Information processing apparatus

Abstract

To estimate the progress of work processes in a work site.SOLUTION: An information processing apparatus 10 estimates posterior distributions of as-built condition of a process line at a designated point of time and a productivity variation ratio at the designated point of time, for each work process in a work site, using a state space model and observed attendance obtained by recording the number of workers entering the work site, the state space model being composed of a system model and an observation model, the system model being represented by a state equation that defines a relationship between an as-built condition in the previous period and an as-built condition at a specific time point for each work site and each work process in the work site, using an as-built condition of a process line at the specific time point, an as-built condition of the process line at a time point in the previous period, and the productivity variation ratio relative to a scheduled number of workers, as state variables, and a state equation that defines a relationship between a productivity variation ratio in the previous period and a productivity variation ratio at the designated time point, the observation model representing a relationship between the state variables and observation variables each indicating the number of workers entering the work site for each period.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device that estimates the progress of a process. [Background technology]

[0002] Patent Document 1 discloses a construction process management system that can acquire construction status data at a construction site and visualize the progress status, and that includes: a photography means for moving around the construction site and taking images of the construction site for each specified work section; a progress data calculation means for determining the work content for each specified work section based on at least one of the continuous movements of workers or machines contained in the video data taken by the photography means, the materials or tools in the taken video data, and changes in the image in the taken video data, and calculating progress data including at least the work content, work status, and number of workers; a differential data calculation means for comparing the progress data with design data consisting of a BIM or CIM model, and calculating differential data including at least the difference between the progress data for the day and the design data and the difference between the progress data for the day and the previous day; a 3D model data creation means for creating 3D modeled data based on the calculated differential data; and a video display means for visualizing and displaying the created data.

[0003] Patent Document 2 discloses a work progress prediction device that includes an input unit for inputting the number of workers to be assigned to a target for which work progress prediction is being performed, a storage unit for storing data indicating the relationship between the number of workers and the work progress level according to at least one of the work content and the work environment, and a calculation unit for calculating the work progress level for the target based on the input number of workers and the data stored in the storage unit.

[0004] Patent Document 3 discloses a method for managing the progress of a building, executed by a computer, which, after completion of a process associated with construction for each room in the building, acquires at least one of location information relating to the current location of the building materials of the building and worker information relating to the workers, as well as building material information relating to the attributes of the building materials, associates at least one of the location information and the worker information with process information relating to the process for each building material, calculates progress information for the process, and visualizes the progress information for the process in chronological order. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent No. 7041551 [Patent Document 2] Japanese Patent Application Laid-Open No. 2002-7656 [Patent Document 3] Japanese Patent Application Publication No. 2020-129312 Summary of the Invention [Problem to be solved by the invention]

[0006] Image data is sometimes used as a method for estimating the progress of a construction process. For example, the technology described in Patent Document 1 quantifies the progress of a construction process by comparing actual data reconstructed from image data taken by moving around the construction site and photographing each work section with plan data, which is three-dimensional shape data of objects generated in advance at the planning stage.

[0007] However, taking photographs of the construction site conditions requires additional equipment and tasks that are not required for the original work, such as photography equipment, and also requires the introduction of a new process to generate performance data from the captured image data. Moreover, when work is carried out in parallel at multiple work sites, the equipment required to estimate the progress of the process must be installed at each work site, and the cost of installing the equipment increases as the number of work sites increases.

[0008] On the other hand, worker data can be used as a simpler method for determining the progress of a process. For example, the technology described in Patent Document 2 determines the progress of each process from the number of workers by using a correspondence table between the number of workers for each process and the progress level for a preset number of workers. The technology described in Patent Document 3 calculates process output information by associating information about workers and processes with each building material of a building.

[0009] However, the technology described in Patent Document 1 has a deterministic relationship between the number of workers and the progress rate, and is unable to evaluate the uncertainty that exists between the number of workers and the progress rate. Furthermore, the technology described in Patent Document 2 requires the introduction of a process that associates building materials with the process and the number of workers.

[0010] The present disclosure has been made in consideration of the above facts, and aims to provide an information processing device that estimates the progress of work processes at a work site using equipment that is already installed at the work site, without adding equipment or tasks that are unnecessary for the actual work. [Means for solving the problem]

[0011] In order to achieve the above object, the information processing device of the present disclosure uses as state variables the completed state at a specific time point relative to a process line that represents a progress plan for a work process performed at each work site, the completed state at a time point one period prior to the specific time point, and a yield fluctuation ratio that indicates the ratio of the number of workers who actually performed the work process to the planned number of workers required to proceed with the work process according to the process line, and calculates a first equation that defines the relationship between the completed state at one period prior and the completed state at the specific time point for each work site and for each work process performed at the work site, and a second equation that defines the relationship between the yield fluctuation ratio one period prior and the yield fluctuation ratio at the specific time point for each work site and for each work process performed at the work site. and a generation unit that generates a state space model composed of a system model expressed by a second equation that defines a relationship between the state variables and the observation variables when the number of workers entering each of the work sites in each period is an observation variable, and a memory unit that stores the state space model in a storage device so that the state space model generated by the generation unit can be used to estimate the posterior distributions of the completed form and the yield variation rate of the process line for each of the work sites and for each of the work processes performed at the work sites at a specified time point specified by a user.In this way, the information processing device of the present disclosure can estimate the progress of a work process at a work site using equipment that is already installed at the work site, without adding equipment or tasks that are not necessary for the actual work.

