Information analysis system

Abstract

This information analysis system comprises a motion information acquisition unit, a position information acquisition unit, a product information acquisition unit, a creation unit that determines a viewing time during which a person was facing a viewed product, and creates first information associating product identification information with the viewing time, and a purchase information acquisition unit that acquires purchase information including at least one of product identification information of a purchased product, which is a product purchased by the person among the plurality of products, and product identification information of a non-purchased product, which is a product not purchased by the person. The creation unit performs second information creation processing for creating second information associating the product identification information, the viewing time, and information on whether or not the person made a purchase with one another by using the created first information and the acquired purchase information.

Description

Information Analysis System

[0001] The present disclosure relates to an information analysis system.

[0002] Conventionally, sales information at retail stores has been analyzed for use in inventory management, etc. For example, in the system disclosed in Patent Document 1, the sales information includes purchase data indicating the time of purchase of the product and a purchase header indicating the attributes of the purchaser, and the analysis is performed for each customer.

[0003] Japanese Patent Application Laid-Open No. 2002-24295

[0004] Sales information can provide information on products that customers have actually purchased, but it cannot provide information on products that customers have considered purchasing but did not end up purchasing.

[0005] The present disclosure can be realized in the following forms.

[0006] (1) According to one aspect of the present disclosure, an information analysis system is provided, the information analysis system including: a motion information acquisition unit that acquires motion information representing a motion of a person's head; a position information acquisition unit that acquires position information of the person; a product information acquisition unit that acquires product position information regarding a plurality of products visible to the person, the product position information being associated with pre-assigned product identification information and information indicating a position for each product; a product information acquisition unit that compares the acquired motion information and the acquired position information with the acquired product position information to identify at least one visual product that is at least one product toward which the person is pointing, among the plurality of products included in the product position information, and a product information acquisition unit that uses the acquired motion information to identify at least one visual product toward which the person is pointing, the product information acquisition unit that acquires motion information representing a motion of the person's head; The system includes a creating unit that calculates the amount of time the person looked at a product and creates first information that associates the product identification information with the viewing time, and a purchasing information acquiring unit that acquires purchasing information including at least one of the product identification information for at least one purchased product that is at least one product purchased by the person among the plurality of products and the product identification information for at least one non-purchased product that is at least one product not purchased by the person among the plurality of products. The creating unit performs a second information creating process that uses the created first information and the acquired purchasing information to create second information that associates the product identification information, the viewing time, and information on whether the person purchased the product. According to this aspect, by using the second information, it is possible to obtain information on displayed products that the customer looked at but did not purchase, i.e., products that were candidates for purchase and were considered for purchase. Therefore, the second information can be utilized, for example, in sales strategies.(2) In the above aspect, the at least one visually inspected product may include a plurality of visually inspected products, the at least one non-purchased product may include a plurality of non-purchased products, and the plurality of visually inspected products may include the at least one purchased product and the plurality of non-purchased products, and the creation unit may perform a third information creation process using the second information to create third information that associates the product identification information with evaluation values ​​indicating the person's attention to the plurality of products, and in the third information creation process, the creation unit may assign a predetermined first evaluation value as the evaluation value to a non-purchased product among the plurality of non-purchased products that has the longest visual inspection time, assign a second evaluation value smaller than the first evaluation value to a non-purchased product among the plurality of non-purchased products that has a shorter visual inspection time than the non-purchased product to which the first evaluation value has been assigned, and assign a third evaluation value equal to or greater than the first evaluation value to the at least one purchased product. Products with longer visual inspection times are considered to be products that have attracted more attention from customers. Therefore, according to this embodiment, the third information can be used to identify, from among multiple products, which products have the highest evaluation values ​​and have attracted the customer's attention. (3) In the above embodiment, the system may further include an attribute information acquisition unit that acquires attribute information related to the person's attributes, and the creation unit may perform a fourth information creation process that creates fourth information by associating the attribute information with the third information. According to this embodiment, the fourth information can be used to analyze the relationship between the person's attributes and products with high evaluation values. (4) In the above embodiment, the system may further include a behavioral information acquisition unit that acquires behavioral information regarding whether the person picked up at least one visually inspected product, and the creation unit may perform a first update process that updates the third information for a non-purchased product picked up by the person among the multiple non-purchased products by adding a predetermined first additional value to the evaluation value assigned in the third information creation process. According to this embodiment, the evaluation value of a product picked up by a customer can be increased.(5) In the above aspect, the system may further include an advertising information acquisition unit that acquires advertisement viewing information indicating whether the person turned their face toward an advertisement for each of the plurality of products, and the creation unit may perform a second update process to update the third information for a non-purchased product among the plurality of non-purchased products corresponding to an advertisement that the person turned their face toward by adding a predetermined second additional value to the evaluation value assigned in the third information creation process. According to this aspect, when an advertisement for a product is displayed, the evaluation value of the product whose advertisement the customer viewed can be increased. (6) In the above aspect, the plurality of products are displayed in a store, and the creation unit may set a period from when the person enters the store to when the person leaves the store as one period and create the third information for each period. The creation unit may perform a third update process to update the third information for a product among the plurality of non-purchased products included in the second information for the previous period that the person turned their face toward but did not purchase by adding a predetermined third additional value to the evaluation value assigned in the third information creation process. According to this aspect, it is possible to increase the evaluation value of a product that was a candidate for purchase but was not purchased last time. (7) In the above aspect, the multiple products are displayed in the same store, and the creation unit may set a period from when the person entered the store to when they left the store as one period, create the third information for each period, and include a weather information acquisition unit that acquires weather information for the period. The creation unit may perform a fifth information creation process that creates fifth information by associating the weather information with the third information. According to this aspect, it is possible to analyze the relationship between the weather information and products with high evaluation values ​​using the fifth information. (8) In the above aspect, the fourth information may include an information group acquisition unit that acquires an information group accumulated for multiple people, and an extracted information creation unit that creates extracted information by extracting the fourth information with the same attributes of the people from the information group. According to this aspect, it is possible to analyze the fourth information with the same attributes of the people using the extracted information. (9) In the above aspect, the movement information may be information acquired using a motion sensor worn on the person's head. According to this aspect, the movement information can be acquired using the motion sensor.The present disclosure can be realized in various forms, and in addition to the above-mentioned information analysis system, it can be realized in the form of, for example, an information analysis method, an information analysis program, a non-transitory tangible recording medium on which an information analysis program is recorded in a computer-readable manner, etc.

