Feature quantity management device and storage medium

By introducing valid deadline management and automatic deletion mechanisms into the feature quantity management device, the privacy protection problem is solved, and the security management and privacy protection of feature quantity data are realized.

CN112541385BActive Publication Date: 2024-11-05TOSHIBA TEC KK
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010803004.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2019-09-20
Filing Date
2020-08-11
Publication Date
2024-11-05
Estimated Expiration
2040-08-11

AI Technical Summary

Technical Problem

The prior art is difficult to effectively manage characteristic data in terms of privacy protection, and there is a privacy risk for saving these data for a long time.

Method used

A feature quantity management device is designed, including a data generation unit, an ID generation unit, a storage unit and a deletion unit, to generate and manage the validity period of the feature quantity data, store the feature quantity data through identification information, and automatically delete it after the validity period has expired. data.

Benefits of technology

The characteristic quantity data management based on the validity period is realized, ensuring the privacy protection of data, avoiding the privacy risks brought about by long-term storage, and allowing changes or extension of the validity period as needed.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112541385B_ABST
    Figure CN112541385B_ABST
Patent Text Reader

Abstract

The present invention discloses a feature quantity management device and a storage medium, which can manage feature quantity data in consideration of privacy, and the feature quantity management device comprises a data generation unit, an ID generation unit, a storage unit and a deletion unit. The data generation unit generates feature quantity data representing the feature quantity of biological information of a person from an image. The ID generation unit generates identification information, and the identification information includes validity period information used to determine the validity period of the feature quantity data. The storage unit associates the feature quantity data with the identification information and stores them. The deletion unit deletes the feature quantity data after the validity period.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] This application claims priority to Japanese patent application No. JP2019-171589, filed on September 20, 2019, and cites the contents of the above application, the disclosure of which is hereby incorporated by reference in its entirety. Technical Field

[0002] The embodiments of the present invention relate to a feature quantity management device and a storage medium. Background Art

[0003] Store operators and the like sometimes wish to perform the following repeat analysis: using a camera installed in a store or the like to recognize that the same person has visited the store multiple times, and to analyze the store visit history and purchase history. In this case, for example, a repeat analysis system generates feature quantity data representing the features of the biological information of the person in the image based on an image captured by the camera. The system then uses the generated feature quantity data to compare with feature quantity data of people who have visited the store in the past, thereby recognizing that the person is the same. However, from the perspective of privacy, it is not ideal to store feature quantity data for a long time. Summary of the invention

[0004] An object of the embodiments of the present invention is to provide a feature value management device and a storage medium capable of managing feature value data while taking privacy into consideration.

[0005] The feature quantity management device of the embodiment includes a data generation unit, an ID generation unit, a storage unit, and a deletion unit. The data generation unit generates feature quantity data representing the feature quantity of biological information of a person from an image. The ID generation unit generates identification information, and the identification information includes validity period information used to determine the validity period of the feature quantity data. The storage unit associates the feature quantity data with the identification information and stores them. The deletion unit deletes the feature quantity data after the validity period.

[0006] According to the feature amount management device described above, it is possible to manage feature amount data based on the validity period.

[0007] In the above-mentioned feature amount management device, the identification information generated by the ID generation unit further includes a serial number unique to each piece of the identification information.

[0008] According to the feature amount management device described above, identification information can be managed using serial numbers.

[0009] The feature amount management device described above further includes a changing unit configured to change the expiration date when determining that the feature amount data generated by the data generating unit and the feature amount data stored in the storage unit are consistent with each other.

[0010] According to the feature quantity management device described above, it is possible to delete only the feature quantity data related to a person who has not arrived within a certain period of time.

[0011] In the above-mentioned feature quantity management device, the changing unit changes the validity period by changing the identification information stored in the storage unit.

[0012] According to the feature amount management device described above, it is possible to manage the validity period changed by the identification information.

[0013] In the above-mentioned feature management device, the changing unit changes the validity period by associating the identification information newly generated by the ID generating unit with the identification information stored in the storage unit, and the deleting unit deletes the feature data after the validity period indicated by the expiration period information contained in the identification information newly generated by the ID generating unit.

[0014] According to the feature amount management device described above, feature amount data can be deleted based on the changed validity period.

[0015] In the above-mentioned feature amount management device, data indicating that the feature amount data has been deleted is stored in association with the identification information.

[0016] According to the feature amount management device described above, it is possible to confirm that the feature amount data has been deleted.

[0017] In the above-mentioned feature quantity management device, the storage unit further stores the collected data including the action history in association with the identification information.

[0018] According to the feature amount management device described above, it is possible to manage feature data and collected data in association with identification information.

[0019] In the above-mentioned feature amount management device, the deleting unit deletes the collected data simultaneously with the deletion of the feature amount data.

[0020] According to the feature amount management device described above, it is possible to delete the collected data together with the feature data.

[0021] In the above-mentioned feature quantity management device, the deleting unit selectively performs any one of the following: deleting the feature data without deleting the collected data, or deleting the collected data while deleting the feature data.