[0012] In addition, the observation model of the information processing device of the present disclosure uses a model that represents the correspondence relationship between the number of workers entering the work site and the change in the completed state of the process line for each work site and each work process. In this way, the information processing device of the present disclosure can estimate the completed state of the process line from the number of workers entering the work site.

[0013] The information processing device of the present disclosure also uses as state variables the completed state at a specific time point relative to a process line that represents a progress plan for a work process performed at each work site, the completed state at a time point one period before the specific time point, and a rate of work fluctuation ratio that indicates the ratio of the planned number of workers required to proceed with the work process according to the process line to the number of workers who actually performed the work process, and the planned number of workers required to proceed with the work process according to the process line, and a system model expressed by a first equation that defines the relationship between the completed state at a specific time point and the completed state at a specific time point, and a second equation that defines the relationship between the rate of work fluctuation ratio one period before and the rate of work fluctuation ratio at a specific time point, for each of the work sites and for each of the work processes performed at the work sites, and the number of workers entering the work site for each of the work sites in each period is used as an observation variable. and an acquisition unit that acquires an observed number of workers that have entered the work site designated by a user for each period up to a designated time point, an estimation unit that applies a sequential Bayes filter using the observed number of workers to the state space model acquired by the acquisition unit to estimate a posterior distribution of the completed form of the process line at the designated time point and the yield fluctuation rate at the designated time point for each work process performed at the designated work site, and an output unit that outputs the posterior distribution of the completed form of the process line at the designated time point and the yield fluctuation rate at the designated time point for each work process estimated by the estimation unit.In this way, the information processing device of the present disclosure can estimate the progress of a work process at a work site using equipment that is already installed at the work site, without adding equipment or tasks that are not necessary for the actual work.

[0014] In addition, the output unit of the information processing device of the present disclosure outputs an alarm when the progress of the work process at the specified time point represented by the posterior distribution of the completed form of the process line is behind the progress plan at the specified work site. In this way, the information processing device of the present disclosure can notify the user of a work delay.

[0015] The work process of the information processing device of the present disclosure is a process related to at least one of construction work, demolition work, and civil engineering work. In this way, the information processing device of the present disclosure can estimate the progress of the work process related to construction work. [Effects of the Invention]

[0016] According to the present disclosure, it is possible to estimate the progress of work processes at a work site using equipment that is already installed at the work site, without adding equipment or tasks that are not necessary for the actual work. [Brief explanation of the drawings]

[0017] [Figure 1] FIG. 2 is a diagram illustrating an example of a functional configuration of an information processing device. [Figure 2] FIG. 10 is a diagram showing an example of the finished product. [Figure 3] FIG. 10 is a diagram illustrating an example of a labor unit plan. [Figure 4] FIG. 2 is a diagram illustrating an example of the configuration of a main part of an electrical system of an information processing device. [Figure 5] 10 is a flowchart illustrating an example of the flow of a generation process of a state space model. [Figure 6] 10 is a flowchart showing an example of the flow of a process for estimating a degree of progress. [Figure 7] FIG. 10 is a diagram showing an example of the posterior distribution of the completed form and the posterior distribution of the rate of work fluctuation ratio in a situation where the work process is progressing according to the progress plan by the planned number of workers. [Figure 8] FIG. 10 is a diagram showing an example of the posterior distribution of the completed form and the posterior distribution of the unit rate variation ratio in a situation where the number of workers is less than the planned number of workers and the work process is behind schedule. [Figure 9] FIG. 10 is a diagram showing an example of the posterior distribution of the completed form and the posterior distribution of the unit rate variation ratio in a situation where the number of workers is greater than the planned number of workers, but the work process is behind schedule. DETAILED DESCRIPTION OF THE INVENTION

[0018] Hereinafter, the present embodiment will be described with reference to the drawings. The same components and processes are denoted by the same reference numerals throughout the drawings, and duplicated explanations will be omitted. The dimensional proportions in the drawings are exaggerated for the sake of explanation, and may differ from the actual proportions.

[0019] FIG. 1 is a diagram showing an example of the functional configuration of an information processing device 10 that estimates the progress of a work process at a work site.

[0020] There are no restrictions on the type of work that can be done at the work site, and any type of work can be done, but in this embodiment, an example will be described in which construction work is being done at the work site. The construction work includes at least one of building work, demolition work, and civil engineering work.

[0021] Since construction work is carried out at each site, the information processing device 10 estimates the progress of the work process at each work site.

[0022] The work site master DB (database) 11A is a database that stores information about work sites (hereinafter referred to as "work site information") for each work site.

[0023] In the workshop master DB 11A, for example, workshop name can be used as a key to acquire workshop information corresponding to the workshop name. The workshop information includes, for example, a workshop ID (identification) assigned in advance to each workshop name, which is information used as identification information to uniquely identify the workshop.

[0024] The work schedule DB11B is a database that stores, for each work site, information relating to the progress of work processes carried out at the work site (hereinafter referred to as "progress information").

[0025] The progress information includes a process line that represents a progress plan for the work process being carried out at each work site. The process line that represents the progress plan for the work process is represented, for example, by a line chart that specifies the start and end dates of the work process. The progress information may also include the actual degree of progress for the work process.

[0026] The degree of progress of a work process is expressed, for example, using a completed state which indicates how much of the work has been completed relative to the progress plan of the work process.

[0027] 2 is a diagram showing an example of the completed state. Lines 12A and 12B represent the completed state. The horizontal axis of the completed state represents a time point along the time series, and the vertical axis represents the degree of progress of the work process.

[0028] The time t0 on the line 12A represents the start of the work process in the progress plan, and the time t m represents the end of the work process in the progress plan. In other words, line 12A represents the planned completed state corresponding to the process line of the progress plan.

