to a polite expression, change the expression of the agent to something that seems to be apologetic, and the estimated user The utterance method and dialogue strategy are selected in accordance with the emotion (707).
[0126]
As described above, the information search method using the agent according to the seventh embodiment of the present invention is also excellent in that the user's interest can be maintained.
[0127]
FIG. 8 shows a processing flow for selecting a dialogue strategy based on a user's voice quality, facial expression, and dialogue history to facilitate a dialogue with the user in an information search method using an agent according to the eighth embodiment of the present invention. .
[0128]
The operation of the information search method using this agent will be described with reference to FIG.
[0129]
First, after a one-turn dialogue with the user (803), the success or failure of the dialogue is recorded, and the voice and facial expression of the user are recorded (804), and the dialogue history, voice status, and facial expressions are extracted (805). Then, the user's emotional state is estimated (806) from the user's voice quality, facial expression, and dialogue result.
[0130]
For example, if the dialogue result is “success”, the voice quality is “soft”, and the facial expression is “neutral”, the user is often satisfied, and conversely, the dialogue result is failure and the voice quality is “angry”. When the expression is “angry”, it is often “angry”. Such estimation is performed for each dialogue turn, and the estimation results are accumulated and used for emotion estimation. If the user is “joyful”, the conversation proceeds efficiently with a simple expression, but if it is “anger”, switch to a polite expression, change the expression of the agent to something that seems to be apologetic, and the estimated user The user selects an utterance method and dialogue strategy that matches his emotion (807).
[0131]
As described above, the information search method using the agent according to the eighth embodiment of the present invention is also excellent in that the user's interest can be maintained.
[0132]
FIG. 9 shows an autonomous information search processing flow in the information search method using the agent according to the ninth embodiment of the present invention.
[0133]
The operation of the information search method using this agent will be described with reference to FIG.
[0134]
First, the agent obtains information including the information search keyword that the agent has, and automatically changes information channels CH one after another (903). As a result, if the search of all information channels is completed (905), the maximum number of registered information, the maximum memory size for storing information, or the search end condition for a preset time is satisfied (906), the search operation is interrupted. Then, the search information up to that point is transmitted to the user by synthesized speech (908). Of course, in response to a call from the user such as “Hey, tell me OO”, it goes without saying that the search information up to that point can be transmitted to the user with synthesized speech.
[0135]
As described above, the information search method using the agent according to the ninth embodiment of the present invention is also excellent in that the information search work of the user can be facilitated.
[0136]
FIG. 10 shows a processing flow for referring to past search results in an information search method using an agent according to the tenth embodiment of the present invention.
[0137]
The operation of the information search method using this agent will be described with reference to FIG.
[0138]
First, when an information search is performed (1002), the agent retrieves the first search result (1003), compares it with a past search result (1004), and whether there is information similar to this information (1005) Search the search result storage section.
[0139]
When similar information is found, the fact is notified to the user (1006), and the search result is read out (1007). For example, when a stock price news is searched, the search is performed after notifying the similarity of past similar information that “the stock has fallen again like three days ago”. It is more efficient not to read past information unless requested by the user. Such processing is performed in all searches.
[0140]
As described above, the information search method using the agent according to the tenth embodiment of the present invention is also excellent in that the user's interest can be maintained.
[0141]
FIG. 11 shows a processing flow for referencing past search results in an information search method using an agent according to the eleventh embodiment of the present invention.
[0142]
The operation of the information search method using this agent will be described with reference to FIG.
[0143]
First, when an information search is performed (1102), the agent checks the past search result storage unit for similar information to this information (1106). The determination of similarity is the genre of the search keyword that has been hit, the noun / object pair of the search condition, or the superordinate concept of the search keyword, or the focus of the searched information. The hit information search keyword itself can of course be used for similarity determination, but the probability of finding similar information increases by using these larger concepts. When similar information is found, the fact is notified to the user (1107), and the search result is read out (1108).
[0144]
For example, if you are using a sportsman agent and you find information that includes “tennis” in the “sports” genre, Is included, “Speaking of which, yesterday Nomo was a perfect match.” After reporting similar information in the past, the information on tennis searched is read out.
[0145]
For example, if “tell me a nearby ramen shop” is input as an information search condition, a pair of verb and object for the information search condition is extracted as a pair of “ramen shop” and “teach”. Search past accumulated information, for example, if there was information found in the information search condition of “Tell me a delicious ramen shop” last week, this is extracted because it has the same pair, the agent said, “Last week, delicious ramen shop I went to ”and read the information on ramen shops that I can find by searching at the moment. By doing in this way, the user can recall the experience at the ramen shop last week and review the current behavior.
[0146]
Also, the superordinate concept is different in that it has a genre and a hierarchy. For example, the superordinate concept of “ramen restaurant” is “Chinese restaurant”, and the superordinate concept of “Chinese restaurant” is “place to eat”. Therefore, in the example of the ramen shop above, if there was information found by searching for “curry store” last week, if you search with the keyword “ramen shop” at the present time, “the place to eat” with the same superordinate concept The information of the curry store is found, and the agent says, “Speaking of that, I went to the curry store last week.” And then reads the search result of the ramen shop at the present time. In this way, the user can recall the experience at the curry store last week and review the current behavior.
[0147]
Also, the focus summarizes the retrieved information and can be extracted as the most frequently occurring word. The agent looks for past accumulated information containing this word and reports it to the user when found. For example, suppose that a businessman agent analyzes information searched for “crude oil” as a keyword, and “price increase” is extracted as a focus. The agent looks for information that focuses on "price information" in the accumulated information in the past, for example, when finding information on information on housing land prices, "Speaking of which, housing prices also went up last week." Then, read the information on the price increase of the crude oil searched at the moment. By doing in this way, the user can get a profit by predicting inflation from last week's rise in house prices and the current rise in crude oil prices, and taking action that suits this.
[0148]
By the way, it is more efficient not to read the past information itself unless there is a request from the user.
[0149]
Such processing is performed in all searches.