[0022] According to the feature amount management device described above, it is possible to selectively execute whether to delete the collected data.

[0023] A storage medium on another aspect of the present invention stores a program, which is used to enable a processor of a feature quantity management device to have the functions of the following units: a data generation unit, which generates feature quantity data representing feature quantities of a person's biological information from an image; an ID generation unit, which generates identification information, and the identification information includes expiration date information used to determine the expiration date of the feature quantity data; a storage unit, which stores the feature quantity data in association with the identification information; and a deletion unit, which deletes the feature quantity data after the expiration date.

[0024] According to the above-described storage medium, it is possible to cause the processor to provide a function of managing feature amount data based on the validity period. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 This is a block diagram showing an example of a main circuit configuration of an analysis system and an analysis device included in the analysis system according to the first to third embodiments.

[0026] Figure 2 It means stored in Figure 1 FIG. 2 is a diagram showing an example of a table according to the first embodiment and the second embodiment of the auxiliary storage device in FIG.

[0027] Figure 3 It means by Figure 1 A flowchart of an example of a process according to the first embodiment executed by a processor in FIG.

[0028] Figure 4 It means by Figure 1 A flowchart of an example of a process according to the first embodiment executed by a processor in FIG.

[0029] Figure 5 It means by Figure 1 A flowchart of an example of processing involved in the second embodiment executed by the processor in.

[0030] Figure 6 It means by Figure 1 A flowchart of an example of processing involved in the second embodiment executed by the processor in.

[0031] Figure 7 It means stored in Figure 1 FIG. 4 is a diagram showing an example of a table according to a third embodiment of the auxiliary storage device in FIG.

[0032] Figure 8 It means by Figure 1 A flowchart of an example of a process involved in the third embodiment executed by a processor in.

[0033] Fig. 9 It means by Figure 1A flowchart of an example of a process involved in the third embodiment executed by a processor in.

[0034] Description of Reference Numerals

[0035] 1......Analysis system, 10......Analysis device, 11......Processor, 12......ROM, 13......RAM, 14......Auxiliary storage device, 15......Camera device interface, 16......Bus, 20......Camera device, 141......Analysis DB. DETAILED DESCRIPTION

[0036] Hereinafter, the analysis system involved in several embodiments is described using the accompanying drawings. It should be noted that the various figures used in the description of the following embodiments are sometimes shown with the structure omitted for the purpose of explanation. In addition, the same symbols in the various figures and the following description represent the same elements.

[0037] [First embodiment]

[0038] Figure 1 1 is a block diagram showing an example of the circuit configuration of the main part of the analysis system 1 and the analysis device included in the analysis system 1 according to the first embodiment. The analysis system 1 is a system for performing repeated analysis. As an example, the analysis system 1 includes an analysis device 10 and an imaging device 20.

[0039] The analysis device 10 is a device used for repeated analysis. As an example, the analysis device 10 includes: a processor 11, a ROM (read-only memory) 12, a RAM (random-access memory) 13, an auxiliary storage device 14, and a camera interface 15. In addition, a bus 16 and the like connect the above-mentioned components. The analysis device 10 is an example of a feature quantity management device.

[0040] The processor 11 is equivalent to the central part of the computer that performs the calculations and controls required for the operation of the analysis device 10. The processor 11 controls each part to realize the various functions of the analysis device 10 based on the programs such as firmware, system software and application software stored in the ROM 12 or the auxiliary storage device 14. It should be noted that part or all of the program can be incorporated into the circuit of the processor 11. The processor 11 is, for example, a CPU (central processing unit), an MPU (microprocessing unit), a SoC (system on a chip), a DSP (digital signal processor), a GPU (graphics processing unit), an ASIC (application specific integrated circuit), a PLD (programmable logic device) or an FPGA (field-programmable gate array). Alternatively, the processor 11 can be a combination of multiple of the above components.

[0041] The ROM 12 is equivalent to the main storage device of the computer with the processor 11 as the core. The ROM 12 is a non-volatile memory dedicated to data reading. The ROM 12 stores, for example, firmware and the like among the above-mentioned programs. In addition, the ROM 12 also stores data and the like used by the processor 11 to execute various processes.

[0042] The RAM 13 is equivalent to the main storage device of the computer with the processor 11 as the core. The RAM 13 is a memory for reading and writing data. The RAM 13 is used as a work area for temporarily storing data used by the processor 11 to perform various processes. The RAM 13 is typically a volatile memory.

[0043] The auxiliary storage device 14 is equivalent to an auxiliary storage device of a computer with the processor 11 as the core. The auxiliary storage device 14 is, for example, an EEPROM (electric erasable programmable read-only memory), an HDD (hard disk drive), or a flash memory. The auxiliary storage device 14 stores the above-mentioned programs, such as system software and application software. In addition, the auxiliary storage device 14 stores data used by the processor 11 to perform various processes, data generated by the processing of the processor 11, and various setting values.

