Information processing program, information processing method, and information processing device

Abstract

This information processing device acquires a video including a person to be detected. The information processing device acquires object information that is outputted by a predetermined video analysis technique, the attribute information and behavior information of a person being associated with the person included in the video. The information processing device generates work assistance information for the person on the basis of the object information. The information processing device verifies the influence on the person when the person has changed an action on the basis of the generated work assistance information. The information processing device outputs the work assistance information when the verification result satisfies a prescribed condition.

Description

Information Processing Program, Information Processing Method, and Information Processing Apparatus 【0001】 The present invention relates to an information processing program and the like. 【0002】 At work sites such as factories and freight consolidation areas, workers perform tasks such as loading, unloading, and transporting goods. Workers may unconsciously perform tasks in a posture that places a burden on their waist. When a burden is placed on the waist, acute or chronic low back pain may develop, and improvement is sought. In the following description, the actions of workers who develop low back pain or the like are referred to as "dangerous actions." 【0003】 For example, a supervisor visually checks the video of a camera installed at the work site to confirm whether a worker is performing a dangerous action. When a dangerous action is confirmed, the supervisor warns the corresponding worker to provide work support. 【0004】 International Publication No. 2023 / 199614 【0005】 However, the above-described conventional technology has a problem that work support cannot be efficiently performed. 【0006】 For example, when a supervisor visually checks the video of a camera to provide work support for a worker, the burden on the supervisor is large and it is not efficient. Also, it is difficult to identify dangerous actions that are found by monitoring a specific worker for a long period of time by visual inspection of the supervisor. 【0007】 In one aspect, an object of the present invention is to provide an information processing program, an information processing method, and an information processing apparatus that can efficiently execute work support. 【0008】In the first plan, the computer is instructed to perform the following processes: The computer acquires video footage containing the person to be detected. The computer acquires object information, which is generated by a predetermined video analysis technique, and associates the person's attribute information and behavior information with the person contained in the video. Based on the object information, the computer generates work support information for the person. The computer verifies the impact on the person if they change their behavior based on the generated work support information. If the verification results meet predetermined conditions, the computer outputs the work support information. 【0009】 It allows for efficient work support. 【0010】 Figure 1 is a diagram showing the system according to this embodiment. Figure 2 is a diagram illustrating the processing of the information processing device according to this embodiment. Figure 3 is a diagram showing an example of skeletal information. Figure 4 is a diagram showing an example of joint names. Figure 5 is a functional block diagram showing the configuration of the information processing device according to this embodiment. Figure 6 is a diagram showing an example of the data structure of an action scene graph. Figure 7 is a diagram illustrating the processing of the video analysis unit. Figure 8 is a diagram illustrating the Visual Prompt creation process. Figure 9 is a diagram illustrating the format conversion process. Figure 10 is a diagram illustrating the judgment process. Figure 11 is a flowchart showing the processing procedure of the information processing device according to this embodiment. Figure 12 is a diagram showing an example of the hardware configuration of a computer that realizes the same functions as the information processing device of the embodiment. 【0011】 The following describes in detail, with reference to the drawings, embodiments of the information processing program, information processing method, and information processing apparatus disclosed in this application. However, this invention is not limited to these embodiments. 【0012】 Figure 1 shows a system according to this embodiment. As shown in Figure 1, this system 5 includes a camera 10, a display device 15, and an information processing device 100. The camera 10, the display device 15, and the information processing device 100 are interconnected via a network 3. 【0013】For the sake of explanation, only the camera 10 and the display device 15 are shown in Figure 1, but the system 5 may have other cameras and other display devices. 【0014】 Camera 10 captures video footage of the work site and transmits the captured video data to the information processing device 100. The work site is a factory, a cargo handling facility, etc. In the following explanation, the video data transmitted by camera 10 to the information processing device 100 will be referred to as "video information." Also, workers performing tasks such as loading, unloading, and carrying cargo at the work site will be referred to as "people." 【0015】 The video information includes multiple frames in chronological order. Each frame is assigned a frame number in ascending chronological order. A single frame is a still image captured by camera 10 at a specific point in time. Each frame may also be assigned time data. 