[0007] 1 is a block diagram showing the configuration of an information analysis system; FIG. 2 is a diagram explaining purchasers to be processed by the information analysis system; FIG. 3 is a diagram explaining detection by a motion sensor; FIG. 4 is a block diagram showing the configuration of an image analysis device; FIG. 5 is a flowchart showing the procedure of first information creation processing; FIG. 6 is a diagram explaining first information; FIG. 7 is a diagram explaining second information; FIG. 8 is a flowchart showing the procedure of third information creation processing; FIG. 9 is a diagram explaining third information; FIG. 10 is a block diagram of an information processing device of a second embodiment; FIG. 11 is a diagram explaining fourth information and fifth information; FIG. 12 is a block diagram of an information processing device of a third embodiment; FIG. 13 is a diagram explaining extracted information.

[0008] A. First Embodiment: A1. Configuration of Information Analysis System: Fig. 1 is a block diagram showing the configuration of an information analysis system 1. Fig. 2 is a diagram explaining a purchaser PU that is a processing target of the information analysis system 1. The purchaser PU carries an ear-worn device 80 and a mobile terminal device 90.

[0009] As shown in Fig. 1, the information analysis system 1 includes an information processing device 10, a mobile terminal device 90, and an ear-worn device 80. The information processing device 10 is configured as a computer in which a processor 20, a storage unit 30, and a communication unit 40 are interconnected by a bus (not shown). The processor 20 performs various processes by executing programs stored in the storage unit 30. The processor 20 includes, as functional units, a motion information acquisition unit 21, a position information acquisition unit 22, a product information acquisition unit 23, a creation unit 24, and a purchase information acquisition unit 25. Each functional unit is realized by executing a program stored in the storage unit 30.

[0010] The storage unit 30 is realized by a memory such as a RAM or a ROM. The storage unit 30 stores product position information 31, operation information 32, position information 33, purchase information 34, first information 35, second information 36, and third information 37. The communication unit 40 communicates with external devices such as the mobile terminal device 90 and an image analysis device 60 (described later) via a network such as the Internet.

[0011] The product information acquisition unit 23 acquires product position information 31. The product position information 31 is information in which a "product ID" as product identification information previously assigned to the product ME shown in FIG. 2 is associated with information indicating a position. In this embodiment, the product ME included in the product position information 31 is a product that is displayed in the store ST and is visible to people, specifically, the purchaser PU. In this embodiment, the information indicating a position included in the product position information 31 includes the fields of "shelf ID," "tier," and "X position." An identifier previously assigned to the product shelf SH in the store ST is input in the "shelf ID" field. A number indicating the tier from the bottom of the product shelf SH is input in the "tier" field. A dimension based on the left end, which is the position on the same tier, is input in the "X position" field.

[0012] The motion information acquisition unit 21 shown in Fig. 1 acquires motion information 32. The motion information 32 is information representing head motion generated using a motion sensor 81 built into an ear-worn device 80 worn on the head of a purchaser PU shown in Fig. 2 .

[0013] The location information acquisition unit 22 shown in FIG. 1 acquires location information 33. The location information 33 is location information of the consumer PU created using a location information acquisition unit 94 attached to the consumer PU shown in FIG. 2. In this disclosure, "attached to a person" includes a state in which the device is fixed to the person's body and a state in which the device is carried by the person. Specific examples of the "state in which the device is carried by a person" include a state in which the device is held in the person's hand or placed in a bag worn by the person. As will be described later, in this embodiment, the motion sensor 81 is built into the ear-worn device 80. The location information acquisition unit 94 is built into the portable terminal device 90 carried by the consumer PU.

[0014] The information processing device 10 communicates with each of the mobile terminal device 90 and the image analyzing device 60. As shown in Fig. 2, the mobile terminal device 90 is carried by a purchaser PU. The purchaser PU carrying the mobile terminal device 90 also wears an ear-worn device 80.

[0015] As shown in Fig. 1, the ear-worn device 80 has a pair of housings 80a each incorporating a motion sensor 81, a sound conversion unit 82, a microphone 83, and a communication unit 84, all of which are shown in Fig. 3. The motion sensor 81 and the microphone 83 may be incorporated in both of the pair of housings 80a, or may be incorporated in either one of the housings 80a.

[0016] The motion sensor 81 detects the movement of the head of the purchaser PU. Specifically, the motion sensor 81 is a general-purpose so-called six-axis motion sensor. Specifically, the motion sensor 81 includes a three-axis acceleration sensor and a three-axis angular velocity sensor. The motion sensor 81 detects the acceleration [m / s ２ ] and the angular velocity [deg / s] of each of the three axes.