[0044] In addition, the auxiliary storage device 14 stores an analysis DB 141. The analysis DB 141 stores and manages data related to repeated analysis. The analysis DB 141 includes, for example, Figure 2 Table T1 shown. Figure 2It is a diagram showing an example of the table T1 stored in the auxiliary storage device 14.

[0045] In table T1, feature data and collected data are associated with feature IDs (identifiers).

[0046] The feature quantity ID is unique identification information added to each feature quantity data registered in the analysis DB 141. The feature quantity ID includes expiration date information and a serial number.

[0047] The validity period information is information that determines the validity period of the feature data. The validity period information is, for example, information indicating the start time or end time of the validity period. The information indicating the start time of the validity period is, for example, the date or date time of the generation of the feature data or feature ID. The information indicating the end time of the validity period is, for example, the date or date time indicating the validity period. It should be noted that the end time of the validity period has the same meaning as the validity period.

[0048] The serial number is, for example, a number that increases each time a feature ID is generated. Therefore, the serial number is a number unique to each feature ID.

[0049] As an example, the generation date and time of the feature data or feature ID is 17:15:20 on May 1, 2019. The feature ID includes "20190501" as information indicating the starting time of the validity period. In addition, when the feature ID is generated for the 1103th time, the serial number is, for example, "00001103". In this case, the feature ID is, for example, "2019050100001103" or "0000110320190501". It should be noted that the feature ID can include expiration date information and a serial number. Here, an example of including expiration date information and a serial number is given.

[0050] It should be noted that the information indicating the start time of the valid period may include hours, minutes, seconds, etc. In this case, the feature ID includes, for example, "20190501171520" or "201905011715" as the information indicating the start time of the valid period.

[0051] In addition, as an example, the validity period of the feature data is set to 6 months from the date of generation. In this case, the validity period is 17:15:20 on November 1, 2019, 6 months after the date of generation. Alternatively, the validity period is rounded up to a time less than 1 day, such as November 1, 2019 or November 2, 2019. In this case, the feature ID includes, for example, "20191101" or "20191101171520" as information indicating the end point of the validity period.

[0052] It should be noted that the validity period information may be expressed in other forms such as UNIX (registered trademark) time to represent the date and time.

[0053] As described above, the feature ID is an example of identification information including validity period information used to determine the validity period of the feature data. In addition, information indicating the start time of the validity period or information indicating the end time of the validity period is an example of validity period information used to determine the validity period of the feature data.

[0054] The feature data is data indicating the characteristics of biometric information, which can be used for personal identification. Biometric information is, for example, body features such as face or behavioral features such as walking posture. It should be noted that the analysis device 10 deletes feature data that has exceeded its validity period. In table T1, a record in which the feature data is NULL indicates that the feature data associated with the feature ID of the record has been deleted. NULL is data indicating that the feature data has been deleted.

[0055] The collected data is various data related to an individual identified by the feature data associated with the feature ID, and is the data used for repeated analysis. For example, the collected data includes the individual's gender, age, race and other attributes, action route data, action history, store visit history and purchase history.

[0056] In addition, the analysis DB 141 stores validity period information indicating the validity period. For example, if the validity period is 6 months, the validity period information indicates 6 months.

[0057] In addition, the analysis DB 141 stores the deleted number N_deleted. Among the feature IDs included in the table T1, feature IDs whose serial numbers are less than or equal to the deleted number N_deleted indicate that the associated feature data has been deleted.

[0058] The program stored in the ROM 12 or the auxiliary storage device 14 includes a program for executing the processing described later. As an example, the analysis device 10 is transferred to the administrator of the analysis device 10, etc., in a state where the program is stored in the ROM 12 or the auxiliary storage device 14. However, the analysis device 10 may be transferred to the administrator, etc., in a state where the program is not stored in the ROM 12 or the auxiliary storage device 14. In addition, the analysis device 10 may be transferred to the administrator, etc., in a state where other programs different from the program are stored in the ROM 12 or the auxiliary storage device 14. Then, the program for executing the processing described later is transferred to the administrator, etc. separately, and is written to the ROM 12 or the auxiliary storage device 14 under the operation performed by the administrator or the service personnel. The transfer of the program at this time can be realized by recording on a removable storage medium such as a magnetic disk, a magneto-optical disk, an optical disk, or a semiconductor memory, or by downloading via a network, etc.

[0059] The camera interface 15 is an interface for the analysis device 10 to communicate with the camera 20. The analysis device 10 receives image data output from the camera 20 using the camera interface 15.

[0060] The bus 16 includes a control bus, an address bus, a data bus, and the like, and transmits signals exchanged between the various components of the analysis device 10 .

[0061] The camera device 20 is set in a specific space such as a store or other facilities. The camera device 20 is set, for example, to capture people who come to the specific space. It should be noted that the specific space can be indoors or outdoors. In addition, multiple camera devices 20 can be set. The camera device 20 captures an image and outputs it. It should be noted that the image can be a still image or an animation.