[0150]
As described above, the information search method using the agent according to the eleventh embodiment of the present invention is also excellent in that the user's interest can be maintained.
[0151]
FIG. 12 is a block diagram of an information search apparatus using an agent according to the twelfth embodiment of the present invention.
[0152]
As shown in FIG. 12, the information retrieval apparatus using the agent includes a central processing unit 1201, an agent display unit 1202 that generally displays a list of selectable agents, and a display unit. 1202 and bus interface circuit 1203, input means 1204 generally composed of a microphone or remote control, agent selection means 1205, , Inspection Search keyword adding means 1206, output means 1207 of an audio device generally including a speaker, and agent specific information search conditions are stored Feeling Information search condition storage means 1208 (Generally a memory device) When , Emotion An information search means 1209 and a system bus 1210 are included.
[0153]
The operation of the information retrieval apparatus using the agent configured as described above will be described.
[0154]
First, the information retrieval apparatus using this agent displays a plurality of agent images acting on behalf of the information retrieval work for the user and their characteristics on the display device 1202, and the user can understand his / her interest from the images and characteristic descriptions. Select an agent who seems to have a similar tendency. For example, in the case of “Oyaji Agent,” an image of an old man who seems to be stubborn, and characteristics such as “Slightly stubborn. Interested in political economy. Weak to grandchildren and wives.” Are displayed. If you want to make a search request for information such as “Oyaji Agent”, you can expect to get almost the information you want.
[0155]
Therefore, the user selects the name or number using the input means 1204. When the input unit 1204 is voice, the input unit 1204 includes a voice recognition device. Only the selected agent remains and other agents are deleted by the agent selection means 1205. Agent selection means 1205 stores the name or number of this agent. Each agent has a unique information search keyword in the information search condition storage means 1208. For example, in the case of a businessman agent, words such as “salary”, “economy”, and “selling” are stored in advance as information search keywords.
[0156]
When there is a request from the user using the input means 1204 to present an information search keyword unique to the agent, a list of keywords is displayed on the display device 1202. In some cases, it is also effective to read out the registered content from the output means 1207 with synthetic speech or the like. When the user thinks that the presented information search keyword is insufficient, the user can additionally register the information search keyword. At that time, the central processing unit 1201 determines whether there is no overlap or contradiction with keywords registered in the past. (Equivalent to memory control means) Checked by.
[0157]
If there is the same keyword in the past, the registration is canceled, and if there is a semantic contradiction, priority is given to the one set by the user, and the conflicting past information search condition is deleted. The information search condition need not be a word like a keyword, but may be a sentence. When the keywords are set, the agent autonomously checks various channels of information sources (for example, Internet sites and text multiplex broadcasts), searches for the ones containing the keywords, and presents them to the user.
[0158]
As described above, the information search apparatus and the information search apparatus using the agent according to the twelfth embodiment of the present invention have an excellent effect in that it is possible to save time and effort for setting information search conditions for the user.
[0159]
FIG. 13 is a block diagram of an information search condition unique to an agent and a new information search condition determination unit 1300 in an information search apparatus using an agent according to a thirteenth embodiment of the present invention.
[0160]
As shown in FIG. 13, the determination unit 1300 includes a sequence control unit 1301, an input unit 1302, a comparison determination unit 1303, a thesaurus dictionary 1304, an agent-specific information search condition storage unit 1305, and a gate unit 1306. It consists of and.
[0161]
The operation of the information search condition specific to the agent of the information search apparatus using the agent configured as described above and the information search condition determination unit 1300 to be newly added will be described.
[0162]
If the user thinks that the information search condition (keyword or sentence) of the twelfth embodiment is insufficient, the information search condition or new information search condition expressed by the sentence is input using the input means 1302. To do. This keyword or sentence is not sent directly to the information retrieval condition storage unit 1305 but is temporarily stored in the gate unit 1306. When the sequence control unit 1301 knows that a keyword or sentence has been input by the notification from the input unit 1302, the sequence control unit 1301 activates the comparison determination unit 1303, and compares the input with what is already stored in the information search condition storage unit 1305. To do.
[0163]
At that time, not only a simple comparison but also a set of related words is used in the thesaurus dictionary 1304 for both the input and the stored one, and it is determined whether these sets have the same elements. As a result, if it is determined that they are not the same, a command is issued to transfer the input stored in the gate means 1306 from the sequence control means 1301 to the information search condition storage means 1305.
[0164]
Further, the comparison determination unit 1303 also determines the consistency between the input and the existing information search condition. In other words, the condition of “high price” and the condition of “cheap price” are meaningless if they exist at the same time. If such a contradiction is found, the comparison judgment unit 1303 notifies the output unit 1307 that there is a contradiction, and the output unit 1307 has a contradiction in the synthesized speech or the like. The condition notifies the user that it has been deleted.
[0165]
In this way, new information search conditions input by the user are automatically compared with existing information search conditions, checked for consistency and redundancy, and overwritten and registered with conflicting ones. If there is no conflict, it is additionally registered.
[0166]
As described above, the information search apparatus and the information search apparatus using the agent according to the thirteenth embodiment of the present invention are excellent in that the user can save time and effort for setting the information search conditions.
[0167]
FIG. 14 shows a block diagram when a voice conversation is performed as the information search condition adding means 1400 in the information search apparatus using the agent according to the fourteenth embodiment of the present invention.
[0168]
As shown in FIG. 14, this information search condition adding means 1400 includes sequence control means 1401, speech recognition means 1402, dialogue management means 1403, comparison judgment means 1404, thesaurus dictionary 1405, and information search condition storage means. 1406 and gate means 1407.
[0169]
The operation in the case of performing a voice dialogue as the information search condition adding means 1400 of the information search apparatus using the agent configured as described above will be described.
[0170]
If the user thinks that the information search conditions (keywords and sentences) of the twelfth embodiment are insufficient, the voice recognition means 1402 is used to change the information search conditions newly expressed by the information search keywords or sentences. input. This keyword or sentence is not sent directly to the information search condition storage means 1406 but is temporarily stored in the gate means 1407.
