JP2019121212A - Information provision system and information provision device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an information providing system and an information providing device capable of providing information desired by a user even if the content of the user's utterance is unclear. SOLUTION: Successful examples of providing information on the utterance contents of past users are collected from a plurality of users together with the characteristics of the user, classified according to the characteristics of the same or similar users, and the successful examples are linked and stored. The grouping DB 14 is created. Then, when the utterance content of the user requesting the information is unclear, among the successful examples stored in the grouping DB 14, the characteristics of the user who is the same as or similar to the characteristics of the user who made the utterance are linked. Configure to provide information based on successful cases. [Selection diagram] Fig. 5

Description

  The present invention relates to an information providing system and an information providing apparatus that provide information according to a user's speech.

  Conventionally, in various information terminals (hereinafter referred to as navigation devices etc.) such as in-vehicle navigation devices, mobile phones, smart phones, tablet-type terminals, personal computers etc., whether information about map images and points are stored in various storage devices Alternatively, it can be obtained by downloading from a server or the like and provided to the user. In addition, as the information on the point, for example, it is possible to provide information on the name, the position, the business hours, the usage charge and the like on the store and the public facilities. Furthermore, it is possible to provide various information in addition to information on map images and points

  Also, in recent years, it has been practiced to utter the conditions of information desired by the user by voice, to recognize the voice on the system side, and to extract and provide the information corresponding to the conditions. However, in information retrieval using speech, there is a problem that it is difficult for the system to accurately grasp the condition of information desired by the user due to factors such as the presence of homonyms and the ambiguity of the user's utterance content. . Therefore, for example, in JP-A-2015-219225, when the user utters a search word, if the search word can be determined from the voice uttered, additional information is added to the search word character string. It is disclosed about creating the added database and using the created database for selection of search word candidates from the next time.

JP, 2015-219225, A (page 8-9, FIG. 2)

  Here, in the technology described in Patent Document 1 described above, the created database is a database in which a place name and a genre are linked to a search word character string. Therefore, if it is possible to specify the place name and genre included in the user's utterance content, it is possible to select an appropriate search word using the database, but the user's utterance content is unclear and is included in the utterance content When a place name or a genre can not be specified, there was a problem that an appropriate search word could not be set.

  The present invention has been made to solve the above-mentioned conventional problems, and the user's speech content is unclear by linking the characteristics of the user and a successful example of past information provision and creating a database. It is another object of the present invention to provide an information providing system and an information providing apparatus which enable a user to provide desired information.

  In order to achieve the above object, an information providing system according to the present invention recognizes information uttered by a user and provides information according to the request of the user, and information on the uttered content of the user in the information providing means Success case collection means for collecting successful cases of provision together with the characteristics of the user from a plurality of users, success case storage means for associating and storing the successful cases by classifying the same or similar similar user characteristics The information providing means is a characteristic of the user identical or similar to the characteristic of the user who made the utterance among the successful cases stored in the successful case storing means when the user's utterance content is unclear Provide information on the basis of the success cases linked.

  In addition, the information providing apparatus according to the present invention recognizes an utterance content of the user and provides information according to the user's request, and a successful example of information provision for the user's utterance content in the information providing unit. Means for collecting success cases from the plurality of users together with the characteristics of the user, success case storage means for storing the success cases in association by classifying the same or similar user characteristics, and providing the information The means is associated with the characteristic of the user identical or similar to the characteristic of the user who made the utterance among the successful cases stored in the successful case storage means when the user's utterance content is unclear Provide information based on successful examples.

  According to the information providing system and the information providing apparatus of the present invention having the above-described configuration, the user's utterance content is unclear by linking the characteristics of the user and a successful example of past information provision and creating a database Also, it is possible to appropriately identify and provide information desired by the user from corresponding past successful cases.

BRIEF DESCRIPTION OF THE DRAWINGS It is the schematic block diagram which showed the information-provision system which concerns on this embodiment. It is a block diagram showing composition of an information service system concerning this embodiment. It is the figure which showed an example of the information memorize | stored in user characteristic DB. It is the figure which showed an example of the information memorize | stored in speech success example DB. It is the figure which showed the data structure of grouping DB. It is a block diagram showing typically a control system of a navigation device concerning this embodiment. It is a flowchart of DB creation processing program concerning this embodiment. It is a flowchart of the information provision processing program which concerns on this embodiment. It is the figure which showed an example of the provision method of information. It is a figure explaining an analysis example of a user's utterance contents. It is a figure explaining an analysis example of a user's utterance contents.

  Hereinafter, an information providing system according to the present invention will be described in detail based on an embodiment embodied with reference to the drawings. First, a schematic configuration of the information providing system 1 according to the present embodiment will be described with reference to FIGS. 1 and 2. FIG. 1 is a schematic configuration view showing an information providing system 1 according to the present embodiment. FIG. 2 is a block diagram showing the configuration of the information providing system 1 according to the present embodiment.

