Data analysis device and method

Abstract

A data analysis device (2) according to the present disclosure controls generation of a data string indicating the result of objects at a site having been detected in chronological order. The data analysis device comprises a display unit (23) for displaying information, an input unit (22) for inputting a user operation, and a control unit (20) for controlling a data management unit that manages object detection results and generates data strings. The control unit: displays, on the display unit, display information including a range where the ends of a plurality of data strings are adjacent to each other at the site (S1); accepts, using the input unit, a user operation to adjust a parameter indicating a condition for the plurality of data strings to be connected to each other in the adjacent range (S3); and controls the data management unit such that the parameter adjusted in the adjacent range is applied in accordance with the user operation in the input unit (S4).

Description

Data analysis apparatus and method

[0001] The present disclosure relates to a data analysis apparatus and method.

[0002] Patent Literature 1 discloses a video analysis device that tracks people in consecutive image frames captured by a camera. This video analysis device detects a person area for each image frame and outputs a score, outputs a score for changes in the person area for each pair of two image frames, recognizes a real person from each person area and outputs a score, and outputs a score for changes in person recognition in the person area. The video analysis device assigns a movement line ID and associates a person ID to each person area in the image frame using all of the above scores. This allows for continued person tracking that is robust against occlusion between people.

[0003] Japanese Patent Application Laid-Open No. 2020-09166

[0004] The present disclosure provides a data analysis device that can easily prevent interruptions in data sequences obtained by detecting objects at a site in time series.

[0005] A data analysis device according to the present disclosure controls the generation of data sequences indicating the results of detecting objects at a site over time. The data analysis device includes a display unit that displays information, an input unit that inputs user operations, and a control unit that controls a data management unit that manages the object detection results and generates the data sequences. The control unit causes the display unit to display display information including ranges at the site where ends of multiple data sequences are adjacent to each other, receives user operations via the input unit that adjust parameters indicating conditions under which the multiple data sequences are connected to each other in the adjacent ranges, and controls the data management unit to apply the adjusted parameters to the adjacent ranges in accordance with the user operations via the input unit.

[0006] These general and specific aspects may be realized by a system, a method, and a computer program, as well as combinations thereof.

[0007] The data analysis device according to the present disclosure can easily prevent interruptions in the data sequence obtained by detecting objects at a site in time series.

[0008] FIG. 1 is a diagram illustrating an overview of a movement line analysis system according to a first embodiment of the present disclosure. A block diagram illustrating a configuration of a data analysis device in the movement line analysis system. A block diagram illustrating a configuration of a movement line management server in the movement line analysis system. A diagram for explaining a break in a movement line in the movement line analysis system. A flowchart illustrating an operation of a data analysis device in the movement line analysis system. A flowchart illustrating a break visualization process in the data analysis device. A diagram showing an example of a display of a movement line analysis screen in the data analysis device. A diagram showing an example of a display of detailed information in the data analysis device. A flowchart illustrating a parameter adjustment process in the data analysis device. A diagram illustrating a break pattern table in the data analysis device. A diagram showing an example of a display of a parameter adjustment process in the data analysis device. A diagram illustrating parameter adjustment information in the data analysis device. A diagram for explaining a modified example of the data analysis device.

[0009] Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, more detailed explanation than necessary may be omitted. For example, detailed explanation of well-known matters or redundant explanation of substantially the same configuration may be omitted. This is to avoid unnecessary redundancy in the following explanation and to facilitate understanding by those skilled in the art.

[0010] The applicant provides the accompanying drawings and the following description to enable those skilled in the art to fully understand the present disclosure, and does not intend for them to limit the subject matter described in the claims.

[0011] First Embodiment Hereinafter, a first embodiment of the present disclosure will be described with reference to the drawings.

[0012] 1. Configuration The configuration of a system using a data analysis device according to the first embodiment will be described with reference to FIG.

[0013] 1-1. About the Traffic Analysis System Fig. 1 shows an overview of a traffic analysis system 1 according to this embodiment. As shown in Fig. 1, this system 1 includes a plurality of cameras 11, a data analysis device 2, and a traffic management server 3. Each of the devices 11, 2, and 3 in this system 1 is connected to a communication network 13, such as a LAN, a WAN, or the Internet, and is capable of data communication with each other.

[0014] The system 1 accumulates information for analysis, such as the trajectory, i.e., the flow line, of each worker W at a workplace 10 where one or more workers W work, such as a factory, logistics warehouse, or store. The system 1 is applicable to data analysis in which a user 15, such as a manager or analyst of the workplace 10, analyzes the time allocation or efficiency of work by each worker W at the workplace 10.

[0015] In the data analysis described above, it is useful to obtain a continuous, uninterrupted flow line from start to finish for each worker W. By reflecting the analysis results of the user 15, the data analysis device 2 of this embodiment can easily obtain a continuous, uninterrupted flow line in the flow line analysis system 1.

[0016] In this system 1, the cameras 11 are arranged, for example, in the workplace 10, so that each captured image includes a different range. The number of cameras 11 in this system 1 is not particularly limited to multiple and may be one. The cameras 11 are communicatively connected, for example, via a communication network 13 to the flow line management server 3 so as to be able to transmit video data D0 of the captured images of the workplace 10. The cameras 11 may be, for example, omnidirectional cameras or box cameras.

[0017] The flow line management server 3 is a server device that accumulates and manages information such as video data D0 captured by each camera 11 and flow line data D1 indicating various flow lines based on the video data D0. The configuration of the flow line management server 3 will be described later.

[0018] 1-2. Configuration of the Data Analysis Device The data analysis device 2 according to this embodiment presents information for the user 15 to analyze from information accumulated in the system 1, such as video data D0 and movement line data D1. The data analysis device 2 is configured as an information processing device, such as a PC (personal computer). The configuration of the data analysis device 2 will be described with reference to FIG. 2.

[0019] Fig. 2 is a block diagram illustrating an example of the configuration of the data analysis device 2. The data analysis device 2 illustrated in Fig. 2 includes a control unit 20, a storage unit 21, an operation unit 22, a display unit 23, a device interface 24, and a network interface 25. Hereinafter, the interface will be abbreviated as "I / F."

[0020] The control unit 20 includes, for example, a CPU or MPU that works in cooperation with software to realize predetermined functions. The control unit 20 controls, for example, the overall operation of the data analysis device 2. The control unit 20 reads data and programs stored in the storage unit 21 and performs various arithmetic processing to realize various functions.

[0021] The control unit 20 executes, for example, a program including a set of instructions for implementing each of the above functions. The program may be provided via the communication network 13 or may be stored on a portable recording medium. The control unit 20 may also be a hardware circuit such as a dedicated electronic circuit or a reconfigurable electronic circuit designed to implement each of the above functions. The control unit 20 may be configured with various semiconductor integrated circuits such as a CPU, an MPU, a GPU, a GPGPU, a TPU, a microcomputer, a DSP, an FPGA, and an ASIC.