[0017] FIG. 3 is a diagram illustrating detection by the motion sensor 81. As shown in FIG. 3, the three axes along which the motion sensor 81 detects acceleration and angular velocity are, specifically, the yaw axis, roll axis, and pitch axis, which are perpendicular to each other. The yaw axis is an axis parallel to the up-down direction relative to the customer PU. The roll axis is an axis parallel to the front-back direction relative to the customer PU. The pitch axis is an axis parallel to the left-right direction relative to the customer PU. With respect to the acceleration along the yaw axis, the motion sensor 81 outputs a positive value when the customer PU moves their head up, and a negative value when the customer PU moves their head down. With respect to the acceleration along the roll axis, the motion sensor 81 outputs a positive value when the customer PU moves their head forward, and a negative value when the customer PU moves their head back. With respect to the acceleration along the pitch axis, the motion sensor 81 outputs a positive value when the customer PU moves their face to the left, and a negative value when the customer PU moves their head to the right. The motion sensor 81 outputs a positive value for the angular velocity of the yaw axis when the consumer PU turns his / her face to the right, and a negative value when the consumer PU turns his / her face to the left. The motion sensor 81 outputs a positive value for the angular velocity of the roll axis when the consumer PU tilts his / her head to the left, and a negative value when the consumer PU tilts his / her head to the right. The motion sensor 81 outputs a positive value for the angular velocity of the pitch axis when the consumer PU turns his / her face down, and a negative value when the consumer PU turns his / her face up. Therefore, head movement can be detected from changes in acceleration and angular velocity on each of the three axes.

[0018] The sound conversion unit 82 shown in Fig. 1 converts sound data, which is an electrical signal, into sound and emits it toward the ear of the purchaser PU. The microphone 83 converts the sound into sound data, which is an electrical signal, and outputs the acquired voice data to the communication unit 84. The communication unit 84 performs short-range communication with the mobile terminal device 90. In this embodiment, the communication unit 84 and the mobile terminal device 90 communicate in accordance with Bluetooth (registered trademark). The communication unit 84 is realized by an electronic circuit or the like.

[0019] In this embodiment, the mobile terminal device 90 is a smartphone. The mobile terminal device 90 includes a processor 91, a storage unit 92, a display operation unit 93, a position information acquisition unit 94, a sensor unit 95, and a communication unit 96.

[0020] The processor 91 performs various processes by executing programs stored in the storage unit 92. The storage unit 92 is realized by a memory such as a RAM or a ROM. An information provision application program 97 is stored in the storage unit 92. The display operation unit 93 has a touch panel. The display operation unit 93 displays information on the touch panel and accepts operations input to the touch panel.

[0021] The position information acquisition unit 94 has a GNSS (Global Navigation Satellite System) receiver (not shown) and receives signals from positioning satellites under the control of the processor 91. In this embodiment, the position information acquisition unit 94 uses the GPS (Global Positioning System) as the GNSS. The position information acquisition unit 94 may acquire position information using other satellite positioning systems such as the Quasi-Zenith Satellite System. The sensor unit 95 includes a geomagnetic sensor and an acceleration sensor. The position information acquisition unit 94 may correct the position information using a detection value from the sensor unit 95, radio waves from a base station of a mobile communication system, radio waves from an access point of a wireless LAN (Local Area Network), etc.

[0022] The communication unit 96 performs short-range communication with the communication unit 84 of the ear-worn device 80. The communication unit 96 also communicates with the communication unit 40 of the information analysis system 1 using a mobile communication system such as 5G (5th Generation Mobile Communication System). The communication method between the communication unit 96 and the communication unit 40 of the information analysis system 1 is not limited to a mobile communication system, but may also be a method using a wireless LAN, or a combination of these. The communication between the ear-worn device 80 and the mobile terminal device 90 is not limited to wireless communication, but may also be wired communication.

[0023] The processor 91 of the mobile terminal device 90 executes the information provision application program 97 to sequentially transmit the motion information acquired by the motion sensor 81 and the position information acquired by the position information acquisition unit 94 to the information analysis system 1. The information analysis system 1 stores the received motion information 32 and position information 33 in the storage unit 30.

[0024] FIG. 4 is a block diagram showing the configuration of the image analysis device 60. As shown in FIG. 2, in this embodiment, the image analysis device 60 is installed in a store ST in which an imaging device 70 is also installed. Product shelves SH are arranged in the store ST. Products ME are displayed on the product shelves SH. Specifically, the imaging device 70 is a camera having an image sensor. The image sensor is a sensor that converts light into an electrical signal, such as a CCD (Charge-Coupled Device) image sensor. The imaging device 70 is installed so that it can capture images of the products ME and the purchaser PU. Note that while FIG. 2 shows only one imaging device 70, multiple imaging devices 70 may be installed in the store ST.

[0025] 4, the image analysis device 60 is configured as a computer in which a processor 61, a storage unit 63, and a communication unit 66 are interconnected by a bus. The processor 61 performs various processes by executing programs stored in the storage unit 63. The processor 61 has an image analysis unit 62 as a functional unit. The image analysis unit 62 is realized by executing the programs stored in the storage unit 63.

[0026] The storage unit 63 is realized by a memory such as a RAM or a ROM. The communication unit 66 and the imaging device 70 are connected via a video cable. The communication unit 66 communicates with the communication unit 40 of the information processing device 10 using a mobile communication system such as 5G. The communication method between the communication unit 66 and the communication unit 40 of the information processing device 10 is not limited to a mobile communication system, and may be a method using a wireless LAN, or a combination of these. The image analysis device 60 is used in a second embodiment described below.