【0016】 The display device 15 is installed in a designated location at the work site. The display device 15 is a digital signage or the like. For example, the display device 15 displays work support information generated by the information processing device 100. The work support information is information to support workers performing work at the work site, and includes things like the correct way to hold loads and use one's body, the preparation of an appropriate work environment, and the use of equipment and auxiliary tools. 【0017】 The information processing device 100 acquires video information from the camera 10, generates work support information by executing the following processes, and outputs the generated work support information to the display device 15 for display. 【0018】 Figure 2 is a diagram illustrating the processing of the information processing device according to this embodiment. For example, the information processing device 100 includes a video analysis unit 151, an LLM (Large Language Models) 152, and a proposal unit 153. 【0019】 The video analysis unit 151 acquires video information 30 from the camera 10 and analyzes it. For example, using predetermined video analysis techniques, the video analysis unit 151 sets a person ID, tracks the person, and identifies the person's attribute information and behavioral information. 【0020】Attribute information includes the person's gender, age, and build. Behavioral information includes the person's position, posture, and relative position to the object. The person's posture may also be represented by skeletal information, as shown in Figure 3. 【0021】 Figure 3 shows an example of skeletal information. For example, as shown in Figure 3, the skeletal information of a person is represented by the positions (3D coordinates) of 21 joints ar0 to ar20. 【0022】 The relationship between each joint a0 to a20 shown in Figure 3 and its name is shown in Figure 4. Figure 4 is a diagram showing an example of a joint name. For example, the name of joint a0 is "SPINE_BASE". The names of joints a1 to a20 are as shown in Figure 4, and their explanation is omitted. 【0023】 Returning to the explanation of Figure 2, the video analysis unit 151 sets the attribute information and behavioral information identified by a predetermined video analysis technique into object information 40 and outputs it to the LLM 152. 【0024】 The LLM 152 generates work support information based on the object information 40. Furthermore, the LLM 152 verifies the impact on a person when they change their behavior based on the generated work support information. If the verification results meet predetermined conditions, the LLM 152 outputs the work support information 50 to the proposal unit 153. 【0025】 For example, LLM152 generates and verifies work support information "Correct way to hold luggage and use your body" based on object information 40. If LLM152 obtains verification results showing that the lower back pain of a person who has changed their work behavior based on the work support information has improved, it outputs the work support information "Correct way to hold luggage and use it" to the suggestion unit 153. 【0026】 For example, the work support information "Correct way to lift and use your body when carrying a load" includes the following information: (1) When lifting a load, keep your back straight. (2) Bend your knees and lower your hips, and lift using the strength of your legs. (3) Keep the load close to your body. (4) Avoid twisting motions and change direction by rotating your entire body. (5) Spread your feet about shoulder-width apart to stabilize your center of gravity. 【0027】The proposal unit 153 outputs and displays the verified work support information 50 obtained from the LLM 152 on the display device 15. The person performs the work by referring to the work support information 50 displayed on the display device 15. 【0028】 In this way, the information processing device 100 generates object information 40 by analyzing the video information captured by the camera 10 using a predetermined video analysis technique. Based on the object information 40, the information processing device 100 generates work support information and verifies the impact on a person when they change their behavior based on the generated work support information. If the results of the verification meet predetermined conditions, the information processing device 100 outputs and displays the work support information on the display device 15. This enables efficient work support. 【0029】 Next, an example of the configuration of the information processing device 100 according to this embodiment will be described. Figure 5 is a functional block diagram showing the configuration of the information processing device according to this embodiment. As shown in Figure 5, this information processing device 100 has a communication unit 110, an input unit 120, a display unit 130, a storage unit 140, and a control unit 150. 【0030】 The communication unit 110 performs data communication with the camera 10 via the network 3. For example, the communication unit 110 receives video information from the camera 10. 【0031】 The communication unit 110 performs data communication with the display device 15 via the network 3. For example, the communication unit 110 transmits work support information generated by the control unit 150 to the display device 15. 【0032】 The input unit 120 is an input device that inputs various types of information to the control unit 150 of the information processing device 100. 【0033】 The display unit 130 is a display device that displays information output from the control unit 150. 【0034】 The memory unit 140 stores layout information 141 and an action scene graph 142. The memory unit 140 is a memory or the like. 【0035】Layout information 141 is information about the space of the work site, and includes information such as the passages used by people (starting point, intermediate point, destination) and the position where goods are placed. By using layout information 141, the positional relationship between goods and people can be determined. 