JP2005275960A - Object identification device, object identification system and popularity voting system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To improve reliability of an inference result by creating object information indicating what kind of emotion or consciousness a user has produced for which object, and to expand the range of use.
SOLUTION: In the object specifying device 1, a body temperature sensor 182 for measuring a user's body temperature, a sweat sensor 183 for measuring sweat, a heart rate sensor 184 for measuring heart rate, and a user can arbitrarily turn on and off. The intention transmission switch 152 is connected via the input detection unit 180. The RFID tag reader 160 acquires the object ID from the RFID tag attached to the external exhibit. Inference data, which is an inference result based on the measured value from each sensor and the switch information from the communication switch 152, is created, and object information including the inference data and the object ID is created. The object information is analyzed, and analysis information indicating the popularity of each exhibit and the user's preference is created.
[Selection] Figure 1

Description

  The present invention relates to a device for inferring user's consciousness, emotion, and the like, and more specifically, an object for creating object information indicating what kind of emotion, consciousness, etc. a user has produced for which object The present invention relates to an identification device, an object identification system, and a popularity voting system.

  2. Description of the Related Art Conventionally, various devices have been proposed that provide a sensor for measuring a user's physiological information, biological information, and the like, and infer the user's consciousness and emotion based on various information measured by the sensor.

In addition to sensors that measure physiological information such as heart rate and skin impedance, a CCD camera for detecting the user's posture and motion state and a microphone for detecting the voice emitted by the user are provided. There is known a consciousness level detection device that can detect more accurately whether or not a person's consciousness level is in a specific state. Furthermore, a game control device is known in which a user can intentionally input a psychological state intentionally (see, for example, Patent Document 1).
Japanese Patent Laid-Open No. 10-57355

  By the way, when the user's interest is directed to a specific object, it is known that the user's emotions and consciousness are greatly influenced by the object. For example, when a user visits an art museum or a museum, there are cases in which a particular exhibit is strongly impressed, but other exhibits are hardly impressed. In addition, a feeling of “sadness” may be generated for one exhibit, while a feeling of “joy” may be generated for another exhibit. For this reason, if it is unclear what the user has caused emotion or consciousness such as “impression” or “excitement”, it is difficult to use the inference result even if the user's emotion or consciousness is inferred. There was a problem.

  In the invention described in Patent Document 1, the user's level of consciousness about the game is detected, but the object to which the user's interest is directed is limited to the game, and the user's consciousness about other objects. I could not infer levels.

  The present invention has been made in order to solve the above-mentioned problems. By creating object information indicating what kind of emotion or consciousness the user has produced for which object, the inference result can be trusted. An object of the present invention is to provide an object identification device, an object identification system, and a popularity voting system that can enhance the performance and expand the range of use.

  In order to achieve the above object, an object identification device according to claim 1 comprises an identification data acquisition means for detecting an object and acquiring identification data of the object, and at least one sensor. A measurement value acquisition unit that acquires a measurement value; an inference data generation unit that generates inference data that is an index value different from the measurement value based on the measurement value acquired by the measurement value acquisition unit; Object information creation means for creating object information including the identification data acquired by the identification data acquisition means and the inference data created by the inference data creation means, and created by the object creation means Object information output means for outputting the object information.

  In addition to the configuration of the invention described in claim 1, the object specifying device of the invention according to claim 2 is characterized in that the identification data acquisition unit is configured to read the object from a recording medium attached to the object or the vicinity of the object. The identification data is obtained.

  In addition to the configuration of the invention described in claim 2, the object specifying device of the invention according to claim 3 is an RFID that reads the identification data from an RFID tag that is the recording medium. It is a tag reader.

  In addition to the configuration of the invention according to any one of claims 1 to 3, the object specifying device of the invention according to claim 4 is user information for the user to operate and input user information. The inference data creation means creates the inference data based on the measurement value acquired by the measurement value acquisition means and the user information input from the user information input means. It is characterized by doing.

  In addition to the configuration of the invention described in claim 4, the inference data creating means uses the user information input means indicating on / off state transitions. When the content of the user information is on, the inference data is created so as to indicate a strong inference of the user.

  According to a sixth aspect of the present invention, in addition to the configuration of the first aspect, the identification data acquisition unit acquires the identification data from each of the plurality of target objects. In this case, an output mode selection unit is provided for selecting any one of a plurality of output modes that define a method for specifying the object to be output as the object information.

  In addition to the configuration of the invention according to any one of claims 1 to 6, the object identification device of the invention according to claim 7 is characterized in that the identification data acquisition means periodically and multiple times with respect to the object. And detecting whether or not the object is an output target of the object information based on the continuity before and after the time-series data acquired by the detection.

  In addition to the configuration of the invention according to claim 7, the identification data acquisition unit performs periodic and multiple detections on the object. When the time-series data acquired by the detection indicates that it has been continuously detected a predetermined number of times, the target object is set as an output target of the target object information.

  In addition to the configuration of the invention according to any one of claims 1 to 8, the object specifying device of the invention according to claim 9 includes a time measuring unit that measures the current date and time, and the object information creating unit includes: When the inference data is created by the inference data creation means, the date and time data related to the current date and time measured by the timing means is acquired, and the object information including the date and time data is created. To do.

  An object specifying system according to a tenth aspect of the invention is an object for acquiring the object information output by the object specifying device according to any one of claims 1 to 9 and the object information output means. Object information acquisition means and object information storage means for storing the object information collected by the object information acquisition means.

  An object specifying system according to an eleventh aspect of the invention includes the object and use based on the object information stored in the object information storage means in addition to the configuration of the invention according to claim 10. Analysis information creating means for creating analysis information indicating the relationship with the person.

  Further, the popularity voting system of the invention according to claim 12 includes: an object specifying device that creates object information; and a popularity analysis device that analyzes the popularity of the object based on the object information. The object voting system is connected via an identification data acquisition unit that detects the object and acquires identification data of the object, and at least one sensor. The measurement value acquisition means for acquiring the measurement value, and the user information input means for operating the user himself to input user information, the measurement value acquired by the measurement value acquisition means, Based on the user input information input from the user information input means, inference data generation means for generating the inference data, and the identification data acquired by the identification data acquisition means, The object information creating means for creating the object information including the inference data created by the inference data creating means, and the object information created by the object information creating means, the popularity analysis device Object information transmitting means for transmitting to the object, the popularity analysis device receiving the object information receiving means for receiving the object information transmitted from the object specifying device, and receiving the object information by the object information receiving means. Object information storage means for storing the object information obtained, and popularity analysis means for analyzing the degree of popularity of the object based on the object information stored in the object information storage means. ing.

  Further, in the popularity voting system of the invention according to claim 13, in addition to the configuration of the invention of claim 12, the popularity analysis means analyzes the popularity of the object and optimizes the arrangement of the object And generating optimization information indicating an optimal arrangement of the objects.

  In the object identification device of the invention according to claim 1, inference data that is an index value different from the measurement value is created based on the measurement value acquired from each sensor and the identification data acquired from the object. The object information including the inference data is output. It is possible to create object information in which the user's consciousness and feelings about the object are inferred, and to improve the reliability of the inference result.

  In addition, in the object specifying device of the invention according to claim 2, in addition to the effect of the invention according to claim 1, identification data is acquired from the object or a recording medium attached to the vicinity of the object. The identification data can be accurately obtained from the medium.

