Location-specific support system and location-specific support method

Abstract

To identify the position of an object perceived by an inquiring subject.SOLUTION: A position identification assisting system for generating data for identifying a position is provided with an arithmetic device for performing predetermined processing, and a storage device accessible by the arithmetic device. The storage device stores integrated 3D data including attributes of stationary objects and attributes of moving objects. The arithmetic device comprises a reception unit for accepting an input of an expression of a moving object recognized by an inquiry subject; a semantic analysis unit for identifying a retrieval term for retrieving the integrated 3D data from the accepted expression of the object and generating a retrieval query including one or more area specification conditions; and a position estimating unit for retrieving the integrated 3D data using the generated retrieval query, acquiring information for narrowing down the position from the accepted expression of the moving object, and generating the information for narrowing down the position.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a position identification support system that generates information for identifying a position from the representation of an object perceived by an inquiry subject.

Background Art

[0002] Today, by using GNSS (Global Navigation Satellite System), one can know one's own position. However, in urban areas (for example, between structural buildings), radio waves from the required number of artificial satellites for positioning calculations may not be received, and the position may not be identifiable by GNSS. For this reason, there is a need to identify a position using information on an object that can be perceived by the inquiry subject. For example, even when the inquiry subject is not familiar with the local geography, such as when away from home or on a trip, and does not know the address or the name of a landmark, it is desired to accurately identify the position in the event of a traffic accident or an emergency.

[0003] As the background art in this technical field, there is the following prior art. Patent Document 1 (Japanese Patent Application Laid-Open No. 2001-133283) discloses a navigation device including a voice recognition unit that inputs voice and outputs various instruction signals, an information search unit that searches for information data from an information recording medium based on a search instruction signal input from the voice recognition unit, and a voice output unit that outputs the search result as voice. The information search unit includes a search genre discrimination unit that discriminates a signal indicating a search genre from the input search instruction signal, a search direction discrimination unit that discriminates a search instruction signal indicating a search direction, a search range setting unit that sets a search range, and a search unit that searches for the information data according to the discriminated search genre, search direction, and search range (see Claim 1).

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] Conventionally, information regarding a location (address, name of a landmark, positioning information by GPS, etc.) is input into a system, and the corresponding location is retrieved from a map information system. However, when the inquirer or operator is not familiar with the geography of the site (for example, does not know the address or the name of the landmark), it becomes difficult to perform a search using landmarks. In this case, information about an object visible to the user (for example, "a building with a red pointed roof is visible", "near a store with a blue sign") is effective for specifying the location, but such information is not registered in the map information system.

[0006] Also, even when the name of a landmark is known, if information indicating that the landmark "is visible" can be used, the location can be further narrowed down.

[0007] In the background art described above, in a navigation device, map data can be retrieved using words indicating directions such as "left" and "right" of the speaker. However, this is a method for providing variations in the expression of the destination in a situation where the position information of the speaker is known in advance, and it is not a technology that can be used in a situation where the reference position is unknown.

[0008] Furthermore, objects that can be perceived by humans include not only static landscapes, but also people, animals, and moving objects (for example, a characteristic vehicle such as a fire truck), and environmental information (for example, temperature, smell, sound) can also be perceived. Using this perceptual information, an improvement in position identification accuracy can be expected.

[0009] An object of the present invention is to realize a position identification support system that identifies a position from information about an object perceived by an inquirer.

Means for Solving the Problems

[0010] A typical example of the invention disclosed in the present application is as follows. That is, a location identification support system that generates data for identifying a location, comprising an arithmetic unit that executes predetermined processing and a storage device accessible by the arithmetic unit, wherein the storage device stores integrated 3D data including attributes of stationary objects and attributes of moving objects, and the arithmetic unit has a reception unit that receives an input of a representation of a moving object recognized by an inquiry subject, and a semantic analysis unit that specifies a search term for retrieving the integrated 3D data from the received representation of the moving object and generates a search query including one or more region designation conditions, and the arithmetic unit to searches the integrated 3D data with the generated search query, obtains information for narrowing down the location from the received representation of the moving object, and has a location estimation unit that generates the information for narrowing down the location.

Advantages of the Invention

[0011] According to one aspect of the present invention, the location can be specified from the information of the object perceived by the inquiry subject. Problems, configurations, and effects other than those described above will be clarified by the description of the following embodiments.

