Development support system and development support method

Abstract

To improve the efficiency of development work by easily judging whether developed recognition processing can be reused or not.SOLUTION: The development support system stores a first configuration file that defines preprocessing on sensor data by a sensor to be adopted, stores a second configuration file that defines a precondition of recognition processing of a predetermined event based on sensor data by another sensor, refers to the preprocessing from the first configuration file, refers to the precondition from the second configuration file, and determines whether content of the preprocessing satisfies the precondition, thereby specifying whether the sensor or the like to be adopted and the recognition processing are applicable to each other.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention generally relates to technology for a development support system and a development support method, and more specifically to technology for easily determining whether or not a developed recognition process can be reused, thereby improving the efficiency of development work. [Background technology]

[0002] At various manufacturing and maintenance sites, there is a need to improve the efficiency of verification and management of worker work and inspections. To address this need, systems have been proposed that automatically recognize the status of worker work. However, there are many cases where the recognition target itself or the recognition device (e.g., glove-type sensors or workwear-type sensors) needs to be changed or modified, or where a new system needs to be developed by appropriately combining existing recognition devices. Therefore, there has been a demand for technology that can flexibly accommodate the development and specification changes of the above systems.

[0003] A prior art in the above field has been proposed as shown in Patent Document 1. Patent Document 1 discloses a technology relating to an efficient method for enabling real-time analysis of sensor data acquired by virtually any type of sensor device using a set of services from a platform, and for facilitating the acquisition, storage, and analysis of sensor data.

[0004] The above technology relates to a system for providing an infrastructure platform in a smart space environment that facilitates rapid and easy development, deployment, and management of sensor-driven applications, the system comprising: a) a set of infrastructure services integrated into the infrastructure platform configured to acquire, store, and analyze sensor data received from a plurality of sensor devices; b) a plurality of application program interfaces (APIs), programming language-specific libraries, and software development kits (SDKs) provided to application developers who use the infrastructure services for developing, testing, deploying, and managing a plurality of sensor-based applications; c) a presentation module including a plurality of web-based portals configured to monitor, manage, and control the infrastructure services, developed applications, and software and hardware infrastructure; and d) a set of infrastructure applications configured to send the sensor data to the platform or receive the sensor data from the platform. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Special Publication No. 2014-534487 Summary of the Invention [Problem to be solved by the invention]

[0006] The specific tasks that can be recognized by the above system are diverse, such as connecting connectors or operating an electric screwdriver. Therefore, it is necessary to develop a recognition process for each task that can be recognized by the system. On the other hand, in order to speed up and streamline the development of such recognition processes, it is desirable to reuse recognition processes that have been developed in the past. Here, "reuse" refers to, for example, replacing the sensor used for recognition with another one, or using the same sensor to recognize a different task.

[0007] On the other hand, in conventional technology, by separating the sensor data collection process and the task extraction process, it is possible to reuse the developed process when changing sensors. However, such reuse requires confirmation of prerequisites, such as at what stage prerequisites such as calibration and filtering should be performed, or whether they are even necessary. The conventional technology does not propose a technique for confirming such prerequisites, and the current situation is that each process relies on the tacit knowledge of the developers, as before. In such cases, even if the conventional technology is adopted, inconsistencies will occur between the sensor data collection process and the task extraction process in terms of the prerequisites, making it difficult to obtain good recognition results.