  In addition, in the object specifying device of the invention according to claim 3, in addition to the effect of the invention according to claim 2, the identification data is acquired from the RFID tag which is the recording medium by the RFID tag reader, and therefore stored in the RFID tag. Identification data can be obtained accurately.

  In addition, in addition to the effect of the invention according to any one of claims 1 to 3, the object specifying device of the invention according to claim 4 is provided with user information input means that can be arbitrarily input by the user. A person can intentionally reflect emotions and consciousness in the object information, and can improve the accuracy of the object information. Moreover, a popularity vote can be performed on a specific object.

  In addition, in addition to the effect of the invention according to any one of claims 1 to 4, in the object specifying device of the invention according to claim 5, inference data indicating strong inference is created when the user information input means is on. Therefore, the user can intentionally reflect emotions and consciousness in the object information. Moreover, a popularity vote can be performed on a specific object.

  Further, in the object specifying device of the invention according to claim 6, in addition to the effect of the invention according to any one of claims 1 to 5, the user can arbitrarily set the output mode when a plurality of objects are detected. Since the output mode selection means that can be selected is provided, the optimum object is output according to the output mode arbitrarily selected by the user, and the object information can be created easily and accurately.

  Moreover, in the object specifying device of the invention according to claim 7, in addition to the effect of the invention according to any one of claims 1 to 6, the object is output based on the continuity before and after the detected time-series data. Since it determines whether it is set as object, an object can be detected correctly.

  Further, in the object specifying device of the invention according to claim 8, in addition to the effect of the invention according to claim 7, when the object is detected for a predetermined number of times, the object is output, so that the object is accurately Can be detected.

  Further, in the object specifying device of the invention according to claim 9, in addition to the effect of the invention according to any of claims 1 to 8, the object information includes date / time data indicating the current date / time. By clarifying the date and time when the object information was created and analyzing the change in the inference result with time, the information value of the inference result can be increased.

  Moreover, in the target object specifying system according to the tenth aspect of the present invention, the target object information output from the target object specifying device is acquired and stored, so that the target object information can be collected and managed.

  Further, in the object specifying system of the invention according to claim 11, in addition to the effect of the invention according to claim 10, analysis information indicating the relationship between the object and the user is created based on the object information. The relationship between objects and users can be understood, and the range of use of objects can be expanded.

  In the popularity voting system of the invention according to claim 12, the object information created by the object identification device is transmitted to the popularity analysis device, and the popularity analysis device uses the popularity of the object based on the object information. The degree is analyzed. Therefore, the user's preference and the popularity of the object can be grasped based on the object information, and the use range of the object can be expanded.

  Further, in the popularity voting system of the invention according to claim 13, in addition to the effect of the invention according to claim 12, optimization information indicating the optimum arrangement of the object is created, so that the optimum arrangement of the object is grasped. And the range of use of the object can be expanded.

  Hereinafter, a first embodiment of the present invention will be described with reference to the drawings. The object specifying device according to the first embodiment is a small portable terminal device carried by a user.

  In this embodiment, when a user visits an exhibit at a museum while carrying the object creation device, the object information is created by inferring the user's consciousness and feelings about each exhibit. Illustrate.

  Below, each measured value of body temperature, perspiration, and heart rate is illustrated as information measured from a sensor. In addition, as information input by the user, information in which a user arbitrarily turns on and off a predetermined switch is exemplified. Note that the object information here is information on the user's consciousness, feelings, etc. with respect to a specific exhibit. In the present embodiment, a case will be described in which object information indicating how much the user is “impressed” with respect to which exhibit is created.

  First, with reference to FIG. 1 thru | or FIG. 4, the structure of the target object identification device 1 which concerns on 1st Embodiment is demonstrated. FIG. 1 is an overall configuration diagram of the object identification device 1. FIG. 2 is a block diagram illustrating a configuration of the object identification device 1. FIG. 3 is a conceptual diagram showing the configuration of the storage area of the RAM 130 of the object identification device 1. FIG. 4 is a conceptual diagram showing the configuration of the storage area of the HDD 140 of the object specifying device 1.

  As shown in FIG. 1, the object identifying device 1 is carried or worn by a user, and a plurality of sensors such as a body temperature sensor, a sweat sensor, and a heart rate sensor are connected to the object identifying apparatus 1. The reading units of these sensors are provided in a state in which the user can be appropriately measured by contacting the skin of the user (shaded portion in FIG. 1). Therefore, in the target object specifying device 1, the user is always held in a state measured by the sensor. In addition, the user can arbitrarily press the intention transmission switch 152 for reflecting his / her intention in the object information.

  When the user approaches the exhibit 9, the object specifying device 1 is configured to be effectively connected to the exhibit 9. In the present embodiment, short-range wireless communication is performed between the RFID tag 8 provided in the exhibit 9 and the RFID tag reader 160. Thereby, the identification data unique to the exhibit 9 stored in the RFID tag 8 is acquired by the object specifying device 1.

  As shown in FIG. 2, the object specifying device 1 is provided with a CPU 110 that controls the object specifying device 1. The CPU 110 includes a ROM 120 that stores a program such as BIOS executed by the CPU 110, a RAM 130 that temporarily stores data, and a hard disk drive (hereinafter referred to as “HDD”) that is a data storage device. 140) is connected. In addition, a timing device 190 for counting the current date and time and the time interval is connected to the CPU 110 via the bus 115. The timing device 190 is an IC chip having a clock function. Further, the timing device 190 may be configured to acquire the date and time via the Internet or wirelessly.

  In addition, an input detection unit 180 that detects input from various devices is connected to the CPU 110 via the bus 115, and the input detection unit 180 allows a user to operate the object specifying device 1. An input panel 181 having buttons and switches, a body temperature sensor 182 for measuring the user's body temperature, a sweat sensor 183 for measuring the user's sweat state, and a heart rate for measuring the user's heart rate A sensor 184 is connected. The body temperature sensor 182, the sweat sensor 183, and the heart rate sensor 184 are not limited in position and measurement method as long as the body temperature, sweat, and heart rate can be measured effectively. A sensor reading unit is provided. The body temperature sensor 182 measures 0 to 50 ° C. as a measured value, the sweat sensor 183 measures 0 to 100% RH, and the heart rate sensor 184 measures 0 to 200 beats as a measured value. And Information measured from the body temperature sensor 182, the sweat sensor 183, and the heart rate sensor 184 corresponds to the “measurement value” of the present invention.

  Each sensor is controlled to automatically perform periodic measurement when the object identification device 1 is powered on and activated. The measurement value of each sensor is stored in a predetermined storage area inside each sensor, and the object specifying device 1 acquires the latest measurement value from the predetermined storage area via the input detection unit 180. In addition, a measurement value storage area (not shown) for each sensor is provided in the RAM 130 or the HDD 140 of the object specifying device 1, and the measurement value of each sensor is stored in the measurement value storage area via the input detection unit 180. In the target object specifying device 1, the latest measured value may be acquired by referring to the measured value storage area.

  In addition, an RFID tag reader 160 that performs short-distance wireless communication by connecting to the RFID tag 8 provided in the nearby exhibit 9 is provided. The RFID tag reader 160 detects the RFID tag 8 by transmitting a carrier wave based on a predetermined inquiry signal, demodulates the reflected wave returned from the RFID tag 8, and uniquely identifies the exhibit 9 from the RFID tag 8. The object ID which is data is acquired.