Brief Description of the Drawings

[0012]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Mode for Carrying Out the Invention

[0013] <Network Configuration Example> FIG. 1 is a block diagram showing the configuration of a position identification support system according to an embodiment of the present invention.

[0014] The position identification support system of this embodiment is constituted by a position identification support server 10, and the position identification support server 10 and the user terminal 30 are connected via a network.

[0015] The position identification support server 10 generates and stores integrated 3D data 113 in real time, which associates metadata 105 representing surrounding environmental information with three-dimensional data 108.

[0016] An inquirer (including a reporter other than the person receiving the service) receiving the position identification support service inputs a plurality of pieces of information such as the relative positions with perceivable stationary objects and moving objects, and surrounding environmental information (for example, "There is a coffee shop on the left hand side", "The sound of music can be heard", "A Pierrot passed by just now") to the position identification support server 10. The position identification support server 10 searches the integrated 3D data 113, calculates a position candidate range that can be estimated from each of the input information, and superimposes the calculated plurality of position candidate ranges to narrow down the position of the inquirer with a high probability.

[0017] The location-specific support server 10 provides location-specific support services, route guidance services, movement support services, etc. to individuals via the user terminal 30, provides location-specific support services to people or organizations that need to identify the location of others (e.g., command rooms of fire departments and police, information desks in large facilities), and can provide location-specific support services to robots 40 and automated guided vehicles traveling indoors.

[0018] In the solution for providing location-specific support services to individuals, by inputting information about the objects perceived by the inquirer (e.g., "There is a coffee shop on the left hand side", "I can hear a music performance", "A Pierrot just passed by") into the user terminal 30 connected to the location-specific support server 10 by the user, the location where the user is likely to be is displayed on the map. For example, when browsing a map on the Internet and the user's location information cannot be obtained by GNSS, if the location-specific support service of this embodiment is used, the user's location can be displayed on the map, and the location can be identified even if the user is unfamiliar with the local geography. In this embodiment, the object includes not only stationary landscapes, but also people, animals, and moving objects (e.g., characteristic vehicles such as fire trucks).

[0019] In the solution for providing location-specific support services to people or organizations that need to identify the location of others, by the operator (commander, information staff, etc.) listening to the information about the objects perceived by others (e.g., "There is a coffee shop on the left hand side", "I can hear a music performance", "A Pierrot just passed by") and inputting it into the user terminal 30 connected to the location-specific support server 10, the location where the other person is likely to be is displayed on the map. In the command rooms of fire departments and police receiving emergency reports, the location of the inquirer is narrowed down by the inquirer communicating the address, name of the landmark, etc. to the operator. However, if the inquirer is unfamiliar with the local geography, the operator listens to the information about the landmark visible to the inquirer to narrow down the location. However, such a method depends on the operator's on-site knowledge and skills. Therefore, with the location-specific support service of this embodiment, the location of the inquirer can be displayed on the map, and the incident location can be quickly identified for emergency reports.

[0020]

[0020] In a solution that provides a location identification support service for a robot 40 or the like, when the brightness, sound, air pressure, smell, and information on surrounding objects acquired by sensors mounted on the robot 40 are sent to the location identification support server 10, the location identification support server 10 provides candidates for the location of the robot 40. It is difficult for the robot 40 that patrols indoors to perform positioning by GNSS (Global Navigation Satellite System), and it is difficult to identify the location of a position where the surrounding three-dimensional data is measured by LiDAR and the environment is similar (for example, in an office building, an underground shopping street, a hotel corridor). Therefore, the location identification support service of this embodiment can identify the location of the robot 40 without installing beacons or markers.

[0021] The location identification support server 10 is connected to sensing devices (for example, a voice acquisition device 21, a video imaging device 22, an environmental measurement device 23), collects surrounding environmental information from these sensing devices 21, 22, and is stored in the metadata 105. The sensing devices 21, 22, and 23 may be fixedly and dispersedly installed in a predetermined area where the location identification support service is provided, or may be mounted on the robot 40 that patrols a predetermined area where the location identification support service is provided.

[0022] The user terminal 30 is composed of a computer having a processor (CPU), a memory, an auxiliary storage device, a communication interface, an input interface, and an output interface, and provides a search request input function and a screen display function. For example, the search request input function and the screen display function may be provided by a web browser executed by the user terminal 30, or may be provided by a dedicated application program executed by the user terminal 30.