[0008] Therefore, the present invention has been made in consideration of the above-mentioned problems, and aims to provide a technology that can easily determine whether or not a developed recognition process can be reused, thereby improving the efficiency of development work. [Means for solving the problem]

[0009] A development support system according to one embodiment of the present invention stores a first configuration file that specifies preprocessing of sensor data by a sensor to be adopted, stores a second configuration file that specifies prerequisites for recognition processing of a specified event based on sensor data by another sensor, references the preprocessing from the first configuration file, references the prerequisites from the second configuration file, and determines whether the contents of the preprocessing satisfy the prerequisites, thereby identifying whether the sensor, etc. to be adopted and the recognition processing are mutually applicable. [Effects of the Invention]

[0010] According to the present invention, it is possible to easily determine whether or not a recognition process that has already been developed can be reused, thereby improving the efficiency of development work. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a diagram illustrating an example of the configuration of a development support system according to an embodiment of the present invention. [Figure 2]FIG. 4 is a diagram illustrating an example of the configuration of a sensor data management table according to the present embodiment. [Figure 3] FIG. 4 is a diagram illustrating an example of the configuration of a work data management table according to the present embodiment. [Figure 4] FIG. 2 is a diagram illustrating an example of the configuration of a compatibility management table according to the present embodiment. [Figure 5] FIG. 2 is a diagram showing an example of a flow (sensor data collection flow) of a development support method according to the present embodiment. [Figure 6] FIG. 10 is a diagram showing an example of a screen (sensor data collection setting screen) in the present embodiment. [Figure 7] FIG. 4 is a diagram illustrating an example of a sensor data collection setting file according to the present embodiment. [Figure 8] FIG. 2 is a diagram showing an example of a flow (work data extraction flow) of a development support method according to the present embodiment. [Figure 9] FIG. 2 is a diagram showing an example of a flow (main flow of conformance determination) of a development support method according to the present embodiment. [Figure 10] FIG. 10 is a diagram showing an example of a screen (task data extraction setting screen) in this embodiment. [Figure 11] FIG. 10 is a diagram illustrating an example of a task data extraction setting file according to the present embodiment. [Figure 12] FIG. 10 is a diagram showing an example of a flow (subflow of conformance determination) of a development support method according to the present embodiment. [Figure 13] FIG. 10 is a diagram showing an example of a screen (suitability determination execution screen) in this embodiment. [Figure 14] FIG. 10 is a diagram showing an example of a screen (suitability determination result display screen) in this embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0012] In the following description, a communication device may be one or more communication interface devices, which may be one or more homogeneous communication interface devices (e.g., one or more NICs (Network Interface Cards)) or two or more heterogeneous communication interface devices (e.g., a NIC and an HBA (Host Bus Adapter)).

[0013] In the following description, a "memory" refers to one or more memory devices, which are an example of one or more storage devices. At least one of the memory devices may be a volatile memory device or a non-volatile memory device.

[0014] In the following description, a "storage device" may refer to one or more persistent storage devices, which are an example of one or more storage devices. A persistent storage device may typically be a non-volatile storage device, specifically, for example, a hard disk drive (HDD), a solid state drive (SSD), or a non-volatile memory express (NVMe) drive.

[0015] In the following description, a "CPU" refers to a computing device and may be one or more processor devices. The at least one processor device may typically be a microprocessor device such as a CPU (Central Processing Unit), but may also be another type of processor device such as a GPU (Graphics Processing Unit). The at least one processor device may be a single-core or multi-core. The at least one processor device may also be a processor core. The at least one processor device may also be a processor device in a broader sense, such as a hardware circuit that performs part or all of the processing (e.g., an FPGA (Field-Programmable Gate Array), a CPLD (Complex Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit)).

[0016] In the following description, information that provides an output in response to an input may be described using expressions such as "xxx table" or "xxx database." However, this information may be data of any structure (for example, structured data or unstructured data), or may be a learning model such as a neural network, genetic algorithm, or random forest that generates an output in response to an input. Therefore, "xxx table" or "xxx database" may be referred to as "xxx information." In the following description, the structure of each database or table is an example, and one database or table may be divided into two or more databases or tables, or all or part of two or more databases or tables may be one database or table.