  In addition, the input panel 181 includes a power reset switch 151 for turning on and off the power of the object identification device 1 and restarting, and the user himself / herself for intentionally inputting his / her intention. Is switched on / off to input switch information, an inference mode selection switch 153 for selecting an inference mode of the object identification device 1, and a plurality of RFID tags 8 are detected. An output mode selection switch 154 for selecting an output mode to be executed is provided at least.

  The user turns on or off the intention transmission switch 152 in order to intentionally transmit his intention to the object identification device 1 intentionally. For example, in the present embodiment, the object identification device 1 infers the “impression” of the user, and therefore when the user is impressed by a certain exhibition 9, the communication switch 152 is turned on to switch it. When the information “ON” is input and the user is not impressed, the switch information “OFF” is input without turning on (turning off) the intention transmission switch 152.

  An inference engine has a function of inferring user's consciousness and emotion based on information measured from each sensor. The inference engine defines inference methods and setting conditions, and is a program for inferring the user's consciousness based on the measured values from each sensor according to the definition, and is selected from the inference mode selection switch 153 An inference engine corresponding to the inferred mode is executed by the CPU 110. In the present embodiment, a plurality of inference engines are stored in the HDD 140, and the user can select any inference mode.

  With such a configuration, in the object identification device 1 according to the first embodiment, the sensor information from the body temperature sensor 182, the sweat sensor 183, the heart rate sensor 184, the switch information from the intention transmission switch 152, and the RFID tag Based on the identification data from 8, object information indicating what kind of emotion or consciousness the user has produced for which object is created. Note that the object information creation program is executed as one of the modules executed by the object specifying device 1 of the present embodiment. It is assumed that the object information creation program is stored in advance in the program storage area 142 (see FIG. 4) on the HDD 140. Further, when installed via a CD-ROM drive, floppy (registered trademark) disk drive, and various interfaces (not shown), an external storage medium such as a CD-ROM or an external storage device via a network can be used on the HDD 140. An object information creation program may be set up in the program storage area 142 or the information storage area 143 (see FIG. 4).

  As shown in FIG. 3, the RAM 130 of the object identification device 1 stores a work area 131 that stores temporary data during execution of the program and an input information storage area 132 that temporarily stores various types of input information. And an output information storage area 133 for temporarily storing various information to be output. Further, the RAM 130 is provided with various storage areas not shown.

  As shown in FIG. 4, the HDD 140 of the object identification device 1 includes an operating system (OS) storage area 141 that stores various programs executed by the CPU 110 to control the operation of the object identification device 1, and an object. A program storage area 142 that stores various programs executed by the object identification device 1 and an object information creation program, an information storage area 143 that stores information such as settings, initial values, and data necessary for the execution of the program, An object information storage area 144 for storing the created object information is provided. The information storage area 143 stores an inference definition table and a correction table, which will be described later.

  Hereinafter, the flow of processing in the object identification device 1 of the present invention will be described with reference to FIGS. FIG. 5 is a main flowchart of the object information creation process. FIG. 6 is a flowchart showing details of the inference engine initialization process (S1). FIG. 7 is a flowchart showing details of the inference data creation process (S3). FIG. 8 is a flowchart showing details of the inference execution process (S164). FIG. 9 is a diagram illustrating a data configuration of the inference definition table 13. FIG. 10 is a flowchart showing details of the RFID tag detection process (S4). FIG. 11 is a flowchart showing details of the processing by output mode (S213). FIG. 12 is an image diagram of the area distribution of the plurality of RFID tags 8. FIG. 13 is a diagram illustrating a data configuration of the object ID identification table 18. FIG. 14 is a flowchart showing details of the object information output process (S11). FIG. 15 is a diagram illustrating a data configuration of the object information 10.

  The main flowchart of the object information creation process shown in FIG. 5 is when the user operates the power reset switch 151 (see FIG. 2) to turn on the object specifying device 1 or when the object specifying device 1 is turned on. When the resetting is performed, the processing is started.

  As shown in FIG. 5, first, an inference engine initialization process (S1) is executed. The inference engine initialization process is a process for initializing a reference value for each sensor that is referred to in the later-described inference data creation process.

  As shown in FIG. 6, in the inference engine initialization process (S1), “0” is assigned to the variable ST, variable SH, and variable SM (S101), and “3” is assigned to the variable T (S102). . And a measured value is acquired from each sensor (S103). That is, the body temperature sensor 182, the sweat sensor 183, and the heart rate sensor 184 measure the body temperature, sweat, and heart rate of the user, and the measurement values are acquired from these sensors.

  The measured values of body temperature, sweating, and heart rate acquired from each sensor are added to the variable ST, variable SH, and variable SM, respectively (S104). If the measurement value is acquired for the first time in S103, since “0” is substituted for the variable ST, variable SH, and variable SM in S102, each of the body temperature, sweating, and heart rate acquired in S103 is obtained. The measured value is directly substituted into the variable ST, variable SH, and variable SM.

  Then, the variable T is decremented by “1” (S105), and if T is not “0” (S106: NO), the process returns to S103, and the measurement values obtained by the sensors are acquired again. In this way, until the number of times set to the variable T in S102 (here, 3 times) is reached, the measurement value acquisition in S103 is executed, and the processing in S103 to S106 is repeated. As a result, the variable ST, the variable SH, and the variable SM store the total value of the measurement values for the number of times set in the variable T.

  The variable ST, variable SH, and variable SM are respectively divided by “3”, which is the value set in the variable T, and assigned to the variable CT, variable CH, and variable CM, respectively (S107). That is, by dividing the total value of the measured values for each sensor by the number of times of measurement, an average value (= normal reference value) of one measured value of each sensor is obtained.

  The variable CT is a reference value for the body temperature sensor 182, the variable CH is a reference value for the sweat sensor 183, and the variable CM is a reference value for the heart rate sensor 184. The reference values of these sensors are stored in a reference value area (not shown) provided in the RAM 130.

  Returning to FIG. 5, the selection of the inference mode is executed (S2). The object specifying device 1 can select an arbitrary one from a plurality of inference modes, and the processing content of the inference data creation process (S3) differs depending on each inference mode. An inference engine corresponding to each inference mode is stored in the program storage area 142, and an inference engine for executing the inference data creation process (S3) is determined in S2. The selection of the inference mode (S2) is executed when the user selects an arbitrary one from the inference mode selection switch 153 of the input panel 181. In addition, when an inference mode to be executed in the object specifying device 1 is set in advance, the set inference mode is automatically read and selected. If the user does not select an inference mode, the default inference mode is automatically set.

  Next, inference data creation processing (S3) for creating inference data based on information measured from the sensor is executed according to the inference mode selected in S2. In this embodiment, as an example, an inference data creation process in an inference mode in which inference data is created by referring to an inference definition table based on measurement values from each sensor is shown.