[0022] The storage unit 21 is a storage medium that stores programs and data necessary to realize the functions of the data analysis device 2. As shown in Fig. 2, the storage unit 21 includes a storage unit 21a and a temporary storage unit 21b.

[0023] The storage unit 21a stores parameters, data, control programs, etc. for realizing predetermined functions. The storage unit 21a is configured, for example, with an HDD or SSD. For example, the storage unit 21a stores the above-mentioned programs and a break pattern table D10, etc. The break pattern table D10 is an example of pattern information that patterns factors that are expected to cause a break in the flow line 40, as will be described later.

[0024] The temporary storage unit 21b is configured with a RAM such as a DRAM or an SRAM, and temporarily stores (i.e., holds) data. For example, the temporary storage unit 21b holds the flow line data D1 and video data D0 received from the flow line management server 3 (FIG. 1). The temporary storage unit 21b may also function as a work area for the control unit 20, and may be configured as a storage area in the internal memory of the control unit 20.

[0025] The operation unit 22 is a general term for operation members operated by the user. The operation unit 22 may be, for example, a keyboard, a mouse, a touchpad, a touch panel, a button, a switch, etc. The operation unit 22 may also include virtual operation members such as various buttons or a pointer displayed on the display unit 23. The operation unit 22 is an example of an input unit that acquires various information input by user operations.

[0026] The display unit 23 is an example of an output unit configured, for example, by a liquid crystal display or an organic EL display. The display unit 23 may display various information such as virtual operating members of the operation unit 22 and information input from the operation unit 22.

[0027] The device I / F 24 is a circuit for connecting an external device to the data analysis apparatus 2. The device I / F 24 is an example of a communication unit that communicates in accordance with a predetermined communication standard. The predetermined standard includes USB, HDMI (registered trademark), IEEE 1394, Wi-Fi, Bluetooth, etc. The device I / F 24 may constitute an input unit in the data analysis apparatus 2 that receives various information from an external device or an output unit that transmits various information to an external device.

[0028] The network I / F 25 is a circuit for connecting the data analysis apparatus 2 to the communication network 13 via a wireless or wired communication line. The network I / F 25 is an example of a communication unit that performs communication in accordance with a predetermined communication standard. The predetermined communication standard includes communication standards such as IEEE802.3, IEEE802.11a / 11b / 11g / 11ac, etc. The network I / F 25 may constitute an input unit that receives various information or an output unit that transmits various information via the communication network 13 in the data analysis apparatus 2.

[0029] The above-described configuration of the data analysis device 2 is an example, and the configuration of the data analysis device 2 is not limited to this. For example, the data analysis device 2 may be configured as various computers including a server device. The data analysis device 2 may be configured integrally with the path management server 3.

[0030] The input unit in the data analysis device 2 may be realized in cooperation with various software in the control unit 20, etc. The input unit in the data analysis device 2 may acquire various pieces of information by reading out the various pieces of information stored in various storage media (e.g., the storage unit 21 a) into a working area of ​​the control unit 20 (e.g., the temporary storage unit 21 b).

[0031] Various display devices such as a projector and a head-mounted display may be used for the display unit 23 of the data analysis device 2. When an external display device is used, the display unit 23 of the data analysis device 2 may be an output interface circuit for a video signal or the like that complies with the HDMI (registered trademark) standard, for example.

[0032] 1-3. Configuration of the trajectory management server The configuration of the trajectory management server 3 in this embodiment will be described with reference to Fig. 3. The trajectory management server 3 is an example of a data management unit in this embodiment.

[0033] 3 is a block diagram illustrating the configuration of the path management server 3 in the present system 1. As shown in Fig. 3, the path management server 3 includes a control unit 30 and a storage unit 31. The path management server 3 further includes interface circuits (not shown) that are communicatively connected to the camera 11 and the data analysis device 2 via, for example, the communication network 13 (Fig. 1).

[0034] In the trajectory management server 3, the control unit 30 includes, for example, a CPU or MPU that cooperates with software to realize predetermined functions, and executes arithmetic processing of, for example, a program including a set of instructions for realizing each of the above functions. For example, the control unit 30 includes, as functional components, a machine learning unit 32 and a trajectory extraction unit 33.

[0035] The control unit 30 may also be a hardware circuit such as a dedicated electronic circuit or a reconfigurable electronic circuit designed to realize each of the above functions. The control unit 30 may also be configured with various semiconductor integrated circuits such as a CPU, an MPU, a GPU, a GPGPU, a TPU, a microcomputer, a DSP, an FPGA, and an ASIC.

[0036] The storage unit 31 is a storage medium that stores programs and data necessary to realize the functions of the flow line management server 3, and includes, for example, an HDD or SSD. The storage unit 31 may include RAM such as DRAM or SRAM, and may function as a work area for the control unit 30. For example, the storage unit 31 stores video data D0, flow line data D1, an image recognition model M1, map information D2, and the like. The map information D2 indicates the layout of, for example, equipment in the workplace 10 in a predetermined coordinate system (hereinafter also referred to as "map coordinates").

[0037] The machine learning unit 32 performs machine learning of the image recognition model M1 based on training data including, for example, video data D0 in which images of the workplace 10 are captured in advance and annotation information related to the images. The machine learning unit 32 stores the trained image recognition model M1 in the storage unit 31.

[0038] The annotation information is information that is manually input by, for example, the user 15, etc., specifying in advance whether an object, such as the worker W, to be detected by image recognition, is shown in the image, and the position of the object on the image. The annotation information may be stored in the storage unit 31 as appropriate, for example, during training of the image recognition model M1. In the present system 1, the data analysis device 2 may further have a function of setting the annotation information.

[0039] The image recognition model M1 is configured using machine learning to input an image, such as a frame of video data D0, and to detect the position of an object, such as a worker W, in the input image as an output. Various machine learning models, such as a convolutional neural network, can be used for the image recognition model M1. The image recognition model M1 may also detect the type of object appearing in the input image. For example, the worker W may be detected as a different type of object when performing each of a plurality of pre-set tasks, or the worker W may be personally identified.

[0040] Based on the video data D0, the image recognition model M1, and the map information D2, the flow line extraction unit 33 extracts the flow lines of the objects from the results of the image recognition model M1 sequentially detecting the objects in the video data D0, and generates flow line data D1 that can be managed using map coordinates. In this embodiment, the flow line extraction unit 33 may be an example of a data management unit. The flow line data D1 represents an example of a flow line of a data string formed by sequentially connecting the detection positions for each frame by the image recognition model M1.