[0171]
At this time, as a phenomenon peculiar to voice recognition, a case where erroneous recognition or rephrasing is required occurs. The dialogue management unit 1403 looks at the result notification from the speech recognition unit 1402 and, when the likelihood of the recognition result is not sufficient, uses the speech synthesis unit 1408 to request the user to replay the voice. When the sequence control unit 1401 knows that a valid keyword or sentence has been recognized by the notification from the dialogue management unit 1403, the sequence control unit 1401 activates the comparison determination unit 1404, and the input is already stored in the information search condition storage unit 1406. Compare things. At this time, not only a simple comparison but also a set of related words is used in the thesaurus dictionary 1405 for both the input and the stored one, and it is determined whether the sets have the same elements. As a result, if it is determined that they are not the same, a command is issued to transfer the input stored in the gate means 1407 from the sequence device to the information search condition storage means 1406.
[0172]
In addition, the comparison determination unit 1404 also determines the consistency between the input and the existing information search condition. In other words, the condition of “high price” and the condition of “cheap price” are meaningless if they exist at the same time. When such a contradiction is found, the comparison determination unit 1404 notifies the voice synthesis unit 1408 that there is a contradiction, and the voice synthesis unit 1408 has a contradiction. Notify the user that it has been deleted.
[0173]
In this way, the new information search condition input by the user is automatically compared with the existing information search condition, and is registered only when there is no problem after checking consistency and redundancy.
[0174]
As described above, the information search device and the information search device using the agent according to the fourteenth embodiment of the present invention have an excellent effect in that it is possible to save time and effort for setting the information search condition of the user.
[0175]
FIG. 15 shows a block diagram when a sentence is input as the information search condition adding means 1500 in the information search apparatus using the agent according to the fifteenth embodiment of the present invention.
[0176]
As shown in FIG. 15, this information search condition adding means 1500 includes a sequence control means 1501, an input means 1502, a syntax analysis means 1503, a meaning understanding means 1504, a keyword extraction means 1505, and a comparison judgment means 1506. , Information retrieval condition storage means 1507, gate means 1508, response sentence generation means 1509, and output means 1510.
[0177]
An operation in the case of inputting a sentence as the information search condition adding unit 1500 of the information search apparatus using the agent configured as described above will be described.
[0178]
If the user thinks that the information search conditions (keywords and sentences) of the twelfth embodiment are insufficient, the information search conditions or new information search conditions expressed by sentences are input using the input means 1502. To do. In general, there are many cases in which input is performed with a remote control. This keyword or sentence is not directly sent to the information search condition storage unit 1507 but is temporarily stored in the gate unit 1508. At this time, as a phenomenon peculiar to sentence input, there is a case where re-input is necessary due to an error. A keyword extraction unit 1505 extracts a keyword from the input decomposed into units close to words by the syntax analysis unit 1503 and the semantic understanding unit 1504.
[0179]
At this time, the syntax analysis unit 1503 and the semantic understanding unit 1504 sequentially transfer scores representing the validity of the analysis to the next keyword extraction unit 1505. The sequence control unit 1501 uses the response sentence generation unit 1509 to request the user to input again when there is an error, by looking at the result of the keyword extraction unit 1505 that has received these. When the sequence control unit 1501 knows that a valid keyword has been extracted by the notification from the keyword extraction unit 1505, it starts the comparison determination unit 1506, and inputs the information already stored in the information search condition storage unit 1507. Compare. At that time, not only a simple comparison but also a set of related words is set in the thesaurus dictionary 1511 for both input and stored ones, and it is determined whether these sets have the same elements.
[0180]
As a result, if it is determined that they are not the same, a command is issued to transfer the input stored in the gate means 1508 from the sequence control means 1501 to the information search condition storage means 1507. In addition, the comparison determination unit 1506 also determines the consistency between the input and the existing information search condition. In other words, the condition of “high price” and the condition of “cheap price” are meaningless if they exist at the same time. When such a contradiction is found, the comparison judgment unit 1506 notifies the output unit 1510 that there is a contradiction, and the output unit 1510 has a contradiction, so the user input is given priority and the existing condition is deleted. To the user.
[0181]
In this way, the new information search condition input by the user is automatically compared with the existing information search condition, and is registered only when there is no problem after checking consistency and redundancy.
[0182]
As described above, the information search apparatus and the information search apparatus using the agent according to the fifteenth embodiment of the present invention are excellent in that the user can save time and effort for setting the information search conditions.
[0183]
FIG. 16 shows a block diagram when switching agents in an information search apparatus using agents according to the sixteenth embodiment of the present invention.
[0184]
In FIG. 16, an information retrieval apparatus using this agent includes a speech recognition unit 1601, a syntax analysis unit 1602, a meaning understanding unit 1603, a dialogue management unit 1604, an information retrieval unit 1605, an information collection unit 1606, The received information storage unit 1607, agent switching unit 1608, recording voice DB 1609, text voice synthesizing unit 1610, image generation unit 1611, output switching unit 1612, and speaker 1613 are included.
[0185]
An operation when the agent is switched in the information search apparatus using the agent configured as described above will be described.
[0186]
First, the agent automatically appears through the image generation unit 1611 when a restriction condition such as a call from the user through the voice recognition unit 1601 or the memory capacity of the agent itself is likely to be exceeded. When the agent is presented from the beginning, it starts to move actively when the above conditions are met. The agent autonomously checks various channels of information sources (for example, Internet sites and text multiplex broadcasting), and information search conditions (keywords) possessed by the agent itself are included in the information search means 1605. However, prior to presentation to the user, the information search means 1605 finds a keyword that is the focus in the searched information.