[0062] The following is based on Figure 3 and Figure 4 The operation of the analysis system 1 according to the first embodiment will be described below. It should be noted that the processing contents in the following operation description are just examples, and various processing that can obtain the same result can be used as appropriate. Figure 3 and Figure 4 This is a flowchart showing an example of processing performed by the processor 11 of the analysis device 10. The processor 11 performs the processing based on a program stored in the ROM 12 or the auxiliary storage device 14, for example. It should be noted that when the processor 11 enters ACT (n+1) after processing ACTn (n is a natural number), the description of this situation is sometimes omitted.

[0063] First, the process related to the generation of feature amount data and the collection of data required for the iterative analysis will be described.

[0064] exist Figure 3In ACT11 of the analysis device 10, the processor 11 determines whether a person has come to the specific space. For example, the processor 11 determines whether a person has come by analyzing the image output from the camera device 20. Alternatively, the processor 11 may use a sensor or the like to determine whether a person has come to the specific space. Alternatively, the processor 11 uses other known methods to determine whether a person has come to the specific space. If the processor 11 does not determine that a person has come to the specific space, it determines as no in ACT11 and repeats ACT11. In addition, if the processor 11 determines that a person has come to the specific space, it determines as yes in ACT11 and repeats ACT11. However, if the processor 11 determines as yes in ACT11, the processing shown in ACT12 to ACT20 is started in parallel or in parallel with ACT11 through other processes or other threads. It should be noted that the processing of ACT12 to ACT20 started by the processor 11 here is performed on the person determined to have come in ACT11. It should be noted that, hereinafter, the person set as the object in the processing of ACT12 to ACT20 is referred to as the "target person". Then, each time the processor 11 determines that a person has arrived, the processor 11 performs the processes of ACT 12 to ACT 20 with the person as the target person.

[0065] In ACT 12, the processor 11 generates feature data from the image showing the target person. For example, the processor 11 digitizes biometric information such as facial features of the target person to generate feature data. The processor 11 performs the processing of ACT 12, thereby functioning as a data generation unit that generates feature data.

[0066] In ACT 13, the processor 11 deletes the image used for generating the feature amount data. This is because it is not desirable to store the image used for generating the feature amount data from the perspective of privacy.

[0067] In ACT 14, the processor 11 refers to the analysis DB 141 to search for feature data with consistent feature quantities. It should be noted that the processor 11 regards feature data with consistent feature quantities at a certain ratio or more as feature data with consistent feature quantities, and determines that the feature quantities are consistent. In addition, hereinafter, the feature ID associated with the feature data discovered by the processing of ACT 14 is referred to as a "discovery ID".

[0068] In ACT 15, the processor 11 determines whether feature amount data with matching feature amounts is found in the process of ACT 14. If the processor 11 does not find feature amount data with matching feature amounts, the processor 11 determines "no" in ACT 15 and proceeds to ACT 16.

[0069] In ACT 16, the processor 11 generates a feature ID based on the feature data or the date and time of generation of the feature ID as described above. By performing the process of ACT 16, the processor 11 functions as an ID generation unit that generates identification information including expiration date information.

[0070] In ACT 17, the processor 11 associates the feature ID generated in ACT 16 with the feature data generated in ACT 12 and stores them in the analysis DB 141. That is, the processor 11 adds a new record including the feature ID and the feature data to the table T1. As described above, the analysis DB 141 is an example of a storage unit that associates the identification information with the feature data. Alternatively, the auxiliary storage device 14 that stores the analysis DB 141 is an example of a storage unit.

[0071] In ACT 18, the processor 11 collects the attributes of the person to be processed, the route data, the history of actions, the history of visits to stores, the history of purchases, and the like, and the data used for repeated analysis. Furthermore, the processor 11 records the collected data as collected data in the analysis DB 141 in association with the feature ID generated in ACT 16. The analysis DB 141 is an example of a storage unit that stores the collected data in association with identification information. It should be noted that the processor 11 uses, for example, the camera 20 and other cameras, sensors, and POS (Point Of Sale) data set in a specific space when collecting the data. Then, the processor 11 ends the processing of ACT 18 according to, for example, the situation in which the person to be processed leaves the specific space.

[0072] Furthermore, if the processor 11 finds feature amount data with the same feature amount, it determines in ACT 15 to proceed to ACT 19. In ACT 19, the processor 11 deletes the feature amount data generated in ACT 12.

[0073] In ACT 20, the processor 11 collects data used for repeated analysis in the same manner as in ACT 18. However, the processor 11 records the collected data as collected data in the analysis DB 141 in association with the discovery ID. At this time, the processor 11 records the new collected data by, for example, appending to the collected data already recorded in association with the discovery ID. Then, the processor 11 ends the processing of ACT 20, for example, when the subject person leaves the specific space.

[0074] When the processing of ACT 18 or ACT 20 is completed, the processor 11 ends the flow or thread executing the processing.

[0075] Next, the process related to deletion of feature amount data will be described.