[0017] In the following description, processing may be described using a "program" as the subject. However, since a program is executed by a CPU to perform a predetermined process using a storage device and / or an interface device, etc., as appropriate, the subject of the process may also be the CPU (or a device such as a controller having a processor). A program may be installed in a device such as a computer from a program source. The program source may be, for example, a program distribution server or a computer-readable (e.g., non-transitory) recording medium. In the following description, two or more programs may be realized as one program, or one program may be realized as two or more programs.

[0018] In addition, in the following description, when describing elements of the same type without distinguishing between them, common parts of the reference symbols may be used, and when describing elements of the same type with distinction between them, reference symbols or element identifiers may be used. <About the configuration of the development support system>

[0019] FIG. 1 is a diagram showing an example of the configuration of a development support system 100 according to one embodiment of the present invention.

[0020] The development support system 100 of this embodiment is a system that makes it easy to determine whether or not a recognition process that has already been developed can be reused, thereby improving the efficiency of development work.It is possible to use an already developed sensor data collection process (sensor data collection process developed for a certain sensor or its preprocessing) or the sensor itself in combination with recognition processing for sensor data from another sensor; in other words, it is configured to determine whether or not it can be adopted and present this to developers, etc.

[0021] The development support system 100 may be communicably connected to a terminal of a developer or the like via an appropriate network such as the Internet. This terminal is a computer that connects to the development support system 100 and acquires and outputs the result of the adoption determination. Each developer uses the terminal or the GUI (Graphical User Interface) of the development support system 100 to input the sensors that the developer is responsible for or has knowledge of, the details of preprocessing of the sensor data, or the prerequisites for recognition processing using such sensor data, and provides the information to the development support system 100.

[0022] An example of an environment assumed in this embodiment is a situation in which workers at a manufacturing site wear glove-type sensors or clothing-type sensors, and the development and enhancement of a system that automatically recognizes work content, etc. based on sensor data observed by the sensors on the movements of the workers is to be made more efficient. Of course, there is no intention to limit the application of the development support system 100 in this embodiment to such work recognition, and the system can be widely applied to systems that automatically recognize various other events.

[0023] The above-mentioned events may include, for example, specific phenomena caused by the operation of various devices and equipment in factories, laboratory facilities, etc. (for example, deterioration, defects, or failures in manufacturing plants), or natural phenomena identified by the characteristics of values ​​observed by specified observation devices (for example, weather, temperature, humidity, the occurrence of typhoons, etc.), but these are also examples. In any case, the present invention can be applied to any event that can be recognized by applying sensor data obtained by a sensor to a specified algorithm.

[0024] The task recognition process in this embodiment roughly includes a sensor data collection process and a task data extraction process. The sensor data collection process exists for each sensor. The task data extraction process exists for each extraction target (recognition target). These processes are developed and saved separately. In particular, there are many cases where the frequency of sensor replacement is not low and / or the frequency of developers changing due to retirement or transfer is not low, which gives rise to the above-mentioned background.

[0025] In particular, the development of work data extraction processing depends on whether its preprocessing is performed in conjunction with the work data extraction processing or in the preceding sensor data collection processing. However, due to differences in developers as mentioned above, it is often unclear whether existing sensor data collection processing or work data extraction processing can be adopted (repurposed) as is. Therefore, if the sensor data collection processing and work data extraction processing are configured in a combination that does not include the necessary preprocessing, the result will be incorrect recognition. In other words, if each of the above processes is developed by a different person and executed for each sensor, it becomes difficult to manage the consistency and necessity of the processes and to utilize them in the future. On the other hand, from another perspective, if sensor data collection processing and work data extraction can be reused, the efficiency of development work can be improved.

[0026] Therefore, in the development support system 100 of this embodiment, the setting file for the sensor data collection process records whether or not preprocessing is performed, and the setting file for the work data extraction process records the conditions (prerequisites) regarding whether or not preprocessing is performed, and these are compared and collated during subsequent development work. By performing this operation, when repurposing existing processes (sensor data collection process, work data extraction process), it is possible to determine whether they can be combined, i.e., whether or not they can be diverted, by determining whether they are consistent.