[0041] The flow line extraction unit 33 has, for example, parameters for connecting detection positions in different frames by the image recognition model M1 when extracting flow lines, i.e., flow line connection parameters P1. The flow line connection parameters P1 indicate conditions that stipulate, for example, the range within which another detection position is allowed as a connection destination from the detection position of a connection source, i.e., connection conditions, and include, for example, the distance range from the connection source to the connection destination, the connection direction, and the wait time. By connecting detection positions, flow lines that have each detection position at their end can be connected to each other.

[0042] The system 1 is configured so that the flow line connection parameter P1 in the flow line management server 3 can be adjusted by a user's operation on the data analysis device 2. The flow line connection parameter P1 can be set to a different value for each area on the map coordinates based on the map information D2 or on the camera coordinates corresponding to the image captured by the camera 11. Setting information indicating various settings for the flow line connection parameter P1 is stored in the storage unit 31, for example.

[0043] The above-described configuration of the path management server 3 in the present system 1 is an example, and the configuration of the present system 1 is not limited to this. The various functions of the path management server 3 of this embodiment may be realized by distributed computing. Furthermore, the path management server 3, and therefore the present system 1, may not include the machine learning unit 32.

[0044] Furthermore, the flow line extraction unit 33 may extract the flow lines by machine learning. The flow line extraction unit 33 may extract the flow lines by machine learning, and various parameters related to such machine learning may be adjustable from the data analysis device 2. Furthermore, the image recognition model M1 may be configured by implementing various image recognition algorithms, not limited to machine learning.

[0045] 2. Operation The operation of the traffic line analysis system 1 and the data analysis device 2 configured as above will be described below.

[0046] 2-1. System Operation An example of the operation of automatically extracting the movement line of a worker W using the trained image recognition model M1 in the movement line analysis system 1 (FIG. 1) of this embodiment will be described. In this system 1, for example, multiple cameras 11 sequentially capture images of their respective imaging ranges in the workplace 10 frame by frame, and transmit the video data D0 of the captured images to the movement line management server 3.

[0047] When the flow line management server 3 receives video data D0 from each camera 11, it stores the data in the memory unit 31 and inputs it to the flow line extraction unit 33. The flow line extraction unit 33 uses the trained image recognition model M1 to detect the position of the worker W in the captured image for each frame indicated by the input video data D0. The flow line extraction unit 33 identifies a destination detection position for a source detection position among multiple detection positions for each frame, for example, according to a preset flow line connection parameter P1, and extracts a flow line in which the identified detection positions are sequentially connected. The flow line extraction unit 33 generates flow line data D1 indicating the extracted flow line and stores it in the memory unit 31.

[0048] The data analysis device 2 communicates data with the flow line management server 3 and receives various information from the flow line management server 3 in response to, for example, operations by the user 15. Based on the information obtained as described above, the data analysis device 2 generates various information that the user 15 uses to analyze the workplace 10, and displays the information on the display unit 23.

[0049] 2-1-1. Regarding Discontinuities in Flow Lines In the automatic extraction of flow lines as described above, various factors in the workplace 10 can cause a problem in which an originally continuous flow line is extracted with a break. The inventors of the present application conducted extensive research into appropriately adjusting the flow line connection parameter P1 to eliminate such breaks in flow lines, leading to the invention of the data analysis device 2 of this embodiment. These findings will be explained using FIG. 4.

[0050] 4A and 4B are diagrams illustrating interruptions in the flow lines 40 in the system 1. Fig. 4A illustrates areas where interruptions occur in the flow lines 40 in the flow line data D1, i.e., interruption areas R11 and R12, on a work site map 50 shown in the map information D2 of the work site 10. Fig. 4B illustrates a captured image 51 of the first interruption area R11 in the video data D0. Fig. 4C illustrates a captured image 52 of the second interruption area R12.

[0051] 4A and 4B show a first discontinuity area R11 in the workplace 10, which overlaps with the passageway through which the worker W passes, and an obstacle 12, such as a ceiling beam, is captured in the image 51 captured by the camera 11. In this discontinuity area R11, the worker W moving along the passageway passes behind the obstacle 12 as seen from the camera 11. In this case, it is conceivable that the worker W will not be detected by the image recognition model M1, and as a result, the extracted traffic line 40 will be interrupted. In this case, it is considered possible to eliminate the interruption in the traffic line 40 by using the predicted destination direction of the worker W as he moves along the passageway after the traffic line 40 is interrupted as the direction of the traffic line connection.

[0052] 4A and 4C , an obstacle 12 appears in the captured image 52 superimposed on the location where the worker W is working in the workplace 10. In this type of discontinuity area R12, it is expected that when the worker W works behind the obstacle 12 as viewed from the camera 11, the worker W will not be detected and the flow line 40 will be interrupted. In this case, it is predicted that the worker W behind the obstacle 12 will appear again in the captured image 52 near the obstacle 12 after working, and it is considered possible to eliminate the interruption in the flow line 40 by reflecting this prediction in the adjustment of the flow line connection parameter P1.

[0053] As described above, the inventors of the present application have noticed that while implementing the analysis of various situations in which the flow lines 40 are interrupted using AI technology or the like would be highly difficult, users 15 of the present system 1 can specifically identify the causes of the interruptions by visually checking the current state of the workplace 10. Therefore, the data analysis device 2 of this embodiment visualizes the situations in which the flow lines 40 are interrupted to the user 15, and provides a user interface that allows the flow line connection parameter P1 to be adjusted to reflect the analysis of the user 15. The operation of the data analysis device 2 of this embodiment will be described in detail below.

[0054] 2-2. Operation of Data Analysis Apparatus The overall operation of the data analysis apparatus 2 of this embodiment will be described with reference to FIG.

[0055] Fig. 5 is a flowchart illustrating an example of the operation of the data analysis device 2 in the present system 1. Each process in the flowchart illustrated in Fig. 5 is executed, for example, by the control unit 20 of the data analysis device 2. The processing of this flow starts, for example, in a state where flow line data D1 has been obtained in the flow line management server 3 from video data D0 captured by the camera 11 using a trained image recognition model M1 and preset flow line connection parameters P1.

[0056] First, the control unit 20 of the data analysis device 2 performs a process (S1) on the display unit 23 to visualize, for the user 15, the state of discontinuities in the flow lines 40 in the workplace 10, based on the current flow line data D1 generated by the flow line management server 3. In the discontinuity visualization process (S1), various display information regarding discontinuity areas R11, R12 in the flow lines 40 in the workplace 10 is presented to the user 15, as shown in Fig. 4, for example. The details of the discontinuity visualization process (S1) will be described later. Hereinafter, the discontinuity areas R11, R12 will be collectively referred to as discontinuity area R1.

[0057] The user 15 checks the various display information visualized in step S1, and if there is a discontinuity area R1 for which the flow line connection parameter P1 should be adjusted, the user 15 can input an operation to designate the discontinuity area R1 on the operation unit 22. The control unit 20 determines whether or not the discontinuity area R1 has been designated based on the user operation input on the operation unit 22 (S2).