[0029] On the other hand, line 12B represents the actual progress of the planned work process (hereinafter referred to as the "actual progress"). The actual progress shown in FIG. 2 is calculated from the time t when the work process starts, which is later than the start of the work process in the progress plan. 0s The progress at time t indicates that the work process in the progress plan is 30% of the total.

[0030] In this way, the completed state indicates the degree of progress of the work process at time t relative to the progress plan.

[0031] When work at a work site is made up of a plurality of work processes, the planned completed form and, if necessary, the actual completed form for each work process are stored in the work schedule DB11B.

[0032] The labor unit plan DB 11C in FIG. 1 is a database that stores, for each work site, information about the labor required by workers when performing work according to a work process (hereinafter referred to as "unit information").

[0033] 3 is a diagram showing an example of the labor unit rate plan 13 stored in the labor unit rate plan DB 11C. The labor unit rate plan 13 is an example of unit rate information, and is information that predetermines for each process line the planned number of workers per day required to proceed with the work process according to the process line of the progress plan.

[0034] In the case of the labor rate plan 13 shown in Figure 3, it is shown that in order for a certain workshop to carry out the work process corresponding to process line A according to the progress plan, 10 workers of job type A and 20 workers of job type B are required per day. Also, it is shown that in order to carry out the work process corresponding to process line B according to the progress plan, 10 workers of job type A, 5 workers of job type B, and 5 workers of job type C are required per day.

[0035] In the labor rate plan 13 shown in FIG. 3, the planned number of workers is specified for each job type, but it is also possible to simply specify the total number of workers required for each work process for each process line, regardless of the job type.

[0036] The labor yield plan DB 11C may also store a yield variation ratio, which is an example of yield information. The yield variation ratio is a value that represents the ratio of the number of workers required to actually perform work in a work process to the planned number of workers defined by the labor yield plan 13. In other words, the yield variation ratio is a value that represents how many times more workers are required compared to the plan defined by the labor yield plan 13.

[0037] The unit rate fluctuation ratio is calculated for each task unit. As an example, when the planned number of workers per day is determined by the labor rate plan 13, it is preferable to use one day as the task unit for the work process. However, the task unit for the work process is not limited to one day, and may be, for example, one hour or one week. In this embodiment, the task unit for the work process may be expressed as a "period."

[0038] The information processing device 10 shown in FIG. 1 includes functional units of a generating unit 10A, a storage unit 10B, an acquiring unit 10C, an estimating unit 10D, and an output unit 10E, as well as a state space model DB 11D.

[0039] The generation unit 10A generates a state space model used to estimate the progress of the work process at each work site. The state space model is composed of a system model that models the work state at the work site using state variables that represent the work state, and an observation model that represents the relationship between the state variables and the observation variables, which are values ​​that can actually be observed at the work site.

[0040] In this embodiment, as an example, the completed state at a specific time t for each process line of work performed at each work site, the completed state at time t-1, which is one period before time t, and the rate of work fluctuation are used as state variables representing the work state. Note that time t is an integer, and the smaller the value of t, the earlier the time point is represented.

[0041] The generation unit 10A defines a state equation that defines the relationship between the completed state at a specific time t and the completed state one period before the time t for each work site and for each work process performed at the work site using state variables. The state equation, which is an example of the first equation, is defined by, for example, equation (1).

[0042] In this embodiment, the subscripts "i", "j", and "k" are used to represent the work site, the process line, and the job type, respectively. "i", "j", and "k" are all integers.

[0043]

number

[0044] In equation (1), x i,j,t is the completed form of process line j at time t of workshop i, x i,j,t-1 represents the completed state of the process line j at time t-1 of the workshop i, that is, the completed state of the process line j one period before the workshop i. x i,j-1,t-1 represents the completed state of the process line j-1 at the previous stage of the workshop i. i,j,t represents the noise component of the completed form of process line j at time t in workshop i, and d i,jrepresents the planned completed state of process line j at workshop i. The operator ∧ represents logical product, and N(1,σ 2 ) has a mean of 1 and a variance of σ 2 represents the normal distribution of v i,j,t ~N(1,σ 2 ) is the noise component v i,j,t The distribution of N(1,σ 2 f(x i,j,t |x i,j,t-1 ) represents the relationship between the completed form of process line j at time t in workshop i and the completed form of process line j one period before in workshop i, that is, the time evolution of the completed form of process line j in workshop i. Equation (1) indicates that the time evolution of the completed form of process line j in workshop i starts after the completion of process line j-1, and the completed form increases by one unit on average for each period until it reaches the planned completed form.

[0045] Furthermore, the generation unit 10A defines, for each workshop, a state equation that defines the relationship between the yield fluctuation rate at time t and the yield fluctuation rate one period before time t using the state variables. The state equation, which is an example of the second equation, is defined by, for example, equation (2).

[0046]

number

[0047] In equation (2), λ i,t represents the rate of change in work rate at time t for workshop i, and λ i,t-1 represents the rate of change in work rate at time t-1 of workshop i, that is, the rate of change in work rate one period before workshop i. i,t represents the noise component of the rate of change in work rate at time t for workshop i, and ρ 2 is the noise component w i,t represents the variance of g(λ i,t |λ i,t-1 ) represents the relationship between the unit rate fluctuation ratio at time t of workshop i and the unit rate fluctuation ratio one period before, i.e., the time evolution of the unit rate fluctuation ratio at workshop i.