【0036】 The behavior scene graph 142 is graph information generated by the video analysis unit 151, which will be described later. Figure 6 shows an example of the data structure of the behavior scene graph. The behavior scene graph 142 has time nodes n2-1, n2-2, n2-3, n2-4, n2-5, and n2-6. The behavior scene graph 142 has event nodes n3-1, n3-2, n3-3, n3-4, n3-5, and n3-6. The behavior scene graph 142 has detection target nodes n4-1, n4-2, n4-3, n4-4, and n4-5. 【0037】 Time nodes n2-1 to n2-6 are nodes that indicate time, and correspond to times T1, T2, T3, T4, T5, and T6, respectively. For example, times T1, T2, T3, T4, T5, and T6 are associated with the time (frame number) of each frame contained in the video information. 【0038】 Event nodes n3-1 to n3-6 are nodes corresponding to attributes and relationships. Detection target nodes n4-1 to n4-5 are nodes corresponding to detection targets. By using the behavior scene graph 142, it becomes possible to grasp various information related to the video information. For example, event node n3-1, which is connected to time nodes n2-1 and n2-6, is connected to detection target node n4-2. This indicates that the detection target of the corresponding attribute exists in the video information during times T1 to T6. 【0039】 Returning to the explanation of Figure 5, the control unit 150 includes an image analysis unit 151, an LLM 152, and a proposal unit 153. The control unit 150 is a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), etc. 【0040】The video analysis unit 151 acquires and analyzes video information 30 from the camera 10. For example, the video analysis unit 151 uses a predetermined video analysis technique to perform setting of a person ID and tracking of a person for the person in the video information 30, and specifies the attribute information and action information of the person. The video analysis unit 151 sets the attribute information and action information specified by the predetermined video analysis technique in the object information 40 and outputs it to the LLM 152. 【0041】 Here, the video analysis unit 151 will be described more specifically. For example, the video analysis unit 151 executes a process of generating an action scene graph 142 and a process of analyzing the generated action scene graph 142. 【0042】 First, the process when the video analysis unit 151 generates an action scene graph 142 will be described. FIG. 7 is a diagram for supplementarily explaining the process of the video analysis unit. The video analysis unit 151 acquires video information 30 from the camera 10 and divides the video information 30 into frames. 【0043】 The video analysis unit 151 analyzes a plurality of frames based on the pre-set detection patterns 35a, 35b, 35c, and detects the object to be detected from each frame. The detection patterns 35a, 35b, 35c are information defining the conditions of the detection target. 【0044】 For example, in the detection pattern 35a, a relationship "Relationship" is defined in which the person corresponding to "Subject" is lifting (or lowering or carrying) the luggage corresponding to "Object" in a strained posture. For example, the video analysis unit 151 may generate the detection pattern 35a based on the layout information 141. 【0045】 In the detection pattern 35b, "Subject" and "Attribute" are defined. For example, in the detection pattern 35b, the attribute information of the person corresponding to "Subject" is set. The attribute information is the gender, age, build, etc. of the person. 【0046】In the detection pattern 35c, a more detailed definition can be made by using "Expression". For example, in the detection pattern 35c, as "Expression", it is defined that a person corresponding to "Subject" is lifting (or lowering, carrying) a load corresponding to "Object" with an unreasonable posture, which means that a load greater than or equal to a reference value is applied to a predetermined part (for example, the waist) of the person lifting (or lowering, carrying) the load. Also, in the detection pattern 35c, as "Expression", it is defined that a person corresponding to "Subject" is lifting (or lowering, carrying) a load corresponding to "Object" with an unreasonable posture, which may also mean that a certain joint angle of the person's skeletal information is not within a predetermined range, or the distance between the position of the person's waist and the load is greater than or equal to a threshold value. 【0047】 Note that in the detection patterns 35a to 35c, "labels" for identifying the detection targets are also defined. In the following description, the detection patterns 35a to 35c are collectively referred to as the detection pattern 35. The video analysis unit 151 may execute subsequent processing using the detection pattern 35 prepared in advance. 【0048】 The video analysis unit 151 outputs the coordinates of the bounding box for each label from each frame using the Open-Vocabulary object detection technology. The video analysis unit 151 may use existing technologies such as "Cheng, Tianheng, et al. 'Yolo-world: Real-time open-vocabulary object detection.' Proceedings of the IEEE / CVF Conference on Computer Vision and Pattern Recognition. 2024." as the Open-Vocabulary object detection technology. 【0049】The video analysis unit 151 generates detection results from each frame based on the detection pattern 35. For example, the detection results include the coordinates of the bounding box corresponding to the label "person" and the coordinates of the bounding box corresponding to the label "luggage". 【0050】 The video analysis unit 151 tracks the coordinates of the bounding box of each label based on the detection results and generates tracking information for each label. Each piece of tracking information is assigned a tracking ID. For example, when performing tracking, the video analysis unit 151 may use existing technologies such as "Bewley, Alex, et al. "Simple online and realtime tracking." 2016 IEEE international conference on image processing (ICIP). IEEE, 2016." The video analysis unit 151 generates the tracking information for each label as tracking result information 36. 