  As shown in FIG. 1, the information providing system 1 according to the present embodiment includes a server device (information providing device) 3 provided in the information providing center 2 and a navigation device 5 which is a communication (guidance) terminal mounted on the vehicle 4. And have basically. In addition, the server device 3 and the navigation device 5 are configured to be able to transmit and receive electronic data to each other via the communication network 6. Note that, instead of the navigation device 5, for example, a mobile phone, a smartphone, a tablet terminal, or a personal computer may be used.

  Here, the server device 3 included in the information provision center 2 has a DB in which various types of information that can be provided to the vehicle 4 is stored, extracts the corresponding information according to the request from each vehicle 4, and distributes it. It is an information distribution server to (provide). In this embodiment, in particular, point information on points (facility) in the whole country and traffic information (congestion, accidents, presence of construction, etc.) of each road in the whole country are targeted for distribution. In particular, when distributing the information, the server device 3 according to the present embodiment uses the voice recognition device to specify the information requested by the user based on the user's uttered voice.

  On the other hand, the server device 3 collects successful examples of information provision for the user's utterance in the past, and also creates a database in which the characteristics of the user and the successful examples of information provision are linked based on the collected information. Then, the created database is used to specify information to be distributed when the user's utterance content is unclear as described later.

  On the other hand, the navigation device 5 is mounted on the vehicle 4 and displays a map around the position of the vehicle based on the stored map data, displays the current position of the vehicle on the map image, or sets a set guidance route. It is an in-vehicle device that performs movement guidance along. The navigation device 5 also guides the user about traffic information such as traffic congestion received from the server device 3 or the like and point information on a point (facilities). The details of the navigation device 5 will be described later.

  Further, the communication network 6 includes a large number of base stations arranged all over the country, and a communication company which manages and controls each base station, and the base station and the communication company are mutually connected by wire (optical fiber, ISDN etc.) or wirelessly. It is configured by connecting. Here, the base station has a transceiver (transceiver) that communicates with the navigation device 5 and an antenna. Then, while the base station performs wireless communication among the communication companies, it relays the communication of the navigation device 5 which is at the end of the communication network 6 and in the range (cell) to which the radio wave of the base station can reach. Have a role to

  Subsequently, the configuration of the server device 3 in the information providing system 1 will be described in more detail with reference to FIG. As shown in FIG. 2, the server device 3 includes a server control ECU 11, a user characteristic DB 12 as information recording means connected to the server control ECU 11, an utterance success example DB 13, a grouping DB 14, a server side map DB 15, and a server. And a side communication device 16.

  The server control ECU 11 (electronic control unit) is an electronic control unit that controls the entire server device 3 and is used as a working memory when the CPU 21 as an arithmetic device and control device and the CPU 21 perform various arithmetic processing. In addition to the RAM 22 and control programs, a ROM 23 on which a DB creation processing program (FIG. 7), an information providing processing program (see FIG. 8), etc. described later is recorded, a flash memory 24 etc. Internal storage device. The server control ECU 11 has various means as a processing algorithm together with the ECU of the navigation device 5 described later. For example, the information providing means recognizes the user's speech content and provides information according to the user's request. The success case collecting means collects a successful case of providing information to the user's utterance content from a plurality of users along with the characteristics of the user. The success case storage unit stores the success cases in association with each other by dividing the same or similar user characteristics.

  Moreover, user characteristic DB12 is a memory means to memorize | store the characteristic of the user for every user (passenger of a vehicle) collected from each vehicle 4 which drive | works the whole country. In the present embodiment, (a) age (b) gender (c) action range is included as the characteristic of the user. Furthermore, (c) the action range includes, in particular, an area with a home (for example, a city or town), an average movement distance per day, and a past travel route.

  FIG. 3 is a diagram showing an example of information stored in the user characteristic DB 12. As shown in FIG. 3, the user characteristic DB 12 includes information on the above (a) to (c) for each user. For example, in addition to the user characteristic DB 12 shown in FIG. 3 being a male 31 to 40 years old as the user characteristic for user A, having a home in a city, and having an average moving distance of 50 km per day The link ID for identifying the past travel route is stored. Similarly, user characteristics of other users are also stored. The user characteristic DB 12 is periodically (eg, every 24 hours) updated based on the information acquired from the navigation device 5. In addition, it is not necessary to necessarily include all the information of (a)-(c) as a user characteristic, for example, only (a) and (b) may be sufficient.

  On the other hand, the speech success example DB 13 is storage means for cumulatively storing successful examples of the information provision for the user's speech in the past. As described above, when delivering information, the server device 3 according to the present embodiment uses the voice recognition device to identify the information requested by the user based on the user's uttered voice and perform delivery. Then, the server device 3 collects the combination of the user's utterance content and the provided information as a successful example of the information provision, when the information provision can be performed without particularly asking the user. . In the present embodiment, (d) Uttered contents (e) Information provided (f) Utterance date and time (for example, morning, noon, evening, night) and (g) Utterance location are included as successful examples of information provision. Be

  FIG. 4 is a diagram showing an example of information stored in the speech success example DB 13. As shown in FIG. 4, the speech success example DB 13 includes information on the above (d) to (g) for each user. Furthermore, the information of (a) to (c) related to the user characteristic stored in the user characteristic DB 12 is also stored. For example, in the speech success example DB 13 shown in FIG. 4, the user A uttered “Tell me the traffic information of city a” around 町 town in the evening as a successful example of the information provision. An example is provided in which traffic information is provided, especially around ○ town. Similarly, other successful cases are also stored. The speech success example DB 13 is updated periodically (for example, every 24 hours) or whenever information provision to the user is successful.