  As shown in FIG. 7, in the inference data creation process (S3), the measured values of the user's body temperature, sweat, and heart rate measured by each of the body temperature sensor 182, the sweat sensor 183, and the heart rate sensor 184 are respectively obtained. Obtained (S161). Next, it is determined whether or not the intention transmission switch 152 is “ON” (S162). If the intention transmission switch 152 is “ON” (S162: YES), each sensor measurement value acquired in S161 is corrected by a predetermined correction value (S163). The correction value is predetermined for each sensor, and this correction processing is executed for each measurement value of each sensor. For example, the body temperature correction value “1 ° C.” is added to the body temperature measurement value “36 ° C.” to be corrected to the body temperature measurement value “37 ° C.”. Similarly, the sweat measurement value is corrected by the sweat correction value, and the heart rate The number measurement value is corrected by the heart rate correction value. Then, an inference execution process is executed based on the sensor measurement values after correction (S164). On the other hand, if the intention transmission switch 152 is “OFF” (S162: NO), an inference execution process described later is executed based on each sensor measurement value acquired in S161 (S164). Then, inference data including the inference type and the inference value acquired in S164 is created (S165).

  As shown in FIG. 8, in the inference execution process (S164), a state variable which is a flag indicating a state change of a measurement value from each sensor is cleared (S171). In the present embodiment, three bits of the second bit for the body temperature measured by the body temperature sensor 182, the first bit for the sweating measured by the sweat sensor 183, and the 0th bit for the heart rate measured by the heart rate sensor 184 are in a state. As a variable. Then, referring to a reference value area (not shown) in the RAM 130, a change in the measured value from each sensor is determined based on the reference value of each sensor calculated in S107 (see FIG. 6).

  First, the body temperature measurement value acquired from the body temperature sensor 182 is compared with a reference value (body temperature threshold) related to body temperature (S172). The reference value (threshold value) is a value stored in a reference value area (not shown) of the RAM 130. As a result, if the measured body temperature is larger than the body temperature threshold (S172: YES), the second bit is set to “UP” (S173). On the other hand, when the body temperature measurement value is not larger than the body temperature threshold (S172: NO), the process proceeds to the next step (S174) as it is. Similarly, the perspiration measurement value acquired from the perspiration sensor 183 is compared with a reference value (perspiration threshold) related to perspiration (S174). If the perspiration measurement value is larger than the perspiration threshold (S174: YES), The first bit is set to “UP” (S175). On the other hand, when the perspiration measurement value is not larger than the perspiration threshold (S174: NO), the process proceeds to the next step (S176) as it is. Further, the heart rate measurement value acquired from the heart rate sensor 184 is also compared with a reference value (heart rate threshold value) relating to the heart rate (S176). As a result, if the heart rate measurement value is greater than the heart rate threshold value (S176) : YES), the 0th bit is set to “UP” (S177). On the other hand, when the heart rate measurement value is not larger than the heart rate threshold value (S176: NO), the process proceeds to the next step (S178).

  Thereafter, the inference type and the inference value corresponding to the patterns of the second bit, the first bit, and the 0th bit of the state variable are acquired from the inference definition table 13 (S178). As shown in FIG. 9, the inference definition table 13 includes an inference type 13a indicating the type of inference, a sensor state 13b indicating a change state of a measured value from each sensor, and an inference indicating the strength of the user's inference numerically. The value 13c is included as a data item. And the correspondence of each data item is defined in a table format. As described above, in this embodiment, inference data relating to the “impression” of the user is created, so the inference definition table 13 referred to also relates to “impression”. Therefore, the inference type 13a defines a type related to “impression”, and there are a plurality of types from “excitement” to “no impression (normal)” depending on the strength of the user's “impression”. Also, an inference value 13c that expresses the strength of the “feeling” as a numerical value is defined. For example, if the inference type 13a is “big excitement”, the inference value 13c is the maximum value “100”. Since the inference definition table 13 shown in FIG. 9 relates to “impression”, the inference value 13c is also displayed as the impression level (E). In S178, since the sensor state 13b is specified by the state variables set in S172 to S177, the inference type 13a and the inference value 13c corresponding to the sensor state 13b are acquired.

  Returning to FIG. 5, the RFID tag detection process is executed (S4). The RFID tag detection process is a process of detecting an RFID tag that exists in the vicinity of the object specifying device 1 and acquiring an object ID unique to the exhibit 9.

  As shown in FIG. 10, in the RFID tag detection process (S4), the RFID tag reader 160 detects the RFID tag 8 (number of detection tags = tn), and the number of continuous detections seq [0] to seq for each detected RFID tag. [Tn] is calculated (S201). That is, the total number of detected RFID tags 8 is defined as the number of detected tags tn, and the object ID acquired from the detected RFID tag 8 is ID [0], ID [1], ID [2]. Identified as ID [tn]. Further, the number of times seq [0] to seq [tn] continuously detected in time series for each object ID is calculated.

  Then, it is determined whether or not the RFID tag 8 is detected (S202). When the RFID tag 8 is detected (tn> 0) (S202: YES), the variable cnt is set to “0”, and the variable tntemp is set. The detection tag number tn is set (S203). Then, it is determined whether or not the variable cnt is smaller than the detection tag number tn (S204). If the variable cnt is smaller than the detection tag number tn (cnt <tn) (S204: YES), the ID [cnt ] Is continuously detected a predetermined number of times (S205). That is, only the RFID tag 8 that has transmitted / received a carrier wave and a reflected wave a predetermined number of times or more with the RFID tag reader 160 is regarded as an appropriately detected RFID tag 8. In the present embodiment, the RFID tag 8 is appropriately detected when it is continuously detected in time series five times or more (seq [cnt] ≧ 5).

  If ID [cnt] has not been detected continuously for a predetermined number of times (S205: NO), information indicating an error (error value) is set in ID [cnt] (S206), and the variable tntemp is decremented by “1” (S207). ), The variable cnt is incremented by “1” (S208), and the process returns to S204. On the other hand, if ID [cnt] has been continuously detected a predetermined number of times (S205: YES), the variable cnt is incremented by “1” (S208), and the process returns to S204.

  As described above, when the processing of S204 to S208 is repeated until the variable cnt is not smaller than the detection tag number tn (cnt ≧ tn) (S204: NO), the variable tntemp is set to the detection tag number tn (S209). ). As a result, information indicating an error (error value) is set for inappropriate ones of detected RFID tags 8, and the number of RFID tags 8 appropriately detected is set for the number of detection tags tn. Is done.

  Then, it is determined whether or not the RFID tag 8 is detected (S210). If not detected (tn = 0) (S210: NO), the process returns to FIG. When the RFID tag 8 is detected (tn> 0) (S210: YES), it is determined whether or not a plurality of RFID tags 8 are detected (S211). When a plurality of objects are not detected (tn = 1) (S211: NO), the detected object ID is output (S212), and the process returns to FIG. When a plurality of RFID tags 8 are detected (tn> 1) (S211: YES), output mode-specific processing (S213) is executed, and the process returns to FIG. Even when the RFID tag 8 is not detected (tn = 0) (S202: NO), the process returns to FIG.

  As shown in FIG. 11, in the output mode-specific processing (S213), the output mode at the time of multiple detection is determined (S221). In the present embodiment, “table mode”, “all output mode”, and “detection order mode” exist as output modes at the time of multiple detection, and any output mode is selected in advance from the output mode selection switch 154. . In S221, the selected output mode is determined. Note that the types of output modes are not limited to those described above, and it is only necessary that the user can select any one of a plurality of output modes.

  If it is determined in S221 that the mode is “all output mode”, all detected object IDs are output (S222), and the process returns to FIG.