[0187]
Based on this, the dialogue management means 1604 selects a recorded voice representing the impression associated with the focused keyword from the recorded voice database 1609. Since a sentence expressing this impression can be determined in advance, it is not necessarily a text-to-speech synthesis, and a recorded / reproduced voice may be used. For example, when the focus of “dropping out” is extracted, a high school girl agent states “Hey, ask me this. It ’s terrible!”. Thereafter, the agent is switched to an agent specialized in reading by the agent switching means 1608. A read-only agent reads the retrieved information using text-to-speech synthesis. Such a change is continued until there is no information retrieved by the information retrieval unit 1605.
[0188]
As described above, the information search apparatus using the agent according to the sixteenth embodiment of the present invention is also excellent in that the user's interest can be maintained.
[0189]
FIG. 17 shows a block diagram of an information retrieval apparatus using an agent according to the seventeenth embodiment of the present invention.
[0190]
In FIG. 17, an information search apparatus using this agent includes a speech recognition unit 1701, a syntax analysis unit 1702, a meaning understanding unit 1703, a dialogue management unit 1704, an information search unit 1705, an information collection unit 1706, The received information storage unit 1707, the agent switching unit 1708, the recording voice database 1709, the text voice synthesizing unit 1710, the image generation unit 1711, the output switching unit 1712, the speaker 1713, and the common sense database 1714 are configured. Yes.
[0191]
The operation of the information retrieval apparatus using the agent configured as described above will be described.
[0192]
First, the agent automatically appears through the image generation unit 1711 when a restriction condition such as a call from the user through the voice recognition unit 1701 or the memory capacity of the agent itself is likely to be exceeded. When the agent is presented from the beginning, it starts to move actively when the above conditions are met. The agent autonomously checks various channels of information sources (for example, Internet sites and text multiplex broadcasting), and information search conditions (keywords) possessed by the agent itself are included in the information search means 1705. However, prior to presentation to the user, the keyword that is the focus in the searched information is extracted, so that the searched information is decomposed into morphemes by the preprocessing of the text-to-speech synthesizer 1710. Then, the focus is extracted by the parsing means 1702 and the semantic understanding means 1703. When there are a plurality of focal points, the meaning understanding means uses the common sense database 1714 to narrow the focal point to one.
[0193]
Based on this, the dialogue management means 1704 selects a recorded voice representing the impression associated with the focused keyword from the recorded voice database 1709. Since a sentence expressing this impression can be determined in advance, it is not necessarily a text-to-speech synthesis, and a recorded / reproduced voice may be used. For example, when the focus of “dropping out” is extracted, a high school girl agent states “Hey, ask me this. It ’s terrible!”. Thereafter, the agent is switched to an agent specialized in reading by the agent switching means 1708. A read-only agent reads the retrieved information using text-to-speech synthesis. Such a change is continued until there is no information retrieved by the information retrieval unit 1705.
[0194]
As described above, the information search apparatus using the agent according to the seventeenth embodiment of the present invention is also excellent in that the user's interest can be maintained.
[0195]
FIG. 18 shows a block diagram of an information retrieval apparatus using an agent according to the eighteenth embodiment of the present invention.
[0196]
In FIG. 18, an information retrieval apparatus using this agent includes a speech recognition unit 1801, a syntax analysis unit 1802, a meaning understanding unit 1803, a dialogue management unit 1804, a dialogue history database 1805, an emotion estimation unit 1806, Information collection means 1807, received information storage means 1808, information search means 1809, agent switching means 1810, recorded voice database 1811, text voice synthesis means 1812, output switching means 1813, speaker 1814, image generation And means 1815.
[0197]
The operation of the information retrieval apparatus using the agent configured as described above will be described.
[0198]
First, the result of one-turn dialogue with the user, which is composed of the output of the text-to-speech synthesis unit 1812 with respect to the input from the voice recognition unit 1801 (or vice versa), is recorded in the dialogue history database 1805, and then from the dialogue history database 1805. The emotion estimation means 1806 is used to estimate the emotional state of the user. For example, it can be easily estimated whether the user is “joyful” or “angry” depending on whether the conversation in the past several turns has succeeded or failed. This is because if there is much success, it will be “joy”, and if there is little success, it will be “anger”. When the user is “joyful”, the dialogue management unit 1804 advances the conversation efficiently with a simple expression, but when “anger”, the dialogue management unit 1804 switches to a polite expression, and the image generation unit 1815 makes the expression of the agent apologize. Change to something that looks like it.
[0199]
As described above, the information search apparatus using the agent according to the eighteenth embodiment of the present invention is also excellent in that the user's interest can be maintained.
[0200]
FIG. 19 is a block diagram of an information search apparatus using an agent according to the nineteenth embodiment of the present invention.
[0201]
In FIG. 19, an information search apparatus using this agent includes a speech recognition unit 1901, a syntax analysis unit 1902, a meaning understanding unit 1903, a dialogue management unit 1904, an emotion estimation unit 1905, an information collection unit 1906, The received information storage unit 1907, the information search unit 1908, the agent switching unit 1909, the recording voice database 1910, the text voice synthesizing unit 1911, the output switching unit 1912, the speaker 1913, and the image generation unit 1914 are configured. ing.
[0202]
The operation of the information retrieval apparatus using the agent configured as described above will be described.
[0203]
First, the emotion estimation means 1905 is used to estimate the emotion state of the user in response to the input from the voice recognition means 1901. For example, if the average pitch frequency is slightly higher and the duration of the ending is longer, the user is often happier. Conversely, if the average pitch frequency is lower, the overall power increases, and the duration of the ending is shorter There are many cases of “anger”. When the user is “joyful”, the dialogue management unit 1904 proceeds with the dialogue efficiently with a simple expression. However, when the user is “angry”, the dialogue management unit 1904 switches to a polite expression, and the image generation unit 1914 makes the expression of the agent apologize. Change to something that looks like it.
[0204]
As described above, the information search apparatus using the agent according to the nineteenth embodiment of the present invention is also excellent in that the user's interest can be maintained.
[0205]
FIG. 20 is a block diagram of an information search apparatus using an agent according to the twentieth embodiment of the present invention.