[0027] The development support system 100 shown in FIG. 1 comprises an external storage device 103 consisting of a nonvolatile storage device such as a hard disk drive or an embedded multimedia card, memory 102 consisting of a volatile storage device such as a RAM (Random Access Memory), a CPU 101 that loads programs stored in the external storage device 103 into memory 102 to perform overall control of the system itself and also performs various judgments, calculations, and control processing, a GUI 104 for connecting to input devices such as a keyboard and output devices such as a display, and sensors 105.

[0028] The functions implemented in the memory 102 of the development support system 100 include a compatibility determination unit 1025, an operation data extraction unit 1026, and a sensor data collection unit 1027. Details of each of these functions will be described later. Data held in the external storage device 103 include an operation data extraction processing setting file 1031 and a sensor data collection processing setting file 1032. The specific configurations of these setting files will be described later. Data held in the memory 102 include a sensor data management table 1021, an operation data management table 1022, and a compatibility management table 1023. The specific configurations of these tables will also be described later.

[0029] The screens generated and output by the GUI 104 include a sensor data collection process setting screen 1041, an operation data extraction process setting screen 1042, a compatibility determination execution screen 1043, and a compatibility determination result display screen 1044. Specific examples of these screens will be described later.

[0030] Note that some of the processing performed by CPU 101 when it executes a program may be executed by another arithmetic device (for example, hardware such as an ASIC or FPGA). Memory 102 may also be a ROM (Read Only Memory), which is a non-volatile storage element. ROM stores unchanging programs (for example, BIOS). RAM is a high-speed, volatile storage element such as DRAM (Dynamic Random Access Memory), and temporarily stores programs executed by CPU 101 and data used when the programs are executed.

[0031] Alternatively, a terminal connected to the development support system 100 via the network 120 may provide the GUI 104. The program executed by the CPU 101 is provided to the development support system 100 via removable media (CD-ROM, flash memory, etc.) or an appropriate network, and is stored in a non-volatile external storage device 103, which is a non-transitory storage medium. Therefore, the development support system 100 reads data from the removable media via a predetermined I / O interface.

[0032] The development support system 100 is a computer system configured on one physical computer, or on multiple logically or physically configured computers, and may operate on a virtual computer built on multiple physical computer resources. The development support system 100 is preferably configured on the cloud, but may also be on-premise configured on a specific computer (hardware).

[0033] The network connecting the development support system 100 and the developer's terminal (not shown) may be, but is not limited to, the Internet, a LAN (Local Area Network), a WAN (Wide Area Network), or a mobile phone network. Specifically, the terminals connected to such networks are implemented as PCs (Personal Computers), tablet terminals, smartphones, and the like.

[0034] Note that data exchange between the development support system 100 and the above terminals may be performed according to, for example, an API (Application Programming Interface) protocol. In this case, it is assumed that each device is pre-implemented with the functions and configurations for executing each process of API requests and responses.

[0035] The sensor 105 is a sensor, such as a glove-type sensor or a workwear-type sensor, from which sensor data is collected by the development support system 100. The sensor data observed by the sensor 105 is acquired by the sensor data collection unit 1027 and stored in the sensor data management table 1021.

[0036] Next, the configuration of each table held by the development support system 100 in this embodiment will be described with reference to FIGS.

[0037] FIG. 2 is a diagram showing an example of the configuration of the sensor data management table 1021 in this embodiment.

[0038] The sensor data management table 1021 is a table that stores sensor data observed by each sensor that is managed by the development support system 100 of this embodiment. It is configured as a collection of records that include the observation time, sensor name, and value.

[0039] FIG. 3 is a diagram showing an example of the configuration of the work data management table 1022 in this embodiment.