  If the “table mode” is determined in S221, the following processing is performed. As shown in FIG. 12, in the image of the area distribution of the plurality of RFID tags 8, the RFID tag 8 with the object ID “tag 1” is displayed in the exhibit 9 “A”, and the object is displayed in the exhibit 9 “B”. The RFID tag 8 with the ID “tag 2” is given, and the RFID tag 8 with the object ID “tag 3” is given to the exhibit 9 “C”, respectively. And since the communication area (area displayed in a circle in FIG. 12) where each RFID tag 8 can perform wireless communication overlaps with each other, the object specifying device 1 depends on which RFID tag 8 communication area overlaps. Can be specified. For example, when the object IDs are detected from the RFID tag readers 160 of all exhibits 9, the object specifying device 1 can specify that the communication areas of the RFID tag readers 160 are all present in the “area s” that overlaps.

  As shown in FIG. 13, in the object ID specifying table 18, the correspondence between the detected object ID and the specified area is defined in a table format. By referring to the object ID identification table 18 based on the detected object ID, the area where the object identification device 1 exists is identified, and the object ID corresponding to the identified area is acquired. For example, when object IDs “tag 1” and “tag 2” are detected from a plurality of RFID tags 8, the area where these two object IDs are detected is “area P” (see FIG. 12). Therefore, the object specifying device 1 exists in the “area P”, and the object ID “tag 4” corresponding to the “area P” is acquired.

  As described above, if the output mode at the time of multiple detection is “table mode”, the object ID is acquired from the object ID specifying table 18 (S223), and the acquired object ID is output (S224). ), Returning to FIG. In addition, if information about interference areas such as communication areas where the RFID tags 8 overlap each other and communication areas where none of them can communicate with each other is stored in the object specifying device 1 in advance, the position of the user can be specified in more detail. can do.

  If it is determined in S221 that the mode is “detection order mode”, first, “0” is set in the variable cnt and “−1” is set in the variable max (S225), and whether or not the variable cnt is smaller than the number of detection tags tn. Is determined (S226). When the variable cnt is smaller than the variable tn (cnt <tn) (S226: YES), it is determined whether or not the continuous detection frequency seq [cnt] is larger than the variable max (S227). When the number of continuous detections seq [cnt] is larger than the variable max (seq [cnt]> max) (S227: YES), the ID [cnt] is set as the object ID (S228), and the variable max is set. The continuous detection frequency seq [cnt] is set (S229).

  When the number of continuous detections seq [cnt] is not greater than the variable max (seq [cnt] ≦ max) (S227: NO), or after the execution of S229, the variable cnt is incremented by “1” (S230), and the process proceeds to S226. Return. In this way, the processing of S226 to S230 is repeated until the variable cnt is not smaller than the detection tag number tn (cnt ≧ tn) (S226: NO), and the ID corresponding to the largest continuous detection count seq [cnt]. [Cnt] is set as the object ID. The set object ID is output (S231), and the process returns to FIG.

  Returning to FIG. 5, clock detection is executed (S5), date and time data indicating the current date and time is acquired by referring to the time measuring device 190, and object information output processing is executed (S11). As shown in FIG. 14, in the object information output process (S11), the inference data created in the inference data creation process (S3), the user ID that is identification data unique to the user, and RFID detection (S4). Object information is created based on the acquired object ID and date / time data acquired in clock detection (S5) (S301). As shown in FIG. 15, the object information 10 includes at least a user ID 10a, date / time data 10b, an inference value 10c, an inference type 10d, an object ID 10e, and switch information 10f. The inference value 10c and the inference type 10d correspond to the inference value 13c and the inference type 13a included in the inference data, respectively. In addition, a user ID 10a unique to the user stored in advance in the object specifying device 1 and switch information 10f indicating whether the intention transmission switch 152 is turned on or off by the user are included. The object information 10 created in S301 is stored in the object information storage area 144 (see FIG. 4) of the HDD 140 (S302).

  Thereafter, returning to FIG. 5, it is determined whether or not a predetermined time has passed (S12). This predetermined time is a time set in advance in the time measuring device 190, and in S12, with reference to the time measuring device 190, the passage of the predetermined time is determined. The predetermined time set in the time measuring device 190 can be set arbitrarily by the user or the designer.

  If the predetermined time has not elapsed (S12: NO), it is determined whether or not the intention transmission switch 152 is “ON” (S13). When the intention transmission switch 152 is not “ON”, that is, is “OFF” (S13: NO), the process returns to S12. Therefore, the processing of S12 to S13 is repeated until a predetermined time elapses or until the intention transmission switch 152 is turned “ON”.

  On the other hand, when the predetermined time has elapsed (S12: YES) or when the intention transmission switch 152 is “ON” (S13: YES), the process returns to S3 to create inference data, and the object information 10 is output. (S11). That is, in the object specifying device 1, the process of outputting the latest object information 10 is repeated every predetermined time or whenever the intention transmission switch 152 is turned “ON”. As a result, a plurality of pieces of object information 10 are stored in time series in the object information storage area 144 (see FIG. 4) of the HDD 140.

  As described above, according to the object identification device of the first embodiment, when a user looks around the exhibition 9 in a museum or the like, the measured value from each sensor and the RFID tag 8 are acquired. Based on the target object ID, it is possible to create target object information 10 indicating what feelings, consciousness, etc. the user has produced for which exhibition 9, and to increase the reliability of the inference result Can do.

  In addition, when a user “impresses” a specific exhibit 9, by arbitrarily inputting switch information from the intention transmission switch 152, the object information that the user is intentionally “impressed”. 10 and the accuracy of the object information 10 can be improved.

  In addition, when an object ID is automatically detected from the nearby RFID tag 8 by the RFID tag reader 160 and a plurality of object IDs are detected, the optimum object ID is determined according to the output mode arbitrarily selected by the user. Since it is output, the object information 10 can be created easily and accurately.

  Next, a second embodiment of the present invention will be described with reference to the drawings. In the popularity voting system according to the second embodiment, an object identification device that is a small portable terminal device carried by a user and a popularity analysis device that is a fixed computer device are connected via a network. It is a connected system.

  In the popularity voting system according to the present embodiment, when a user carrying an object identification device is impressed by seeing an exhibit at a museum or the like, he / she presses a predetermined switch in the vicinity of the exhibit to vote for popularity on the exhibit. I do. And the case where the object information created by each of the plurality of object specifying devices is collected by the popularity analysis device via the network and the popularity vote result of the exhibit is analyzed is illustrated.

  First, the configuration of the popularity voting system according to the second embodiment will be described with reference to FIGS. FIG. 16 is an overall configuration diagram of the popularity voting system. FIG. 17 is a block diagram showing another configuration of the object identification device 1. FIG. 18 is a block diagram showing the configuration of the popularity analysis device 2.

  As shown in FIG. 16, in the popularity voting system according to the present embodiment, each of the plurality of object specifying devices 1 and the popularity analysis device 2 are connected via a network 90. The user carries the object specifying device 1 and looks around each of the plurality of exhibits 9 at a museum or the like. The network 90 only needs to be effectively connected so that data can be transmitted and received between terminals regardless of wired or wireless.

  As shown in FIG. 17, each of the object specifying devices 1 has basically the same configuration as that of the first embodiment (see FIG. 2), but communication for connecting to an external network 90. It differs in the point provided with the part 170. The communication unit 170 only needs to be able to be effectively connected to the external network 90 by wire or wireless. For example, in this embodiment, the communication unit 170 is a wireless LAN adapter for executing connection with the network 90 by a wireless LAN. .