[0027] A2. First information creation process: The information provision application program 97 determines whether the purchaser PU has entered the store ST. Specifically, if the information provision application program 97 determines, using the location information acquired by the location information acquisition unit 94, that the current location of the purchaser PU is within a predetermined reference location range, it determines that the purchaser PU has entered the store ST. Here, the reference location range is a location range that indicates the area inside the store ST. When the information provision application program 97 determines that the purchaser PU has entered the target store OST, it sends a start request message to the information processing device 10. When the processor 20 of the information processing device 10 receives the start request message, it starts the first information creation process.

[0028] 5 is a flowchart showing the steps of the first information creation process. In step S10, the creation unit 24 determines whether the detected speed Sm obtained from the acceleration detection value of the motion sensor 81 is equal to or less than a reference speed Smth. The reference speed Smth is a speed used to determine whether the purchaser PU has stopped to select a product ME, and is determined in advance through experiments, etc. The reference speed Smth is, for example, 0.5 m / s. If the creation unit 24 determines in step S10 that the detected speed Sm is not equal to or less than the reference speed Smth, the process proceeds to step S24.

[0029] If it is determined in step S10 that the detected speed Sm is equal to or less than the reference speed Smth, then in step S12, the creation unit 24 determines whether the detected angular speed Sa detected by the motion sensor 81 is equal to or less than the reference angular speed Sath. The reference angular speed Sath is an angular speed used to determine whether the purchaser PU is gazing at one product ME in order to select a product ME, and is determined in advance through experiments, etc. The detected angular speed Sa is, for example, 5 deg / s. In step S12, if all of the angular velocities about the three axes are equal to or less than the reference angular speed Sath, the creation unit 24 determines that the detected angular speed Sa is equal to or less than the reference angular speed Sath.

[0030] If it is determined in step S12 that the detected angular velocity Sa is not equal to or less than the reference angular velocity Sath, the creation unit 24 advances the process to step S24.

[0031] If it is determined in step S12 that the detected angular velocity Sa is equal to or less than the reference angular velocity Sath, then in step S14, the creation unit 24 identifies the location at which the consumer PU is facing, i.e., the location at which the consumer PU is presumed to be looking. Specifically, the creation unit 24 compares the action information 32 and the position information 33 with the product position information 31 to identify the product ID of the product ME at which the consumer PU is facing. The product ME at which the consumer PU is facing is also referred to as the "visual product."

[0032] In step S16, the creation unit 24 determines whether the detected angular velocity Sa is greater than the reference angular velocity Sath. Step S16 is a processing step for determining whether the purchaser PU has shifted his or her gaze to a product ME other than the product ME that he or she has been gazing at. In step S16, if the angular velocity of at least one of the three axes is greater than the reference angular velocity Sath, the creation unit 24 determines that the detected angular velocity Sa is greater than the reference angular velocity Sath.

[0033] If it is determined in step S16 that the detected angular velocity Sa is not greater than the reference angular velocity Sath, the creation unit 24 repeatedly executes step S16 at predetermined time intervals until it determines that the detected angular velocity Sa is greater than the reference angular velocity Sath. The predetermined time is, for example, about several milliseconds.

[0034] If it is determined in step S16 that the detected angular velocity Sa is greater than the reference angular velocity Sath, then in step S18 the creation unit 24 creates first information 35 that associates the commodity ID of the visually inspected commodity with the visual inspection time.

[0035] FIG. 6 is a diagram illustrating the first information 35. As shown in FIG. 6, the first information 35 is information in which the fields "Date and Time," "Product ID," and "Viewing Time" are grouped together. In step S18, the creation unit 24 specifically inputs values ​​into each field of the first information 35 to add one row. The "Date and Time" field of the first information 35 is the date and time at which it was determined in step S12 that the detected angular velocity Sa is equal to or less than the reference angular velocity Sath. The "Viewing Time" field of the first information 35 is the time from the time at which it was determined in step S12 that the detected angular velocity Sa is equal to or less than the reference angular velocity Sath to the time at which it was determined in step S16 that the detected angular velocity Sa is greater than the reference angular velocity Sath. In other words, the first information 35 is history information in which the product IDs and viewing times of the products ME are arranged in the order in which the purchaser PU turned their face.

[0036] In step S20, the creation unit 24 determines whether the detected speed Sm obtained from the acceleration detection value of the motion sensor 81 is greater than the reference speed Smth. Step S20 is a processing step for determining whether the consumer PU has moved. If it is determined in step S20 that the detected speed Sm is not greater than the reference speed Smth, the creation unit 24 returns the process to step S12. This is because in this case, the consumer PU is likely to look at the product ME displayed on the same product shelf SH without moving.

[0037] If it is determined in step S20 that the detected speed Sm is greater than the reference speed Smth, then in step S24 the creation unit 24 determines whether the purchaser PU has left the store ST. If it is determined in step S24 that the purchaser PU has not left the store ST, the creation unit 24 returns the process to step S10. This is because in this case, there is a high possibility that the purchaser PU will move around the store and look at a product ME on another product shelf SH.

[0038] In step S24, when it is determined that the purchaser PU has left the store ST, the creation unit 24 ends this processing routine. This processing routine creates first information 35, which is a history of the products ME that the purchaser PU viewed from the time they entered the store ST until they left, and the viewing time.