[0048] In this way, the generation unit 10A defines a system model that represents the time evolution of the state variables by the state equations shown in formula (1) and (2).

[0049] Furthermore, the generation unit 10A defines an observation model that represents the relationship between the state variables and the observation variables, using the number of workers entering each work site at time t as an observation variable. Specifically, a model that represents the correspondence relationship between the number of workers entering each work site and the change in the completed state of the process line for each work site and each work process is used as the observation model.

[0050] Such an observation model is defined, for example, by equation (3).

[0051]

number

[0052] In equation (3), y i,t represents the number of workers entering workshop i at time t. k,j represents the planned number of workers engaged in job type k in the work process represented by process line j. Also, y i,t ~N(a, b) is y i,t This indicates that follows a normal distribution with mean a and variance b.

[0053] The generation unit 10A generates a state space model using the system model shown in equations (1) and (2) and the observation model shown in equation (3).

[0054] The storage unit 10B stores the state space model generated by the generation unit 10A in a state space model DB 11D.

[0055] The state space model DB 11D is a database that stores the state space model generated by the generation unit 10 A. Although Fig. 1 shows an example in which the state space model DB 11D is included in the information processing device 10, the state space model DB 11D may be constructed in a storage device that is accessible from the information processing device 10 and is provided outside the information processing device 10.

[0056] On the other hand, when the user instructs the information processing device 10 to estimate the degree of progress of the work process at the specified time t in the specified work site, the information processing device 10 starts an estimation process to estimate the degree of progress of the work process at the specified time t in the specified work site.

[0057] In the estimation process, the acquisition unit 10C acquires a state space model of the specified workshop from the state space model DB 11D. The acquisition unit 10C also acquires the observed number of visitors, which is the number of workers who have entered the workshop specified by the user for each period up to time t.

[0058] The observed number of visitors is stored in advance in, for example, the worker number DB 11E, so the acquisition unit 10C can acquire the observed number of visitors to the specified work site from the worker number DB 11E.

[0059] In order to grasp the working conditions of workers, each work site is equipped with a time attendance management device that records their arrival and departure times. As part of the work rules, workers are required to record their arrival and departure times using the time attendance management device, and the recorded arrival and departure times are stored in the worker number DB 11E for each work site.

[0060] Therefore, the number of observed visitors to a designated work site can be obtained using equipment that is already installed at the work site.

[0061] The estimation unit 10D applies a sequential Bayes filter using the observed number of people to the state space model acquired by the acquisition unit 10C, and calculates the posterior distribution p(x i,j,t |y i,1:t ) and posterior distribution p(λ i,t |y i,1:t ) is estimated. The notation "1:t" in the posterior distribution represents the observed number of workers entering the work site for each period from the start of the work process to time t.

[0062] The output unit 10E outputs the posterior distribution p(x i,j,t |y i,1:t ) and the posterior distribution p(λ i,t |y i,1:t Specifically, the output unit 10E outputs the posterior distribution p(x i,j,t |y i,1:t ) and the posterior distribution p(λ i,t |y i,1:t ) is displayed on the display unit 23 (see FIG. 4).

[0063] It should be noted that the information processing device 10 does not necessarily have to include the functional units of the generation unit 10A, the storage unit 10B, the acquisition unit 10C, the estimation unit 10D, and the output unit 10E. For example, the functional units may be separated into an information processing device 10-1 including the generation unit 10A and the storage unit 10B, and an information processing device 10-2 including the acquisition unit 10C, the estimation unit 10D, and the output unit 10E. In this case, the information processing device 10-1 generates a state space model, and the information processing device 10-2 calculates the posterior distribution p(x i,j,t |y i,1:t ) and the posterior distribution p(λ i,t |y i,1:t ) is estimated.

[0064] 1 is configured using, for example, a computer 20. FIG. 4 is a diagram showing an example of the configuration of the main parts of the electrical system of the information processing device 10 configured using the computer 20.

[0065] The computer 20 includes a CPU (Central Processing Unit) 20A, which is an example of a processor that executes the processing of each functional unit shown in Fig. 1. The computer 20 also includes a RAM (Random Access Memory) 20B, which is used as a temporary work area for the CPU 20A, a nonvolatile memory 20C, and an input / output interface (I / O) 20D. The CPU 20A, RAM 20B, nonvolatile memory 20C, and I / O 20D are all connected to each other via a bus 20E.

[0066] The nonvolatile memory 20C is an example of a storage device that maintains stored information even when power supplied to the nonvolatile memory 20C is cut off, and is, for example, a semiconductor memory such as an SSD (Solid State Drive), but a hard disk may also be used. The nonvolatile memory 20C stores information that must not be erased every time the computer 20 is restarted or a power outage occurs, such as an information processing program that causes the computer 20 to function as the information processing device 10.

[0067] In this embodiment, as an example, a workshop master DB 11A, a schedule DB 11B, a labor-yield schedule DB 11C, a state space model DB 11D, and a number of workers DB 11E are stored in the nonvolatile memory 20C.

[0068] The nonvolatile memory 20C does not necessarily have to be built into the computer 20, and may be, for example, a portable storage device that is detachable from the computer 20. Also, a storage device that is provided outside the information processing device 10 and accessible from the information processing device 10 may be used as the nonvolatile memory 20C.

[0069] On the other hand, to the I / O 20D of the computer 20, for example, a communication unit 21, an input unit 22, and a display unit 23 are connected.

[0070] The communication unit 21 is connected to a communication line (not shown) and has a communication protocol for transmitting and receiving data to and from an external device connected to the communication line.