[0023] FIG. 2 is a block diagram showing the physical configuration of the location identification support server 10 of this embodiment.

[0024] The location-specific support server 10 is composed of a computer having a processor (CPU) 1, a memory 2, an auxiliary storage device 3, and a communication interface 4. The location-specific support server 10 may have an input interface 5 and an output interface 6.

[0025] The processor 1 is an arithmetic unit that executes a program stored in the memory 2. By the processor 1 executing various programs, the functions of each functional unit of the location-specific support server 10 (for example, the voice analysis unit 101, the video analysis unit 102, the sensor information analysis unit 103, the information receiving unit 104, the 3D data analysis unit 106, the 3D data receiving unit 107, the facility information input unit 109, the information integration unit 111, etc.) are realized. Note that a part of the processing performed by the processor 1 when executing a program may be executed by another arithmetic unit (for example, hardware such as an ASIC or an FPGA).

[0026] The memory 2 includes a ROM which is a non-volatile memory element and a RAM which is a volatile memory element. The ROM stores unchanging programs (for example, BIOS), etc. The RAM is a high-speed and volatile memory element such as a DRAM (Dynamic Random Access Memory), and temporarily stores the programs executed by the processor 1 and the data used during the execution of the programs.

[0027] The auxiliary storage device 3 is, for example, a large-capacity and non-volatile storage device such as a magnetic storage device (HDD) or a flash memory (SSD). Also, the auxiliary storage device 3 stores the data (for example, metadata 105, three-dimensional data 108, facility information 110, dictionary data 112, integrated 3D data 113, etc.) used by the processor 1 when executing a program, and the programs executed by the processor 1. That is, the programs are read from the auxiliary storage device 3, loaded into the memory 2, and executed by the processor 1 to realize the various functions of the location-specific support server 10.

[0028] The communication interface 4 is a network interface device that controls communication with other devices (e.g., user terminal 30) according to a predetermined protocol.

[0029] The input interface 5 is an interface to which input devices such as a keyboard 7 and a mouse 8 are connected and which receives input from an operator. The output interface 6 is an interface to which output devices such as a display device 9 and a printer (not shown) are connected and which outputs the execution result of a program in a form visible to the operator.

[0030] The program executed by the processor 1 is provided to the location identification support server 10 via a removable medium (such as a CD-ROM or a flash memory) or a network and stored in the non-volatile auxiliary storage device 3 which is a non-transitory storage medium. Therefore, the location identification support server 10 may preferably have an interface for reading data from a removable medium.

[0031] The location identification support server 10 is a computer system configured physically on one computer or on a plurality of computers configured logically or physically, and may operate on a virtual computer constructed on a plurality of physical computer resources. For example, the voice analysis unit 101, the video analysis unit 102, the sensor information analysis unit 103, the information reception unit 104, the 3D data analysis unit 106, the 3D data reception unit 107, the facility information input unit 109, and the information integration unit 111 may each operate on a separate physical or logical computer, or a plurality of them may be combined and operate on one physical or logical computer.

[0032] FIG. 3 and FIG. 4 are diagrams showing the logical configuration of the location identification support server 10 of the present embodiment. FIG. 3 shows the configuration at the time of generating integrated 3D data in which metadata is associated with three-dimensional data, and FIG. 4 shows the configuration at the time of location estimation.

[0033] As shown in FIG. 3, when generating integrated 3D data, the location identification support server 10 includes an audio analysis unit 101, a video analysis unit 102, a sensor information analysis unit 103, an information reception unit 104, a 3D data analysis unit 106, a 3D data reception unit 107, a facility information input unit 109, and an information integration unit 111, and stores metadata 105, three-dimensional data 108, dictionary data 112, and integrated 3D data 113.

[0034] The audio analysis unit 101 generates the result of analyzing the acoustic signal acquired by the audio acquisition device 21. For example, the acoustic signal acquired by the audio acquisition device 21 is analyzed to identify the noise level. Also, characteristic sounds are extracted, and data with labels attached to the extracted characteristic sounds is generated. For example, if the noise level is 80 decibels or more, a label of "noisy" is assigned, and when the sound of a level crossing is extracted, labels of "level crossing" and "sound" are assigned.