【0051】 The video analysis unit 151 generates clips by grouping multiple frames into predetermined frame groups. The video analysis unit 151 generates clip information 37 containing multiple clips by repeatedly performing this process. 【0052】 The video analysis unit 151 determines, based on the detection pattern 35, tracking result information 36, and clip information 37, whether each clip satisfies the relationships and attributes specified in the detection pattern 35. 【0053】 When the video analysis unit 151 performs such a determination, it executes a Visual Prompt creation process, a format conversion process, and a determination process for all Subjects and Objects shown in the detection pattern 35, respectively. 【0054】The Visual Prompt creation process executed by the video analysis unit 151 will now be explained. Figure 8 is a diagram illustrating the Visual Prompt creation process. In Figure 8, for the sake of explanation, the Subject is set to a person with tracking ID "P2" and the Object to a forklift with tracking ID "F1". The video analysis unit 151 also uses the tracking information of the person with tracking ID "P2" and the tracking information of the forklift with tracking ID "F1" included in the tracking result information 36. 【0055】 The video analysis unit 151 draws a bounding box in red for the person with tracking ID "P2" in each frame of clip C1 included in clip information 37, based on the tracking information of the person with tracking ID "P2". The video analysis unit 151 also draws a bounding box in green for the forklift with tracking ID "F1" in each frame of clip C1 included in clip information 37, based on the tracking information of the forklift with tracking ID "F1". For example, the result of drawing the bounding box on clip C1 is denoted as prompt V1. 【0056】 The video analysis unit 151 generates a Visual Prompt 37v by performing the same processing on clip C2 and other clips included in the clip information 37 as it did on clip C1. For example, the result of drawing a bounding box on clip C2 is denoted as prompt V2. 【0057】 In Figure 8, for the sake of explanation, the Subject is set to a person with tracking ID "P2" and the Object to a forklift with tracking ID "F1". However, even if the Subject is set to a person with tracking ID "P2" and the Object to a package with "a certain tracking ID", the Visual Prompt 37v can be generated in the same way. 【0058】Next, the format conversion process performed by the video analysis unit 151 will be described. Figure 9 is a diagram illustrating the format conversion process. The video analysis unit 151 generates a detection prompt 38 by performing a format conversion process on the detection pattern 35. The detection prompt 38 is a prompt that causes the VLM to respond whether the Subject and Object of the detection pattern 35 satisfy the relationships and attributes defined in the detection pattern 35. For example, the detection prompt 38 is a prompt that causes the VLM to respond whether a person surrounded by a red bounding box is lifting (or unloading, carrying) luggage surrounded by a green bounding box in an awkward position. 【0059】 Next, the determination process performed by the video analysis unit 151 will be described. Figure 10 is a diagram illustrating the determination process. The video analysis unit 151 obtains the determination result 46 by inputting the Visual Prompt 37v and the detection prompt 38 to the VLM 45. 【0060】 For example, the video analysis unit 151 inputs the prompt V1 of the Visual Prompt 37v and the detection prompt 38 to the VLM 45, and based on the determination result 46, it can determine that in a certain clip, an event has occurred in which a person with a certain tracking ID is lifting (or unloading, carrying) a package with a certain tracking ID in an awkward position. 【0061】 The video analysis unit 151 performs the Visual Prompt creation process, format conversion process, and judgment process described above for all Subjects and Objects shown in the detection pattern 35. This allows the video analysis unit 151 to identify the time period in which video information 30 occurs that satisfies the "Relationship" defined in the detection pattern 35 for each pair of Subject (e.g., a person) and Object (e.g., luggage). Furthermore, the video analysis unit 151 can identify the time period in which video information 30 occurs that satisfies the "Attribute (attribute information)" defined in the detection pattern 35 for each Subject (e.g., a person). 【0062】Next, the video analysis unit 151 generates an action scene graph 142 based on the judgment result 46 and registers it in the storage unit 140. An example of the processing of the video analysis unit 151 will be explained using Figure 6. If the judgment result 46 includes the fact that in a certain clip (frame numbers fr1 to fr10), a person with tracking ID "P2" is lifting (or unloading, carrying) luggage with tracking ID "O1" in an awkward position, the video analysis unit 151 performs the following processing. For convenience, the time corresponding to frame number fr1 is denoted as time T2, and the time corresponding to frame number fr10 is denoted as time T3. 【0063】 In this case, the video analysis unit 151 generates a detection target node n4-1 corresponding to tracking ID "P2", a detection target node n4-5 corresponding to tracking ID "O1", and an event node n3-5 corresponding to the relationship "lifting (or unloading, carrying) cargo in an awkward position". The video analysis unit 151 connects the detection target node n4-1 to the event node n3-5, and connects the detection target node n4-5 to the event node n3-5. The video analysis unit 151 also connects the event node n3-5 to time nodes n2-2 and n2-3. 【0064】 As a result, the video analysis unit 151 can set in the action scene graph 142 that, at times T2 to T3, the person with tracking ID "P2" was lifting (or unloading, carrying) the luggage with tracking ID "O1" in an awkward position. 