[0071] The input unit 22 is a device that receives instructions from a user and notifies the CPU 20 A. The user's instructions are notified via, for example, a button, a touch panel, a mouse, a keyboard, a pointing device, or the like.

[0072] The display unit 23 is a display device that displays information processed by the CPU 20A as an image, and may be a liquid crystal display, an organic EL (Electro Luminescence) display, or the like.

[0073] Note that the units connected to the I / O 20D are not limited to the communication unit 21, the input unit 22, and the display unit 23, but are connected to units according to the functions of the information processing device 10. For example, when the information processing device 10 is operated from an external device via a communication line, it is not necessarily necessary to connect the input unit 22 and the display unit 23 to the I / O 20D.

[0074] Next, the flow of processing in the information processing device 10 will be described in detail.

[0075] FIG. 5 is a flowchart showing an example of the flow of the state space model generation process executed by the CPU 20A of the information processing device 10 when an instruction to generate a state space model is received from the user.

[0076] An information processing program that defines the generation process of the state space model is stored in advance in, for example, the nonvolatile memory 20C of the information processing device 10. The CPU 20A reads the information processing program stored in the nonvolatile memory 20C and executes the generation process of the state space model.

[0077] In step S10, the CPU 20A selects one of the workshops.

[0078] In step S20, the CPU 20A acquires the work site information of the work site selected by the process of step S10 from the work site master DB 11A constructed in the nonvolatile memory 20C.

[0079] In step S30, the CPU 20A uses the workshop ID included in the workshop information acquired by the processing of step S20 to acquire progress information and unit rate information of the selected workshop from the process schedule DB 11B and labor unit rate plan DB 11C constructed in the non-volatile memory 20C, respectively. Using the acquired progress information and unit rate information, the CPU 20A defines a system model according to equations (1) and (2) for the selected workshop.

[0080] In step S40, the CPU 20A defines an observation model according to equation (3) for the selected workshop using the labor unit plan 13 included in the unit information and the process line included in the progress information.

[0081] In step S50, CPU 20A determines whether or not all work sites for which the progress of the construction work is to be estimated have been selected. If there are any work sites that have not yet been selected, the process proceeds to step S10, where one unselected work site is selected from each of the work sites. That is, by repeatedly executing the processes of steps S10 to S50 until it is determined by the determination process of step S50 that all work sites have been selected, a state space model for all work sites is defined.

[0082] On the other hand, if it is determined in step S50 that all work sites have been selected, the process proceeds to step S60.

[0083] In step S60, CPU 20A associates the defined state space model of each workshop with the workshop ID and stores it in state space model DB 11D constructed in nonvolatile memory 20C.

[0084] This completes the process of generating the state space model shown in Fig. 5. Through the process of generating the state space model, a state space model for each workshop is generated.

[0085] FIG. 6 is a flowchart showing an example of the flow of a process for estimating the degree of progress executed by the CPU 20A of the information processing device 10 when an instruction to estimate the degree of progress of a work process at a work site designated by a user is received.

[0086] An information processing program that defines the process of estimating the degree of progress is stored in advance, for example, in the nonvolatile memory 20C of the information processing device 10. The CPU 20A reads the information processing program stored in the nonvolatile memory 20C and executes the process of estimating the degree of progress.

[0087] The estimation instruction includes the work site ID of the work site for which the progress of the work process is to be estimated, and the time t for which the progress of the work process is to be estimated. The time t included in the estimation instruction is an example of a specified time.

[0088] In step S100, CPU 20A acquires the work site ID included in the estimated instruction.

[0089] In step S110, the CPU 20A uses the workshop ID acquired in the process of step S100 to acquire a state space model corresponding to the workshop ID from the state space model DB 11D constructed in the nonvolatile memory 20C.

[0090] In step S120, the CPU 20A uses the work site ID acquired by the processing of step S100 to acquire the observed number of workers entering the work site corresponding to the work site ID for each period from the start of the work process to time t from the worker number DB11E constructed in the non-volatile memory 20C.

[0091] In step S130, the CPU 20A applies a sequential Bayes filter using the observed number of visitors acquired in the process of step S120 to the state space model acquired in the process of step S110, and calculates the posterior distribution p(x i,j,t |y i,1:t ) and posterior distribution p(λ i,t |y i,1:t ) is estimated.

[0092] As an example, in consideration of ease of implementation and applicability to nonlinear models, the CPU 20A calculates the posterior distribution p(x i,j,t |y i,1:t ), and the posterior distribution of the yield fluctuation ratio p(λ i,t |y i,1:t ) is estimated.

[0093] In step S140, the CPU 20A calculates the posterior distribution p(x i,j,t |y i,1:t ), and the posterior distribution of the yield fluctuation ratio p(λ i,t |y i,1:t ) on the display unit 23. In this case, the CPU 20A displays the posterior distribution p(x i,j,t |y i,1:t ), at least one of the planned completed form and the actual completed form may be superimposed and displayed on the display unit 23. Furthermore, the CPU 20A may calculate the posterior distribution p(λ i,t |y i,1:t ) may be displayed on the display unit 23 with the rate of change calculated from the observed number of visitors superimposed thereon.

[0094] In step S150, the CPU 20A calculates the posterior distribution p(x i,j,t |y i,1:t ) with the planned completed state, and determines whether there is an operation process whose progress is behind the progress plan. Specifically, the CPU 20A compares the estimated completed state posterior distribution p(x i,j,t |y i,1:t ), if the completed state at time t, assuming that the progress is at its highest, is less than the planned completed state at time t, it is determined that the progress of the work process is behind the progress plan.

