User management system
By detecting user presence and actions through sensors and combining this with database analysis, the privacy protection challenge in user management has been solved, enabling accurate identification and management of user behavior while protecting privacy.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- TOYOTA JIDOSHA KK
- Filing Date
- 2025-10-20
- Publication Date
- 2026-07-31
AI Technical Summary
Existing technologies struggle to accurately identify and manage user actions while protecting privacy, and using cameras or other means to directly identify personal information incurs privacy violations.
Sensors are used to detect user presence and actions. Users are managed through anonymous and specific tags. By combining database records and analysis of user behavior patterns, user identification and processing can be achieved, avoiding direct identification of personal information.
It enables accurate identification and management of user actions while protecting user privacy, thereby improving the privacy protection capabilities of the user management system.
Smart Images
Figure CN122490567A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to a user management system for managing users who utilize one or more rooms. Background Technology
[0002] Patent Document 1 discloses a motion detection device that uses a camera to detect human movement. The motion detection device uses camera images captured by the camera to determine a person passing through a door by comparing facial images. The motion detection device uses the camera images to track the person and detect characteristics of the person's movements.
[0003] Patent Document 1: Japanese Patent Application Publication No. 2011-034357
[0004] Consider the scenario of managing one or more users utilizing one or more rooms. To gain detailed knowledge of each user's actions and achieve proper user management, user identification is required. However, constantly capturing images of users with cameras for this purpose is not preferable from a user privacy perspective. Summary of the Invention
[0005] One objective of this disclosure is to provide a technology that enables user management based on a privacy protection perspective.
[0006] The first viewpoint involves a user management system that manages users from the first room to the Nth room, specifically users from the first user to the Pth user (where N and P are both integers greater than 1).
[0007] The user management system has one or more processors and a database.
[0008] One or more processors are configured as follows:
[0009] For actions performed in room i (i = 1 to N), where it is uncertain which user performed the action, detection processing is performed.
[0010] Event data is recorded in a database. This event data establishes a correlation between the actions detected during the detection process and the time of detection.
[0011] Perform the first determination process.
[0012] The first determination process includes:
[0013] Determine whether the detected action matches a specific action associated with the p-th user (p = 1 to P); and
[0014] If the detected action matches the p-th specific action, the event data is assigned a p-th specific flag indicating that the p-th user performed the detected action.
[0015] The user management system disclosed herein uses separate detection processing for detecting uncertain users and a first determination process for identifying users who have performed actions based on specific actions taken by the user. The user management system can also perform the first determination process on past actions based on a time series shown in a database. Therefore, devices that directly determine an individual, such as cameras, are not required. In other words, the user management system allows for the monitoring of user actions from a privacy perspective. Attached Figure Description
[0016] Figure 1 This is a schematic diagram showing the overview of the user management system.
[0017] Figure 2 This is a flowchart illustrating the processing flow of the user management system.
[0018] Figure 3 This is a diagram illustrating several examples of re-anonymization.
[0019] Figure 4 This is a schematic diagram illustrating the general outline of the move determination process.
[0020] Figure 5 This is a schematic diagram illustrating an example of indirect user-defined processing.
[0021] Figure 6 It is a schematic diagram representing a portion of a database that records actions detected on a particular day.
[0022] Figure 7 It is a schematic diagram representing a portion of a database related to actions recorded on another day.
[0023] Figure 8 It is a schematic diagram representing a portion of a database related to actions recorded on another day.
[0024] Figure 9 It is a schematic diagram used to illustrate examples of deterministic processing involving learning.
[0025] Figure 10 This is a block diagram illustrating an example of the structure of a user management system.
[0026] Explanation of reference numerals in the attached figures
[0027] 1...User Management System; 10...Facilities; 130...Detection Unit; 140...User Determination Unit; F...Identification Information; U...User; DB...Database. Detailed Implementation
[0028] The embodiments of this disclosure will be described with reference to the accompanying drawings.
[0029] 1. User Management System
[0030] 1-1. Main Components
[0031] Figure 1 This is a schematic diagram illustrating the general structure of the user management system 1. The user management system 1 manages users numbered from the first room to the Nth room (N being an integer greater than or equal to 1) – specifically, the first user to the Pth user (hereinafter referred to as "User U"; P being an integer greater than or equal to 1). The first room to the Nth room are configured to allow movement between them via passageways and other rooms. Typically, the user management system 1 is applied to spaces consisting of multiple individual rooms and used by multiple specific individuals (such as residential housing or offices).