[0076] The processor 11 periodically starts, for example Figure 4 Alternatively, the processor 11 executes Figure 4 The indicated processing starts when Figure 4 Processor 11 starts Figure 4 In the processing shown, the variable X is allocated to RAM 13 or the like.

[0077] exist Figure 4 In ACT 31, the processor 11 substitutes the deleted number N_deleted into the variable X. In ACT 32, the processor 11 increases the value of the variable X by 1.

[0078] In ACT 33, the processor 11 determines whether there is a feature quantity ID with a serial number of X in the table T1. As an example, if X is 108, the processor 11 determines whether there is a feature quantity ID with a serial number of "00000108" in the table T1. If there is a feature quantity ID with a serial number of X in the table T1, the processor 11 determines yes in ACT 33 and proceeds to ACT 34.

[0079] In ACT 34, the processor 11 determines whether the feature data associated with the feature ID with the serial number X has exceeded the validity period. For example, if the feature ID contains information indicating the starting time of the validity period, the processor 11 adds the validity period indicated by the validity period information to the starting time. Then, if the result of the addition is before the current date and time, the processor 11 determines that the feature data has exceeded the validity period. In addition, if the feature ID contains information indicating the end time of the validity period, and the end time is before the current date and time, the processor 11 determines that the feature data has exceeded the validity period. If the processor 11 determines that the feature data has exceeded the validity period, it is determined in ACT 34 to enter ACT 35.

[0080] In ACT35, the processor 11 deletes the characteristic data associated with the characteristic ID with the serial number X. Then, the processor 11 sets the value of the characteristic data field of the record specified by the characteristic ID in table T1 to NULL. After processing ACT35, the processor 11 returns to ACT32. It should be noted that although the characteristic data is deleted, the collected data is not deleted. In order to analyze the route data, action history, etc. of the store visitors for store operations, the collected data is not deleted. However, it is also considered that the analysis results of the collected data of the object person who has not visited the store for a long time are inappropriate. Therefore, deletion information indicating the deletion of the collected data is saved in a specified area of ​​RAM13. When the deletion information is saved, the collected data is deleted together with the characteristic data. When the deletion information is not saved, the collected data is not deleted. In this way, appropriate collected data can be saved.

[0081] In this way, the processor 11 checks the validity period in order from the feature amount data having the earliest expiration time, and deletes the feature amount data having exceeded the validity period.

[0082] As described above, the processor 11 performs the process of ACT 35, thereby functioning as a deleting unit that deletes the feature amount data when the expiration date has passed.

[0083] If there is no X-th feature ID in table T1, processor 11 determines in ACT 33 whether to proceed to ACT 36. If processor 11 determines that feature data associated with X-th feature ID has not expired, processor 11 determines in ACT 34 whether to proceed to ACT 36.

[0084] In ACT 36, the processor 11 sets the value of the deleted number N_deleted to (X-1). This shows that the feature data associated with the feature ID before the serial number has been deleted. After the processor 11 completes the processing of ACT 36, the process ends. Figure 4 Processing shown.

[0085] According to the analysis system 1 of the first embodiment, the processor 11 of the analysis device 10 uses the validity period information included in the feature ID associated with the feature data to determine whether the feature data has exceeded the validity period. In addition, the processor 11 deletes the feature data that has exceeded the validity period. In this way, the analysis device 10 of the first embodiment deletes the feature data within a certain period of time, so it can be said that privacy is taken into consideration.

[0086] Furthermore, according to the analysis system 1 of the first embodiment, the processor 11 of the analysis device 10 determines whether the feature data exceeds the validity period in the order of the serial number included in the feature ID associated with the feature data from small to large. Furthermore, when there is feature data that has not exceeded the validity period, the processor 11 does not determine whether the feature data with a serial number later than the feature data has exceeded the validity period. This is because the earlier the serial number, the earlier the expiration date, so the feature data with a serial number later than the feature data that has not exceeded the validity period also has not exceeded the validity period. In this way, the analysis device 10 of the first embodiment can prevent useless processing by including the serial number in the feature ID.

[0087] Furthermore, according to the analysis system 1 of the first embodiment, the processor 11 of the analysis device 10 determines whether the feature data has exceeded the validity period starting from the data whose serial number is the number after the deleted number N_deleted. For the data whose serial number is less than or equal to the deleted number N_deleted, the feature data has been deleted. Therefore, the analysis device 10 of the first embodiment can prevent useless processing by using the deleted number N_deleted.

[0088] [Second embodiment]

[0089] The analysis system 1 according to the second embodiment updates the expiration date by rewriting the feature ID each time the same person comes to the specific space when the person comes to the specific space two or more times.

[0090] The configuration of the analysis system 1 of the second embodiment is the same as that of the first embodiment, and therefore the description thereof will be omitted.