[0035] The audio acquisition device 21 is a microphone that acquires acoustic signals (such as voices, music, environmental sounds, etc.), and may be fixedly installed in a distributed manner so as to cover a predetermined area where the location identification support service is provided as described above, or may be mounted on a robot that patrols a predetermined area where the location identification support service is provided.

[0036] The video analysis unit 102 generates the result of analyzing the video captured by the video capture device 22. For example, the video captured by the video capture device 22 is analyzed to extract moving objects that are not stationary, and the type (such as people, dogs, passenger cars, trucks, etc.), attributes (such as gender, clothing, etc.), actions (such as walking, running, lying down, falling, etc.), and moving speed (such as walking, running, etc.) of the extracted moving objects are analyzed. For example, analyzing that a clown is walking eastward, labels of "person", "clown", "east direction", and "walking" are assigned.

[0037] The video imaging device 22 is a camera that captures video. As described above, it may be fixedly installed in a distributed manner so as to cover a predetermined area where the position identification support service is provided, or it may be mounted on a robot that patrols a predetermined area. The video imaging device 22 may be composed of a voice acquisition device 21 and a single device (a camera with a microphone).

[0038] The sensor information analysis unit 103 generates the result of analyzing the environmental information acquired by the environmental measurement device 23. For example, it categorizes and labels the brightness, temperature, humidity, moving objects, etc. measured by the environmental measurement device 23.

[0039] The environmental measurement device 23 is a sensor that measures the environmental information of a predetermined area where the position identification support service is provided. For example, it is an illuminance sensor that measures brightness, a temperature sensor that measures temperature, a humidity sensor that measures humidity, a LiDAR that detects moving objects, etc.

[0040] The information receiving unit 104 combines the analysis results output from the voice analysis unit 101, the video analysis unit 102, and the sensor information analysis unit 103 based on the position information associated with the ID of the observed sensor, and generates structured metadata 105.

[0041] The metadata 105 is data in which the analysis results output from the voice analysis unit 101, the video analysis unit 102, and the sensor information analysis unit 103 are structured, and has a structure that can be searched by text in association with the position information.

[0042] The 3D data analysis unit 106 analyzes the three-dimensional data 108 acquired by the 3D data measurement device 24 and sends it to the 3D data receiving unit 107. The 3D data analysis unit 106 may use existing three-dimensional data (for example, Plateau provided by the Ministry of Land, Infrastructure, Transport and Tourism, or three-dimensional data at the time of building design) instead of the three-dimensional data 108 acquired by the 3D data measurement device 24. Also, instead of the measured data, data such as a surface mesh created manually may be used.

[0043] The 3D data measurement device 24 is a sensor capable of acquiring three-dimensional data, such as a LiDAR, a stereo camera, or a distance image camera, and acquires three-dimensional data representing the spatial shape of a predetermined area where the position identification support service is provided.

[0044] The 3D data receiving unit 107 is a 3D engine (so-called 3D game engine) excellent in handling three-dimensional data, which converts the three-dimensional data output from the 3D data measurement device 24 into a predetermined format and stores it in the three-dimensional data 108.

[0045] The facility information input unit 109 receives the input of information on facilities provided in a predetermined area where the position identification support service is provided and stores it in the facility information 110. For example, information such as store names, business types, shapes, members, colors, and finishes of facilities (walls, signs, doors, etc.), which are keys for people to perceive and inquire, is input in advance before the provision of the position identification support service.

[0046] The information integration unit 111 generates integrated 3D data 113 by integrating the metadata 105 generated by the information receiving unit 104, the three-dimensional data 108 generated by the 3D data receiving unit 107, and the facility information 110 input to the facility information input unit 109 based on the position information. At this time, it is integrated with the position information within the range that people can perceive (objects can be seen, sounds can be heard, smells can be smelled, etc.) according to the type of the metadata 105. In addition, the information integration unit 111 generates dictionary data 112, which is a synonym dictionary for aggregating search terms included in the search request. The dictionary data 112 may be input in advance before the provision of the position identification support service.

[0047] As shown in FIG. 4, at the time of position estimation, the search request input unit 121 receives the input of a search request by voice or text from the user terminal 30. The search request is configured to receive a plurality of area designation conditions representing the perception of the inquiry subject. For example, each of "There is a coffee shop on the left hand side", "The performance of music can be heard", and "Just now, Pierrot passed by" shown in FIG. 1 is an area designation condition.