[0032] Each of the first to Nth rooms is equipped with a detection unit 130 and a user determination unit 140.
[0033] The user management system 1 performs a detection process to detect users U present in rooms equipped with detection units 130. This detection process checks for the presence of a person (user U) and does not determine who the detected person is. The user management system 1 assigns an "anonymous flag" to users detected through the detection process. The detection unit 130 includes, for example, a human body sensor such as an infrared sensor or a wireless sensing detection device. Wireless sensing detection detects objects by detecting changes in radio waves caused by the interception of wireless communication radio waves by an object. In this embodiment, for ease of explanation, the user detected through the detection process in the i-th room (i = 1 to N) is defined as "first user U-1". That is, the detection process is the process of detecting the first user U-1 present in the i-th room and assigning an anonymity flag.
[0034] Various sensors are used in the detection process. These sensors are contained within the detection unit 130. The sensors are installed in various locations. For example, by installing pressure sensors on a bed, table, chair, etc., actions performed by user U, such as getting up, going to bed, sitting down, or standing, can be detected. The detection process is the process of detecting the presence of user U by detecting the actions performed by user U. That is, the detection process can be called both action detection processing for detecting actions and user detection processing for detecting the presence of user U.
[0035] User management system 1 determines whether a first user U-1, who has been assigned an anonymous flag, has performed a "specific action." A specific action is an action used to identify each user U. Examples of specific actions include physical actions (sitting in a specific location, raising both hands, etc.), turning on the power of a designated electronic device (e.g., a PC), or logging into a specific system via an electronic device. Upon detecting a specific action associated with the first user U-1, user management system 1 determines who the user is by assigning a "first specific flag" to the first user U-1, who has been assigned an anonymous flag. Hereinafter, the process of assigning a specific flag to identify user U will be referred to as the "user identification process." Assume that the first user U-1 performs the first specific action in room j (j = any one of 1 to N) and is identified through the user identification process.
[0036] The detection process and the user determination process can be performed in the same room or in different rooms. That is, the user U detected by the detection process can move to other rooms and is determined by performing a specific action in the room where the user is moving to.
[0037] User management system 1 acquires information related to anonymous and specific tags as tag information F. User management system 1 centrally manages the received tag information F. Specifically, user management system 1 manages the number of users U in each room and the entry and exit status of users U relative to each room based on tag information F.
[0038] This embodiment illustrates a user management system 1 being applied to... Figure 1 The lower part shows the configuration of facility 10. Facility 10 is formed by a cluster of hexagonal rooms, with the central room allowing access to any of the other rooms. That is, the rooms of facility 10 are configured to allow access to each other via the central room. Facility 10 is merely an example illustrating the application of user management system 1, and the number, shape, and arrangement of the rooms are not limited to the example shown in this embodiment.
[0039] 1-2. Processing flow
[0040] Figure 2 This is a flowchart illustrating the processing flow of the user management system 1. The right side of this diagram schematically shows the status of facility 10 in a series of steps.
[0041] In step S10, the user management system 1 performs detection processing in the i-th room. If a user is detected (S10; Yes), the process proceeds to step S11. If no user is detected (S10; No), step S10 is repeated.
[0042] In step S11, the user management system 1 assigns an anonymity flag to the first user U-1 detected in the i-th room. At this point in time, the detection unit 130 identifies the presence of the first user U-1 in the i-th room, but does not determine who the first user U-1 is. Next, the process proceeds to step S12.
[0043] In step S12, the user management system 1 determines whether a first specific action has been performed in room j. If the first specific action has been performed (S12; Yes), the process proceeds to step S13. If the first specific action has not been performed (S12; No), the process repeats step S12.
[0044] In step S13, the user management system 1 assigns a first specific flag to the first user U-1. At this point in time, the user determination unit 140 is able to determine who the first user U-1 detected in the i-th room is. After that, the process ends.
[0045] <Effect>
[0046] The user management system 1 uses a separate "detection process" for detecting uncertain users U and a "user determination process" for determining user U based on specific actions performed by user U. This series of processes does not require devices that directly identify an individual, such as cameras or microphones. The sensors used in the user management system 1 simply need to detect the presence of action. Furthermore, when detecting specific actions in the user determination process, information that directly identifies an individual (such as images captured by a camera or sounds captured by a microphone) is not required. In other words, the user management system 1 can obtain information related to user U's activity lines and behavior patterns while taking user U's privacy into account.