[0206]
In FIG. 20, an information retrieval apparatus using this agent includes a speech recognition unit 2001, a syntax analysis unit 2002, a meaning understanding unit 2003, a dialogue management unit 2004, an image recognition unit 2005, an emotion estimation unit 2006, Information collection means 2007, received information storage means 2008, information search means 2009, agent switching means 2010, recorded voice database 2111, text voice synthesis means 2012, output switching means 2013, speaker 2014, image generation And means 2015.
[0207]
The operation of the information retrieval apparatus using the agent configured as described above will be described.
[0208]
First, the emotion estimation means 2006 is used to estimate the emotional state of the user for the facial expression of the user that enters through the image recognition means 2005 simultaneously with the input from the voice recognition means 2001. For example, when both eyes are narrow and both ends of the mouth are raised, it is often “joy”, and when the distance between the eyebrows is shortened and the mouth is slightly opened, it is often “angry”. . When the user is “joyful”, the dialogue management means 2004 proceeds efficiently with a simple expression, but when “anger”, the dialogue management means 2004 switches to a polite expression, and the image generation means 2015 makes the expression of the agent apologize. Change to something that looks like it.
[0209]
As described above, the information search apparatus using the agent according to the twentieth embodiment of the present invention is also excellent in that the user's interest can be maintained.
[0210]
FIG. 21 shows a block diagram of an information retrieval apparatus using an agent according to the twenty-first embodiment of the present invention.
[0211]
In FIG. 21, an information retrieval apparatus using this agent includes a speech recognition unit 2101, a syntax analysis unit 2102, a meaning understanding unit 2103, a dialogue management unit 2104, an image recognition unit 2105, an emotion estimation unit 2106, Information collection means 2107, received information storage means 2108, information search means 2109, agent switching means 2110, recorded voice database 2111, text voice synthesis means 2112, output switching means 2113, speaker 2114, image generation And means 2115.
[0212]
The operation of the information retrieval apparatus using the agent configured as described above will be described.
[0213]
First, the emotion state of the user is estimated using the emotion estimation hand 2106 for the facial expression of the user that enters through the image recognition unit 2105 simultaneously with the input from the voice recognition unit 2101. For example, if the dialogue result is “success”, the voice quality is “soft”, and the facial expression is “neutral”, the user is often satisfied, and conversely, the dialogue result is failure and the voice quality is “angry”. When the expression is “angry”, it is often “angry”. When the user is “joyful”, the dialog management means 2104 proceeds with the conversation efficiently with a simple expression. However, when the user is “angry”, the conversation management means 2104 switches to a polite expression, and the image generation means 2115 makes the expression of the agent apologize. Change to something that looks like it.
[0214]
As described above, the information search apparatus using the agent according to the twenty-first embodiment of the present invention is also excellent in that the user's interest can be maintained.
[0215]
FIG. 22 shows a block diagram of an information retrieval apparatus using an agent according to the twenty-second embodiment of the present invention.
[0216]
In FIG. 22, an information search apparatus using this agent includes a sequence control means 2201, an input means 2202, a comparison judgment means 2203, a thesaurus dictionary 2204, an information search condition storage means 2205, a gate means 2206, and an output. A means 2207, an information search means 2208, a time monitoring means 2209, a text-to-speech synthesis means 2210, a received information storage means 2211, an information collection means 2212, and a plurality of information sources 2213 are included.
[0217]
The operation of the information retrieval apparatus using the agent configured as described above will be described.
[0218]
First, the agent obtains information including the information search keyword that the agent has, replaces the plurality of information sources 2213 one after another by the information collection unit 2212, and searches the information stored in the reception information storage unit 2211 by the information search unit 2208. To go. This search operation is monitored by the time monitoring unit 2209. When the time required for the search set in the sequence control unit 2201 is exceeded, the search operation is terminated, and the search result is displayed by the text-to-speech synthesis unit 2210. To tell.
[0219]
As described above, the information search apparatus using the agent according to the twenty-second embodiment of the present invention is also excellent in that the user's information search work can be facilitated.
[0220]
FIG. 23 shows a block diagram of an information retrieval apparatus using an agent according to the twenty-third embodiment of the present invention.
[0221]
In FIG. 23, the information retrieval apparatus using this agent includes a sequence control unit 2301, an input unit 2302, a comparison judgment unit 2303, a thesaurus dictionary 2304, an information retrieval condition storage unit 2305, a gate unit 2306, and an output. It comprises means 2307, information search means 2308, search number investigation means 2309, text speech synthesis means 2310, received information storage means 2311, information collection means 2312, and a plurality of information sources 2313.
[0222]
The operation of the information retrieval apparatus using the agent configured as described above will be described.
[0223]
First, the agent obtains information including an information search keyword possessed by the agent, replaces the plurality of information sources 2313 one after another by the information collecting unit 2312, and searches the information stored in the received information storage unit 2311 by the information search unit 2308. To go. This search operation is monitored by the search number investigation unit 2309. When the upper limit number set in the sequence control unit 2301 is exceeded, the search operation is terminated and the search result is displayed by the text-to-speech synthesis unit 2310. To tell.
[0224]
As described above, the information search apparatus using the agent according to the twenty-third embodiment of the present invention is also excellent in that the user's information search work can be facilitated.
[0225]
FIG. 24 shows a block diagram of an information retrieval apparatus using an agent according to the twenty-fourth embodiment of the present invention.
[0226]
In FIG. 24, an information retrieval apparatus using this agent includes a sequence control unit 2401, an input unit 2402, a comparison judgment unit 2403, a thesaurus dictionary 2404, an information retrieval condition storage unit 2405, a gate unit 2406, and an output. It comprises means 2407, information search means 2408, memory size investigation means 2409, text speech synthesis means 2410, received information storage means 2411, information collection means 2412, and a plurality of information sources 2413.
[0227]
The operation of the information retrieval apparatus using the agent configured as described above will be described.