  On the other hand, grouping DB14 is a database produced | generated by statistics each information stored in user characteristic DB12 and speech success example DB13. In particular, in the present embodiment, linking of successful examples of information provision is performed with respect to the same or similar user characteristics, and a database indicating the relationship between the user characteristics and the information requested by the user is provided. Then, the server device 3 provides information to the user as described later based on the created grouping DB 14. For example, FIG. 5 is a diagram showing an example of data stored in the grouping DB 14.

  As shown in FIG. 5, the grouping DB 14 groups users according to the same or similar user characteristics. Then, successful examples of the information provision are linked and stored for each group. For example, as shown in FIG. 3, the user A and the user B have the same age and gender, and the action range is similar. Therefore, the user A and the user B are determined to have the same or similar user characteristics, and are classified into the same group. Specifically, among the items (a) to (c) indicating the user characteristics, when the predetermined number (for example, two or more) of the items match, it is considered to have the same or similar user characteristics. Moreover, what is stored as a successful example of information provision is the information regarding said (d)-(g).

  In the example shown in FIG. 5, successful examples of providing information are classified and stored in association with identical or similar user characteristics. However, successful examples of providing information are classified in identical user characteristics. You may attach and memorize. Specifically, when all the items in the items (a) to (c) indicating the user characteristics match, it is considered that the user characteristics are the same.

  The created grouping DB 14 indicates the relationship between the characteristics of the user and the information requested by the user. Therefore, the server device 3 can grasp information which tends to be requested for each characteristic of the user, using the information stored in the grouping DB 14 particularly when the content of speech of the user is unclear. Then, information is provided in consideration of those tendencies. Details will be described later.

  On the other hand, the server-side map DB 15 is storage means for storing server-side map information 25 which is map information of the latest version registered based on input data and input operation from the outside. Here, the server-side map information 25 basically has the same configuration as the map information stored in the navigation device 5, and various types of route networks, route guidance, and map display, including the road network. It consists of information. For example, network data including nodes and links representing a road network, link data 26 for roads (links), node data for node points, intersection data for each intersection, point data 27 for points such as facilities, a map It comprises map display data, search data for searching for a route, search data for searching for a point, and the like.

  On the other hand, the server side communication device 16 is a communication device for communicating with the navigation device 5 of each vehicle 4 to which information is to be distributed via the communication network 6. In addition to the navigation device 5, traffic consisting of traffic jam information, regulation information, traffic accident information, etc. transmitted from the Internet network, a traffic information center, for example, a VICS (registered trademark: Vehicle Information and Communication System) center, etc. It is also possible to receive information.

  Next, the schematic configuration of the navigation device 5 will be described using FIG. 6. FIG. 6 is a block diagram schematically showing a control system of the navigation device which is the navigation device 5 according to the present embodiment.

  As shown in FIG. 6, the navigation device 5 according to the present embodiment includes a current position detection unit 31 for detecting the current position of the vehicle 4 on which the navigation device 5 is mounted, and a data recording unit 32 in which various data are recorded. A navigation ECU 33 for performing various arithmetic processing based on the input information, an operation unit 34 for receiving an operation from the user, and a liquid crystal display 35 for displaying a map and a guide route to a destination for the user; A speaker 36 for outputting voice guidance regarding route guidance, a DVD drive 37 for reading a DVD as a storage medium, a communication module 38 for communicating between the server device 3 and a VICS center, etc. And a speech recognition unit 39 for analysis. In addition, the navigation device 5 is connected to a microphone 40 or the like for recording and collecting speech voices of occupants in the vehicle via an on-vehicle network such as CAN.

Below, each component which comprises the navigation apparatus 5 is demonstrated in order.
The current position detection unit 31 includes the GPS 41, the vehicle speed sensor 42, the steering sensor 43, the gyro sensor 44 and the like, and can detect the current position and direction of the vehicle, the traveling speed of the vehicle, the current time and the like. . Here, in particular, the vehicle speed sensor 42 is a sensor for detecting the movement distance and the vehicle speed of the vehicle, generates a pulse according to the rotation of the drive wheel of the vehicle, and outputs a pulse signal to the navigation ECU 33. And navigation ECU33 calculates the rotational speed and moving distance of a driving wheel by counting the pulse which generate | occur | produces. The navigation device 5 does not have to include all the four types of sensors described above, and the navigation device 5 may have only one or more of these sensors.

  Further, the data recording unit 32 reads a hard disk (not shown) as an external storage device and a recording medium, a terminal side map DB 45 recorded on the hard disk, a user information DB 46 and a predetermined program etc. And a recording head (not shown) which is a driver for writing data. The data recording unit 32 may be configured by a non-volatile memory, a memory card, or an optical disk such as a CD or a DVD instead of the hard disk.