  As shown in FIG. 18, the popularity analysis apparatus 2 includes a CPU 210, a ROM 220, a RAM 230, an HDD 240, a display control unit 260 to which a display 261 is connected, a voice control unit 270 to which a microphone 271 and a speaker 272 are connected, and a mouse 281. And an input detection unit 280 to which a keyboard 282 is connected is provided via a bus 215. Such a configuration of the popularity analysis device 2 is known as a configuration of an ordinary computer device, and therefore details thereof are omitted. The popularity analysis device 2 is provided with a communication interface 291 for effectively connecting to the external network 90 by wire or wireless. The communication interface 291 is only required to be able to be effectively connected to the network 90. For example, in this embodiment, the communication interface 291 is a LAN card for cable connection to a wired LAN. Also, a popularity analysis program for executing a popularity analysis process described later is stored in a program storage area (not shown) of the HDD 240.

  Hereinafter, the flow of processing in the popularity voting system of the present invention will be described with reference to FIGS. FIG. 19 is a flowchart showing other details of the object information output process (S11) in the object specifying device 1. FIG. 20 is a main flowchart of popularity analysis processing in the popularity analysis device 2. FIG. 21 is a diagram for explaining the analysis execution process (S22). FIG. 22 is a diagram showing the contents of the time transition information 23. FIG. 23 is a flowchart showing details of exhibition optimization by the analysis execution process (S22). FIG. 24 is a diagram showing the contents of the optimization information 24.

  First, processing in the object specifying device 1 will be described. The processing in the object specifying device 1 is basically the same as that in FIG. 5, but the object information output process (S11) is different. As shown in FIG. 19, in the object information output process (S11), object information is created as in FIG. 14 (S301). Then, the object information created in S301 is transmitted from the communication unit 170 to the popularity analysis device 2 via the network 90 (S303). The object information transmitted to the popularity analysis device 2 is the same as the object information 10 shown in FIG.

  The execution timing of the transmission process in S303 is not limited to the creation of the object information 10, and the object information 10 created in S301 is stored in the object information storage area 144 (see FIG. 4) of the HDD 140. The transmission process of S303 may be executed every predetermined period or when there is an instruction from the user. The object information 10 transmitted to the popularity analysis device 2 is received by the communication interface 291 via the network 90 and is stored in an object information storage area (not shown) provided in the HDD 240 of the popularity analysis device 2. ).

  Next, processing in the popularity analysis device 2 will be described. In the popularity analysis device 2, a popularity analysis process for analyzing the popularity vote result of the exhibit 9 is executed based on a plurality of pieces of object information 10 collected in the object information storage area (not shown). The popularity analysis process is periodically executed at predetermined time intervals, or is executed when a process execution is instructed from the mouse 281 or the keyboard 282.

  As shown in FIG. 20, in the popularity analysis process, the object information 10 to be analyzed is read from the object information storage area (not shown) (S21). Here, all the object information 10 stored in the object information storage area (not shown) may be read, or only a part may be read. Moreover, you may enable it for the user to select the target object information 10 used as reading object.

  Next, based on the object information 10 read in S21, an analysis execution process (S22) is executed, and analysis information regarding the popularity of the exhibit 9 is created. The analysis information created in S22 is stored in an analysis information storage area (not shown) of the HDD 240 (S23). Here, as a method for creating analysis information based on the object information 10, various methods can be applied according to the purpose and use form, and what kind of content the analysis information is created by the user or design Is voluntary. Below, the example of the process in S22 is shown.

  When the analysis information is created for the popularity vote for each user indicating which exhibition 9 the user “impressed” and which exhibition 9 has been voted for popularity, based on the user ID 10a (see FIG. 15). The object information 10 is totaled for each user. As a result, as shown in FIG. 21, the impression (E) 21a indicating the inference value 10c for “impression”, the ON / OFF 21b of the popular vote switch (intention transmission switch 152) indicating the switch information 10f, and the object ID 10e User-specific popularity information 21 associated with an exhibit 21c indicating the corresponding exhibit 9 is created for each user. If such user-specific popularity degree information 21 is utilized, a user's preference can be grasped.

  In addition, in the case of creating analysis information on the exhibition-specific popularity vote indicating which exhibition 9 has given the user “impression” and which exhibition 9 the popularity vote has gathered, the object ID 10e (FIG. 15). The object information 10 is tabulated for each exhibit 9 based on the reference). As a result, as shown in FIG. 21, the average sensitivity (E) 22a obtained by dividing the total number of users of the sensitivity (E) to the exhibition 9 by the number of users, and the popularity vote switch ( The popularity information 22 for each exhibit 9 is created for each exhibit 9 in association with the ratio 22b of the person who turned on the intention transmission switch 152). By using such popularity information 22 by exhibit, the popularity of the exhibit 9 can be grasped.

  Further, when creating analysis information indicating the transition of popularity of each exhibit 9 over time, the popularity information 22 by exhibit for each unit time is created based on the date / time data 10b (see FIG. 15). . Then, when the average sensitivity (E) obtained by dividing the total of all the users of the sensitivity (E) to the exhibition 9 by the number of users is obtained for each unit time, and graphed in time series, FIG. The time transition information 23 shown can be created. FIG. 22 shows the transition of the average sensitivity (E) every two hours from 8 o'clock to 22 o'clock for the exhibit 9 “A” and the exhibit 9 “B”. By using such time transition information 23, the popularity of the exhibition 9 for each time zone can be grasped. Similarly, the time transition information 23 may be created by the ratio of those who turned on the popularity vote switch (the intention transmission switch 152) for all users per unit time.

  Furthermore, as an analysis execution process (S22), an exhibition optimization process for optimizing the arrangement of the exhibits 9 can be executed. In the following, an example of exhibition optimization for the exhibit 9 “A” and the exhibit 9 “B” shown in FIG. 22 is shown as an example. As shown in FIG. 23, in the exhibition optimization process, first, time transition information 23 (see FIG. 22) is created as described above (S401). Next, each parameter necessary for this processing is initialized, and “8” is set as the time t (S402). Then, it is determined whether or not the time t is longer than “22” (S403). If the time t is not greater than “22” (t ≦ 22) (S403: NO), the sensitivity (E) of the exhibit 9 “A” is the sensitivity of the exhibit 9 “B” at the time t. It is determined whether it is greater than (E) (S404). If the sensitivity (E (A)) of the exhibit 9 “A” is greater than the sensitivity (E (B)) of the exhibit 9 “B” (E (A)> E (B)) (S404) : YES), the sensitivity (E (A)) is set in the variable S [t] at time t (S405). On the other hand, if the sensitivity (E (A)) of the exhibit 9 “A” is not greater than the sensitivity (E (B)) of the exhibit 9 “B” (E (A) ≦ E (B)) (S404: NO), the sensitivity (E (B)) is set to the variable S [t] at time t (S406). Thereafter, “2” is added to the time t (S407), and the process returns to S403. In this way, S403 to S407 are repeated, and the maximum sensitivity (E) every 2 hours from 10:00 to 22:00 is set in the variable S [t]. If the time t is greater than “22” (t> 22) (S403: YES), the parameter array S for the variable S [t] is output as the optimization information 24 (S408).