[0058] When a discontinuity area R1 is designated by an input user operation (YES in S2), the control unit 20 performs a process of accepting a user operation to adjust a flow line connection parameter P1 for the designated discontinuity area R1 (S3). In the parameter adjustment process (S3), various information is presented to guide the user 15 so as to adjust the flow line connection parameter P1 to appropriately reflect the situation identified in the discontinuity area R1 designated by the user 15 (S3). The parameter adjustment process (S3) will be described in detail later.

[0059] Next, the control unit 20 transmits parameter adjustment information including flow line connection parameters P1 resulting from the parameter adjustment process (S3) for, for example, the discontinuity area R1 designated by the user 15 to the flow line management server 3 (S4). Thereafter, the control unit 20 performs, for example, step S1 and subsequent processes again. The discontinuity visualization process (S1) at this time is performed, for example, using flow line data D1 obtained by re-extracting the flow lines 40 in the flow line management server 3 while reflecting the adjustment result of step S3. For example, the user 15 can check the adjustment result of step S3 in the subsequent step S1 and repeat the parameter adjustment process (S3) until the discontinuity area R is eliminated.

[0060] If the discontinuity area R1 is not specified by the input user operation (NO in S2), the control unit 20 ends the processing shown in this flowchart.

[0061] According to the above process, the data analysis device 2 visualizes to the user 15 the current state of interruptions in the flow lines 40 extracted by the flow line management server 3 (S1), and adjusts the flow line connection parameter P1 in accordance with the user's operation (S3). This makes it possible to more easily suppress interruptions in the flow lines 40 extracted in the workplace 10 using the trained image recognition model M1 by reflecting the analysis of the user 15.

[0062] 2-2-1. Interruption Visualization Processing Details of the interruption visualization processing in step S1 of FIG. 5 will be described with reference to FIGS.

[0063] Fig. 6 is a flowchart illustrating the interruption visualization process (S1 in Fig. 5) in the data analysis device 2. Fig. 7 shows an example of a display of a flow line analysis screen in the data analysis device 2. Fig. 8 shows an example of a display of detailed information in the data analysis device 2.

[0064] First, the control unit 20 acquires the flow line data D1 for a predetermined period (e.g., one day) to be analyzed from the flow line management server 3 via, for example, the network I / F 25, and displays a flow line analysis screen including the flow lines 40 indicated by the acquired flow line data D1 on the display unit 23 (S11). An example of the display in step S11 is shown in Fig. 7(A).

[0065] For example, in step S11, the flow line management server 3 transmits flow line data D1, which is the result of the flow line extraction unit 33 extracting flow lines 40 from the detection results of the image recognition model M1 based on the current flow line connection parameters P1, to the data analysis device 2 together with, for example, map information D2. For example, as shown in FIG. 7A , the display unit 23 of the data analysis device 2 displays a flow line analysis screen in which the flow lines 40 indicated by the acquired flow line data D1 are superimposed on a workplace map 50 of the map information D2. The map information D2 may be stored in advance in the storage unit 21 of the data analysis device 2.

[0066] Next, the control unit 20 displays, on the flow line analysis screen of Fig. 7A, for example, candidates for the discontinuity area R1 to notify the user 15 (S12). An example of the display in step S12 is shown in Fig. 7B.

[0067] For example, in step S12, the control unit 20 first detects, based on the acquired flow line data D1, an area where the start and end of the flow line 40 are adjacent to each other within a predetermined distance in the map information D2 and where the number of adjacent ends is equal to or greater than a predetermined number, as a potential discontinuity area R10. The predetermined distance and the predetermined number are set in advance as criteria for determining that the ends of the flow line 40 are densely packed.

[0068] Furthermore, in step S12, the control unit 20, for example, refers to the map information D2 and excludes from the notification target the area corresponding to the entrance / exit of the workplace 10 in the potential interruption area R10 detected as described above. The areas to be excluded are not limited to the above, and can be set to various areas where both ends of the traffic line 40 are expected to be located, regardless of the interruption of the traffic line 40, and may include, for example, the end areas of the angle of view range of the camera 11 or the detection range of the present system 1.

[0069] The control unit 20 detects the remaining candidate discontinuity areas R10 that have not been excluded as described above as targets for notification, and displays the detected candidate discontinuity areas R10 for notification on the display unit 23 with a notification marker 45 attached (S12), as shown in Fig. 7(B) for example. The notification marker 45 is a marker for notifying the user 15 of candidates for the discontinuity area R1.

[0070] The notification marker 45 may be in the form of various icons, or may be various highlighting displays such as highlighting the potential interruption area R10 in a highlighted color, hatching, blinking, etc. The notification in step S12 may not require a marker display, and only the potential interruption area R10 to be notified may be displayed.

[0071] The control unit 20 receives various user operations via the operation unit 22 while the flow line analysis screen of Fig. 7B is displayed, and determines whether a candidate for the discontinuity area R1 has been selected by the user operation (S13). For example, the user 15 can input an operation to the operation unit 22 using the pointer 4 to select a desired candidate for the discontinuity area R10 from the candidate for the discontinuity areas R10 displayed on the flow line analysis screen of Fig. 7B.

[0072] When a candidate interruption area R10 is selected by a user operation (YES in S13), the control unit 20 causes the display unit 23 to display detailed information about the selected candidate interruption area R10 (S14). The detailed information includes various information for allowing the user 15 to confirm a situation in which the flow line 40 is interrupted in the workplace 10. An example of the display in step S14 is shown in FIG. 8.

[0073] 8 , the display unit 23 displays a flow line list 55 and a flow line video 56, each of which is an example of detailed information about the interruption candidate area R10 selected by a user operation in step S13. The flow line list 55 lists, for example, each flow line 40 whose end is located within the interruption candidate area R10, various pieces of information about the flow line 40 in association with each other. The flow line video 56 is, for example, a video of the interruption candidate area R10 captured during a time period related to one of the flow lines 40 in the flow line list 55.

[0074] The information in the flow line list 55 includes, for example, a "flow line No." which is an identification number of the flow line 40, a "start time" which is the time corresponding to the start of the flow line 40, an "end time" which is the time corresponding to the end of the flow line 40, and a "video link" which is link information associated with the flow line video 56 of the flow line 40. The flow line list 55 may also include information indicating whether the end of each flow line 40 located in the potential interruption area R10 is the start or end. For example, either the "start time" or the "end time" may be highlighted, or only one of them may be displayed.

[0075] 8 shows an example in which a user operation is input to the operation unit 22 using the pointer 4 to specify the video link of flow line No. 2 from the flow line list 55. When the video link is specified, the control unit 20 acquires the corresponding video data D0 from, for example, the flow line management server 3, and plays and displays the flow line video 56. The flow line video 56 is played and displayed, for example, from around the time when the corresponding flow line 40 was positioned in the selected break candidate area R10.