[0228]
First, the agent obtains information including an information search keyword that the agent has, replaces a plurality of information sources 2413 one after another by the information collecting unit 2412, and searches the information stored in the received information storage unit 2411 by the information search unit 2408. To go. This search operation is monitored by the memory size investigation unit 2409. When the data stored in the reception information storage unit 2411 exceeds the upper limit size set in advance in the sequence control unit 2401, the search operation is terminated. The search result at that time is transmitted to the user by the text-to-speech synthesizer 2410.
[0229]
As described above, the information search apparatus using the agent according to the twenty-fourth embodiment of the present invention is also excellent in that the user's information search work can be facilitated.
[0230]
FIG. 25 is a block diagram of an information search apparatus using an agent according to the twenty-fifth embodiment of the present invention.
[0231]
In FIG. 25, an information search apparatus using this agent includes a sequence control means 2501, an input means 2502, a comparison judgment means 2503, a thesaurus dictionary 2504, an information search condition storage means 2505, a gate means 2506, and an output. Means 2507, information search means 2508, search upper limit condition investigation means 2509, text-to-speech synthesis means 2510, received information storage means 2511, information collection means 2512, a plurality of information sources 2513, and past received information The storage area 2514 is composed of an agent speech speech database 2515.
[0232]
The operation of the information retrieval apparatus using the agent configured as described above will be described.
[0233]
First, the agent uses information collection means 2512 to autonomously search for information that matches the information search condition of the agent itself from a plurality of information sources 2513. If there is no information similar to this information, The reception information storage area 2514 is checked. When similar information is found, the optimum speech is selected from the agent speech speech database 2515, the fact is reported to the user through the output unit 2507, and the search result is read out using the text speech synthesis unit 2510. For example, when searching for stock price news, report the similarities of past similar information, saying, “Stocks went down again like three days ago.” Then, the retrieved information is read out. Such an operation is continued until the search upper limit condition investigation unit 2509 orders the stop.
[0234]
As described above, the information search apparatus using the agent according to the twenty-fifth embodiment of the present invention is also excellent in that the user's interest can be maintained.
[0235]
FIG. 26 shows a block diagram of an information retrieval apparatus using an agent according to the twenty-sixth embodiment of the present invention.
[0236]
In FIG. 26, the information search apparatus using this agent includes a sequence control means 2601, an input means 2602, a comparison judgment means 2603, a thesaurus dictionary 2604, an information search condition storage means 2605, a gate means 2606, and an output. Means 2607, information search means 2608, search upper limit condition investigation means 2609, text-to-speech synthesis means 2610, received information storage means 2611, information collection means 2612, a plurality of information sources 2613, and past received information A keyword genre storage area 2614, a keyword genre assigning means 2615, and an agent speech speech database 2616 are included.
[0237]
The operation of the information retrieval apparatus using the agent configured as described above will be described.
[0238]
First, the agent autonomously retrieves information that matches the information retrieval condition of the agent itself from a plurality of information sources 2613 using the information collecting means 2612. However, the search is performed to check whether there is information similar to this information. The genre of the search keyword of the information thus obtained is determined by the keyword genre assigning means 2615, and the keyword genre storage area 2614 of past received information is examined. If it is judged that the comparison judgment means 2603 is similar, the optimum speech is selected from the agent speech speech database 2616, the fact is reported to the user through the output means 2607, and the search result is read out using the text speech synthesis means 2610. For example, when searching for stock price news, report the similarities of past similar information, saying, “Stocks went down again like three days ago.” Then, the retrieved information is read out. Such an operation is continued until the search upper limit condition investigation means 2609 commands the stop.
[0239]
As described above, the information search apparatus using the agent according to the twenty-sixth embodiment of the present invention is also excellent in that the user's interest can be maintained.
[0240]
FIG. 27 shows a block diagram of an information retrieval apparatus using an agent according to a twenty-seventh embodiment of the present invention.
[0241]
In FIG. 27, an information search apparatus using this agent includes a sequence control means 2701, an input means 2702, a comparison judgment means 2703, a thesaurus dictionary 2704, an information search condition storage means 2705, a gate means 2706, and an output. Means 2707, information search means 2708, search upper limit condition investigation means 2709, text-to-speech synthesis means 2710, received information storage means 2711, information collection means 2712, a plurality of information sources 2713, and information received in the past The retrieval condition verb and object storage area 2714, the information retrieval condition verb and object extraction means 2715, and the agent speech speech database 2716 are configured.
[0242]
The operation of the information retrieval apparatus using the agent configured as described above will be described.
[0243]
First, the agent uses the information collecting means 2712 to autonomously search for information that matches the information search condition of the agent itself from a plurality of information sources 2713, but searches for information similar to this information. The extracted information search condition verb and object are extracted by the extraction means 2715, and the previously received information search condition verb and object storage area 2714 is examined. If it is judged that the comparison judgment means 2703 is similar, an optimum voice is selected from the agent speech speech database 2716, the fact is reported to the user through the output means 2707, and the search result is read out using the text speech synthesis means 2710. For example, when searching for stock price news, report the similarities of past similar information, saying, “Stocks went down again like three days ago.” Then, the retrieved information is read out. Such an operation is continued until the search upper limit condition investigation means 2709 commands a stop.
[0244]
As described above, the information search apparatus using the agent according to the twenty-seventh embodiment of the present invention is also excellent in that the user's interest can be maintained.
[0245]
FIG. 28 shows a block diagram of an information retrieval apparatus using an agent according to the twenty-eighth embodiment of the present invention.
[0246]
In FIG. 28, the information search apparatus using this agent includes a sequence control means 2801, an input means 2802, a comparison judgment means 2803, a thesaurus dictionary 2804, an information search condition storage means 2805, a gate means 2806, and an output. Means 2807, information retrieval means 2808, search upper limit condition investigation means 2809, text-to-speech synthesis means 2810, received information storage means 2811, information collection means 2812, a plurality of information sources 2813, and past received information The search search keyword superordinate concept storage area 2814, search keyword superordinate concept assigning means 2815, and agent speech speech database 2816 are configured.
[0247]
The operation of the information retrieval apparatus using the agent configured as described above will be described.