[0091] The following is based on Figure 5 and Figure 6 The operation of the analysis system 1 according to the second embodiment will be described below. It should be noted that the processing contents in the following operation description are just examples, and various processing that can obtain the same result can be used as appropriate. Figure 5 and Figure 6 1 is a flowchart showing an example of processing executed by the processor 11 of the analysis device 10. The processor 11 executes the processing based on a program stored in the ROM 12 or the auxiliary storage device 14, for example. It should be noted that in the second embodiment, the processor 11 replaces the first embodiment. Figure 3 processing Figure 5 Furthermore, in the second embodiment, the processor 11 replaces the first embodiment. Figure 4 processing Figure 6 processing.

[0092] In the second embodiment, the processor 11 proceeds to ACT 41 after processing ACT 19 .

[0093] In ACT 41, the processor 11 generates a feature ID in the same manner as in ACT 16. In ACT 42, the processor 11 rewrites the discovery ID to the feature ID generated in ACT 41. Therefore, the processor 11 functions as a changer that changes the validity period by performing the process in ACT 42.

[0094] In ACT 43, the processor 11 repeatedly collects the data used for analysis in the same manner as in ACT 18. However, the processor 11 records the collected data as collected data in the analysis DB 141 in association with the feature ID rewritten by the process of ACT 42. At this time, the processor 11 records the new collected data by, for example, adding to the collected data already recorded in association with the feature ID. Then, the processor 11 ends the process of ACT 43, for example, when the subject person leaves the specific space.

[0095] When the processing of ACT 18 or ACT 43 is completed, the processor 11 ends the flow or thread that executes the processing.

[0096] In the second embodiment, if the processor 11 Figure 6 If ACT33 is judged as yes, the process proceeds to ACT51.

[0097] In ACT 51, the processor 11 determines whether the feature data associated with the feature ID having the serial number X is deleted. If the feature data is not deleted, the processor 11 determines in ACT 51 that it is no and proceeds to ACT 34. On the other hand, if the feature data is deleted, the processor 11 determines in ACT 51 that it is yes and returns to ACT 32.

[0098] According to the analysis system 1 of the second embodiment, the processor 11 of the analysis device 10 rewrites the discovery ID to the newly generated feature ID. As a result, each time a person specified by the feature data associated with the discovery ID comes to the specific space, the validity period of the feature data is extended. Therefore, the analysis device 10 of the second embodiment can delete only the feature data of a person who has not come to the specific space within a certain period of time.

[0099] Furthermore, the analysis device 10 according to the second embodiment can extend the validity period of feature data by a simple operation of rewriting the feature ID.

[0100] [Third embodiment]

[0101] When the same person comes to a specific space twice or more, the analysis system 1 of the third embodiment associates a newly generated feature ID with the feature ID generated when the person first comes to the specific space each time the person comes to the specific space, thereby updating the validity period.

[0102] The configuration of the analysis system 1 of the third embodiment is the same as that of the first embodiment, and therefore the description thereof is omitted. However, in the third embodiment, the analysis DB 141 stored in the auxiliary storage device 14 includes the table T1 instead of the table T2. Figure 7 Table T2 shown. Figure 7 It is a diagram showing an example of the table T2 stored in the auxiliary storage device 14.

[0103] Table T2 further includes a parent ID in addition to Table T1. That is, Table T2 associates feature data, collected data, and a parent ID with the feature ID.

[0104] A node whose parent ID is NULL represents a path node. And a node whose parent ID is not NULL represents a child node whose parent node is a node specified by the parent ID. It should be noted that each record of table T2 represents information about each node. In addition, the feature ID of a child node is called a child ID.

[0105] In table T2, feature data of nodes other than path nodes are NULL. In table T2, even if feature data of nodes other than path nodes are NULL, it does not mean that the associated feature data is deleted.

[0106] In addition, the analysis DB 141 of the third embodiment includes an undeleted index. The undeleted index includes, for example, feature IDs related to data whose feature data of a parent node specified by the parent ID is the latest in a child node with the same parent ID and has not been deleted, and feature IDs related to data whose feature data is not deleted in a path node without a child node. Thus, the undeleted index becomes a list of feature IDs representing feature data that has not been deleted. It should be noted that the undeleted index arranges feature IDs in ascending order of serial numbers.

[0107] The following is based on Figure 8 and Fig. 9 The operation of the analysis system 1 according to the third embodiment will be described below. Note that the contents of the processing in the following operation description are just examples, and various processing that can obtain the same result can be used as appropriate. Figure 8 and Fig. 9 1 is a flowchart showing an example of processing executed by the processor 11 of the analysis device 10. The processor 11 executes the processing based on a program stored in the ROM 12 or the auxiliary storage device 14, for example. It should be noted that in the third embodiment, the processor 11 replaces the second embodiment. Figure 5 processing Figure 8 Furthermore, in the third embodiment, the processor 11 replaces the processor 11 of the second embodiment. Figure 6 processing Fig. 9 processing.

[0108] In the third embodiment, the processor 11 Figure 8After the processing of ACT 17, the process proceeds to ACT 61. In ACT 61, the processor 11 updates the non-deleted index. That is, the processor 11 adds the feature ID generated in ACT 16 to the non-deleted index. After the processing of ACT 61, the processor 11 proceeds to ACT 18.