  Here, the terminal side map DB 45 is a storage means in which map information used for route search and travel guidance in the navigation device 5 is stored. Note that the terminal-side map DB 45 is not necessarily required in the case of acquiring map information from an external server.

  In addition, the user information DB 46 is a storage unit in which information on an occupant of a vehicle that is a user is stored. Specifically, the age, sex, position of home, average travel distance per day, past travel route and the like are stored. The information stored in the user information DB 46 is periodically transmitted to the server device 3 as information for specifying the characteristics of the user.

  On the other hand, the navigation ECU (Electronic Control Unit) 33 is an electronic control unit that controls the entire navigation device 5 and is a working memory when the CPU 51 as an arithmetic device and control device and the CPU 51 perform various arithmetic processing. In addition to the RAM 52 that stores route data etc. when a route is searched, and a control program, it is read from ROM 53 and ROM 53 where information providing processing program (see FIG. 8) and the like described later are recorded. An internal storage device such as a flash memory 54 for storing the program is provided.

  The operation unit 34 is operated when inputting a departure place as a traveling start point and a destination as the traveling end point, and has a plurality of operation switches (not shown) such as various keys and buttons. And navigation ECU33 performs control in order to perform various corresponding operations based on the switch signal outputted by pressing etc. of each switch. The operation unit 34 may have a touch panel provided on the front surface of the liquid crystal display 35. If there is a microphone and a voice recognition device, the operation unit 34 may be omitted.

  In addition, the liquid crystal display 35 includes a map image including a road, traffic information, operation guidance, an operation menu, key guidance, a guidance route from the departure place to the destination, guidance information along the guidance route, news, weather forecast, The time, mail, television program etc. are displayed. In particular, in the present embodiment, it is also used to display traffic information such as traffic congestion received from the server device 3 according to the user's uttered voice, point information on points (facilities), and the like. Instead of the liquid crystal display 35, HUD or HMD may be used.

  Further, the speaker 36 outputs voice guidance for guiding traveling along the guidance route based on an instruction from the navigation ECU 33, and guidance for traffic information. In particular, in the present embodiment, it is also used to output traffic information such as traffic congestion received from the server device 3 according to the user's uttered voice, point information on points (facilities), and the like.

  Also, the DVD drive 37 is a drive that can read data recorded on a recording medium such as a DVD or a CD. Then, based on the read data, reproduction of music and video, update of the terminal side map DB 45, and the like are performed. In place of the DVD drive 37, a card slot for reading and writing a memory card may be provided.

  The communication module 38 is, for example, a communication device for receiving information such as map update information, support information, traffic information and the like transmitted from the server device 3, VICS center, map distribution center, etc. And DCM apply.

  Further, the voice recognition unit 39 is a device that analyzes the voice recorded and acquired by the microphone 40 installed in the car. Then, in the navigation device 5 according to the present embodiment, the voice recognition unit 39 recognizes the voice uttered by the occupant of the vehicle, and the recognized voice content is transmitted to the server device 3. However, the voice recognition may be performed on the server device 3 side. In that case, the recorded voice data is transmitted to the server device 3.

  Also, the microphone 40 is a device that converts sound into an electric signal, and the sound converted into the electric signal is transmitted to the voice recognition unit 39. Here, the microphone 40 is attached to the upper surface of the instrument panel, and is installed so that the sound collection direction is the seat direction.

  Subsequently, a DB creation processing program executed by the CPU 21 in the server device 3 constituting the information providing system 1 according to the present embodiment having the above configuration will be described based on FIG. FIG. 7 is a flowchart of a DB creation processing program according to the present embodiment. Here, the DB creation processing program is executed at predetermined time intervals (for example, every 24 hours), and a DB linking the user's characteristic and the successful example of the information provision is created by statistics on the successful examples of the past information provision. Is a program that The programs shown in the flowcharts of FIGS. 7 and 8 below are stored in the RAM 52 or ROM 53 included in the navigation ECU 33 or in the RAM 22 or ROM 23 included in the server device 3 and executed by the CPU 51 or CPU 21. Ru.

  First, in step (hereinafter abbreviated as S) 1 in the DB creation processing program, the CPU 21 updates the user characteristic DB 12 based on information collected from the navigation device 5. The user characteristic DB 12 is a database storing characteristics of each user as described above, and specifically includes (a) age (b) gender (c) action range as shown in FIG. In particular, (c) the action range is appropriately updated based on the information periodically transmitted from the navigation device 5.

  Next, in S2, the CPU 21 newly generates a successful example of information provision based on the result of the information provision performed by the information provision processing program (FIG. 8) described later from the previous processing time to the current time. Store in In particular, in the present embodiment, a case where the provision of information can be performed without asking the user a question is regarded as a successful example of the provision of information. The speech success example DB 13 includes (d) speech contents (e) information provided (f) speech date and time (for example, morning, afternoon, evening, night) and (g) speech place as shown in FIG. It is divided and stored for each.