[0076] The above-described various detailed information is displayed on the display unit 23 in response to a user operation, for example, as a pop-up on the flow line analysis screen (S14). By checking the information on the flow line analysis screen and various detailed information, the user 15 can identify various conditions, such as whether a break in the flow line 40 has occurred in the break candidate area R10 selected in step S13 or the cause of the break.

[0077] The control unit 20 determines whether the selected interruption candidate area R10 has been designated as the interruption area R1 by a user operation, for example, based on a user operation on the operation unit 22 (S15). The user operation targeted in step S15 may be, for example, an operation in which the user 15 designates a range using the pointer 4 or the like to a portion of the workshop map 50 or the flow line video 56 where the user 15 believes an interruption has occurred in the interruption candidate area R10. Alternatively, the user may designate the entire selected interruption candidate area R10, or may be a click operation on the notification marker 45, for example.

[0078] If the discontinuity area R1 is designated by a user operation (YES in S15), the control unit 20 acquires information indicating the discontinuity area R1 designated by a user operation (S16) and ends the discontinuity visualization process (S1 in FIG. 5). In this case, the control unit 20 proceeds to YES in step S2 in FIG. 5.

[0079] On the other hand, if the area is not designated as the discontinuity area R1 by a user operation (NO in S15), the control unit 20 performs the processes from step S13 onwards again. For example, if the user 15 confirms that no discontinuity occurs in the discontinuity candidate area R10 that they have selected, they can newly select another discontinuity candidate area R10 (S13).

[0080] For example, if the candidate discontinuity area R10 is not selected by a user operation (NO in S13), the control unit 20 does not acquire information indicating the discontinuity area R1 (S16) and ends the discontinuity visualization process (S1 in FIG. 5). In this case, the control unit 20 proceeds to NO in step S2 in FIG. 5.

[0081] According to the above-described interruption visualization process (S1 in FIG. 5), the data analysis device 2 can visualize the current state of interruptions in the traffic flow 40 to the user 15 by generating various display information, for example, as illustrated in FIG. 7 and FIG. 8.

[0082] 2-2-2 Parameter Adjustment Processing The parameter adjustment processing in step S3 of Fig. 5 will be described with reference to Figs.

[0083] Fig. 9 is a flowchart illustrating the parameter adjustment process (S3 in Fig. 5) in the data analysis device 2. Fig. 10 illustrates an example of the discontinuity pattern table D10 in the data analysis device 2. Figs. 11(A) to (C) show display examples of the parameter adjustment process.

[0084] The process illustrated in Fig. 9 is performed using, for example, a break pattern table D10 stored in advance in the storage unit 21 of the data analysis device 2. The break pattern table D10 illustrated in Fig. 10 manages, for multiple patterns, a "No." that identifies each pattern, a corresponding "use case," a "designated area," and an "adjustment parameter" in association with one another. The designated area is an example of a requirement to which a change in the flow line connection parameter P1 is applied in the pattern, and indicates, for example, a location where a break is expected in the corresponding use case. The adjustment parameter indicates the type of flow line connection parameter P1 expected to be adjusted in the pattern.

[0085] For example, in the interruption pattern table D10 of FIG. 10 , pattern No. 1 corresponds to the use case of “passing behind an obstacle” (see FIGS. 4B and 8 ) and includes a designated area “location interrupted by an obstacle” and an adjustment parameter “connection direction.” Pattern No. 2 corresponds to the use case of “working behind an obstacle” (see FIG. 4C ) and includes a designated area “work location” and adjustment parameters “waiting time” and “distance range.” Pattern No. 3 corresponds to the use case of “entering and exiting a room, etc.” and includes a designated area “room entrance / exit” and an adjustment parameter “waiting time.” Pattern No. 4 indicates a custom setting in which the user 15 can set each item, for example.

[0086] In the example of Figure 9, the data analysis device 2 uses, for example, the interruption pattern table D10 to sequentially display the screens of Figures 11 (A) to (C) in dialog boxes or the like in addition to the flow analysis screen and detailed information displayed in Figures 7 and 8, thereby guiding the user 15.

[0087] Specifically, the control unit 20 of the data analysis apparatus 2 first controls the display unit 23 to display a screen presenting use case options to the user 15 for the discontinuity area R1 being adjusted, which was specified in step S16 of Fig. 6 (S21). An example of the display in step S21 is shown in Fig. 11(A).

[0088] 11A includes a message prompting the user 15 to select a use case and a plurality of use cases as options. The control unit 20 references the use cases of each pattern in the discontinuity pattern table D10, for example, and causes the display unit 23 to display the use case selection screen (S21), and the operation unit 22 accepts user operations.

[0089] The user 15 can input an operation to the operation unit 22 to select a use case suitable for the discontinuity area R1 being adjusted from among multiple use case options while checking information such as the flow line video 56. For example, in the example of FIG. 8 (and FIG. 4(B)), use case No. 1 is selected. The control unit 20 acquires information about the selected use case based on the user's operation on the operation unit 22 (S22).

[0090] Next, the control unit 20 causes the display unit 23 to display a screen for specifying requirements to which the change in the flow line connection parameter P1 is to be applied, in accordance with the acquired use case information, etc. (S23). An example of the display in step S23 is shown in Fig. 11(B) .

[0091] 11(B) illustrates an example in which use case No. 1 is selected in FIG. 11(A). The requirement specification screen in the example of FIG. 11(B) includes a message prompting the user 15 to specify requirements, a section for setting a designated area, and a section for setting other requirements. The section for setting the designated area includes identification information for the camera 11 in the present system 1, an input field 61 for the designated area in the camera coordinates of the camera 11, and an input field 62 for the designated area in the corresponding map coordinates. In this example, the designated area is specified in each input field 61, 62 by the horizontal position x, vertical position y, width w, and height h in the respective coordinate systems.

[0092] For example, in step S23, the control unit 20 sets the designated area in the discontinuity pattern table D10 corresponding to the use case acquired in step S22 on the requirement designation screen. The control unit 20 also identifies the camera 11 that captures the discontinuity area R1 designated in step S16 of Fig. 6, and displays the position of the discontinuity area R1 designated in step S16 in the camera coordinates of the identified camera 11 as the initial value of each of the input fields 61 and 62.

[0093] For example, the user 15 can check the flow line video 56 and input an operation to specify in detail the range to which the adjustment of the flow line connection parameter P1 is to be applied in the camera coordinate input field 61. For example, the user 15 can input the position and size of the specified area so as to surround the location in the camera coordinates where the X obstacle 12 is interrupted with a rectangle or the like. The control unit 20 acquires information on the specified requirement, such as the specified area, based on the user's operation on the operation unit 22 while the requirement specification screen is displayed (S24).