[0109] Furthermore, in the third embodiment, the processor 11 proceeds to ACT 62 after processing ACT 41 .

[0110] In ACT62, the processor 11 associates the feature ID generated in ACT41 with the discovery ID. That is, the processor 11 adds a new record to table T2. And, the processor 11 sets the value of the feature ID field of the record to the feature ID generated in ACT41. In addition, the processor 11 sets the value of the feature data field of the record to NULL. Furthermore, the processor 11 sets the value of the parent ID field of the record to the discovery ID. Thus, the newly added record represents the information of the child nodes of the node indicated by the feature ID associated with the feature data discovered in ACT14. The processor 11 performs the processing of ACT62, thereby acting as a change unit that changes the validity period.

[0111] In ACT 63, the processor 11 updates the undeleted index. That is, the processor 11 deletes the feature ID whose parent ID is the discovery ID from the undeleted index. Furthermore, the processor 11 adds the feature ID generated in ACT 41 to the undeleted index.

[0112] In ACT 64, the processor 11 collects data for repeated analysis in the same manner as in ACT 18. However, the processor 11 records the collected data as collected data in the analysis DB 141 in association with the feature ID generated in ACT 41. Then, the processor 11 terminates the processing of ACT 64, for example, when the subject person leaves the specific space.

[0113] Therefore, in the third embodiment, when the processor 11 performs the repetitive analysis using the collected data, it uses not only the collected data of the path node but also the collected data of the child nodes of the path node.

[0114] When the processing of ACT 18 or ACT 64 is completed, the processor 11 ends the flow or thread executing the processing.

[0115] The processor 11 periodically starts, for example Fig. 9 Alternatively, the processor 11 executes Fig. 9 When the processing instructions are shown, start Fig. 9 Processing shown.

[0116] exist Fig. 9In ACT 71 , the processor 11 reads the non-deleted index from the analysis DB 141 .

[0117] In ACT 72, the processor 11 determines whether there is an unselected feature ID in the undeleted index. It should be noted that the selection of the feature ID will be described later. If there is an unselected feature ID in the undeleted index, the processor 11 determines in ACT 72 that it is time to proceed to ACT 73.

[0118] In ACT 73, the processor 11 selects the feature ID with the smallest serial number among the feature IDs that have not been selected in the undeleted index. It should be noted that if there is a feature ID that is being selected, the processor 11 cancels the selection and then selects the feature ID. Here, the feature ID that has not been selected refers to the feature ID from the beginning. Fig. 9 The feature quantity ID that has not been selected once in the process of ACT 73 during the period from the time of the process to the time of the end.

[0119] In ACT 74, processor 11 uses the selected feature ID in the same manner as ACT 34 to determine whether the feature data associated with the selected feature ID has exceeded the validity period. It should be noted that if the selected feature ID is the feature ID of a child node, the feature data associated with the feature ID is the feature data of the parent node specified by the parent ID.

[0120] If the processor 11 determines that the feature amount data has expired, it determines in ACT 74 to proceed to ACT 75 .

[0121] In ACT 75, the processor 11 deletes the feature data associated with the feature ID being selected. Then, the processor 11 sets the value of the feature data field to NULL for the record associated with the deleted feature data.

[0122] In ACT 76, the processor 11 updates the non-deleted index. That is, the processor 11 deletes the feature quantity ID being selected from the non-deleted index. After the processing of ACT 76, the processor 11 returns to ACT 72.

[0123] On the other hand, if there is no unselected feature ID in the undeleted index, the processor 11 determines "no" in ACT 72 and ends the process. Fig. 9 If the processor 11 determines that the feature data associated with the selected feature ID has not exceeded the validity period, the processor 11 determines that it is not in ACT 74 and ends the process. Fig. 9 Processing shown.

[0124] According to the analysis system 1 of the third embodiment, the processor 11 of the analysis device 10 associates the newly generated feature ID with the discovery ID. Thus, the analysis device 10 of the third embodiment can obtain the same effects as those of the second embodiment.

[0125] Furthermore, the analysis device 10 according to the third embodiment does not rewrite the feature ID, so feature data or collected data identified by the feature ID will not become unidentifiable due to rewriting.

[0126] The first to third embodiments described above may be modified as follows.

[0127] The serial number in the feature ID may be a value that decreases instead of increasing as the feature ID is generated. Such a serial number is, for example, a value that starts from 99999999 and decreases by 1 each time the feature ID is generated.

[0128] A part or all of the feature ID may be encrypted.

[0129] In the above-mentioned embodiment, a system that performs repetitive analysis is described as an example. However, in a system or device that uses feature data for other purposes, feature data can be managed in the same manner as in the above-mentioned embodiment.

[0130] The analysis device 10 according to the third embodiment can associate the parent ID with the child ID by a method other than the above.