[0248]
First, the agent uses the information collecting means 2812 to autonomously search for information that matches the information search condition of the agent itself from a plurality of information sources 2813. However, the search is performed to check whether there is information similar to this information. The superordinate concept of the search keyword of the information thus obtained is given by the grant means 2815, and the superordinate concept storage area 2814 of the search keyword of the past received information is examined.
[0249]
When it is judged that the comparison judgment means 2803 is similar, the optimum speech is selected from the agent speech speech database 2816, the fact is reported to the user through the output means 2807, and the search result is read out using the text speech synthesis means 2810. The superordinate concept is different in that it has a genre and a hierarchy. For example, the superordinate concept of “ramen restaurant” is “Chinese restaurant”, and the superordinate concept of “Chinese restaurant” is “place to eat”.
[0250]
Therefore, in the example of the ramen shop above, if there was information found by searching for “curry shop” last week, if you search with the keyword “ramen shop” at the present time, the “superior concept” is the same “place to eat” The information of the curry store is found, and the agent says, “Speaking of that, I went to the curry store last week.” And then reads the search result of the ramen shop at the present time. In this way, the user can recall the experience at the curry store last week and review the current behavior. The information retrieval apparatus continues such an operation until the retrieval upper limit condition investigation unit 2809 instructs to stop.
[0251]
As described above, the information search apparatus using the agent according to the twenty-eighth embodiment of the present invention is also excellent in that the user's interest can be maintained.
[0252]
FIG. 29 shows a block diagram of an information retrieval apparatus using an agent according to the twenty-ninth embodiment of the present invention.
[0253]
In FIG. 29, an information search apparatus using this agent includes a sequence control means 2901, an input means 2902, a comparison judgment means 2903, a thesaurus dictionary 2904, an information search condition storage means 2905, a gate means 2906, and an output. Means 2907, information search means 2908, search upper limit condition investigation means 2909, text-to-speech synthesis means 2910, received information storage means 2911, information collection means 2912, a plurality of information sources 2913, and past received information A focus storage area 2914, search information focus extraction means 2915, and an agent speech speech database 2916 are included.
[0254]
The operation of the information retrieval apparatus using the agent configured as described above will be described.
[0255]
First, the agent autonomously retrieves information that matches the information retrieval condition of the agent itself from a plurality of information sources 2913 by using the information collecting means 2912. However, retrieval is performed to check whether there is information similar to this information. The focus of the received information is estimated by the estimation means 2915, and the focus storage area 2914 of past received information is examined. If it is judged that the comparison judgment means 2903 is similar, the optimum speech is selected from the agent speech speech database 2916, the fact is reported to the user through the output means 2907, and the search result is read out using the text speech synthesis means 2910.
[0256]
For example, suppose that a businessman agent analyzes information searched for “crude oil” as a keyword, and “price increase” is extracted as a focus. The agent looks for information that focuses on "price information" in the past accumulated information. For example, when he finds information on housing land prices, he says, "Speaking of which, housing prices also went up last week." Then, the information on the price increase of crude oil searched at present is read out.
[0257]
By doing in this way, the user can get a profit by predicting inflation from last week's rise in house prices and the current rise in crude oil prices, and taking action that suits this. The information retrieval apparatus continues such an operation until the retrieval upper limit condition investigation means 2909 instructs to stop.
[0258]
As described above, the information search apparatus using the agent according to the twenty-ninth embodiment of the present invention is also excellent in that the user's interest can be maintained.
[0259]
【The invention's effect】
As described above, the present invention obtains information desired by a user only by selecting an agent that seems to be close to the user's own information search condition from a plurality of agents having preset information search conditions. The user can obtain information without taking time and effort.
[Brief description of the drawings]
FIG. 1 is a flowchart of an information search method using an agent according to a first embodiment of the present invention.
FIG. 2 is a process flow diagram for inputting additional information search conditions by voice interaction in an information search method using an agent according to the second embodiment of the present invention;
FIG. 3 is a process flow diagram for inputting additional information search conditions as a sentence in an information search method using an agent according to the third embodiment of the present invention;
FIG. 4 is a process flow diagram in which an agent that reads out searched information and an agent that performs dialogue are separated in an information search method using an agent according to a fourth embodiment of the present invention;
FIG. 5 is a processing flow diagram of selection of a dialogue strategy based on user emotion estimation for facilitating dialogue with a user in an information search method using an agent according to a fifth embodiment of the present invention.
FIG. 6 is a processing flow diagram of selection of a dialogue strategy based on estimation of a user's emotion for facilitating dialogue with the user in an information search method using an agent according to the sixth embodiment of the present invention.
FIG. 7 is a process flow diagram of selection of a dialogue strategy based on a user's facial expression for facilitating dialogue with the user in the information search method using an agent according to the seventh embodiment of the present invention.
FIG. 8 is a process flow diagram of selection of a dialogue strategy based on a user's voice quality, facial expression, and dialogue history in order to facilitate a dialogue with the user in an information search method using an agent according to an eighth embodiment of the present invention.
FIG. 9 is an autonomous information search processing flowchart in an information search method using an agent according to a ninth embodiment of the present invention;
FIG. 10 is a processing flowchart for referencing past search results in an information search method using an agent according to the tenth embodiment of the present invention;
FIG. 11 is a processing flowchart for referencing past search results in an information search method using an agent according to an eleventh embodiment of the present invention;
FIG. 12 is a block diagram of an information retrieval apparatus using an agent according to a twelfth embodiment of the present invention.
FIG. 13 is a block diagram of a determination unit for an information search condition unique to an agent and an information search condition to be newly added in an information search apparatus using an agent according to a thirteenth embodiment of the present invention;
FIG. 14 is a block diagram of a case where a voice conversation is performed as an information search condition adding unit in an information search apparatus using an agent according to a fourteenth embodiment of the present invention.
FIG. 15 is a block diagram when a sentence is input as an information search condition adding unit in the information search apparatus using an agent according to the fifteenth embodiment of the present invention;
FIG. 16 is a block diagram of an agent switching unit in an information search apparatus using an agent according to a sixteenth embodiment of the present invention.