  Subsequently, in S3, the CPU 21 updates the grouping DB 14 by statistics of the information stored in the user characteristic DB 12 updated in S1 and the utterance success example DB 13 updated in S2. The grouping DB 14 groups users according to identical or similar user characteristics as shown in FIG. 5 and stores successful examples of information provision linked to each group. The grouping DB 14 updated in S3 indicates the relationship between the characteristics of the user and the information requested by the user. Therefore, as described later, the server device 3 can grasp information which tends to be requested for each characteristic of the user by using the information stored in the grouping DB 14 when the content of speech of the user is unclear. Become.

  Next, an information providing processing program executed in the server device 3 and the navigation device 5 constituting the information providing system 1 according to the present embodiment will be described based on FIG. FIG. 8 is a flowchart of an information providing processing program according to the present embodiment. Here, the information providing processing program is a program that is executed after the ACC power supply (accessory power supply) of the vehicle 4 is turned on, and provides various information in response to the request of the user who is the vehicle occupant.

First, an information providing processing program executed by the navigation device 5 will be described.
In S11, the CPU 51 analyzes the voice data collected by the microphone 40 with the voice recognition unit 39 to determine whether or not there is an utterance of a user who desires to provide information in the car. The information providing system 1 according to the present embodiment is targeted for providing information on point information on points (facilities) in the whole country and traffic information of each road in the whole country (congestion, accidents, presence or absence of construction, etc.) I assume. However, it is naturally possible to make other information the target of provision.

  Then, when it is determined that there is an utterance of a user who wants to provide information in the car (S11: YES), the process proceeds to S12. On the other hand, when it is determined that there is no speech of the user who desires to provide the information in the car (S11: NO), the information providing processing program is ended without providing the information.

  In S12, the CPU 51 transmits an information request instruction instructing the server device 3 to request information. The information request instruction includes a user ID identifying an occupant (user) of the vehicle in which the navigation device 5 is installed, and the content (for example, text data) of the user's speech accepted in S11. Thereafter, extraction and distribution of information desired by the user are performed in the server device 3 which has received the information request instruction from the navigation device 5 as described later (S22 to S29).

  The voice recognition may be performed on the server device 3 side. In that case, it is also possible to transmit to the server device 3 voice data collected instead of the contents of the utterance in S12.

  Subsequently, in S13, the CPU 51 receives the information distributed from the server device 3 in response to the transmission of the information request instruction signal. The information received in S13 is information corresponding to the content of the user's speech accepted in S11, and is information desired by the user. It specifies by the process of below-mentioned S22-S29.

  Thereafter, in S14, the CPU 51 outputs the information received in S13 using the liquid crystal display 35 or the speaker 36. For example, FIG. 9 is a diagram showing an example of the information output by the navigation device 5 in S14. In addition, in FIG. 9, the facility guidance screen 61 displayed on the liquid crystal display 35 is shown when outputting the information regarding the gas station which is around the home.

As shown in FIG. 9, the facility guidance screen 61 includes two display areas, a left screen 62 for displaying a map image, and a right screen 63 for displaying the facility names of the searched facilities in a list.
Here, the right screen 63 is provided with an information display space 64 for displaying the names of gas stations around the corresponding home in a list. Also, when the name is selected by the user, detailed information (distance from own vehicle position, opening hours, address, etc.) of the gas station corresponding to the selected name is displayed, or the gas station is set as the destination Execute the process to
On the other hand, on the left screen 62, a map image 66 is displayed. Further, on the map image 66, POI marks 71 to 76 for specifying the position of the gas station whose name is displayed in the information display space 64 are superimposed and displayed.

Next, an information providing processing program executed by the server device 3 will be described.
First, in S21, the CPU 21 determines whether or not there is transmission of an information request instruction instructing a request for information from each vehicle 4 traveling the whole country.

  Then, when it is determined that the information request instruction has been transmitted (S21: YES), the information request instruction to be transmitted is received (S22). The information request instruction signal includes a user ID for identifying an occupant (user) of the vehicle that has requested the information, and the content of the user's utterance (for example, text data).

  On the other hand, when it is determined that the information request instruction has not been transmitted (S21: NO), the information providing processing program is ended.

  At S23, the CPU 21 analyzes, among the information request instructions received at S22, particularly the content of the user's speech. Then, in S24, the CPU 21 determines, as a result of the analysis in S23, whether the uttered content of the user is unclear, that is, whether the information desired by the user can not be specified from the uttered content.

Hereinafter, the analysis processing of the utterance content in S23 will be described in more detail.
First, as shown in FIG. 10, the CPU 21 divides the utterance content into clauses. For example, in the example shown in FIG. 10, the user's utterance content is "Teach traffic information of a city", and is divided into "a city's", "traffic information", and "Teach me".
Next, items (conditions) necessary to specify the information desired by the user are extracted from each of the divided clauses. For example, in the example shown in FIG. 10, "a city's" and "traffic information" are extracted.
Then, based on the extracted clause, it is determined whether the user can specify desired information. Specifically, it is first determined which of the traffic information and the point information is desired. Furthermore, in the case of traffic information, it is determined which area of traffic information is desired. In addition, in the case of point information, it is determined which point of point information is desired.