[0131] In ACT 35 , the processor 11 may delete not only the feature data associated with the feature ID having the Xth serial number, but also the feature ID. Furthermore, the processor 11 may delete the record identified by the feature ID together.

[0132] The processor 11 can realize part or all of the processing realized by the program in the above-mentioned embodiment by means of a hardware configuration of a circuit.

[0133] Several embodiments of the present invention have been described above, but the above embodiments are provided as examples and are not intended to limit the scope of the invention. The above new embodiments can be implemented in various other ways, and various omissions, substitutions, changes, and combinations can be made without departing from the gist of the invention. The above embodiments and their variations are included in the scope and gist of the invention, and are also included in the schemes recorded in the claims and their equivalents.

Claims

1. A feature quantity management device, It is characterized in that have: a data generating unit for generating feature quantity data representing a feature quantity of biological information of the person from an image showing the person; an ID generating unit that generates identification information including validity period information indicating a start time point or an end time point of a validity period of the feature data used for determining a validity period of the feature data; a storage unit for storing the feature data and the identification information in association with each other; a deleting unit that deletes the feature data stored in the storage unit when the validity period is before the current date and time; as well as The changing unit, when determining that the feature data generated by the data generating unit is consistent with the feature data stored in the storage unit, changes the validity period by rewriting the identification information containing the validity period information associated with the feature data stored in the storage unit into the identification information containing the validity period information of the feature data generated by the data generating unit.

2. The feature quantity management device according to claim 1, in, The identification information generated by the ID generating unit further includes a serial number unique to each of the identification information, and the serial number is a number that increases each time the identification information is generated. The deleting unit determines whether the expiration date of the feature data stored in the storage unit is before the current date and time in ascending order of the serial numbers.

3. The feature quantity management device according to claim 1, in, Data indicating that the feature amount data has been deleted is stored in association with the identification information.

4. The feature quantity management device according to claim 1, in, The storage unit further stores the collected data including the action history in association with the identification information.

5. The feature quantity management device according to claim 4, in, The deleting unit deletes the collected data simultaneously with the deletion of the feature amount data.

6. The feature quantity management device according to claim 4, in, The deleting unit selectively performs any one of the following: deleting the feature data without deleting the collected data, or deleting the collected data while deleting the feature data.

7. A feature quantity management device, It is characterized in that have: a data generating unit for generating feature quantity data representing a feature quantity of biological information of the person from an image showing the person; an ID generating unit that generates identification information including validity period information indicating a start time point or an end time point of a validity period of the feature data used for determining a validity period of the feature data; a storage unit for storing the feature data and the identification information in association with each other; a deleting unit that deletes the feature data stored in the storage unit when the validity period is before the current date and time; as well as a changing unit that, when it is determined that the feature data generated by the data generating unit is consistent with the feature data stored in the storage unit, changes the expiration date by associating the identification information including the expiration date information newly generated by the ID generating unit with the identification information including the expiration date information associated with the feature data stored in the storage unit, The deleting unit deletes the feature data stored in the storage unit when the expiration date determined using the expiration date information included in the identification information newly generated by the ID generating unit is before the current date and time.

8. The feature quantity management device according to claim 7, in, The identification information generated by the ID generating unit further includes a serial number unique to each of the identification information, and the serial number is a number that increases each time the identification information is generated. The deleting unit determines whether the expiration date of the feature data stored in the storage unit is before the current date and time in ascending order of the serial numbers.

9. A storage medium storing a program for causing a processor of a feature quantity management device to function as the following units: a data generating unit for generating feature quantity data representing a feature quantity of biological information of the person from an image showing the person; an ID generating unit that generates identification information including validity period information indicating a start time point or an end time point of a validity period of the feature data for determining a validity period of the feature data; a storage unit for storing the feature data and the identification information in association with each other; a deleting unit that deletes the feature data stored in the storage unit when the validity period is before the current date and time; as well as The changing unit, when determining that the feature data generated by the data generating unit is consistent with the feature data stored in the storage unit, changes the validity period by rewriting the identification information containing the validity period information associated with the feature data stored in the storage unit into the identification information containing the validity period information of the feature data generated by the data generating unit.

10. A storage medium storing a program for causing a processor included in a feature quantity management device to function as the following units: a data generating unit for generating feature quantity data representing a feature quantity of biological information of the person from an image showing the person; an ID generating unit that generates identification information including validity period information indicating a start time point or an end time point of a validity period of the feature data used for determining a validity period of the feature data; a storage unit for storing the feature data and the identification information in association with each other; a deleting unit that deletes the feature data stored in the storage unit when the validity period is before the current date and time; as well as a changing unit that, when it is determined that the feature data generated by the data generating unit is consistent with the feature data stored in the storage unit, changes the expiration date by associating the identification information including the expiration date information newly generated by the ID generating unit with the identification information including the expiration date information associated with the feature data stored in the storage unit, The deleting unit deletes the feature data stored in the storage unit when the expiration date determined using the expiration date information included in the identification information newly generated by the ID generating unit is before the current date and time.