[0095] If there is an operation whose progress is behind the progress plan, the process proceeds to step S160.

[0096] Since the progress degree is behind the progress plan, in step S160, CPU 20A outputs a warning to the user and ends the progress degree estimation process shown in Fig. 6. The warning may be output in any form that allows the user to notice the warning, such as a display on display unit 23, a voice notification, or an email notification.

[0097] On the other hand, if it is determined in the determination process of step S150 that there is no work process whose progress is behind the progress plan, the process of estimating the progress shown in Figure 6 is terminated without executing the process of step S160.

[0098] 7 to 9 are graphs showing the posterior distribution p(x i,j,t |y i,1:t ), and the posterior distribution of the yield fluctuation ratio p(λ i,t |y i,1:t ) is a diagram showing an example.

[0099] 7 to 9, graph 18A shows an example of the planned completed state and the actual completed state, and graph 19A shows an example of the yield fluctuation ratio. The horizontal axis of graph 18A represents a point in time along the time series, and the vertical axis represents the progress of the work process. The horizontal axis of graph 19A represents a point in time along the time series, and the vertical axis represents the yield fluctuation ratio.

[0100] On the other hand, graphs 18B and 19B in FIGS. 7 to 9 show the posterior distributions p(x i,j,t |y i,1:t ), and the posterior distribution of the yield fluctuation ratio p(λ i,t |y i,1:t ) is shown. The horizontal axis of graph 18B represents a point in time along the time series, and the vertical axis represents the progress of the work process. The horizontal axis of graph 19B represents a point in time along the time series, and the vertical axis represents the rate of change in work rate.

[0101] For the sake of convenience, it is assumed that work at the workshop is composed of process lines A and B, and that the labor unit plan 13 shown in FIG. 3 is established for each of the process lines A and B.

[0102] 7 to 9, line 12A-1 represents the planned completed shape corresponding to process line A, and line 12A-2 represents the planned completed shape corresponding to process line B. Line 12B-1 represents the actual completed shape corresponding to process line A, and line 12B-2 represents the actual completed shape corresponding to process line B.

[0103] Line 14A shows the estimated posterior distribution p(x i,j,t |y i,1:t ), the most advanced completed state estimated at each point in time, i.e., the upper limit completed state, and line 14B represents the posterior distribution p(x i,j,t |y i,1:t ) represents the latest estimated completed state at each point in time, i.e., the lower limit completed state.

[0104] Line 16A represents the rate of change when workers perform work according to labor rate plan 13, i.e., the standard rate of change, and line 16B represents the rate of change that results in the actual observed number of employees entering the workforce.

[0105] Line 17A shows the posterior distribution p(λ i,t |y i,1:t ) represents the highest yield fluctuation ratio estimated at each time point, i.e., the upper limit yield fluctuation ratio, and line 17B represents the lowest yield fluctuation ratio estimated at each time point, i.e., the lower limit yield fluctuation ratio.

[0106] Figure 7 shows the posterior distribution p(x i,j,t |y i,1:t ), and the posterior distribution of the yield fluctuation ratio p(λ i,t |y i,1:t ) is shown.

[0107] In this case, the actual completed forms of process lines A and B overlap with the planned completed forms of the respective process lines, and the yield fluctuation ratio overlaps with the standard yield fluctuation ratio.

[0108] Figure 8 shows the posterior distribution p(x i,j,t |y i,1:t ), and the posterior distribution of the yield fluctuation ratio p(λ i,t |y i,1:t ) is shown.

[0109] Figure 9 shows the posterior distribution p(x i,j,t |y i,1:t ), and the posterior distribution of the yield fluctuation ratio p(λ i,t |y i,1:t ) is shown.

[0110] In any of the cases shown in FIGS. 7 to 9, the posterior distribution p(x i,j,t |y i,1:t ), and the posterior distribution of the yield fluctuation ratio p(λ i,t |y i,1:t It is recognized that there is a tendency for the actual completed work and the rate of work fluctuation ratio at each point in time to fall within the range of

[0111] Therefore, the information processing device 10 can calculate the posterior distribution p(x i,j,t |y i,1:t ) and the posterior distribution p(λ i,t |y i,1:t ) can be estimated.

[0112] While one form of the information processing device 10 has been described above using the embodiment, the disclosed form of the information processing device 10 is merely an example, and the form of the information processing device 10 is not limited to the scope described in the embodiment. Various changes or improvements can be made to the embodiment without departing from the gist of the present disclosure, and forms incorporating such changes or improvements are also included in the technical scope of the disclosure.

[0113] For example, the internal processing order of the process for generating the state space model shown in FIG. 5 and the process for estimating the degree of progress shown in FIG. 6 may be changed without departing from the spirit of the embodiment.

[0114] In the above embodiment, as an example, the process of generating a state space model and the process of estimating the degree of progress are described as being implemented by software. However, the processes equivalent to the flowcharts of the processes shown in Figures 5 and 6 may be executed by hardware. In this case, the process can be executed faster than when the process of generating a state space model and the process of estimating the degree of progress are implemented by software.

[0115] In the above embodiment, the term "processor" refers to a processor in a broad sense, and includes general-purpose processors (e.g., CPU 20A) and dedicated processors (e.g., GPU: Graphics Processing Unit, ASIC: Application Specific Integrated Circuit, FPGA: Field Programmable Gate Array, programmable logic device, etc.).

[0116] The operations of the processors in the above embodiments may not only be performed by one processor, but may also be performed by a plurality of processors located at physically separate locations working together.