【0065】 Furthermore, if the video analysis unit 151 finds in the determination result 46 that an event satisfying the "Attribute (attribute information)" has occurred in a certain clip, it performs the following processing. For convenience, the time corresponding to the starting frame number of a certain clip is defined as time T1, and the time corresponding to the ending frame number is defined as time T6. 【0066】In this case, the video analysis unit 151 generates a detection target node n4-3 corresponding to the tracking ID "P3" and an event node n3-2 corresponding to attribute information "a certain gender, a certain age, a certain physique, etc.". The video analysis unit 151 connects the detection target node n4-3 and the event node n3-2. The video analysis unit 151 also connects the event node n3-2 to time nodes n2-1 and n2-6. 【0067】 As a result, the video analysis unit 151 can set in the behavior scene graph 142 that, during times T1 to T6, an event occurred in which the person with tracking ID "P3" satisfies "Attribute (certain gender, age, physique, etc.)". 【0068】 The above describes an example of the process by which the video analysis unit 151 generates a behavioral scene graph 142 based on video information 30 and detection patterns 35. The video analysis unit 151 may also acquire video analysis results from other modules or external data and add various types of information to the behavioral scene graph 142. For example, the video analysis unit 151 may associate the skeletal information of a person obtained as a result of video analysis with the detection target node of the person. 【0069】 Furthermore, the video analysis unit 151 may associate the information regarding the location of a person obtained as a result of the video analysis with the node that is the target of person detection. 【0070】 The above describes an example of the process by which the video analysis unit 151 generates the action scene graph 142. 【0071】 Next, an example of the process by which the video analysis unit 151 obtains object information 40 by analyzing the generated action scene graph 142 will be described. For example, the video analysis unit 151 obtains object information 40 by performing a first analysis process or a second analysis process. 【0072】The first analysis process performed by the video analysis unit 151 will now be described. The video analysis unit 151 scans the action scene graph 142 and identifies the detection target node of a person connected to a specific event node. For example, the specific event node is an event node corresponding to the relationship "lifting (or unloading, carrying) a load in an awkward position". The video analysis unit 151 identifies the person whose detection target node connected to the specific event node is a person whose load on a predetermined body part exceeds a predetermined threshold. 【0073】 The video analysis unit 151 acquires object information 40, which includes attribute information connected to the detection target node identified by a specific event node, and the relationship with the specific event node. The video analysis unit 151 outputs the object information 40 to the LLM 152. 【0074】 The second analysis process performed by the video analysis unit 151 will now be described. The video analysis unit 151 identifies the detection target node of a person connected to a specific event node that has been occurring continuously for a predetermined time or longer. The specific event node is an event node corresponding to the relationship "lifting (or unloading, carrying) a load in an awkward posture". The time period during which the specific event node occurs can be identified by referring to the time node connected to the event node. The video analysis unit 151 identifies the person of the detection target node connected to the specific event node as a person whose cumulative load on a predetermined body part has exceeded a predetermined threshold over a predetermined period. 【0075】 The video analysis unit 151 acquires object information 40, which includes attribute information connected to the detection target node identified as a specific event node, the relationship with the specific event node, and the period during which the specific event node occurred. The video analysis unit 151 outputs the object information 40 to the LLM 152. 【0076】 As described above, the video analysis unit 151 sets attribute information and behavioral information identified by predetermined video analysis techniques for the video information 30 into object information 40 and outputs it to the LLM 152. The video analysis unit 151 may also set information regarding the location of a person into object information 40. 【0077】The LLM152 performs the processes of generating work support information and verifying the generated work support information. 【0078】 First, an example of the process by which LLM152 generates work support information will be described. LLM152 sets object information 40 in a pre-prepared first prompt and generates work support information based on this first prompt. For example, the first prompt may contain the following text: "A person with the characteristics of object information 40 has the problems shown in the relationships of object information 40; therefore, please provide work support information that will improve these problems." If object information 40 includes information indicating the person's location, the first prompt will generate work support information that further takes into account the information indicating the person's location. 【0079】 Next, an example of the process by which LLM152 verifies work support information will be described. LLM152 sets the object information 40 and the work support information generated in the above process in a pre-prepared second prompt and performs verification. For example, the second prompt may contain the following text: "A person with the characteristics of object information 40 has the problems shown in the relationship of object information 40, but please verify with a number from 1 to 10 how effective the attached work support information is when presented. The larger the number, the more effective it is." 