[0048] The voice analysis unit 122 uses voice recognition technology to convert the voice of the search request input to the search request input unit 121 into text. If the location identification support server 10 does not support voice input, the voice analysis unit 122 does not have to be implemented.

[0049] The semantic analysis unit 123 uses morphological analysis technology to decompose the search request input in text to the search request input unit 121 and the search request texturized by the voice analysis unit 122 into words, and converts the fluctuations and ambiguous expressions in the input natural sentence into predetermined search keys to create a search query including the search key. For example, the area designation condition of "There is a coffee shop on the left hand side" is replaced with "Within a radius of 10 m from the café" and "At a position where the café can be seen on the left" to generate two search queries.

[0050] The position estimation unit 124 refers to the integrated 3D data 113 to estimate the position corresponding to the input search request. Then, the ranges of the estimated positions for each of the plurality of area designation conditions input as the search request are superimposed to narrow down the position corresponding to the search request. The details of the position estimation process executed by the position estimation unit 124 will be described with reference to FIGS. 5 to 8. And the position estimation unit 124 superimposes the range of the estimated position for each of the plurality of input search requests on the map to generate an image (for example, an image to be displayed in the map display area 910 of the search result screen shown in FIG. 9) for narrowing down the position corresponding to the search request.

[0051] The location identification support server 10 of this embodiment outputs the estimated location in voice and / or image. When outputting the estimated location in voice, the voice synthesis unit 125 identifies the most likely location using the range of the estimated location and its accuracy, and vocalizes the most likely estimated location using voice synthesis technology. The result transmission unit 126 outputs the vocalized most likely location to the user terminal 30. The user terminal 30 outputs the voice signal received from the location identification support server 10 from the speaker to notify the inquiry subject of the highly accurate location. Note that the user terminal 30 that outputs the result may be the same as or different from the user terminal 30 to which the search request is input. For example, a search request may be input to a smartphone carried by the inquiry subject, and the estimated location may be output as voice from a speaker installed near the estimated location.

[0052] When outputting the estimated location in image, the result transmission unit 126 outputs a result display screen (Figure 9) including the generated image to the user terminal 30. The user terminal 30 outputs the result display screen received from the location identification support server 10 to the display to notify the inquiry subject of the likely location.

[0053] Figure 5 is a flowchart of the location estimation process executed by the location estimation unit 124.

[0054] Before the location estimation unit 124 executes the location estimation process, the semantic analysis unit 123 receives a search request including the perceptual information perceived by the inquiry subject from the search request input unit 121 or the voice analysis unit 122 (201), decomposes the search request into words using morphological analysis technology, converts the fluctuations and ambiguous expressions in the input natural sentence into predetermined search keys, and creates a search query including the search keys (202). Thereafter, the location estimation unit 124 starts the location estimation process.

[0055] The position estimation unit 124 searches the integrated 3D data 113 with a search query generated from one area specification condition included in the search request, and acquires an object that matches the area specification condition (203). For example, when the search query is "within a radius of 10 m from the café" and "at a position where the café can be seen on the left", the café within the area where the position-specific support service is provided is acquired as an object.

[0056] Then, the position estimation unit 124 starts processing each of the acquired plurality of objects (204). First, the position estimation unit 124 estimates the attributes of the object (205). If the integrated 3D data 113 has a definition of attributes, the attributes of the object may be acquired from the integrated 3D data 113. Also, the attributes of the object may be determined according to the type of the sensing device that is the basis of the area specification condition of this object. For example, among the objects detected by a camera or LiDAR, a stationary object is regarded as a stationary object, an object for which movement is detected is regarded as a moving object, and an object related to the area specification condition detected by a sensing device other than a camera or LiDAR may be regarded as environmental information.

[0057] Then, since the target area calculation method differs depending on the attributes of the object, the position estimation unit 124 distributes the processing. If the attribute of the object is a stationary object, the target area calculation process 207 for stationary objects is executed. Details of the target area calculation process 207 for stationary objects will be described with reference to FIG. 6. If the attribute of the object is a moving object, the target area calculation process 208 for moving objects is executed. Details of the target area calculation process 208 for moving objects will be described with reference to FIG. 7. If the attribute of the object is environmental information, the target area calculation process 209 for environmental information is executed. Details of the target area calculation process 209 for environmental information will be described with reference to FIG. 8.

[0058] Thereafter, it is determined whether there is another unprocessed search query (210). If there is an unprocessed search query, the process returns to step 206 and continues. When the processing of all the search queries is completed, the processing for each object from step 204 is repeated (211).