[0047] 2. Related processing
[0048] 2-1. Re-anonymization
[0049] Consider the case where there are multiple users U. In this case, when there are multiple users U-1 to M (M is an integer greater than 2) in the k-th room (k = 1 to N), including the first user U-1 who has been assigned a first specific flag, it is preferable to update the first specific flag assigned to the first user U-1 to the anonymous flag. Hereinafter, the process of updating the specific flag to the anonymous flag is referred to as "re-anonymization processing".
[0050] Figure 3 This is a diagram illustrating several examples of re-anonymization. Figure 3(A) illustrates a situation where a second user U-2, assigned anonymity, enters the k-th room where the first user U-1 is located. Since the user management system 1 manages users U based on the number of flags in each room, it's impossible to identify which user is the identified first user U-1 when there are two users in the k-th room. Therefore, in this case, it's preferable to update the first user U-1's specific flag to an anonymity flag, resulting in two anonymous users in the k-th room. This re-anonymization process helps prevent errors in the correspondence between the two flags (anonymity flag and specific flag). Figure 3 As shown in (B), when the second user U-2, who has been given a second specific flag, enters the k-th room, not only the first user U-1, but also the second user U-2 is re-anonymized.
[0051] 2-2. Movement Detection Processing
[0052] Consider the case where rooms 1 through N include two adjacent rooms. User management system 1 can perform a "movement determination process" to determine whether a user existing in one of the two adjacent rooms has moved to the other of the two adjacent rooms. Figure 4 This is a schematic diagram illustrating the general outline of the movement determination process. If we define two adjacent rooms as room s and room t (s, t = 1~N), the movement determination process can be described as determining whether user U has moved between room s and room t. The movement determination process is executed based on the number of users s (ns) and t (nt). The number of users s (ns) represents the number of users present in room s. In other words, the number of users s (ns) can be described as the number of flags in room s (the sum of anonymous and specific flags). Similarly, the number of users t (nt) represents the number of users present in room t. Figure 4 In the example, user U moves from room s to room t. When user U is in room s, the number of users s, ns, is 1, and the number of users t, nt, is 0. When user U moves to room t, the number of users s, ns, is 0, and the number of users t, nt, is 1. Since rooms s and t are adjacent, the changes in the number of users s, ns, and nt, accompanying user U's movement, should occur within a short time. Generally, if both the number of users s, ns, and nt, nt, change within a specified time, the user management system 1 determines that there is a movement of user U between room s and room t.
[0053] Information related to the number of users ns (s-th) and nt (t-th) can be called the neighboring user count information. That is, the movement determination process can be described as a process based on the neighboring user count information to determine whether a user U existing in one of two adjacent rooms has moved to the other of those two adjacent rooms. In other words, by repeatedly performing the movement determination process, the user management system 1 can track users U within the facility 10.
[0054] 2-3. Indirect User Determination Processing
[0055] In addition to action-based methods as described in paragraph 1-1, methods for indirectly determining the first user U-1 can also be considered for user determination processing. Such user determination processing is specifically referred to as "indirect user determination processing".
[0056] Figure 5 This is a schematic diagram illustrating an example of indirect user confirmation processing. S1 and S2 are related to... Figure 3 The same situation as (A) in S1. In S1, the first user U-1 is associated with the user ID corresponding to the first specific identifier, namely "A". Here, the user ID only needs to be a simple identification symbol and does not need to be associated with personal information such as facial photos, addresses, phone numbers, or email addresses.
[0057] In S2, re-anonymization is performed, and the first user U-1 and the second user U-2 are identified as two anonymous users by the user management system 1. At this time, the user management system 1 records that the two anonymous users include "A".
[0058] Afterwards, the two anonymous users, including "A", move separately, reaching state S3. At this point, if the move detection process is executed, the user management system 1 can track the two anonymous users, including "A". However, it cannot determine which of the two anonymous users is "A".
[0059] In S4, suppose one of the two anonymous users is determined to be "B" (i.e., not "A") through user identification processing. At this time, since the other of the two anonymous users (the one who is not "B") can be uniquely identified as "A", the user management system 1 can indirectly determine "A". At this time, the user management system 1 can determine "A" without determining the first specific action.