【0080】 The LLM152 determines that the work support information is valid if the numerical value of the verification result based on the second prompt is 5 or greater, and outputs the work support information to the suggestion unit 153. 【0081】 On the other hand, if the numerical value of the verification result based on the second prompt is less than 5, the LLM 152 determines that the work support information is not valid and suppresses outputting the work support information to the proposal unit 153. 【0082】Furthermore, the LLM 152 may communicate with an LLM server connected via network 3 to implement its functions. Alternatively, the LLM 152 may act as an agent utilizing the LLM 152. For example, the agent generates a first and second prompt to be input to the LLM 152 and uses the information output from the LLM 152 to exchange data with the video analysis unit 151 and the proposal unit 153. 【0083】 The proposal unit 153 outputs and displays the verified work support information 50 obtained from the LLM 152 on the display device 15. The person performs the work by referring to the work support information 50 displayed on the display device 15. 【0084】 Next, an example of the processing procedure of the information processing device 100 according to this embodiment will be described. Figure 11 is a flowchart showing the processing procedure of the information processing device according to this embodiment. As shown in Figure 11, the video analysis unit 151 of the information processing device 100 acquires video information from the camera 10 (step S101). 【0085】 The video analysis unit 151 analyzes the video information and generates object information (step S102). The LLM 152 of the information processing device 100 generates work support information based on the object information (step S103). 【0086】 The LLM 152 verifies the work support information (step S104). Based on the verification results, the LLM 152 outputs the work support information to the proposal unit 153 (step S105). The proposal unit outputs the work support information to the display device for display (step S106). 【0087】 Next, the effects of the information processing device 100 according to this embodiment will be described. 【0088】The information processing device 100 generates object information 40 by analyzing video information captured by the camera 10 using a predetermined video analysis technique. Based on the object information 40, the information processing device 100 generates work support information 50 and verifies the impact on a person when they change their behavior based on the generated work support information 50. If the verification results meet predetermined conditions, the information processing device 100 outputs and displays the work support information 50 on the display device 15. This enables efficient work support. 【0089】 The information processing device 100 outputs work support information when the load on a predetermined body part of a person identified by behavioral information exceeds a predetermined threshold. This enables effective work support to be provided to a person whose load on a predetermined body part exceeds a predetermined threshold. 【0090】 The information processing device 100 calculates the load on a predetermined body part and outputs work support information when the cumulative load on the predetermined body part exceeds a predetermined threshold. This makes it possible to provide effective work support to individuals whose load on a predetermined body part exceeds a predetermined threshold over a long period of time. 【0091】 The information processing device 100 further uses location information to generate work support information. This enables work support that takes location into consideration. 【0092】 Next, we will describe in order an example of a computer hardware configuration that realizes the same functions as the information processing device 100 shown in the above embodiment. 【0093】Figure 12 shows an example of a computer hardware configuration that realizes similar functions to the information processing device in the embodiment. As shown in Figure 12, the computer 200 has a CPU 201 that performs various calculations, an input device 202 that receives data input from the user, and a display 203. The computer 200 also has a communication device 204 and an interface device 205 that exchange data with the camera 10, display device 15, etc. via a wired or wireless network. The computer 200 also has a RAM 206 for temporarily storing various information and a hard disk drive 207. Each of the devices 201 to 207 is connected to a bus 208. 【0094】 The hard disk drive 207 contains a video analysis program 207a, an LLM program 207b, and a proposed program 207c. The CPU 201 reads each of the programs 207a to 207c and loads them into the RAM 206. 【0095】 The video analysis program 207a functions as the video analysis process 206a. The LLM program 207b functions as the LLM process 206b. The proposed program 207c functions as the proposed process 206c. 【0096】 The processing of the video analysis process 206a corresponds to the processing of the video analysis unit 151. The processing of the LLM process 206b corresponds to the processing of the LLM 152. The processing of the proposal process 206c corresponds to the processing of the proposal unit 153. 【0097】 Furthermore, it is not necessary to store each program 207a to 207c on the hard disk drive 207 from the beginning. For example, each program may be stored on a "portable physical medium" such as a flexible disk (FD), CD-ROM, DVD, magneto-optical disk, or IC card inserted into the computer 200. Then, the computer 200 may read and execute each program 207a to 207c. 【0098】100 Information Processing Unit 110 Communication Unit 120 Input Unit 130 Display Unit 140 Storage Unit 141 Layout Information 142 Action Scene Graph 150 Control Unit 151 Video Analysis Unit 152 LLM 153 Proposal Unit