  In the example shown in FIG. 10, the user can determine from the clause of "traffic information" that the request object of information is "traffic information". Moreover, it can be determined that the user desires traffic information of "a city" from the phrase "of a city". However, the corresponding area is wide in a city, and it can not be identified from the contents of utterance what traffic information of a city is desired. Therefore, it is determined that the utterance content of "Teach the traffic information of city a" is unclear, that is, it is not possible to specify the information desired by the user from the utterance content.

  On the other hand, the example shown in FIG. 11 is an example in the case where the user's speech content is "Where is the gas station?". It can be determined from the phrase "Where?" That the target object of the user's information request is "point information". Also, from the phrase "gas station", it can be determined that the user wants point information of "gas station". However, it can not be specified from the utterance content what kind of name of a gas station or information about a gas station in which area is desired. Therefore, it is determined that the utterance content of "Where is the gas station?" Is unclear, that is, the user can not specify the desired information from the utterance content.

  Then, if it is determined as a result of the analysis in S23 that the user's utterance content is unclear, that is, it is determined that the user's desired information can not be specified from the utterance content (S24: YES), the process proceeds to S25. . On the other hand, as a result of the analysis in S23, when it is determined that the user's utterance content is clear, that is, it is possible to specify the information desired by the user from the utterance content (S24: NO), the process proceeds to S28.

  Thereafter, in S28, the CPU 21 extracts the information desired by the user specified from the user's utterance content from the server-side map DB 15, and distributes the extracted information to the navigation device 5 of the request source. For example, when it is specified that the information desired by the user is point information on a gas station in the vicinity of the home, information on the gas station in the vicinity of the user's home is extracted from the server side map DB 15. And deliver. The traffic information may be acquired by communication from an external server device such as a VICS center or a probe center. Further, the combination of the present user's speech content and the provided information is stored in the speech success example DB 13 as a successful example of the information provision (S2).

  On the other hand, in S25, the CPU 21 reads the information stored in the grouping DB 14. The grouping DB 14 is created by the above-mentioned DB creation processing program (FIG. 7), and is divided into groups for each identical or similar user characteristic as shown in FIG. It is a database in which the characteristics of the storage user and the successful example of the information provision are linked.

  Next, in S26, the CPU 21 determines whether or not there is a successful example of the group including the user of the information request source who has requested the information in the grouping DB 14. The user of the information request source is identified by the user ID included in the information request instruction received in S22. For example, in the case where the grouping DB 14 shown in FIG. 5 is stored, when the user who has requested information is the user A, a success example of the group G1 including the user A is stored. It is determined that the

  Then, when it is determined that there is a successful example of the group including the user of the information request source who has requested the information in the grouping DB 14 (S26: YES), the process proceeds to S29. On the other hand, when it is determined that the group DB 14 does not have a successful example of the group including the information request source user who has requested information (S26: NO), the process proceeds to S27.

  In S27, the CPU 21 performs an inquiry process. Specifically, a question for clarifying a portion determined to be unclear is output through the navigation device 5. For example, when it is unclear which area the user wants traffic information for, it is output the question "which area do you want traffic information for?". Then, the user's uttered content uttered as a question answer is acquired via the navigation device 5. The query processing is repeated until the user can specify the desired information.

  Thereafter, in S28, the CPU 21 extracts, from the server-side map DB 15, the information desired by the user specified from the content of the user's speech. The traffic information may be acquired by communication from an external server device such as a VICS center or a probe center. Then, the extracted information is distributed to the navigation device 5 of the request source (S31).

  On the other hand, in S29, among the success examples of the group including the information request source user who requested the information, the success example of the utterance content identical or similar to the utterance content of the user received in S22 is particularly in the grouping DB 14 It is determined whether the In addition, when the utterance contents are similar, for example, the utterance contents to be compared are each divided by a clause, and the utterance contents are similar when the phrases considered to indicate the information desired by the user are partially or completely common. I reckon. For example, when the utterance content of the user received in S22 is "Teach traffic information of city a", a successful example of the utterance content including "of a city" and "traffic information" is displayed in the grouping DB 14 If there is, it is determined that there is a successful example of the same or similar utterance content in the grouping DB 14.

  Then, when it is determined that there is a successful example of the utterance content identical or similar to the user's utterance content among the successful examples of the group including the information request source user (S29: YES), the process proceeds to S30. Do. On the other hand, if it is determined that there is no successful example of the utterance content identical to or similar to the user's utterance content among the successful examples of the group including the user of the information request source (S29: NO), the process proceeds to S27. And transition.

  In S30, the CPU 21 extracts, from the server-side map DB 15, the information provided in the success example of the utterance content most similar to the user's utterance content among the success examples of the group including the information request source user who requested the information. . The extracted information is information provided when another user having the same or similar user characteristics in the past has similar utterance content, and it can be inferred that the information matches the information requested by the current user. However, for information that changes with the passage of time, such as traffic information, the latest information at the current time is acquired. Further, the traffic information may be acquired by communication from an external server device such as a VICS center or a probe center.