[0060] Indirect user identification processing can be applied not only to cases with two anonymous users, but also to the general case with multiple users. Generally, indirect user identification processing is applied when, after assigning an anonymity flag to the first user U-1 through re-anonymization in room k, all users from the second user to the Mth user are assigned the second specific flag to the Mth specific flag.
[0061] 3. User confirmation processing using the database.
[0062] User management system 1 may also include a database DB. By referring to the database DB, user management system 1 can efficiently perform user determination processing. Actions detected through detection processing and the times when those actions were performed are recorded in the database DB. The data that establishes the correspondence between actions and times is called "event data." The longer the user management system 1 is used, the more event data accumulates in the database DB. The user determination processing using the database DB will be described below. Here, it is assumed that facility 10 is a residence for family members. In the following description, the first to third rooms are adjacent to the kitchen, and the kitchen and living room are adjacent to each other.
[0063] Figure 6 This is a schematic diagram representing a portion of the database DB that records actions detected on a given day. For ease of explanation, each action is numbered. A summary of each action is shown below. As data including actions A1 to A10, event data E1 to E10 are attached as reference numerals. Actions moving within each room are determined using the movement determination process described above. Figure 6 The action patterns of each user shown are defined as pattern X. It is assumed that users P through P utilize facility 10.
[0064] <Action A1> Get up in the first room
[0065] <Action A2> Get up in the second room
[0066] <Action A3> Get up in the third room
[0067] <Action A4> Move from the first room to the kitchen
[0068] <Action A5> Making breakfast in the kitchen
[0069] <Action A6> Having breakfast in the kitchen
[0070] <Action A7> Move from the kitchen to the living room
[0071] <Action A8> Move from the second room to the kitchen
[0072] <Action A9> Having breakfast in the kitchen
[0073] <Action A10> Clean the living room with a vacuum cleaner
[0074] 3-1. First Determined Process
[0075] User management system 1 performs a first determination process. In this first determination process, user management system 1 determines whether each action recorded in database DB matches a specific action associated with each user. If the recorded action matches a specific action, a specific flag is assigned to the event data. Except for the use of database DB, this process is the same as the user determination process described in paragraph 1-1. Figure 6 The upper part represents the contents of the database DB after the first determination process. Event data E1 containing action A1 is assigned a first specific flag F1 indicating that it was performed by the first user U-1. Event data containing action A2 is assigned a second specific flag F2 indicating that it was performed by the second user U-2. Event data containing action A3 is assigned a third specific flag F3 indicating that it was performed by the third user. Since actions A1 to A3 are all actions of getting out of bed in the room, they are detected, for example, by a sensor installed on the bed. Furthermore, by matching the getting-out action with the room where the action was detected, the user who performed the action can be identified. Since the user management system 1 cannot determine which user performed actions A4 to A10, no specific flag is assigned to the corresponding event data E4 to E10. Hereinafter, the person performing each action will be referred to as an "actor".
[0076] More generally, the first determination process includes determining whether the action detected by the detection process matches a specific action (p is any one of 1 to P) associated with the p-th user. The first determination process also includes assigning a specific flag (p-specific) to the event data, indicating that the p-th user performed the action, if the detected action matches the specific action (p-specific). Event data assigned the specific flag (p-specific) through the first determination process is called p-specific event data. Event data not assigned the specific flag (p-specific) through the first determination process is called anonymous event data. That is, in Figure 6 In the data, actions A1 to A3 represent the first specific event data to the third specific event data, respectively. On the other hand, actions A4 to A10 represent anonymous event data.
[0077] 3-2. Second Determined Process
[0078] Following the first determination process, the user management system 1 executes the second determination process. The second determination process assigns specific flags to anonymous event data based on the time series displayed in the database DB. Figure 6The lower part represents the content of the database DB after the second determination process. For example, in action A4, it is clear that the user who can move from the first room to the kitchen is the first user U-1, who was originally in the first room. Therefore, the user management system 1 assigns a first specific flag F1 to action A4. Since it is clear that the first user U-1 performed action A4, it is also clear that the subsequent actions A5 to A7 were performed by the first user U-1. This is because there are no other users in the kitchen besides the first user U-1 during this time period. Following the same logic as action A4, it is clear that action A8 was performed by the second user U-2. Furthermore, it is clear that action A9, which immediately follows action A8, was also performed by the second user U-2. Although the part about eating breakfast is common in actions A5 and A8, at the time of action A8, there are no users other than the second user U-2 in the kitchen (the first user U-1 has moved to the living room). Therefore, it is clear that action A8 was performed by the second user U-2. It is clear that action A10 was performed by the first user U-1, who moved to the living room in action A7. User management system 1 assigns specific flags to anonymous event data with clearly identified actors. Additionally, since no movement originating from the third room was detected (recorded), it is determined that the third user did not move from the third room.