Claims

1. An information processing program characterized by causing a computer to execute the following processes:

1. Acquire video footage including a person to be detected; acquire object information, which is generated by a predetermined video analysis technique, and associates the person's attribute information and behavior information with the person included in the video; generate work support information for the person based on the object information; verify the impact on the person when the person changes their behavior based on the generated work support information; and output the work support information if the verification result satisfies predetermined conditions.

2. The information processing program according to claim 1, characterized in that the output process outputs the work support information when the load on a predetermined part of the person identified by the behavior information exceeds a predetermined threshold.

3. The information processing program according to claim 2, characterized in that the object information includes information on the person's actions over a predetermined period, and the computer is further instructed to perform a process of calculating the load on a predetermined body part based on the information on the person's actions over the predetermined period, and outputting the work support information when the cumulative load on the predetermined body part exceeds a predetermined threshold.

4. The information processing program according to claim 1, wherein the object information includes information indicating the location of the person, and the generating process further uses the location information to generate the work support information.

5. An information processing method characterized in that a computer performs the following processes: acquires video footage including a person to be detected; acquires object information, which is generated by a predetermined video analysis technique, and associates the person's attribute information and behavior information with the person included in the video footage; generates work support information for the person based on the object information; verifies the impact on the person when the person changes their behavior based on the generated work support information; and outputs the work support information if the result of the verification satisfies predetermined conditions.

6. The information processing method according to claim 5, characterized in that the output process outputs the work support information when the load on a predetermined part of the person identified by the behavior information exceeds a predetermined threshold.

7. The information processing method according to claim 6, characterized in that the object information includes information on the person's actions over a predetermined period, the computer further performs a process of calculating the load on a predetermined body part based on the information on the person's actions over the predetermined period, and outputting the work support information when the cumulative load on the predetermined body part exceeds a predetermined threshold.

8. The information processing method according to claim 5, wherein the object information includes information indicating the location of the person, and the generating process further uses the location information to generate the work support information.

9. An information processing device having a control unit that performs the following processes: acquires video footage including a person to be detected; acquires object information, which is generated by a predetermined video analysis technique, and associates the person's attribute information and behavior information with the person included in the video footage; generates work support information for the person based on the object information; verifies the impact on the person when the person changes their behavior based on the generated work support information; and outputs the work support information if the result of the verification satisfies predetermined conditions.

10. The information processing apparatus according to claim 9, characterized in that the output process outputs the work support information when the load on a predetermined part of the person identified by the behavior information exceeds a predetermined threshold.

11. The information processing apparatus according to claim 10, wherein the object information includes information on the person's actions over a predetermined period, and the control unit further performs a process of calculating the load on a predetermined body part based on the information on the person's actions over the predetermined period, and outputting the work support information when the cumulative load on the predetermined body part exceeds a predetermined threshold.

12. The information processing apparatus according to claim 9, wherein the object information includes information indicating the location of the person, and the generating process further uses the location information to generate the work support information.

Images