[0094] The above user operation may be input into the map coordinate input field 62. The control unit 20 appropriately calculates coordinate conversion between camera coordinates and map coordinates so that the input fields 61, 62 indicate the same position. The control unit 20 may also highlight the input designated area on the workshop map 50 or the flow line video 56 of the flow line analysis screen on the display unit 23. The control unit 20 may also accept, via the operation unit 22, a user operation to input a designated area on the workshop map 50 or the flow line video 56 using the pointer 4 or the like.

[0095] The control unit 20 then displays a screen for setting the flow line connection parameter P1 on the display unit 23 in accordance with the acquired information such as the use case (S25). An example of the display in step S25 is shown in FIG. 11C.

[0096] 11(C) illustrates an example of a parameter adjustment screen following that of FIG. 11(B). The parameter adjustment screen of the example of FIG. 11(C) includes a message prompting the user to set a flow line connection parameter P1, a section for setting adjustment parameters for a selected use case among the various flow line connection parameters P1, and a section for setting others. The section for setting the various parameters P1 also includes an input field 63 for inputting the setting values ​​of the adjustment results.

[0097] For example, in step S25, the control unit 20 controls the display unit 23 to display such a parameter adjustment screen by, for example, referring to the interruption pattern table D10. The control unit 20 also acquires the current setting values ​​of various parameters P1 through data communication with the flow line management server 3, for example, and displays them in the input fields 63 as initial values.

[0098] To adjust the desired flow line connection parameter P1, the user 15 can input a user operation to change the setting value from the initial value displayed in the corresponding input field 63. The control unit 20 acquires the setting value of the flow line connection parameter P1 as a result of adjustment based on the user operation on the operation unit 22 while the parameter adjustment screen is displayed (S26).

[0099] Based on the information obtained by the above various user operations, the control unit 20 stores parameter adjustment information indicating the result of adjusting the flow line connection parameter P1 (S27). An example of the parameter adjustment information in step S27 is shown in FIG.

[0100] 12 illustrates parameter adjustment information D15 corresponding to the adjustment results of FIGS. 11A to 11C. For example, the control unit 20 generates parameter adjustment information D15 by associating the requirements, such as the designated area, acquired in step S24 with the setting value of the flow line connection parameter P1 acquired in step S26, and stores the generated parameter adjustment information D15 in the storage unit 21 (S27). The control unit 20 may further include information on the use case acquired in step S22 in the parameter adjustment information D15.

[0101] The control unit 20 saves the parameter adjustment information D15 (S27), and then ends the parameter adjustment process (S3 in FIG. 5).

[0102] According to the above parameter adjustment process (S3 in FIG. 5), the data analysis device 2 presents various information prompting the user 15 to adjust the flow line connection parameter P1, and obtains parameter adjustment information D15 that is the adjustment result that reflects the intention of the user 15 (S27). In the subsequent step S4, the control unit 20 transmits the saved parameter adjustment information D15 to the flow line management server 3. This controls the generation of subsequent flow line data D1 by the flow line management server 3.

[0103] When the flow line management server 3 receives the parameter adjustment information D15, it refers to the received parameter adjustment information D15 during subsequent operation of the flow line extraction unit 33. Specifically, the flow line extraction unit 33 determines whether or not the requirements in the received parameter adjustment information D15 are met, and if the requirements are met, extracts the flow line 40 using the setting value resulting from the adjustment of the flow line connection parameter P1 in the parameter adjustment information D15. On the other hand, if the requirements are not met, the flow line extraction unit 33 does not use the setting value resulting from the adjustment, but uses the setting value before the adjustment.

[0104] In this way, the system 1 can generate flow line data D1 that eliminates discontinuities in the flow lines 40 for the discontinuity area R1 specified by the user 15. After extracting or connecting the flow lines 40, the flow line extraction unit 33 may use the flow line connection parameter P1 when reconnecting the flow lines. In this case, as in the above, whether or not to use the setting value resulting from the adjustment is switched depending on whether or not the corresponding requirement is met.

[0105] Furthermore, according to the parameter adjustment process described above, the user 15 can be guided to adjust the flow line connection parameter P1 using use cases relating to interruptions in the flow line 40, thereby facilitating parameter adjustment by the user 15.

[0106] 4B and 8, the user 15 selects in step S22 a use case in which the user passes behind the obstacle 12 (FIG. 11A). As a result, in subsequent steps S23 and S25, the user is prompted to input a location where the flow line 40 is interrupted by the obstacle 12 as a designated area and to set a connection direction of the corresponding adjustment parameter, as shown in FIGS. 11B and 11C.

[0107] 4C, by selecting a use case in which work is performed behind an obstacle 12, the user is prompted to set a distance range according to the range in which the work location is hidden, and to set a waiting time according to the work time at the work location. In this way, it is possible to facilitate the adjustment of the flow line connection parameter P1 to an appropriate value according to the use case selected by the user 15.

[0108] Furthermore, in the above-described guidance, the user 15 is not limited to adjusting the adjustment parameters corresponding to the selected use case, but can also adjust other flow line connection parameters P1, such as the waiting time when passing behind an obstacle 12, as shown in FIG. 11(C) (S25, S26).

[0109] Furthermore, the requirements set in steps S23 and S24 are not limited to the designated area, and other requirements may be set. For example, the data analysis device 2 may set time information for applying the change in the flow line connection parameter P1, such that the adjustment result is applied only during a specific time period. Alternatively, the requirements may include personal identification or various attributes of the worker W. The control unit 20 accepts a user operation specifying the various requirements described above, for example, on the requirement specification screen of FIG. 11(B) (S24), and includes information on the specified requirements in the parameter adjustment information D15 (S27). By referring to the requirements in the parameter adjustment information D15, the flow line management server 3 can selectively apply the flow line connection parameter P1 when various requirements are met.

[0110] 3. Summary As described above, the data analysis device 2 in this embodiment controls the generation of a traffic line 40 as an example of a data sequence showing the time-series detection results of a worker W, an example of an object, at a work site such as the workplace 10. The data analysis device 2 includes a display unit 23, an operation unit 22, an example of an input unit, and a control unit 20. The display unit 23 displays information. The operation unit 22 inputs user operations. The control unit 20 controls the traffic line management server 3, an example of a data management unit that manages the detection results of the object and generates a data sequence. The control unit 20 causes the display unit 23 to display various display information including a break area R1 or a potential break area R10, which are examples of ranges in which the ends of multiple traffic lines 40 in the workplace 10 are adjacent to each other at intervals corresponding to breaks in the traffic lines 40 (see S1, FIG. 7, etc.). In this range, the ends of the traffic lines 40 are adjacent to each other at intervals that are expected to be determined to be breaks in the traffic lines 40. The control unit 20 accepts a user operation at the operation unit 22 to adjust a flow line connection parameter P1, which is an example of a parameter that indicates a condition under which multiple flow lines 40 connect to each other in the discontinuity area R1 (S3). The control unit 20 controls the flow line management server 3 to apply the adjusted flow line connection parameter P1 in the discontinuity area R1 in accordance with the user operation at the operation unit 22 (S4).