[0079] In the second determination process, the user management system 1 determines whether an action was clearly performed by user p based on the time series shown in the database containing data of a specific event p. Furthermore, if it is clear that user p performed an action, the user management system 1 assigns a specific flag (p-th flag) to the anonymous event data. That is, in... Figure 6 In the example, the user management system 1 assigns a first specific flag F1 to event data E4-E7 and E10, and a second specific flag F2 to event data E8-E9.
[0080] Figure 7 This is a schematic diagram representing a portion of a database (DB) related to actions recorded on another day. Figure 7 The action patterns of each user shown are defined as pattern Y. In pattern Y, the timing of actions A4 and A8 is swapped with that of pattern X. In this case, the actors of each action determined by the second determination process are different from those in pattern X. Specifically, actions A5-A8 and A10 are clearly actions performed by the second user U-2, and actions A4 and A9 are clearly actions performed by the first user U-1. In this case, the user management system 1 assigns a second specific flag F2 to event data E5-E8 and E10, and assigns a first specific flag F1 to event data E4 and E9.
[0081] In the second determination process, the actor is not always clear about all actions. Figure 8This is a schematic diagram representing a portion of a database (DB) related to actions recorded on another day. Figure 8 The action patterns of each user shown are defined as Pattern Z. In Pattern Z, immediately following action A3, two actions (A4 and A8) are recorded involving movement towards the kitchen. In this case, since two users are simultaneously present in the kitchen, the user management system 1 cannot determine the correspondence between the two users, the first user U-1, and the second user U-2. That is, the user management system 1 performs re-anonymization. Therefore, for actions A5, A6, and A9 performed in the kitchen, the actor is unclear. Therefore, the user management system 1 does not assign a specific label to event data after 7:30. Furthermore, even in this case, it is determined that actions after 7:30 are performed by either the first user U-1 or the second user U-2 (the possibility that the third user, who did not move from the third room, is the actor is excluded). Therefore, as in Pattern Z, even when the actor is not uniquely identified, the user management system 1 is still somewhat beneficial in understanding action patterns.
[0082] 3-3. Feature Extraction of Actions
[0083] By extracting the features of each action, the user management system 1 can execute the first determination process more efficiently. The following describes this process.
[0084] For example, in pattern X (refer to) Figure 6 Under mode X, it is determined that the first user U-1 performed actions A5 and A10. The user management system 1 can extract the features of actions A5 and A10 performed by the first user U-1. The features of each action are extracted based on information obtained from the sensors. Features of action A5 include, for example, the time period for making breakfast, the time required to make breakfast, the speed of moving cooking utensils, acceleration, whether the stove is used, etc. Alternatively, the load applied to the kitchen floor can be measured by the set sensors, and the measured value can be regarded as body weight and extracted as a feature. Features of action A10 include, for example, the time period for using the vacuum cleaner, the length of time the vacuum cleaner is used, the speed of moving the vacuum cleaner, acceleration, etc. That is, the user management system 1 extracts the features inherent to actions A5 and A10 performed by the first user U-1 from the data of mode X. In other words, the more mode X is repeated, the more the user management system 1 learns the behavior and habits that accompany actions A5 performed by the first user U-1. Similarly, in mode Y (refer to Figure 7 In the case of ), the user management system 1 extracts (learns) the inherent features of the actions A5 and A10 performed by the second user U-2.