[0117] In the above embodiment, an example has been described in which the information processing program is pre-stored in the non-volatile memory 20C. However, the storage destination of the information processing program is not limited to the non-volatile memory 20C. The information processing program may also be provided in a form recorded on a storage medium readable by the computer 20.

[0118] For example, the information processing program may be provided in a form recorded on an optical disk such as a CD-ROM (Compact Disk Read Only Memory), a DVD-ROM (Digital Versatile Disk Read Only Memory), or a Blu-ray disc. The information processing program may also be provided in a form recorded on a portable semiconductor memory such as a USB (Universal Serial Bus) memory or a memory card. Non-volatile memory 20C, CD-ROM, DVD-ROM, Blu-ray disc, USB memory, and memory card are examples of non-transitory storage media.

[0119] Furthermore, the information processing device 10 may download an information processing program from an external device connected to a communication line via the communication unit 21, and store the downloaded information processing program in the nonvolatile memory 20C.

[0120] The following are notes related to this disclosure.

[0121] (Appendix 1) a generation unit that generates a state space model consisting of a system model expressed by a first equation that defines the relationship between the completed form one period ago and the completed form at the specific time point for each workshop and for each of the work processes performed at each workshop, and a second equation that defines the relationship between the completed form one period ago and the completed form at the specific time point, with the state variables being the completed form at a specific time point for a process line that represents a progress plan for the work process performed at each workshop, the completed form at a time point one period ago relative to the specific time point, and a yield fluctuation ratio that indicates the ratio of the planned number of workers required to proceed with the work process according to the process line to the number of workers who actually performed the work process; and an observation model that defines the relationship between the state variables and the observation variables when the number of workers entering each workshop for each period is used as an observation variable; a storage unit that stores the state space model generated by the generation unit in a storage device so that the state space model can be used to estimate the posterior distribution of the completed form and the yield variation rate of the process line for each of the work sites and each of the work processes performed at the work sites at a specified time point designated by a user; An information processing device comprising:

[0122] (Appendix 2) As the observation model, a model is used which represents a correspondence relationship between the number of workers entering the work site and the change in the completed form of the process line for each work site and each work process. 2. The information processing device according to claim 1.

[0123] (Appendix 3) a system model expressed by a first equation defining the relationship between the completed form one period ago and the completed form at the specific time point for each of the work processes performed at each of the work sites and for each of the work processes performed at each of the work sites, and a second equation defining the relationship between the completed form one period ago and the completed form at the specific time point, and a second equation defining the relationship between the completed form one period ago and the completed form at the specific time point, with the state variables being the completed form at a specific time point for each of the work processes performed at each of the work sites and the completed form at a specific time point for each of the work processes performed at each of the work sites, and an observation model expressing the relationship between the number of workers entering each of the work sites for each period as an observation variable, and an acquisition unit for acquiring an observed number of workers entering the work site for each period up to a specified time point for the work site designated by a user; an estimation unit that applies a sequential Bayes filter using the observed number of people to the state space model acquired by the acquisition unit to estimate a posterior distribution of the completed form of the process line at the specified time point for each of the work processes performed at the designated work site and the yield variation ratio at the specified time point; an output unit that outputs a posterior distribution of the completed form of the process line at the specified time point for each of the work processes estimated by the estimation unit and the yield variation ratio at the specified time point; An information processing device comprising:

[0124] (Appendix 4) The output unit outputs an alarm when the progress of the work process at the specified time point represented by the posterior distribution of the completed form of the process line is behind the progress plan at the specified work site. 4. The information processing device according to claim 3.

[0125] (Appendix 5) The work process is a process related to at least one of construction work, demolition work, and civil engineering work. 5. The information processing device according to any one of Supplementary notes 1 to 4.

[0126] (Appendix 6) A state space model is generated that is composed of a system model expressed by a first equation that defines the relationship between the completed form one period ago and the completed form at the specific time point for each of the work processes performed at each of the work sites and for each of the work processes performed at each of the work sites, and a second equation that defines the relationship between the completed form one period ago and the completed form at the specific time point, and a second equation that defines the relationship between the completed form one period ago and the completed form at the specific time point, and an observation model that defines the relationship between the number of workers entering each of the work sites at each of the work sites in each period as an observation variable, and A computer executes a process of storing the state space model in a storage device so that the state space model thus generated can be used to estimate the posterior distributions of the completed form and the yield variation ratio of the process line for each of the work processes performed at each of the work sites at a specified time point designated by a user. Information processing methods.

[0127] (Appendix 7) The state variables are the completed state at a specific time point relative to the process line representing the progress plan for the work process to be performed at each work site, the completed state at a time point one period prior to the specific time point, and the unit rate variation ratio, which indicates the ratio of the planned number of workers required to proceed with the work process according to the process line to the number of workers who actually performed the work process, and the number of workers who actually performed the work process. The system model is expressed by a first equation defining the relationship between the completed state at a specific time point and the completed state at a specific time point, and a second equation defining the relationship between the unit rate variation ratio one period prior to the specific time point, for each of the work sites and for each of the work processes performed at the work sites; and an observation model expressing the relationship between the number of workers entering the work site for each period as an observation variable, and an observed number of workers entering the work site for each period up to the specified time point for the work site specified by the user. Applying a sequential Bayes filter using the observed number of people to the acquired state space model, and estimating the posterior distribution of the completed form of the process line at the specified time point for each of the work processes performed at the specified work site and the yield variation ratio at the specified time point; A computer executes a process of outputting the estimated posterior distribution of the completed form of the process line at the specified time point for each of the work processes and the yield fluctuation ratio at the specified time point. Information processing methods.