[0059] When the processing of all objects is completed, it is determined whether there are other area designation conditions (212). If there are unprocessed area designation conditions, the process returns to step 203 and continues. When the processing of all area designation conditions is completed, the position estimation process ends.

[0060] Figure 6 is a detailed flowchart of the target area calculation process 207 for stationary objects.

[0061] The position estimation unit 124 acquires the area designation conditions (221). Since the target area calculation method differs depending on the area designation conditions, the process is distributed (222). If the area designation condition is related to distance, a circle centered on the moving object corresponding to the area designation condition is acquired (223). For example, if the search query is "within a radius of 10 m from the café", a circle with a radius of 10 m is generated. If the area designation condition is related to direction, the area from the current candidate location to the target object is acquired (224). For example, if the search query is "at a position where the café can be seen to the left", the area between the café and the current candidate location is generated.

[0062] Thereafter, the position estimation unit 124 calculates the target area based on the spatial information (225). For example, the position estimation unit 124 superimposes the generated areas to narrow down the positions corresponding to the search request.

[0063] Figure 7 is a detailed flowchart of the target area calculation process 208 for moving objects 。

[0064] The position estimation unit 124 determines whether there is a moving object within a predetermined time range before and after the time of the area designation condition (231). At this time, it may be narrowed down by the moving speed of the object described in the area designation condition. If there is no moving object corresponding to the area designation condition, the target area based on the moving object cannot be specified, so the target area calculation process for the moving object is terminated. On the other hand, if there is a moving object corresponding to the area designation condition, the area designation condition regarding the moving object is acquired (232). Since the target area calculation method differs depending on the area designation condition, the process is distributed (233). If the area designation condition is related to distance, a circle centered on the moving object corresponding to the area designation condition is acquired (234). If the area designation condition is related to distance, a circle centered on the moving object corresponding to the area designation condition is generated (234). For example, if the area designation condition is "the clown has just passed by", a circle with a radius of 4 m is generated from the position of the clown at the time of the area designation condition. If the area designation condition is related to direction, the area from the current candidate location to the target object is acquired (235). For example, area designation conditions related to direction include "in front of the eyes", "front", "left hand", "right side", "wall side", etc. If the area designation condition is related to time, the total area of circles centered on the target objects existing within a specific time range corresponding to the area designation condition is acquired (236). For example, if the area designation condition includes "running away", a circle centered on the position of the target object for 3 seconds is generated with the 3 seconds during which running can be seen as the time range.

[0065] After that, the position estimation unit 124 calculates the target area based on the spatial information (237). For example, the position estimation unit 124 superimposes the calculated target areas and narrows down the positions corresponding to the search request.

[0066] Figure 8 is a flowchart of the target area calculation process 209 for environmental information.

[0067] First, the semantic analysis unit 123 extracts words corresponding to environmental information from the area designation condition (241). For example, environmental information such as hot, bright, windy, smelly, music, etc. is extracted.

[0068] After that, the position estimation unit 124 refers to the integrated 3D data 113 with the extracted environmental information and selects a region corresponding to the extracted environmental information (242). For example, according to environmental information such as hot, bright, strong wind, odor, music, etc., using propagation characteristics (attenuation rate, diffraction, etc.), spatial features (spatial shape, absorption rate, reflectivity, etc.), and the nature of the perception of the inquiry subject (such as the height of the line of sight), a perceptible region that can be perceived by the inquiry subject is generated, and a probability density is calculated according to the degree of perception of the environmental information.

[0069] After that, the position estimation unit 124 calculates a target region based on the spatial information (237). For example, the position estimation unit 124 superimposes the calculated target regions to narrow down the position corresponding to the search request.

[0070] FIG. 9 is a diagram showing an example of a search result screen displayed on the user terminal 30.

[0071] In the search result screen shown in FIG. 9, a search request input field 901 and a narrowing-down button 902 are provided on the left side, and a map display area 910 is provided on the right side.

[0072] The search request input field 901 text-displays the words input as a search request to the user terminal 30 based on the voice recognition result. A text input field that accepts text input by keyboard operation may be provided. When the inquiry subject operates the narrowing-down button 902, the search request displayed in the search request input field 901 is transmitted to the position identification support server 10, and the display of the region specified by the search condition is added to the map display area 910. In the search request input field 901, the words used for searching the integrated 3D data 113 are highlighted. On the left side of each region designation condition of the search request, a mark that is superimposed and displayed on the map in the map display area 910 corresponding to the region designation condition is displayed. In the map display area 910, a map with the region specified by the search superimposed is displayed.