[0085] User management system 1 can use the learned features for the first deterministic process. The first deterministic process without accompanying feature learning can be called "deterministic process without learning", and the first deterministic process with accompanying feature learning can be called "deterministic process with learning". Here, the difference between these two processes is described. Figure 9 This is a schematic diagram used to illustrate examples of deterministic processing involving learning. The database DB contains schema Z (and...). Figure 8 (Same). In Figure 8 It is an example of deterministic processing without learning. Figure 9 The difference lies in the presence of deterministic processing with learning. Without deterministic processing, because the actors of actions A5 and A10 are unclear, no specific flags are assigned to event data E5 and E10. On the other hand, with deterministic processing with learning (… Figure 9 In the case of ( ), actions A5 and A10 may be clearly defined. This is because the user management system 1 has learned the inherent characteristics of the actions performed by each user under modes X and Y. Figure 9 In the process, the user management system 1 identifies the actor of action A5 as the first user U-1 and the actor of action A10 as the second user U-2.
[0086] That is, the user management system 1 extracts features of actions contained in anonymous event data that have been assigned a specific label p through a second determination process. The user management system 1 also uses the extracted features as features of the specific p-th action in the first determination process. The longer the user management system 1 operates, the more event data accumulates, and the more progress is made in learning the actions performed by each user. As a result, the efficiency of the user management system 1 in determining each user in the first determination process gradually improves. The extracted action features can include the time period in which the action was performed, the location where the action was performed, the duration of the action, and the mechanical parameters related to the action. Mechanical parameters are parameters such as speed, acceleration, and load obtained from sensors installed on equipment or materials.
[0087] Furthermore, in the second determination process, based on the time sequence relationship, it is determined that the room movement immediately preceding action A10 (action A7) was performed by the second user U-2. For actions A6 and A9, although the actor is not determined, it may be possible to identify them through further continuous feature learning. Even if... Figure 9 The state shown also allows us to track the activity lines of the two users. That is, it is determined that the actor for action A6 is either the first user U-1 or the second user U-2, and the actor for action A9 is the other user. Therefore, in mode Z, the user management system 1 can determine that the first user U-1 moved from the first room to the kitchen and the second user U-2 moved from the second room through the kitchen to the living room.
[0088] 3-4. Data on Unknown Events
[0089] In the user management system 1, there may also be event data that, even after the first and second determination processes, has not been assigned a specific flag. For example, suppose someone enters facility 10 from outside, moves to the kitchen, and then leaves. The user management system 1 detects this series of actions and records it in the database DB. However, in this case, the user management system 1 is essentially unable to determine the actor responsible for this series of actions. The user management system 1 can assign an "unknown flag" to such event data, indicating that the actor is unknown. Event data assigned the unknown flag will be referred to as "unknown event data" below. Since the actor responsible for unknown event data could also be an unauthorized intruder, the user management system 1 can notify the administrator of the user management system 1 and user U of the situation when it has accumulated unknown event data.
[0090] As another scenario, consider the case where user U's friend regularly visits facility 10 and cooks in the kitchen. The user management system 1 initially treats this cooking action as undefined event data. As described above, since the user management system 1 can extract the characteristics of this cooking action, if the friend repeatedly performs the cooking action, it can treat this cooking action as a specific action and perform a first determination process. That is, the user management system 1 treats this friend as a new user.
[0091] As described above, the user management system 1 performs user identification processing on past actions based on the time series shown in the database DB. Therefore, the user management system 1 can identify the actor of each action without relying on information that can directly identify an individual, such as images or sounds. The use of the database DB in the user management system 1 is particularly effective when a camera is not included. The timing of the user identification processing (i.e., the first and second identification processes) using the database DB is not particularly limited. Typically, these identification processes are performed periodically at arbitrarily set intervals (monthly, quarterly, semi-annually, etc.).
[0092] 4. Example of composition
[0093] Figure 10 This is a block diagram representing an example of the structure of the user management system 1.
[0094] 4-1. Example of the composition of the i-th room
[0095] Figure 10 The right side represents an example of the structure of room i. Since the structures of rooms 1 through N are common, room i is shown here as a representative example.
[0096] Control device 110 is a computer that controls the devices installed in room i. Control device 110 includes one or more processors 111 (hereinafter referred to as processor 111) and one or more storage devices 112 (hereinafter referred to as storage devices 112). Processor 111 performs various processes. For example, processor 111 includes a CPU (central processing unit). Processor 111 can also be referred to as processing circuitry. Storage device 112 stores various information. Examples of storage devices 112 include volatile memory, non-volatile memory, HDD (hard disk drive), SSD (solid state drive), etc.