  As shown in FIG. 24, in the optimization information 24, the one having the higher impression level (E) for each time zone is displayed among the exhibit 9 “A” and the exhibit 9 “B”. By utilizing such optimization information 24, it is possible to grasp which exhibitions are exhibited at which time periods and which maximum utility can be obtained.

  As described above, according to the popularity voting system of the second embodiment, when each user looks around the exhibition 9 at a museum or the like, each object specifying device 1 uses which exhibition 9 The object information 10 indicating what kind of emotion or consciousness is generated is generated and transmitted to the popularity analysis device 2, so that the object information 10 can be collected and managed by the popularity analysis device 2.

  In addition, the popularity analysis device 2 executes popularity analysis processing for analyzing the popularity vote result of the exhibit 9, so that the user's preference and popularity of the exhibit 9 can be grasped by using the analysis result. And the range of use of the object information 10 can be expanded.

  In addition, the user can vote for the exhibition 9 by pressing the intention transmission switch 152 in the vicinity of the exhibition 9, and the popularity vote has been received (the intention transmission switch 152 has been turned “ON”). The reflected object information 10 can be created.

  By the way, in the first and second embodiments, the input detection unit 180 (FIG. 1) that detects the input of the measurement value from the body temperature sensor 182, the sweat sensor 183, and the heart rate sensor 184 is the “measurement” of the present invention. It corresponds to “value acquisition means”. The CPU 110 that executes the inference engine corresponding to the inference data creation process (S3) shown in FIG. 7 corresponds to the “inference data creation means” of the present invention. The CPU 110 that executes S301 in the object information output process (S11) shown in FIG. 14 or FIG. 19 corresponds to the “object information creating means” of the present invention, and the CPU 110 that executes S302 or S303 of the present invention “ This corresponds to “object information output means”. The intention transmission switch 152 corresponds to “user information input means” of the present invention, and the output mode selection switch 154 corresponds to “output mode selection means” of the present invention.

  The exhibit 9 corresponds to the “object” in the present invention, and the object ID is “identification data” in the present invention. The RFID tag 8 is the “recording medium” in the present invention, and the RFID tag reader 160 corresponds to the “identification data acquisition unit” in the present invention. The communication unit 170 corresponds to “object information transmitting means” of the present invention, and the communication interface 291 corresponds to “object information acquisition means” and “object information receiving means” of the present invention. The HDD 140 and the HDD 240 correspond to the “object information storage unit” of the present invention. CPU210 which performs the analysis execution process (S22) shown in FIGS. 21-24 corresponds to the "analysis information preparation means" and the "popularity analysis means" of this invention.

  The present invention is not limited to the first and second embodiments described in detail above, and it goes without saying that various modifications are possible.

  For example, in the above embodiment, the object ID is acquired from the RFID tag 8 by the RFID tag reader 160 in the RFID tag detection (S4) shown in FIG. However, the object ID of the exhibit 9 may be acquired by other means. For example, the present invention may be realized by a barcode reader that reads an object ID from a barcode assigned to the exhibit 9, or a CCD camera that reads the object ID from a two-dimensional barcode assigned to the exhibit 9. You may implement | achieve this invention by. Further, the RFID tag reader 160 is provided with a function for measuring the distance to the RFID tag 8 and the object specifying device 1 is provided with a means for measuring the distance to the RFID tag 8, and the distance value to the RFID tag 8 is obtained to be the closest. An object at a distance may be specified as the exhibit 9 to be detected.

  Further, the object information creation process shown in FIG. 5 is executed regularly or in response to an instruction from the user, but may be executed at other timing. For example, the object information creation process may be executed when the RFID tag 8 detected by the RFID tag reader 160 changes to another RFID tag 8. In addition, the object information 10 created by the object identification device 1 is transmitted to the popularity analysis device 2, but the measurement values from each sensor are directly transmitted from the object identification device 1 to the popularity analysis device 2. Then, the object information creation processing (FIG. 5) and the popularity analysis processing (FIG. 20) may be executed together by the popularity analysis device 2.

  Further, in the present embodiment, the object information 10 is transmitted to the popularity analysis device 2 in real time, but various methods can be applied as a method for collecting the object information 10 in the popularity analysis device 2. For example, the object identification device 1 is lent to visitors at the entrance of a museum or museum, the object identification device 1 is collected at the exit, and the object information 10 stored in the object identification device 1 is popular at once. You may take out to degree analysis apparatus 2. In addition, a communication unit for communicating with the object identification device 1 and taking out the object information 10 is provided at an exit of a museum or a museum, and when a visitor carrying the object identification device 1 passes through the exit, The object information 10 may be automatically collected from the object specifying device 1.

  Moreover, the object identification device 1 carried by the user can have various forms. For example, a wristband type wound around the user's wrist or a small earphone type inserted into the user's ear may be used. Further, if the object identification device 1 is formed integrally with a digital camera, the object ID can be read from the two-dimensional barcode given to the exhibit 9 as described above.

  The inference data creation process (S11) is not limited to that shown in FIG. 7, and various processes are possible depending on the inference mode selected in the inference mode selection (S2). FIG. 25 is a diagram showing the data structure of the correction table 14, and the correction table 14 may be used for processing as follows. Based on the measured value from each sensor, the inference execution process (S164) of S164 is executed to acquire the inference type 13a and the inference value 13c. If the intention transmission switch 152 is ON, the correction value 14c at the time of switch ON corresponding to the inference type 13a (14a) and the inference value 13c (14b) is acquired with reference to the correction table 14. The corrected inference type 14d and inference value 14e are obtained from the correction value 14c when the switch is ON.

  Further, in the above embodiment, the case where the object information 10 is inferred about “impression” has been described. However, in addition to the user's emotion and consciousness, The object information 10 may be inferred with respect to an abstract concept (also referred to as a context) that indicates the context and context of the context and cannot be grasped only by facts and evidence. Therefore, the object information 10 inferred about “sadness”, “anger”, “fun”, “liveness”, “busy”, etc. may be created. And the inference definition table 13 corresponding to the inference content of each object information 10 may be set. For example, when it is desired to create the object information 10 based on the user's “sadness”, the inference definition table 13 corresponding to “sadness” may be set.

  In addition, in the inference definition table 13, a table for arbitrary inference contents may be set in advance by the user or the designer, and a plurality of tables corresponding to each of a plurality of inference contents are included in the inference definition table 13. It may be set in advance, and an optimum table may be automatically selected in the inference data creation process (FIG. 7).

  In addition, in the inference engine initialization process (FIG. 6), the sampling value is measured and the average value is calculated as the reference value, but the time-series data of the sampling value is acquired and based on the characteristics of the transition The reference value may be calculated. Further, the reference value may be calculated by excluding abnormal sampling values. Further, in the comparison process (S172, S174, S176) in the inference execution process (FIG. 8), a change threshold value ε is provided for each sensor, and the correction value obtained by correcting the threshold value with the change threshold value ε Comparison with the measured value may be performed. For example, as the allowable error range of the change threshold ε, about 5% of the threshold is set. Further, in the present embodiment, the state change is determined by comparing the measured value from each sensor with a threshold value, but a predetermined reference value is subtracted from the measured value from each sensor to obtain an increment value, The state change may be determined by comparing whether the increment value is larger or smaller than a threshold value.