  Thereafter, in S31, the CPU 21 distributes the information extracted in S30 to the navigation device 5 of the request source. Thereafter, the information distributed in the navigation device 5 is output (S14).

In addition to the content of the utterance, the place where the utterance is performed may be considered.
For example, in addition to the user ID and the user's utterance content in S22, the CPU 21 acquires from the navigation device 5 also the place where the utterance is performed.
Thereafter, when it is determined that the user's uttered content is unclear (S24: YES), this is a success example of a group including the information request source user who requested the information in S26, and the utterance is a line It is determined whether or not there is a linked successful example of the same place as or a similar place to the received place in the grouping DB 14. The places where the utterances are performed are similar to, for example, places within a predetermined distance, places of the same genre, and the like.
As a result, it is possible to more accurately identify the information desired by the user, also taking into consideration the place where the speech has been made.

On the other hand, the time (time zone, day of the week, etc.) when the utterance is performed may be considered in addition to the utterance content.
For example, in addition to the user ID and the user's utterance content in S22, the CPU 21 acquires from the navigation device 5 also the time zone in which the utterance was performed (for example, morning, daytime, evening, night).
Thereafter, when it is determined that the user's uttered content is unclear (S24: YES), this is a success example of a group including the information request source user who requested the information in S26, and the utterance is a line It is determined whether there is a linked successful example of the same place as or a similar place to the received time zone in the grouping DB 14. The case in which the time zones in which the speech has been performed is similar corresponds to, for example, a predetermined time difference or the like.
As a result, it is possible to more accurately identify the information desired by the user, also taking into consideration the time when the utterance was made.

Furthermore, it is possible to consider both where the speech was made and when the speech was made.
For example, in addition to the user ID and the user's utterance content in S22, the CPU 21 acquires from the navigation device 5 also the place and time when the utterance is performed.
Thereafter, when it is determined that the user's uttered content is unclear (S24: YES), this is a success example of a group including the information request source user who requested the information in S26, and the utterance is a line It is determined whether there is a linked successful example of the same place or time as the received place and time or in the grouping DB 14.
This makes it possible to more accurately identify the information desired by the user.

  In addition, in the navigation apparatus 5 instead of the server apparatus 3, the processes of S22 to S31 may be executed. In that case, the user characteristic DB 12, the speech success example DB 13 and the grouping DB 14 are distributed from the server device 3 to the navigation device 5. The database creation processing program (FIG. 7) may also be executed by the navigation device 5.

  As described above in detail, in the information providing system 1 and the server device 3 according to the present embodiment, successful examples of the information provision for the utterance content of the user in the past are collected from a plurality of users together with their characteristics. A grouping DB 14 is created that is divided into each similar user characteristic and stores successful examples in association (S1 to S3). Then, when the utterance content of the user requesting the information is unclear, among the success examples stored in the grouping DB 14, the characteristics of the user identical or similar to the characteristics of the user who made the utterance are linked. Since information is provided based on successful examples (S22 to S31), even if the user's utterance content is unclear, it is possible to appropriately identify and provide information desired by the user from the corresponding past successful examples. It becomes possible.

The present invention is not limited to the above embodiment, and it is needless to say that various improvements and modifications can be made without departing from the scope of the present invention.
For example, in the present embodiment, one server device 3 performs the process of creating each DB of the user characteristic DB 12, the speech success example DB 13 and the grouping DB 14 and the process of providing information, but the process of creating each DB The processing for providing information may be performed by different server devices. For example, the server device 3 may receive information provided by each DB created by another server device.

  Further, in the present embodiment, the information providing system 1 is intended to provide point information on points (facility) in the whole country and traffic information (congestion, accidents, presence or absence of construction, etc.) of each road in the whole country. Information can also be provided. For example, there is information on a guide route, information on a vehicle, and the like.

  Moreover, although the execution subject of the DB creation processing program shown in FIG. 7 is the server device 3 in the present embodiment, the navigation device 5 may be configured to execute part or all. Further, instead of the navigation device 5, it is possible to configure the information providing system 1 with another device having an information providing function. For example, a mobile phone, a smartphone, a tablet terminal, a personal computer, etc. are possible. For example, in the case of using a smartphone, it is possible to include information on a website, SNS, a user's schedule, an email, etc. as information to be provided.

  In addition, although the embodiment in which the information providing system according to the present invention is embodied has been described above, the information providing system can also have the following configuration, in which case the following effects can be obtained.

For example, the first configuration is as follows.
A plurality of information providing means (21) for providing information according to the user's request by recognizing the user's utterance contents, and a plurality of successful examples of information provision for the user's utterance contents in the information providing means together with the characteristics of the user A success case collection means (21) collected from the users of the above, and a success case storage means (21) for associating and storing the success cases divided into the characteristics of the same or similar users, Among the successful cases stored in the successful case storing means, the information providing means ties the user's characteristics identical or similar to the characteristics of the user who made the speech, when the user's utterance content is unclear. Provide information based on the success stories attached.
According to the information providing system having the above configuration, by correlating the characteristics of the user with the past successful cases of information provision and creating a database, even if the user's utterance content is unclear, the corresponding past successful cases It becomes possible to appropriately identify and provide information desired by the user.