[0097] The flag program PROG1 is a computer program executed by the processor 111. The functions of the control device 110 are realized through the cooperation of the processor 111 executing the flag program PROG1 and the storage device 112. For example, the aforementioned detection processing and user determination processing are performed by the control device 110 executing the flag program PROG1. The flag program PROG1 is stored in the storage device 112. Alternatively, the flag program PROG1 may also be recorded on a computer-readable recording medium.
[0098] Control device 110 performs detection processing and user confirmation processing. Control device 110 obtains information required for detection processing via detection unit 130 and information required for user confirmation processing via user confirmation unit 140. Additionally, control device 110 communicates with management device 200 via communication device 120. Control device 110 sends the results of detection processing and user confirmation processing, i.e., flag information F, from management device 200.
[0099] User registration information (UR) is the information required by the user for processing. User registration information (UR) is a form in which each user's (U) user ID and the data related to the specific action corresponding to that user ID are linked together.
[0100] 4-2. Example of the configuration of a management device
[0101] Control device 210 is a computer that controls management device 200. Control device 210 includes one or more processors 211 (hereinafter referred to as processor 211) and one or more storage devices 212 (hereinafter referred to as storage devices 212). Processor 211 performs various processes. For example, processor 211 includes a CPU (central processing unit). Processor 211 can also be referred to as processing circuitry. Storage device 212 stores various information. Examples of storage devices 212 include volatile memory, non-volatile memory, HDD (hard disk drive), SSD (solid state drive), etc.
[0102] User management program PROG2 is a computer program executed by processor 211. The functions of control device 210 are realized through the cooperation of processor 211 and storage device 212 in executing user management program PROG2. User management program PROG2 is stored in storage device 212. Alternatively, user management program PROG2 may also be recorded on a computer-readable recording medium.
[0103] The tag information F is information related to anonymous tags and specific tags in each room. Tag information F includes information on when and in which room a particular tag was assigned. The management device 200 can use tag information F to determine the number of users U in each room, the time periods during which users U tend to congregate, etc. Tag information F is used as adjacent user count information in the movement determination process.
[0104] Database DB records user U's actions along with their time series. Database DB is used for parsing user U's activity lines and action patterns within facility 10.
[0105] The control device 210 communicates with the communication device 120 on the i-th room side via the communication device 220.
[0106] 4-3. Other
[0107] Furthermore, the management device 200 can also perform at least a portion of the detection processing and user determination processing. For example, when information obtained by the detection unit 130 and the user determination unit 140 is sent from the control device 110 to the management device 200, the management device 200 can perform at least a portion of the detection processing and user determination processing.
[0108] Generally, one or more processors perform various processes such as detection processing, user determination processing, movement determination processing, and re-anonymization processing.
Claims
1. A user management system, which manages users P through N rooms, wherein... It has one or more processors and a database. The one or more processors are configured as follows: Perform detection processing for actions performed in room i where it is uncertain which user performed the action. Event data is recorded in the database, and this event data is data that establishes a correlation between the actions detected by the detection process and the time. Execute the first determination process. The first determination process includes: Determine whether the detected action matches a specific action associated with user p; and If the detected action matches the p-th specific action, the event data is assigned a p-th specific flag indicating that the p-th user performed the detected action. Where N is an integer greater than or equal to 1, P is an integer greater than or equal to 1, i is any one of 1 to N, and p is any one of 1 to P.
2. The user management system according to claim 1, wherein, The p-th specific event data includes event data that has been assigned the p-th specific flag through the first determination process. Anonymous event data includes event data that was not assigned the p-th specific flag by the first determining process. The one or more processors are configured to further perform a second determining process. The second determination process includes: Based on the time series represented by the database containing the data of the p-th specific event, it is determined whether the detected action was clearly performed by the p-th user; and If the detected action is clearly performed by the p-th user, the anonymous event data is assigned a specific flag for the p-th user.
3. The user management system according to claim 1, wherein, The one or more processors are further configured to: Extract the features of the detected action. The extracted features are used as features of the p-th specific action in the first determination process.
4. The user management system according to claim 3, wherein, The characteristics of the detected action include at least one of the following: the time period during which the detected action was performed, the location where the detected action was performed, the duration of the detected action, and mechanical parameters associated with the detected action.
5. The user management system according to any one of claims 1 to 4, wherein, Cameras are not included.