[0039] After creating the first information 35, the creation unit 24 performs a second information creation process to create second information 36 using the created first information 35 and the acquired purchase information 34. The purchase information 34 is information on the product ID of the product purchased by the purchaser PU from among multiple products ME displayed in the store ST. The purchase information 34 is acquired by the purchase information acquisition unit 25. Specifically, when the purchase is made electronically, the purchase information acquisition unit 25 references the transaction information to acquire information on the product ME purchased by the purchaser PU. Note that other embodiments of the method for acquiring information on the product ME purchased by the purchaser PU may include acquiring information entered by the purchaser PU himself, information entered by a store clerk at the store ST, or information analyzed by an image analysis unit.

[0040] Of the multiple products ME included in the product location information 31, the products ME excluding the purchased products included in the purchase information 34, i.e., the purchased products purchased by the purchaser PU, are also referred to as non-purchased products. In other words, non-purchased products are products ME that the purchaser PU did not purchase. The purchase information 34 may include information on non-purchased products in addition to information on purchased products. The purchase information 34 may include either information on purchased products or information on non-purchased products.

[0041] FIG. 7 is a diagram illustrating the second information 36. As shown in FIG. 7, the second information 36 is a set of information including "date and time," "product ID," "visual inspection time," and "purchase." "Purchase" indicates information about whether or not the purchaser PU has made a purchase. For "purchase," "1" is entered for a purchased product ME, and "0" is entered for a product ME that has not been purchased. As described above, a product ME that has been purchased by the purchaser PU is also referred to as a "purchased product." A product ME that has not been purchased by the purchaser PU is also referred to as a "non-purchased product."

[0042] 8 is a flowchart showing the procedure for the third information creation process. The creation unit 24 performs the third information creation process after creating the second information 36. When the creation unit 24 starts the third information creation process, it sets the value of the variable n used in this process routine to the initial value of "1" and sets the value of the purchase flag used in this process routine to the initial value of "0."

[0043] In step S30, the creation unit 24 sums up the viewing times for each product ID in the second information 36. More specifically, the product IDs are arranged in chronological order in the second information 36. That is, the second information 36 may contain multiple rows with the same product ID. In step S30, when the second information 36 contains multiple rows with the same product ID, the creation unit 24 sums up the viewing times for the same product ID and updates the second information 36.

[0044] In step S32, the creation unit 24 sets the product ID in the nth row as the processing target. In step S34, the creation unit 24 determines whether the product ID in the nth row is a purchased product ME. If it is determined that it is a purchased product ME, in step S36 the creation unit 24 sets the purchase flag to "1". The purchase flag is a flag used in this processing routine and is set to a value of "1" or "0". The purchase flag is stored in the memory unit 30. If it is determined in step S34 that it is not a purchased product ME, the creation unit 24 proceeds to step S38.

[0045] In step S38, the creation unit 24 assigns the value of the viewing time to the target product ID as an evaluation value. In step S38, the creation unit 24 specifically inputs the value of the viewing time totaled in step S30 into the evaluation value. That is, in this embodiment, the value of the viewing time is used as is as the evaluation value. This makes it possible to increase the evaluation value of a product ME that the consumer PU is facing and looking at for a long time. The evaluation value indicates the degree of attention that the consumer PU pays to the product ME.

[0046] In step S40, the creation unit 24 increments the variable n. In step S42, the creation unit 24 determines whether or not processing has been completed for all rows of the second information 36. If it is determined in step S42 that processing has not been completed for all rows, the creation unit 24 returns the processing to step S32.

[0047] If it is determined in step S42 that processing has been completed for all rows, then in step S44 the creation unit 24 determines whether the purchase flag is "1". If it is determined in step S44 that the purchase flag is "1", then in step S46 the creation unit 24 assigns the maximum value of the evaluation values ​​entered for the non-purchased items as the evaluation value to the product ID of the purchased item, and terminates this processing routine. In step S46, more specifically, the creation unit 24 enters the maximum value of the evaluation values ​​entered for the non-purchased items as the evaluation value for the product ID of the purchased item. If it is determined in step S44 that the purchase flag is not "1", then this processing routine terminates.

[0048] FIG. 9 is a diagram illustrating the third information 37 created by the third information creation process. As shown in FIG. 9, the third information is a set of information including the following items: "product ID," "viewing time," "purchase," and "evaluation value." For a purchased product ME, the same evaluation value as the highest evaluation value among the non-purchased products ME is input. In the example of FIG. 9, the product ME with product ID "M010" has a viewing time of 5 seconds, but is a purchased product. Therefore, "20," the same as the viewing time of the product ID "M021" with the longest viewing time among the non-purchased products, is input as the evaluation value for the product ID "M010." The purchaser PU tends not to look at products ME that he or she has decided to purchase. Therefore, by setting the same evaluation value as the highest evaluation value among the non-purchased products as the evaluation value of the purchased product, a high evaluation value can be set for the purchased product ME.

[0049] The maximum value of the evaluation values ​​entered for non-purchased items is also referred to as the first evaluation value. The evaluation values ​​entered for non-purchased items other than the maximum value are also referred to as the second evaluation value. The evaluation value assigned to purchased items is also referred to as the third evaluation value.