[0073] As described above, according to the embodiments of the present invention, the position can be specified from the information of the object perceived by the inquiry subject. As objects that can be perceived by humans, not only stationary landscapes but also moving objects and environmental information are used, so the position specification accuracy can be improved.

[0074] Note that the present invention is not limited to the above-described embodiments, and includes various modifications and equivalent configurations within the scope of the appended claims. For example, the above-described embodiments have been described in detail for easy understanding of the present invention, and the present invention is not necessarily limited to those having all the configurations described. Also, a part of the configuration of one embodiment may be replaced with the configuration of another embodiment. Further, the configuration of another embodiment may be added to the configuration of one embodiment. Also, for a part of the configuration of each embodiment, addition, deletion, or replacement with other configurations may be made.

[0075] In addition, each of the above-described configurations, functions, processing units, processing means, etc. may be realized in hardware by designing a part or all of them, for example, by an integrated circuit, or may be realized in software by a processor interpreting and executing a program for realizing each function.

[0076] Information such as programs, tables, and files for realizing each function can be stored in a storage device such as a memory, a hard disk, an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, or a DVD.

[0077] Also, the control lines and information lines show those considered necessary for explanation, and do not necessarily show all the control lines and information lines necessary for implementation. In practice, it may be considered that almost all the components are interconnected.

Description of Reference Numerals

[0078] 1 Processor 2 Memory 3 Auxiliary Storage Device 4 Communication Interface 5 Input Interface 6 Output Interface 7 Keyboard 8 Mouse 9 Display Device 10 Location-Specific Support Server 11 Search Request Reception Unit 12 Search Key Generation Unit 13 Target Object Search Unit 14 Target Area Extraction Unit 15 Term Dictionary 16 3D City Model 17 Visible Location Information 18 Map Information 19 Screen Generation Unit 30 User Terminal 21 Search Request Input Function 22 Screen Display Function

Claims

1. A position identification support system for generating data for identifying a position, comprising: an arithmetic unit that executes a predetermined process, and a storage device accessible by the arithmetic unit; the storage device stores integrated 3D data including attributes of stationary objects and attributes of moving objects; a reception unit that receives an input of an expression of a moving object recognized by an inquiry subject by the arithmetic unit; a semantic analysis unit that specifies a search term for searching the integrated 3D data from the received expression of the moving object and generates a search query including one or more region designation conditions by the arithmetic unit; a position estimation unit that searches the integrated 3D data with the generated search query, obtains information for narrowing down the position from the received expression of the moving object, and generates information for narrowing down the position, wherein the position identification support system is characterized by having the position estimation unit.

2. The position identification support system according to claim 1, wherein the integrated 3D data includes information on the surrounding environment, the reception unit receives an input of an expression of the environment recognized by the inquiry subject, the semantic analysis unit specifies a search term for searching the integrated 3D data from the received expression of the environment and generates a search query, and the position estimation unit searches the integrated 3D data with the generated search query and obtains information for narrowing down the position from the received expression of the environment.

3. The position identification support system according to claim 1, wherein the position estimation unit generates screen data for superimposing and displaying regions corresponding to a plurality of the region designation conditions related to the moving object recognized by the inquiry subject on a map.

4. The position identification support system according to claim 1, wherein the arithmetic unit further includes an audio analysis unit that analyzes audio acquired by an audio acquisition device, a video analysis unit that analyzes video captured by a video capture device, an environment analysis unit that analyzes environmental values measured by an environmental measurement device, an information reception unit that generates metadata by combining the analysis result of the audio analysis unit, the analysis result of the video analysis unit, and the analysis result of the environment analysis unit based on position information, and an integration unit that integrates the generated metadata and three-dimensional map information based on position information to generate the integrated 3D data.

5. The position identification support system according to claim 1, wherein the position estimation unit if the area designation condition relates to a moving object, determines whether there is a moving object within a predetermined time range before and after the time of the area designation condition, if there is a moving object corresponding to the area designation condition, distributes processing according to the area designation condition related to the moving object, and generates information for narrowing down the position, characterized in that it is a position identification support system.