  Needless to say, the measured values from each sensor are not limited to body temperature, sweating and heart rate. For example, the vibration, brain wave, respiration, acceleration, inclination, biorhythm, etc. of the user may be measured from the user. Further, each sensor (body temperature sensor 182, sweat sensor 183, heart rate sensor 184) and input panel 181 do not need to be integrated with the object identification device 1, and are input via an interface such as a USB or network. It is only necessary to remotely connect to the detection unit 180 and effectively acquire measurement values and input information.

  Similarly, in the popularity analysis device 2, the display 261, the microphone 271, the speaker 272, the mouse 281 and the keyboard 282 are not necessarily required configurations, so that an external display device, microphone, Remote control may be performed by remotely connecting to a speaker or the like.

  Further, a plurality of popularity degree analysis devices 2 may be provided in the popularity voting system. Moreover, it is good also as an apparatus by which the target object identification apparatus 1 and the popularity analysis apparatus 2 were comprised integrally. On the contrary, the object identification device 1 may be one.

  The object specifying device, the object specifying system, and the popularity voting system according to the present invention can be applied to a computer device for inferring a user's consciousness, emotion, and the like regarding a specific object.

1 is an overall configuration diagram of an object identification device 1. FIG. 1 is a block diagram illustrating a configuration of an object specifying device 1. FIG. 3 is a conceptual diagram showing a configuration of a storage area of a RAM 130 of the object specifying device 1. FIG. 3 is a conceptual diagram illustrating a configuration of a storage area of an HDD 140 of the object specifying device 1. FIG. It is a main flowchart of object information creation processing. It is a flowchart which shows the detail of an inference engine initialization process (S1). It is a flowchart which shows the detail of an inference data creation process (S3). It is a flowchart which shows the detail of an inference execution process (S164). It is a figure which shows the data structure of the inference definition table. It is a flowchart which shows the detail of RFID tag detection processing (S4). It is a flowchart which shows the detail of the process according to output mode (S213). It is an image figure of area distribution of a plurality of RFID tags. It is a figure which shows the data structure of the target object ID specific table. It is a flowchart which shows the detail of a target object information output process (S11). It is a figure which shows the data structure of the target object information. It is a whole block diagram of a popularity voting system. It is a block diagram which shows the other structure of the target object identification apparatus. 3 is a block diagram showing a configuration of a popularity analysis device 2. FIG. It is a flowchart which shows the other detail of the target object information output process (S11) in the target object identification apparatus 1. 4 is a main flowchart of popularity analysis processing in the popularity analysis device 2. It is a figure for demonstrating an analysis execution process (S22). It is a figure which shows the content of the time transition information 23. FIG. It is a flowchart which shows the detail of the exhibition optimization by an analysis execution process (S22). It is a figure which shows the content of the optimization information 24. FIG. It is a figure which shows the data structure of the correction table.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Object identification apparatus 2 Popularity analysis apparatus 8 RFID tag 9 Exhibit 10 Object information 13 Inference definition table 14 Correction table 18 Object ID identification table 21 Popularity information according to user 22 Popularity information according to exhibition 23 Time transition Information 24 Optimization information 90 Network 110 CPU
115 bus 120 ROM
130 RAM
140 HDD
151 Power Reset Switch 152 Communication Switch 153 Inference Mode Selection Switch 154 Output Mode Selection Switch 160 RFID Tag Reader 170 Communication Unit 180 Input Detection Unit 181 Input Panel 182 Body Temperature Sensor 183 Sweating Sensor 184 Heart Rate Sensor 190 Timing Unit 210 CPU
215 bus 220 ROM
230 RAM
240 HDD
260 Display Control Unit 261 Display 270 Audio Control Unit 271 Microphone 272 Speaker 280 Input Detection Unit 281 Mouse 282 Keyboard 291 Communication Interface

Claims (13)

Identification data acquisition means for detecting an object and acquiring identification data of the object;
Measurement value acquisition means for acquiring measurement values from at least one sensor;
Based on the measurement value acquired by the measurement value acquisition means, inference data creation means for creating inference data that is an index value different from the measurement value;
Object information creating means for creating object information including the identification data acquired by the identification data acquiring means and the inference data created by the inference data creating means;
An object specifying device comprising: object information output means for outputting the object information created by the object creating means.   The object identification device according to claim 1, wherein the identification data acquisition unit acquires the identification data from a recording medium attached to the object or a vicinity of the object.   The object identification device according to claim 2, wherein the identification data acquisition unit is an RFID tag reader that reads the identification data from an RFID tag that is the recording medium. Provided with user information input means for the user himself / herself to input user information,
The inference data creation means creates the inference data based on the measurement value acquired by the measurement value acquisition means and the user information input from the user information input means. The object specifying device according to any one of claims 1 to 3.   The inference data creation means creates the inference data to indicate strong inference of the user when the content of the user information indicating the on / off state transition of the user information input means is on. The object specifying device according to claim 4.   When the identification data acquisition means acquires the identification data from each of a plurality of objects, any one of a plurality of output modes defining a method for specifying the object to be output as the object information. 6. The object specifying device according to claim 1, further comprising output mode selection means for selecting one.   The identification data acquisition means performs detection on the object periodically and a plurality of times, and based on the continuity before and after the time series data acquired by the detection, the object information is the object information. The object specifying device according to any one of claims 1 to 6, wherein it is determined whether or not to be output.   In the case where the identification data acquisition means performs periodic and multiple detections on the object, and indicates that the time-series data acquired by the detection is continuously detected a predetermined number of times. The target object specifying apparatus according to claim 7, wherein the target object is an output target of the target object information. It has time measuring means to measure the current date and time,
When the inference data is created by the inference data creation means, the object information creation means obtains date / time data related to the current date / time measured by the timing means, and includes the date / time data and the object The object identifying device according to claim 1, wherein information is created. The object identifying device according to any one of claims 1 to 9,
Object information acquisition means for acquiring the object information output by the object information output means;
An object identification system comprising: object information storage means for storing the object information collected by the object information acquisition means.   11. The apparatus according to claim 10, further comprising analysis information creating means for creating analysis information indicating a relationship between the target object and a user based on the target object information stored in the target object information storing means. Object identification system. A popularity voting system in which an object identification device for creating object information and a popularity analysis device for analyzing the popularity of the object based on the object information are connected via a network,
The object specifying device includes:
Identification data acquisition means for detecting the object and acquiring identification data of the object;
Measurement value acquisition means for acquiring measurement values from at least one sensor;
A user information input means for the user himself / herself to input user information,
Inference data creation means for creating the inference data based on the measurement value acquired by the measurement value acquisition means and the user information input from the user information input means;
Object information creating means for creating the object information including the identification data obtained by the identification data obtaining means and the inference data created by the inference data creating means;
Object information transmitting means for transmitting the object information created by the object information creating means to the popularity analysis device;
The popularity analysis device
Object information receiving means for receiving the object information transmitted from the object specifying device;
Object information storage means for storing the object information received by the object information receiving means;
A popularity voting system comprising: popularity analysis means for analyzing the popularity of the object based on the object information stored in the object information storage means. The said popularity analysis means analyzes the popularity of the said object, optimizes the arrangement | positioning of this object, and produces the optimization information which shows the optimal arrangement | positioning of the said object. The popular voting system described.

Images