[0111] According to the data analysis device 2 described above, by visualizing the interruption areas R1 etc. to the user 15 and adjusting the flow line connection parameter P1 through user operation, it is possible to easily suppress interruptions in the flow line 40 detected over time of the worker W in the workplace 10.

[0112] In the data analysis device 2 of this embodiment, the control unit 20 accepts, via the operation unit 22, a user operation specifying requirements for applying the adjusted flow line connection parameter P1 in the discontinuity area R1 (S24). The control unit 20 controls the flow line management server 3 (S4), for example, using parameter adjustment information D15, so that the adjusted flow line connection parameter P1 is not applied if the specified requirements are not met, and the adjusted flow line connection parameter P1 is applied if the specified requirements are met. This allows the adjustment of the flow line connection parameter P1 to be applied within a range intended by the user 15, thereby accurately suppressing discontinuities in the flow lines 40.

[0113] In the data analysis device 2 of this embodiment, the control unit 20 detects, based on the flow line 40 generated by the flow line management server 3, an area where the ends of the flow line 40 are adjacent as a potential break area R10, which is an example of a potential break in the flow line 40, and notifies the user 15 of the detected potential break area R10 using a notification marker 45 or the like in the display information (S12). This allows the user 15 to be notified of the potential break area R10 detected by the data analysis device 2, making it easier to prevent breaks in the flow line 40.

[0114] In the data analysis device 2 of this embodiment, the control unit 20 receives a user operation to specify a potential break area R10 on the display information such as a flow line analysis screen via the operation unit 22 (S13). The control unit 20 then displays detailed information on the flow line 40 whose end is located in the specified potential break area R10 on the display unit 23 (S14, see FIG. 8). This makes it easier for the user 15 to analyze the state of the break in detail.

[0115] In this embodiment, the data analysis device 2 further includes a memory unit 31 that stores a break pattern table D10, which is an example of pattern information including multiple patterns in which a worker W is not detected in the workplace 10. The control unit 20 accepts a user operation at the operation unit 22 to select one pattern from the multiple patterns indicated in the break pattern table D10 (S22), and displays information on the display unit 23 that prompts the user to adjust the flow line connection parameter P1 in accordance with the selected pattern (S23, S25). This guides the user 15 to adjust the parameter, making it easier to suppress breaks in the flow line 40.

[0116] In this embodiment, the flow line management server 3 manages, in the flow line extraction unit 33, the detection results of the image recognition model M1 that detects the worker W based on captured images of the workplace 10, and sequentially connects the detection results of the image recognition model M1 based on the flow line connection parameter P1 to generate the flow line 40. By adjusting the applied flow line connection parameter P1 in this manner, the data analysis device 2 can control the generation of the flow line 40 and prevent interruptions in the flow line 40.

[0117] In this embodiment, the data analysis device 2 further includes a network I / F 25, which is an example of a communication unit that performs data communication with the trajectory management server 3. The control unit 20 receives trajectory data D1 of the trajectory 40 from the trajectory management server 3 via the communication unit (S11), and transmits parameter adjustment information D15 of the adjusted trajectory connection parameter P1 to the trajectory management server 3 via the communication unit (S4). Through such data communication, the data analysis device 2 can control an external data management unit to prevent interruptions in the trajectory 40.

[0118] In the data analysis device 2 of this embodiment, the data string is a flow line 40 that indicates the detection result of the movement of a worker W on a workplace map 50 that shows the workplace 10. The data analysis device 2 of this embodiment can easily prevent such interruptions in the data string.

[0119] In this embodiment, a data analysis method is provided for controlling the generation of a data string indicating the results of time-series detection of an object at a work site such as a workplace 10. The data string is generated by a path management server 3 that manages the detection results of the object. This method includes step S1 of causing the display unit 23 to display display information including a range in the workplace 10 where ends of a plurality of data strings are adjacent to each other, step S3 of accepting, at the operation unit 22, a user operation to adjust a parameter indicating a condition under which the plurality of data strings are connected to each other in the adjacent range, and step S4 of controlling the path management server 3 to apply the adjusted parameter to the adjacent range in accordance with the user operation at the operation unit 22.

[0120] In this embodiment, a program is provided for causing the computer control unit 20 to execute the above-described data analysis method. The data analysis method of this embodiment can easily prevent interruptions in the data sequence obtained by detecting objects in a time series at a site.

[0121] (Other Embodiments) As described above, embodiment 1 has been described as an example of the technology disclosed in the present application. However, the technology in the present disclosure is not limited to this, and can be applied to embodiments in which modifications, substitutions, additions, omissions, etc. are made as appropriate. Furthermore, it is also possible to combine the components described in each of the above embodiments to create a new embodiment. Therefore, other embodiments will be described below as examples.

[0122] In the first embodiment described above, the flow line 40 of the movement of the worker W has been described as an example of a data sequence in the data analysis device 2. The data analysis device 2 of this embodiment may use various data sequences, not limited to the flow line 40. Such a modified example will be described with reference to FIG. 13 .

[0123] Fig. 13 is a diagram illustrating a modified example of the data analysis device 2. The data analysis device 2 of this modified example is applied to a system that analyzes, for example, the efficiency with which a worker W performs work. Fig. 13(A) illustrates an image 53 captured by the camera 11 in this system. Fig. 13(B) illustrates a timeline 43 of an example of a data string in this system.

[0124] In the system of the example of FIG. 13 , the camera 11 is installed so that, for example, the location where an individual worker W performs a task is captured in the captured image 53. The image recognition model M1 of this modified example detects a state in which the worker W performs a predetermined task in the captured image 53. The predetermined task can be set to various tasks, such as holding or wrapping an object or writing a letter. Instead of the flow line extraction unit 33 or the flow line management server 3 of the first embodiment, the system includes a data management unit that generates a timeline 43 based on the detection results of the image recognition model M1. The timeline 43 is an example of a data sequence configured by chronologically arranging detection results indicating whether or not the worker W performed a predetermined task.

[0125] In the example of Fig. 13(A), when the worker W performs a predetermined task in the image area R2 near an obstacle 12 located between the camera 11 and the worker W, the image recognition model M1 may not be able to detect this state. Such a detection failure can be expected to cause a break in the timeline 43, as shown in Fig. 13(B).

[0126] In this case, since the detection results corresponding to each end of the interrupted time line 43 are obtained in image area R2 near the obstacle 12, it is thought that the above interruption can be resolved by having the data management unit perform interpolation to connect these ends of the interrupted time line 43. For example, with regard to the detection results in image area R2, it is thought that the interruption of the time line 43 can be resolved by adjusting parameters such as extending the waiting time for connecting the time line 43 even if it is interrupted, or widening the allowable range of the connection direction in image area R2.