The second configuration is as follows.
When the successful case collecting means (21) can provide the information without asking the user, the combination of the user's speech content and the provided information is taken as a successful example of the information provision. collect.
According to the information providing system having the above configuration, it is possible to store an example in which the user's desired information can be appropriately provided from the past information provision results as a successful example.

The third configuration is as follows.
The said information provision means (21) is the most similar among the success examples associated with the characteristics of the user identical or similar to the characteristics of the user who uttered, when the user's uttered content is unclear Provide the information provided in the success case including the utterance content.
According to the information providing system having the above configuration, among the successful examples of the information providing in the past, the information provided when another user having the same or similar user characteristics has the most similar utterance content in the past, By assuming that the present user matches the desired information, it becomes possible to appropriately identify and provide the desired information for the user.

The fourth configuration is as follows.
The characteristics of the user include at least one of age, gender, and activity range.
According to the information providing system having the above configuration, it is possible to specify the user's characteristic from one or more items, and it is possible to specify the user's desired information according to the characteristic of the user who requests the information. .

The fifth configuration is as follows.
The successful example collecting means (21) also collects the place where the utterance was given when the information provision for the user's utterance content was successful, and the successful example storing means (21) is added to the characteristics of the user. It divides into every place where the utterance was performed, associates and stores the successful examples, and the information providing means, when the utterance content of the user is unclear, the characteristics and the utterance of the user who made the utterance Information is provided on the basis of the success example in which the characteristics of the user identical or similar to the place where the <a> was performed and the place where the speech was performed are linked.
According to the information providing system having the above configuration, by considering the place where the utterance is performed in addition to the utterance content, it is possible to more appropriately specify the information desired by the user even if the user's utterance content is unclear It is possible to

The sixth configuration is as follows.
The successful example collecting means (21) collects also the time when the utterance when the information provision for the user's uttered content is successful is performed, and the successful example storing means (21) adds to the characteristics of the user. The success cases are classified and stored for each time when the utterance is performed, and the information providing unit stores the characteristics and the utterance of the user who made the utterance when the content of the utterance of the user is unclear. The information is provided based on the successful example in which the characteristics of the user identical to or similar to the time when the event was performed and the time when the utterance was performed are linked.
According to the information providing system having the above configuration, by considering the time when the utterance is performed in addition to the utterance content, the user's desired information can be specified more appropriately even if the user's utterance content is unclear It is possible to

1 information provision system 2 probe center 3 server device 4 vehicle 5 navigation device 11 server control ECU
12 User Characteristic DB
13 Utterance Success Example DB
14 Grouping DB
21 CPU
22 RAM
23 ROM

Claims (7)

An information providing unit that recognizes user's utterance content and provides information according to the user's request;
A success case collection unit that collects, from the plurality of users, a success example of the information provision with respect to the user's utterance content in the information provision unit together with the characteristic of the user;
Success case storage means for storing the success cases linked and divided into the same or similar user characteristics;
Among the successful cases stored in the successful case storing means, the information providing means has characteristics of the user identical or similar to the characteristics of the user who made the speech, when the user's utterance content is unclear. An information providing system that provides information based on linked success cases.   The successful case collection means collects the combination of the user's utterance content and the provided information as a successful example of the information provision, when the information provision can be performed without asking the user for a question. The information provision system according to Item 1.   The information providing means is, when the user's uttered content is unclear, the most similar uttered content among the successful examples associated with the characteristics of the user identical or similar to the characteristics of the user who uttered The information providing system according to claim 2, wherein the information providing system provides information provided in a successful example including:   The information providing system according to any one of claims 1 to 3, wherein the characteristic of the user includes at least one of an age, a gender, and an action range. The success case collecting means also collects the location where the utterance was given when the information provision to the user's utterance content was successful,
The success case storage means is divided into each location where speech is given in addition to the characteristics of the user, and stores the success cases in association.
When the user's uttered content is unclear, the information providing means is a string of the characteristics of the user who uttered and the characteristics and the place of the user who performed the same utterance The information provision system according to any one of claims 1 to 4, wherein provision of information is performed based on the attached success case. The successful case collecting means also collects the time when the utterance when the information provision for the user's utterance content is successful is performed,
The successful case storage unit is divided into each time when an utterance is performed in addition to the characteristics of the user, and the successful cases are associated and stored.
When the user's uttered content is unclear, the information providing means is a string of characteristics of the uttered user and characteristics of the user same as or similar to the timing of the uttered character. The information provision system according to any one of claims 1 to 5, wherein provision of information is performed based on the attached success case. An information providing unit that recognizes user's utterance content and provides information according to the user's request;
A success case collection unit that collects, from the plurality of users, a success example of the information provision with respect to the user's utterance content in the information provision unit together with the characteristic of the user;
Success case storage means for storing the success cases linked and divided into the same or similar user characteristics;
Among the successful cases stored in the successful case storing means, the information providing means has characteristics of the user identical or similar to the characteristics of the user who made the speech, when the user's utterance content is unclear. An information providing device that provides information based on a linked success example.

Images