[0050] According to the first embodiment described above, the information analysis system 1 includes the motion information acquisition unit 21, the position information acquisition unit 22, the product information acquisition unit 23, the creation unit 24, and the purchase information acquisition unit 25. The creation unit 24 creates the second information 36 using the created first information 35 and the purchase information 34. By using the second information 36, it is possible to obtain information on products ME displayed in the store ST that were not purchased but that the purchaser PU looked at, i.e., products ME that were considered as candidates for purchase. The second information 36 is information that lists the products ME in the order in which the purchaser PU looked at them. Therefore, using the second information 36, it is possible to analyze in detail the behavior of the purchaser PU, such as whether the purchaser PU was searching for a product ME that he or she had previously decided to purchase, or whether the purchaser PU was considering a product ME after looking at multiple products ME.

[0051] Furthermore, the creation unit 24 uses the second information 36 to create third information 37 that associates product IDs with evaluation values. In this embodiment, in the third information 37, evaluation values ​​are assigned to non-purchased products such that the longer the viewing time, the larger the evaluation value. In the third information 37, the largest value among the evaluation values ​​assigned to non-purchased products is assigned to purchased products. This makes it possible to use the third information 37 to find out which product ME has the highest evaluation value, which has been rated more highly by the purchaser PU, out of multiple products ME.

[0052] B. Second Embodiment: Fig. 10 is a block diagram of an information processing device 210 according to this embodiment. The processor 20 of the information processing device 210 differs from the first embodiment in that it includes, as functional units, an attribute information acquisition unit 121, a behavioral information acquisition unit 122, an advertisement information acquisition unit 123, and a weather information acquisition unit 124. The storage unit 30 of this embodiment also differs from the storage unit 30 of the first embodiment in that it stores attribute information 131, behavioral information 132, advertisement viewing information 133, and weather information 134. The same components as those in the first embodiment are denoted by the same reference numerals, and detailed descriptions thereof will be omitted as appropriate.

[0053] The creation unit 24 of this embodiment sets the period from when the purchaser PU enters the store ST until when he / she leaves as one period, and creates the third information 37 for each period.

[0054] The attribute information acquisition unit 121 acquires attribute information 131 of the purchaser PU. The attribute information 131 is information about a person's attributes, specifically, gender, age, place of origin, etc. After creating the third information 37, the creation unit 24 performs a fourth information creation process to create fourth information in which the attribute information is associated with the third information 37. In this embodiment, the attribute information acquisition unit 121 acquires attribute information 131 input by the purchaser PU himself / herself. As another form, the attribute information acquisition unit 121 can be configured to acquire information input by a clerk at the store ST, information analyzed by an image analysis unit, etc.

[0055] The behavioral information acquisition unit 122 acquires behavioral information 132 indicating whether or not the purchaser PU picked up the product ME. Specifically, the behavioral information acquisition unit 122 acquires behavioral information 132 created by the image analysis unit 62 through analysis using an image of the purchaser PU captured by the imaging device 70. The creation unit 24 performs a first update process for updating the third information 37 of the product ME picked up by the purchaser PU, among non-purchased products, by adding a predetermined first additional value to the evaluation value of the third information 37. The first additional value is, for example, "5."

[0056] The advertisement information acquisition unit 123 acquires advertisement visual observation information 133 indicating whether or not a person has turned their face toward an advertisement such as a flyer, poster, or POP (Point of Purchase Advertising) related to the product ME posted in the store ST. Specifically, the advertisement information acquisition unit 123 acquires the advertisement information 133 created by the image analysis unit 62 through analysis using an image of the purchaser PU captured by the imaging device 70.

[0057] The creation unit 24 performs a second update process for updating the third information 37 of the non-purchased product ME of the advertised product that the purchaser PU is facing by adding a predetermined second additional value to the evaluation value of the third information 37. The second additional value is, for example, "5." The second additional value may be the same as or different from the first additional value.

[0058] The weather information acquisition unit 124 acquires weather information 134 for the period during which the purchaser PU is in the store ST. The weather information 134 includes weather information such as sunny or rainy, temperature, humidity, etc. In this embodiment, the weather information acquisition unit 124 acquires weather information 134 provided by a server that provides the weather information 134. In another embodiment, the weather information acquisition unit 124 may acquire weather information 134 created by analyzing images captured by an imaging device 70 capable of capturing images of the outside of the store ST.

[0059] The creating unit 24 performs a fifth information creating process to create fifth information by associating the weather information 134 with the third information 37 .

[0060] Fig. 11 is a diagram illustrating the fourth information and the fifth information. As shown in Fig. 11, the fourth information is a set of items: "information ID," "customer ID," and "customer information." An identifier uniquely assigned to the third information 37 for one period is input in the "information ID." An identifier uniquely assigned to one purchaser PU is input in the "customer ID."

[0061] The fifth information is a set of information including the items "information ID" and "weather information." As shown in FIG. 11, the information ID may further be associated with "visit information." In addition to the items shown in FIG. 11, the "visit information" may include "number of visits" and "purchase amount." Although the fourth information and the fifth information are shown in the same table in FIG. 11 for convenience, the fourth information and the fifth information may be separate data.

[0062] According to the second embodiment described above, the information processing device 210 includes an attribute information acquisition unit 121, a behavioral information acquisition unit 122, an advertisement information acquisition unit 123, and a weather information acquisition unit 124. The creation unit 24 creates fourth information by associating attribute information 131 with third information 37. This allows the fourth information to be used to analyze the relationship between a person's attributes and a product ME with a high evaluation value. Furthermore, the creation unit 24 updates the third information 37 by adding a first additional value to the evaluation value of a non-purchased product picked up by the person. This allows the evaluation value of a product ME picked up by the consumer PU to be increased. Furthermore, the creation unit 24 updates the third information 37 by adding a second additional value to a non-purchased product corresponding to an advertisement that the person is facing. This allows the evaluation value of a product ME advertised by the consumer PU to be increased when an advertisement for the product ME is posted. Furthermore, the creation unit 24 creates fifth information by associating weather information 134 with the third information 37. This makes it possible to use the fifth information to analyze the relationship between the weather information 134 and the product ME with a high evaluation value.