FIG. 17 is a block diagram of an information retrieval apparatus using an agent according to a seventeenth embodiment of the present invention.
FIG. 18 is a block diagram of an information retrieval apparatus using an agent according to an eighteenth embodiment of the present invention.
FIG. 19 is a block diagram of an information retrieval apparatus using an agent according to a nineteenth embodiment of the present invention.
FIG. 20 is a block diagram of an information retrieval apparatus using an agent according to a twentieth embodiment of the present invention.
FIG. 21 is a block diagram of an information retrieval apparatus using an agent according to a twenty-first embodiment of the present invention.
FIG. 22 is a block diagram of an information retrieval apparatus using an agent according to the twenty-second embodiment of the present invention.
FIG. 23 is a block diagram of an information retrieval apparatus using an agent according to a twenty-third embodiment of the present invention.
FIG. 24 is a block diagram of an information retrieval apparatus using an agent according to a twenty-fourth embodiment of the present invention.
FIG. 25 is a block diagram of an information retrieval apparatus using an agent according to a twenty-fifth embodiment of the present invention.
FIG. 26 is a block diagram of an information retrieval apparatus using an agent according to a twenty-sixth embodiment of the present invention.
FIG. 27 is a block diagram of an information retrieval apparatus using an agent according to a twenty-seventh embodiment of the present invention.
FIG. 28 is a block diagram of an information retrieval apparatus using an agent according to a twenty-eighth embodiment of the present invention.
FIG. 29 is a block diagram of an information retrieval apparatus using an agent according to a twenty-ninth embodiment of the present invention.
FIG. 30 is a block diagram of an information search apparatus using a conventional agent.
[Explanation of symbols]
1201 Central processing unit
1202 Agent display means
1203 interface circuit,
1204, 1302, 1502, 2202, 2302, 2402, 2502, 2602, 2702, 2802, 2902 Input means
1205 Agent selection means
1206 Search keyword addition means
1207, 1510, 2207, 2307, 2407, 2507, 2607, 2707, 2807, 2907 output means
1208, 1305, 1406, 1507, 2205, 2305, 2405, 2505, 2605, 2705, 2805, 2905 information retrieval condition storage means
1209, 1605, 1705, 1809, 1908, 2009, 2109, 2208, 2308, 2408, 2508, 2608, 2708, 2808, 2908 Information retrieval means
1301, 1401, 1501, 2201, 2301, 2401, 2501, 2601, 2701, 2801, 2901 Sequence control means
1303, 1404, 1506, 2203, 2303, 2403, 2503, 2603, 2703, 2803, 2903 Comparison judgment means
1304, 1405, 2204, 2304, 2504, 2604, 2704, 2804, 2904 Thesaurus
1402, 1601, 1701, 1801, 1901, 2001, 2101 Voice recognition means
1403, 1604, 1704, 1804, 1904, 2004, 2104 Dialogue management means
1503, 1602, 1702, 1802, 1902, 2002, 2102 Syntax analysis means
1504, 1603, 1703, 1803, 1903, 2003, 2103 Meaning understanding means
1505 Keyword extraction means
1509 Response sentence generation means
1606, 1706, 1807, 1906, 2007, 2107, 2212, 2312, 2412, 2512, 2612, 2712, 2812, 2811, 2912 Information collecting means
1607, 1707, 1808, 1907, 2008, 2108, 2211, 2311, 2411, 2511, 2611, 2711, 2811, 2911 Reception information storage means
1608, 1708, 1810, 1909, 2010, 2110 Agent switching means
1609 Sound recording DB
1610, 1710, 1911, 2210, 2310, 2410, 2510, 2610, 2710, 2810, 2910 Text-to-speech synthesis means
1611, 1711, 1815, 1914, 2015, 2115 Image generation means
1709, 1811, 1910, 2011, 2111 Recording audio database
1714 Common sense database
1805 Dialog history database
1806, 1905, 2006, 2106 Emotion estimation means
1812, 1911, 2012, 2112, 2210, 2310 Text-to-speech synthesis means
2005, 2105 Image recognition means
2209 Time monitoring means
2313, 2213, 2413, 2513, 2613, 2713, 2813, 2913 Multiple information sources
2309, 2509, 2609, 2709, 2809, 2909 Search upper limit condition investigation means
2514 Storage area for past received information
2515, 2616, 2716, 2816, 2916 Agent speech database
2614 Keyword genre storage area of past received information
2615 Keyword genre assigning means
2714: Verb and object storage areas for past received information search conditions
2715: Verb and object extraction means for search conditions
2814 Higher concept storage area of search keyword for past received information
2815 Means for assigning superordinate concepts of search keywords
2914 Focus storage area of past received information
2915: Focus extraction means for search information

Claims (2)

Storage means for storing search conditions;
Input means for entering new search conditions;
Gate means for storing new search conditions input by the input means;
Storage control means for additionally storing new search conditions stored in the gate means in the storage means;
A search unit that autonomously searches for information from an information source using the search condition stored in the storage unit,
The storage control means compares the meaning of the new search condition stored in the gate means with the meaning of the search condition already stored in the storage means based on the thesaurus, and the two contradict each other. The search condition already stored in the storage means is deleted from the storage means and the search condition having a meaning inconsistent with the meaning of the new search condition stored in the gate means is stored in the gate means. A new search condition is additionally stored in the storage means . Storage means for storing search conditions;
Input means for entering new search conditions;
Gate means for storing new search conditions input by the input means;
Storage control means for additionally storing new search conditions stored in the gate means in the storage means;
A search unit that autonomously searches for information from an information source using the search condition stored in the storage unit,
The storage control means compares the meaning of a new search condition stored in the gate means based on a thesaurus dictionary with the meaning of a search condition already stored in the storage means, and the two overlap. The information search apparatus is characterized in that the search condition stored in the storage means is maintained without additionally storing the new search condition stored in the gate means in the storage means .

Images