[0040] The work data management table 1022 is a table that stores the work names and details recognized based on sensor data for the work managed by the development support system 100 of this embodiment. It is configured as a collection of records that include the recognition time, work name, and value. For example, if the value is "0," it means that the performance of the work name has not been identified, and if the value is "1," it means that the performance of the work name has been identified.

[0041] FIG. 4 is a diagram showing an example of the configuration of the compatibility management table 1023 in this embodiment.

[0042] The compatibility management table 1023 is a table that stores information about the suitability of combining sensor data collection processing and work data extraction processing, as determined by the development support system 100 of this embodiment. It is made up of a collection of records that include sensor data collection processing, work data extraction processing, prerequisites, and individual compatibility.

[0043] Of these, "preconditions" specifies preprocessing (e.g., calibration) that must be performed in the sensor data collection process before the task data extraction process is performed. "Individual suitability" stores the results of the development support system 100's determination of the suitability of the combination of the sensor data collection process and the task data extraction process. <Development support flow: Sensor data collection>

[0044] Next, the development support method according to this embodiment will be described with reference to the drawings.

[0045] FIG. 5 is a diagram showing an example of a flow (sensor data collection flow) of the development support method according to this embodiment.

[0046] The sensor data collection unit 1027 in the development support system 100 reads out the pre-processing contents from the sensor data collection process setting file 1032 (S1).

[0047] This sensor data collection processing setting file 1032 is a file of data acquired when the development support system 100 displays a sensor data collection processing setting screen 1041 shown in Fig. 6 on a display or a terminal of a developer. As shown in Fig. 6, this sensor data collection processing setting screen 1041 includes a sensor data collection processing name input field 10411 and a preprocessing content input field 10412.

[0048] Of these, the sensor data collection process name input section 10411 has input fields for the process name and the sensor name. Furthermore, the preprocessing content input section 10412 has input fields for the preprocessing and its value. The developer inputs values ​​into these input fields for the sensor for which preprocessing is to be set, the process name, and whether or not the preprocessing is to be executed (necessary). An example of the sensor data collection process setting file 1032 generated from the values ​​received via these input fields is shown in FIG. 7. The developer inputs information for each sensor in this way to generate the sensor data collection process setting file 1032.

[0049] In this embodiment, it is assumed that a glove-type sensor with pressure sensors attached to the fingertips of a worker is used to detect the work of a person using a tool such as an electric screwdriver. Therefore, when the contents of the preprocessing are read, the target is a record related to the glove-type sensor (one for which a corresponding value is set in the "sensor name" field of the sensor data collection process name input field 10411), and the values ​​to be read are the values ​​in the "preprocessing" field and the "value" field of the preprocessing content input field 10412.

[0050] Next, the sensor data collection unit 1027 connects to the sensor 105 and acquires the sensor data (S2). The sensor 105 from which sensor data is acquired is the sensor that is the target of preprocessing read out in S1 above. The sensor data collection unit 1027 also performs preprocessing on the sensor data (S3). This preprocessing is the content of preprocessing such as calibration and filtering read out in the processing of S1 above. For example, if the sensor data is pressure data, and the value exceeds a threshold, the value received from the pressure sensor may be converted into a signal value proportional to the amount of force applied to the fingertip in preparation for extraction processing, which is a processing in which a predetermined task is deemed to have been performed when the value exceeds the threshold, in order to facilitate adjustment of the threshold.

[0051] The sensor data collection unit 1027 also writes the sensor data that has been preprocessed up to this point into the sensor data management table 1021 (S4), and ends the flow. By repeating the process of S4 for each sensor 105, the sensor data management table 1021 already illustrated in FIG. 2 is generated. <Development support flow: Work data extraction>

[0052] Next, the operation data extraction process of the development support method according to this embodiment will be described with reference to the drawings.

[0053] FIG. 8 is a diagram showing an example of a flow (work data extraction flow) of the development support method according to this embodiment.

[0054] The work data extraction unit 1026 in the development support system 100 reads sensor data from the sensor data management table 1021 (S10). The sensor data to be read here can be assumed to be, for example, data specified by the developer via the terminal or the like.