6. The position identification support system according to claim 5, wherein the position estimation unit if the area designation condition relates to distance, generates a circle centered on the moving object corresponding to the area designation condition, if the area designation condition relates to direction, generates an area from the current candidate location to the moving object corresponding to the area designation condition, if the area designation condition relates to time, generates a total area of a plurality of circles centered on the position of the target object within the time range in the search query, characterized in that it is a position identification support system.

7. The position identification support system according to claim 1, wherein the position estimation unit if the area designation condition relates to a stationary object and the area designation condition relates to distance, generates a circle centered on the moving object corresponding to the area designation condition, if the area designation condition relates to a stationary object and the area designation condition relates to direction, generates an area from the current candidate location to the moving object corresponding to the area designation condition, characterized in that it is a position identification support system.

8. The position identification support system according to claim 2, wherein the position estimation unit generates a perceptible area where the environmental information extracted from the search query can be perceived, characterized in that it is a position identification support system.

9. A position identification support method in which a position identification support system generates data for identifying a plurality of positions, the position identification support system is composed of a computer having an arithmetic device for executing predetermined processing and a storage device accessible by the arithmetic device, the storage device stores integrated 3D data including the attributes of stationary objects and the attributes of moving objects, the position identification support method a reception step in which the arithmetic device receives an input of the expression of the moving object recognized by the inquiry subject, A semantic analysis step in which the arithmetic unit specifies a search term for retrieving the integrated 3D data from the received representation of the moving object and generates a search query including one or more area specification conditions; A position identification support method characterized by comprising: a position estimation step in which the arithmetic unit searches the integrated 3D data with the generated search query, obtains information for narrowing down the position from the received representation of the moving object, and generates information for narrowing down the position.

10. The position identification support method according to claim 9, wherein the integrated 3D data includes information on the surrounding environment, in the receiving step, the arithmetic unit receives an input of a representation of the environment recognized by the inquiry subject, in the semantic analysis step, the arithmetic unit specifies a search term for retrieving the integrated 3D data from the received representation of the environment and generates a search query, in the position estimation step, the arithmetic unit searches the integrated 3D data with the generated search query and obtains information for narrowing down the position from the received representation of the environment.

11. The position identification support method according to claim 9, wherein in the position estimation step, the arithmetic unit generates screen data for superimposing and displaying on a map areas corresponding to a plurality of the area specification conditions regarding the moving object recognized by the inquiry subject.

12. The position identification support method according to claim 9, comprising: an audio analysis step in which the arithmetic unit analyzes audio acquired by an audio acquisition device; a video analysis step in which the arithmetic unit analyzes video captured by a video capture device; an environment analysis step in which the arithmetic unit analyzes environmental values measured by an environmental measurement device; an information reception step in which metadata obtained by combining the analysis result of the audio analysis step, the analysis result of the video analysis step, and the analysis result of the environment analysis step based on position information is generated; and an integration step in which the generated metadata and three-dimensional map information are integrated based on position information to generate the integrated 3D data.

13. The position identification support method according to claim 9, In the position estimation step, if the area designating condition relates to a moving object, the arithmetic unit determines whether there is a moving object within a predetermined time range before and after the time of the area designating condition. If there is a moving object corresponding to the area designating condition, the processing is distributed according to the area designating condition related to the moving object, and information for narrowing down the position is generated. A position identification support method characterized by the above.

14. The position identification support method according to claim 13, In the position estimation step, if the area designating condition relates to a stationary object and the area designating condition relates to distance, a circle centered on the moving object corresponding to the area designating condition is generated. If the area designating condition relates to a stationary object and the area designating condition relates to direction, an area from the current candidate location to the moving object corresponding to the area designating condition is generated. If the area designating condition relates to time, a total area of a plurality of circles centered on the position of the target object within the time range in the search query is generated. A position identification support method characterized by the above.

15. The position identification support method according to claim 9, In the position estimation step, if the area designating condition relates to distance, a circle centered on the moving object corresponding to the area designating condition is generated. If the area designating condition relates to direction, an area from the current candidate location to the moving object corresponding to the area designating condition is generated. A position identification support method characterized by the above.

16. The position identification support method according to claim 10, In the position estimation step, the arithmetic unit generates a perceptible area in which the environmental information extracted from the search query can be perceived. A position identification support method characterized by the above.

Images