[0063] C. Third Embodiment: Fig. 12 is a block diagram of an information processing device 310 according to this embodiment. The processor 20 of the information processing device 310 differs from the first embodiment in that it includes, as functional units, an attribute information acquisition unit 121, an information group acquisition unit 125, and an extraction information creation unit 126. The storage unit 30 of this embodiment also differs from the storage unit 30 of the first embodiment in that it stores attribute information 131, an information group 135, and extraction information 136. The same components as those in the above embodiments are denoted by the same reference numerals, and detailed descriptions thereof will be omitted as appropriate.

[0064] In this embodiment, as in the second embodiment, the creation unit 24 defines a period from when the purchaser PU enters the store ST until when he or she leaves the store ST as one period, and creates third information 37 for each period. Furthermore, the creation unit 24 performs a third update process to update the third information 37 for non-purchased products, including products ME included in the second information 36 for the previous period, that the purchaser PU looked at but did not purchase, by adding a predetermined third additional value to the evaluation value. The third additional value is, for example, "5." The second additional value may be the same value as the first additional value or the second additional value, or it may be a different value. The situation regarding whether the purchaser PU had time to examine the product ME last time and this time differs. Therefore, it may not be appropriate to treat the viewing time the same for the previous and current times. Even in this case, by performing the third update process to add the third additional value, the evaluation value of the product ME that the purchaser PU looked at but did not purchase can be increased.

[0065] The information group acquisition unit 125 acquires an information group 135 in which the fourth information is accumulated for a plurality of people. The extracted information creation unit 126 creates extracted information 136 by extracting the fourth information having the same person attribute from the information group 135.

[0066] 13 is a diagram illustrating extracted information 136 in which fourth information, whose extraction condition is female in her twenties, is extracted. The extracted information creation unit 126 extracts fourth information of attributes of people who satisfy the set extraction condition from the information group 135, and creates the extracted information 136. In this embodiment, the extracted information creation unit 126 adds up the evaluation values ​​for each product ID, as shown in FIG. 13, and creates the extracted information 136 in which the product ID is associated with the sales volume. The sales volume is information acquired by the purchase information acquisition unit 25.

[0067] As another example, the extracted information 136 may further include a classification of the product ME, such as food or clothing.

[0068] In the extracted information 136, product IDs are associated with evaluation values, so the product IDs can be rearranged in descending order of evaluation value. In addition, in the extracted information 136, product IDs are associated with sales quantities, so the product IDs can be rearranged in descending order of sales quantity. The extracted information 136 can be used for purchasing products ME in the store ST, changing the display format of the products ME, and so on. For example, it can be considered to rearrange products ME with high evaluation values ​​to positions where they are more likely to catch the attention of the purchaser PU.

[0069] According to the third embodiment described above, the information processing device 310 includes an information group acquisition unit 125 and an extracted information creation unit 126. The creation unit 24 updates the third information 37 by adding a third additional value to a product ME that the purchaser PU looked at but did not purchase during the previous period. This increases the evaluation value of a product ME that was a candidate for purchase but was not purchased during the previous period. The extracted information creation unit 126 also creates extracted information 136 by extracting fourth information having the same person attribute from the information group 135. This makes it possible to analyze the fourth information having the same person attribute using the extracted information 136.

[0070] D. Other Embodiments: (D1) In the second embodiment, the evaluation value of a non-purchased product is assigned based on the viewing time. Alternatively, the evaluation value may be assigned based on a table or formula that associates viewing time categories with evaluation values. For example, if the viewing time is greater than 10 seconds but less than 20 seconds, an evaluation value of "20" may be assigned, and if the viewing time is less than 10 seconds, an evaluation value of "10" may be assigned. Furthermore, the evaluation value may not be limited to numbers, but may also be alphabetic. A predetermined first evaluation value is assigned to a non-purchased product with the longest viewing time, and a second evaluation value smaller than the first evaluation value is assigned to a non-purchased product with a shorter viewing time than the non-purchased product to which the first evaluation value is assigned. This allows a higher evaluation value to be assigned to a product with a longer viewing time. Furthermore, the third evaluation value assigned to a purchased product may be greater than the first evaluation value, which is the largest of the evaluation values ​​assigned to the non-purchased products.

[0071] (D2) In the first embodiment, the detection value of the motion sensor 81 is used as the operation information, but this is not limiting. For example, the operation information may be obtained using an image of the purchaser PU captured by the imaging device 70.

[0072] (D3) In the first embodiment, functional units such as the creation unit 24 are provided in the information processing device 10. However, this is not limiting, and each functional unit may be provided in, for example, the mobile terminal device 90, or functions may be shared between the information processing device 10 and the mobile terminal device 90.

[0073] (D4) In the second embodiment, the fourth information is a set of items of “information ID,” “customer ID,” and “customer information.” In another form, the fourth information may be a set of items of “information ID” and “customer information.”

[0074] (D5) The information such as the third information created in each of the above embodiments is information about one store ST. In another embodiment, information such as the third information may be created about multiple stores ST and integrated.

[0075] (D6) In the first embodiment, the first information 35 is created by performing a first information creation process. Machine learning may be used to create the first information 35, specifically, to identify the product ME that the purchaser PU is facing or gazing at, and to detect the viewing time.