[0127] Therefore, the data analysis device 2 of this modified example visualizes such on-site conditions to the user 15 in the same manner as in the first embodiment, and adjusts parameters to reflect the analysis of the user 15. For example, the control unit 20 of this modified example performs the same operation as in the first embodiment ( FIG. 5 ), and detects a break in the timeline 43 in a break visualization process (S1), and visualizes the break in the timeline 43 to the user 15 by displaying a notification marker 45, etc.

[0128] 6, the control unit 20 of this modification causes the display unit 23 to display captured images 53 for a corresponding time period in response to a user operation to designate a notification marker 45 for notifying the user of an interruption in the timeline 43. For example, in the parameter adjustment process (S3 of FIG. 5), the control unit 20 accepts, via the operation unit 22, a user operation to designate the image area R2 as a designated area to which parameter adjustment is to be applied, and a user operation to adjust the various parameters. As a result, the data analysis device 2 of this modification can reflect the intention of the user 15 in suppressing interruptions in a data string such as the timeline 43, as in the first embodiment.

[0129] The data analysis device 2 of this modified example may be applied to a system that analyzes both the timeline 43 and the flow line 40. For example, the timeline 43 regarding the work of a worker W and the flow line 40 regarding the movement of the worker W may be analyzed.

[0130] As described above, in the data analysis device 2 of this embodiment, the data sequence may include at least one of the flow line 40 of the movement of the object at the site and the timeline 43 showing the detection results of the object in chronological order. The data analysis device 2 of this embodiment can easily prevent interruptions in various data sequences.

[0131] Furthermore, in each of the above embodiments, an example has been described in which the data management unit is an external component of the data analysis device 2, such as the trajectory management server 3. In this embodiment, the data management unit may be an internal component of the data analysis device 2. For example, the data analysis device 2 may include a trajectory extraction unit 33. In this case, in step S4 of FIG. 5 , the data analysis device 2 sets the parameter adjustment information D15 in the internal trajectory extraction unit 33, thereby controlling the generation of trajectory data D1 so as to reflect the adjustment results.

[0132] In the above-described embodiments, parameters for connecting data strings, such as the flow line connection parameter P1, have been exemplified. In the data analysis device 2 of this embodiment, the parameters for connecting data strings are not limited to the above, and various other parameters can be employed. For example, in the present system 1, when determining the destination of a flow line using various scores, as in the method disclosed in Patent Document 1, threshold values ​​for such scores may be employed as the above-described parameters. As in the above-described embodiments, such parameters can be appropriately adjusted to reflect the analysis of the user 15, making it easier to prevent interruptions in the flow lines, etc.

[0133] In each of the above embodiments, the worker W has been described as an example of an object in the data analysis device 2, but the object is not particularly limited to this. In the data analysis device 2 of this embodiment, the object may be a person other than the worker W, or may be various moving objects such as living creatures, various vehicles, or robots, without being limited to people. Furthermore, the object is not limited to moving objects, and may be various objects or object states.

[0134] In each of the above embodiments, the work site 10 is illustrated as an example of a site to which the data analysis device 2 is applied. The data analysis device 2 of this embodiment is not limited to the work site 10 and can be applied to various sites, and can be used to analyze data sequences regarding detection results of various objects at the site.

[0135] As described above, the embodiments have been described as examples of the technology in the present disclosure, and for that purpose, the accompanying drawings and detailed description have been provided.

[0136] Therefore, the components shown in the accompanying drawings and detailed description may include not only essential components for solving the problem, but also components that are not essential for solving the problem in order to illustrate the above technology. Therefore, the fact that these non-essential components are shown in the accompanying drawings or detailed description should not be interpreted as immediately indicating that these non-essential components are essential.

[0137] Furthermore, since the above-described embodiments are intended to illustrate the technology of the present disclosure, various modifications, substitutions, additions, omissions, etc. may be made within the scope of the claims or their equivalents.

[0138] The present disclosure is applicable to applications in which data sequences indicating the results of detecting various objects over time at various locations are analyzed, such as analyzing the movement paths of moving objects.

Claims

1. A data analysis device that controls generation of a data sequence indicating a result of detecting an object at a site in time series, comprising: A display unit for displaying information; an input unit for inputting a user's operation; a control unit that controls a data management unit that manages the detection result of the object and generates the data string; The control unit is displaying on the display unit display information including a range in which ends of a plurality of data strings are adjacent to each other at the site; receiving, via the input unit, a user operation for adjusting a parameter indicating a condition under which the plurality of data strings are connected to each other in the adjacent range; Controlling the data management unit to apply the adjusted parameters in the adjacent range according to the user operation on the input unit. Data analysis equipment.

2. The control unit is receiving, via the input unit, a user operation that specifies a condition under which the adjusted parameter is to be applied in the adjacent range; The data management unit is controlled so that the adjusted parameters are not applied when the specified requirements are not met, and the adjusted parameters are applied when the specified requirements are met. The data analysis apparatus according to claim 1 .

3. The control unit detects the adjacent range as a candidate for a break in the data string based on the data string generated by the data management unit, and notifies the detected range in the display information. The data analysis device according to claim 1 or 2.

4. The control unit receives a user operation to specify the adjacent range in the display information at the input unit, Displaying detailed information on a data string whose end is located within the specified range on the display unit The data analysis device according to claim 1 or 2.

5. A storage unit for storing pattern information including a plurality of patterns in which the object is not detected at the site, The control unit is receiving, by the input unit, a user operation for selecting one pattern from a plurality of patterns indicated by the pattern information; displaying information on the display unit to prompt the user to adjust the parameters according to the selected pattern; The data analysis device according to claim 1 or 2.

6. The data management unit Manage the detection results of an image recognition model that detects the object based on the captured image of the site; The detection results of the image recognition model are sequentially connected based on the parameters to generate the data string. The data analysis device according to claim 1 or 2.

7. A communication unit that performs data communication with the data management unit, The control unit is receiving the data string from the data management unit via the communication unit; The adjusted parameters are transmitted to the data management unit via the communication unit. The data analysis device according to claim 1 or 2.

8. The data string includes at least one of a flow line indicating a detection result of the movement of the object on a map indicating the site, and a timeline indicating the detection result of the object in chronological order. The data analysis device according to claim 1 or 2.

9. 1. A data analysis method for controlling generation of a data sequence indicating a time-series detection result of an object at a site, comprising: the data string is generated by a data management unit that manages the detection results of the object, displaying, on a display unit, display information including a range in which ends of a plurality of data strings are adjacent to each other at the site; receiving, via an input unit, a user operation for adjusting a parameter indicating a condition under which the plurality of data strings are connected to each other in the adjacent range; controlling the data management unit to apply the adjusted parameters in the adjacent range according to the user operation on the input unit; Data analysis methods including:

10. A program for causing a control unit of a computer to execute the data analysis method according to claim 9.