[0128] (Appendix 8) A state space model is generated that is composed of a system model expressed by a first equation that defines the relationship between the completed form one period ago and the completed form at the specific time point for each of the work processes performed at each of the work sites and for each of the work processes performed at each of the work sites, and a second equation that defines the relationship between the completed form one period ago and the completed form at the specific time point, and a second equation that defines the relationship between the completed form one period ago and the completed form at the specific time point, and an observation model that defines the relationship between the number of workers entering each of the work sites at each of the work sites in each period as an observation variable, and and causing a computer to execute a process of storing the state space model in a storage device so that the generated state space model can be used to estimate the posterior distribution of the completed form and the yield variation rate of the process line for each of the work sites and each of the work processes performed at the work sites at a specified time point specified by a user. Information processing program.

[0129] (Appendix 9) The state variables are the completed state at a specific time point relative to the process line representing the progress plan for the work process to be performed at each work site, the completed state at a time point one period prior to the specific time point, and the unit rate variation ratio, which indicates the ratio of the planned number of workers required to proceed with the work process according to the process line to the number of workers who actually performed the work process, and the number of workers who actually performed the work process. The system model is expressed by a first equation defining the relationship between the completed state at a specific time point and the completed state at a specific time point, and a second equation defining the relationship between the unit rate variation ratio one period prior to the specific time point, for each of the work sites and for each of the work processes performed at the work sites; and an observation model expressing the relationship between the number of workers entering the work site for each period as an observation variable, and an observed number of workers entering the work site for each period up to the specified time point for the work site specified by the user. Applying a sequential Bayes filter using the observed number of people to the acquired state space model, and estimating the posterior distribution of the completed form of the process line at the specified time point for each of the work processes performed at the specified work site and the yield variation ratio at the specified time point; a process for causing a computer to execute a process for outputting the estimated posterior distribution of the completed form of the process line at the specified time point for each of the work processes and the yield fluctuation ratio at the specified time point; Information processing program. [Explanation of symbols]

[0130] 10, 10-1, 10-2 Information processing device 10A generator 10B Storage section 10C Acquisition Department 10D Estimation section 10E Output section 11A Workplace Master DB 11B Process chart DB 11C Labor rate planning DB 11D State Space Model DB 11E Worker number DB 12A-1, 12A-2 Planned finished shape of process line Actual finished shape of 12B-1 and 12B-2 process lines 13 Labor Unit Plan 14A Maximum completed length 14B Lower limit finished shape 16A Standard yield fluctuation ratio 16B Rate of change in yield 17A Upper limit of rate fluctuation ratio 17B Lower limit of rate fluctuation ratio 18A Graph showing finished product 18B Graph showing the posterior distribution of finished product 19A Graph showing the rate of change in earnings 19B Graph showing the posterior distribution of the rate of change 20 Computer 20A CPU 20B RAM 20C Non-volatile Memory 20D I / O 20E Bus 21 Communication unit 22 Input Unit 23 Display unit

Claims

1. a generation unit that generates a state space model consisting of a system model expressed by a first equation that defines the relationship between the completed form one period ago and the completed form at the specific time point for each of the work sites and for each of the work processes performed at each of the work sites, and a second equation that defines the relationship between the completed form one period ago and the completed form at the specific time point, with the state variables being the completed form at a specific time point for a work process line that represents a progress plan for the work process performed at each of the work sites, the completed form at a time point one period ago relative to the specific time point, and a yield fluctuation ratio that indicates the ratio of the planned number of workers required to perform the work process according to the work process line to the number of workers who actually performed the work process; and an observation model that defines the relationship between the state variables and the observation variables when the number of workers entering each of the work sites for each of the work sites in each period is used as an observation variable; a storage unit that stores the state space model generated by the generation unit in a storage device so that the state space model can be used to estimate the posterior distribution of the completed form and the yield variation rate of the process line for each of the work sites and each of the work processes performed at the work sites at a specified time point designated by a user; An information processing device comprising:

2. As the observation model, a model is used which represents a correspondence relationship between the number of workers entering the work site and the change in the completed form of the process line for each work site and each work process. The information processing device according to claim 1 .

3. a system model expressed by a first equation defining the relationship between the completed form one period ago and the completed form at the specific time point for each of the work processes performed at each of the work sites and for each of the work processes performed at each of the work sites, and a second equation defining the relationship between the completed form one period ago and the completed form at the specific time point, and a second equation defining the relationship between the completed form one period ago and the completed form at the specific time point, with the state variables being the completed form at a specific time point for each of the work processes performed at each of the work sites and the completed form at a specific time point for each of the work processes performed at each of the work sites, and an observation model expressing the relationship between the number of workers entering each of the work sites for each period as an observation variable, and an acquisition unit acquiring an observed number of workers entering the work site for each period up to a specified time point for the work site designated by a user; an estimation unit that applies a sequential Bayes filter using the observed number of people to the state space model acquired by the acquisition unit to estimate a posterior distribution of the completed form of the process line at the specified time point for each of the work processes performed at the designated work site and the yield variation ratio at the specified time point; an output unit that outputs a posterior distribution of the completed form of the process line at the specified time point for each of the work processes estimated by the estimation unit and the yield variation ratio at the specified time point; An information processing device comprising:

4. The output unit outputs an alarm when the progress of the work process at the specified time point represented by the posterior distribution of the completed form of the process line is behind the progress plan at the specified work site. The information processing device according to claim 3 .

5. The work process is a process related to at least one of construction work, demolition work, and civil engineering work.

5. The information processing device according to claim 1.

Images