[0076] The present disclosure is not limited to the above-described embodiments and can be realized in various configurations without departing from the spirit thereof. For example, the technical features of the embodiments corresponding to the technical features in each aspect described in the Summary of the Invention section can be appropriately replaced or combined to solve some or all of the above-described problems or achieve some or all of the above-described effects. Furthermore, if a technical feature is not described as essential in this specification, it can be appropriately deleted.

[0077] 1...information analysis system, 10, 210, 310...information processing device, 20...processor, 21...motion information acquisition unit, 22...position information acquisition unit, 23...product information acquisition unit, 24...creation unit, 25...purchase information acquisition unit, 30...storage unit, 31...product position information, 32...motion information, 33...position information, 34...purchase information, 35...first information, 36...second information, 37...third information, 40...communication unit, 60...image analysis device, 61...processor, 62...image analysis unit, 63...storage unit, 66...communication unit, 70...imaging device, 71...image sensor, 80...ear-worn device, 80a...housing, 81...motor Location sensor, 82...sound conversion unit, 83...microphone, 84...communication unit, 90...portable terminal device, 91...processor, 92...storage unit, 93...display operation unit, 94...location information acquisition unit, 95...sensor unit, 96...communication unit, 97...information provision application program, 121...attribute information acquisition unit, 122...behavioral information acquisition unit, 123...advertising information acquisition unit, 124...weather information acquisition unit, 125...information group acquisition unit, 126...extracted information creation unit, 131...attribute information, 132...behavioral information, 133...advertising viewing information, 134...weather information, 135...information group, 136...extracted information

Claims

1. An information analysis system comprising: a motion information acquisition unit that acquires motion information representing a motion of a person's head; a position information acquisition unit that acquires position information of the person; a product information acquisition unit that acquires product position information regarding a plurality of products visible to the person, the product position information being associated for each product with pre-assigned product identification information and information indicating a position; a creation unit that compares the acquired motion information and the acquired position information with the acquired product position information to identify at least one visual product that is at least one product toward which the person turned their face among the plurality of products included in the product position information, calculates a gaze time that the person turned their face toward the at least one visual product using the acquired motion information, and creates first information that associates the product identification information with the gaze time; and a purchase information acquisition unit that acquires purchase information including at least one of the product identification information of at least one purchased product that is at least one product purchased by the person among the plurality of products, and the product identification information of at least one non-purchased product that is at least one product not purchased by the person among the plurality of products, The creation unit performs a second information creation process using the created first information and the acquired purchase information to create second information that associates the product identification information, the viewing time, and information on whether the person made a purchase. This is an information analysis system.

2. An information analysis system as described in claim 1, wherein the at least one visually inspected product includes a plurality of visually inspected products, the at least one non-purchased product includes a plurality of non-purchased products, and the plurality of visually inspected products include the at least one purchased product and the plurality of non-purchased products, and the creation unit performs a third information creation process using the second information to create third information that associates the product identification information with an evaluation value indicating the person's attention to the plurality of products, and in the third information creation process, the creation unit assigns a predetermined first evaluation value as the evaluation value to a non-purchased product of the plurality of non-purchased products that has the longest visual inspection time, assigns a second evaluation value smaller than the first evaluation value as the evaluation value to a non-purchased product of the plurality of non-purchased products that has a shorter visual inspection time than the non-purchased product to which the first evaluation value has been assigned, and assigns a third evaluation value equal to or greater than the first evaluation value as the evaluation value to the at least one purchased product.

3. An information analysis system as described in claim 2, comprising an attribute information acquisition unit that acquires attribute information relating to the person's attributes, and wherein the creation unit performs a fourth information creation process that creates fourth information by associating the attribute information with the third information.

4. An information analysis system as described in claim 2, comprising a behavioral information acquisition unit that acquires behavioral information on whether or not the person has picked up the at least one visually inspected product, and the creation unit performs a first update process that updates the third information for a non-purchased product that the person has picked up among the plurality of non-purchased products by adding a predetermined first additional value to the evaluation value assigned in the third information creation process.

5. An information analysis system as described in claim 2, comprising an advertisement information acquisition unit that acquires advertisement viewing information indicating whether the person turned their face toward an advertisement for each of the plurality of products, and the creation unit performs a second update process that updates the third information for a non-purchased product among the plurality of non-purchased products that corresponds to the advertisement that the person turned their face toward by adding a predetermined second additional value to the evaluation value assigned in the third information creation process.

6. An information analysis system as described in claim 2, wherein the plurality of products are displayed in a store, the creation unit sets the period from when the person enters the store to when they leave as one period, and creates the third information for each period, and the creation unit performs a third update process to update the third information for products that the person looked at but did not purchase, among the plurality of non-purchased products, which are included in the second information for the previous period, by adding a predetermined third additional value to the evaluation value assigned in the third information creation process.

7. An information analysis system as described in claim 2, wherein the multiple products are displayed in the same store, the creation unit sets the period from when the person enters the store to when they leave as one period and creates the third information for each period, and the system is equipped with a weather information acquisition unit that acquires weather information for the period, and the creation unit performs fifth information creation processing to create fifth information that associates the weather information with the third information.

8. An information analysis system as described in claim 3, comprising: an information group acquisition unit that acquires the fourth information as an information group accumulated for a plurality of people; and an extracted information creation unit that creates extracted information by extracting the fourth information having the same attributes as the people from the information group.

9. An information analysis system according to any one of claims 1 to 8, wherein the movement information is information acquired using a motion sensor attached to the person's head.

Images