[0055] Next, the task data extraction unit 1026 extracts task data from the sensor data read in S10 (S11). This extraction corresponds to a process of identifying whether a task has been performed and its content by applying the sensor data to a specific algorithm, i.e., a task content recognition program or recognition model. The recognition program can be a program that uses a regression equation defined by statistical processing such as multiple regression analysis as a recognition engine to output recognition results regarding the relationship between the sensor data and the task content. The recognition model can be a learning model generated by deep learning based on the task content that was actually being performed when certain sensor data was observed, i.e., training data, regarding the relationship between the sensor data and the task content.

[0056] The task data extraction unit 1026 then writes the task data obtained in S11, i.e., information on the task content, etc., to the task data management table 1022 (S12), and the flow ends. The task data extraction unit 1026 repeatedly executes the above process, thereby generating the task data management table 1022 shown in Figure 3. <Development support method: conformance assessment>

[0057] Next, the conformance determination process in the development support method of this embodiment will be described.

[0058] FIG. 9 is a diagram showing an example of a flow of determining conformance in the development support method of this embodiment.

[0059] The compatibility determination unit 1025 in the development support system 100 reads out the contents of pre-processing from the sensor data collection processing setting file 1032 (S20). In this case, the contents read out may be those related to randomly selected sensors, or those specified by the developer on the compatibility determination execution screen 1043 (see FIG. 13).

[0060] 13 includes a sensor data collection process name selection section 10431 and a work data extraction process name selection section 10432. The developer specifies the sensor 105 (and its sensor data) from which sensor data is to be collected in the sensor data collection process name selection section 10431. The developer also specifies the name of the work from which work data is to be extracted in the work data extraction process name selection section 10432. Therefore, the compatibility determination section 1025 receives input on this compatibility determination execution screen 1043 and presses the confirm button, which triggers the start of this flow.

[0061] The compatibility determination unit 1025 also reads prerequisites from the task data extraction process setting file 1031 (S21). This task data extraction process setting file is generated by the development support system 100 when it displays a task data extraction process setting screen 1042 shown in FIG. 10 and receives input from a developer or the like. In the example of FIG. 10, the task data extraction process setting screen 1042 includes a task data extraction process name input section 10421 and a prerequisites input section 10422. In other words, the developer inputs and sets, on the task data extraction process setting screen 1042, the prerequisites and their presence or absence for the sensor data used for automatic recognition, which are necessary when automatically recognizing whether or not a task has been performed and its contents. As a result of receiving such input, the task data extraction process setting file 1031 shown in FIG. 11 is generated.

[0062] The compatibility determination unit 1025 also determines whether the pre-processing content satisfies the prerequisites (S22). Details of this determination will be described later with reference to Fig. 12. The compatibility determination unit 1025 also stores the result of this determination in the compatibility management table 1023 (S23), and ends this flow.

[0063] Here, the details of the step of determining whether the pre-processing content satisfies the prerequisites (S22) in the above-described compatibility determination flow will be described with reference to Fig. 12. The compatibility determination unit 1025 of this embodiment first determines whether or not the prerequisites exist (S30). If the result of this determination is that there are no prerequisites (S30: NO), the compatibility determination unit 1025 determines that the pre-processing content satisfies the prerequisites (S31) and ends this flow.

[0064] On the other hand, if the result of the above determination is that a prerequisite exists (S30: YES), the compatibility determination unit 1025 determines whether the prerequisite matches the preprocessing content (S32). If the result of this determination is that the prerequisite does not match the preprocessing content (S32: NO), the compatibility determination unit 1025 determines that the preprocessing content does not satisfy the prerequisite (S33), and ends the flow.

[0065] On the other hand, if the result of the above determination is that the preconditions and preprocessing contents match (S32: YES), the compatibility determination unit 1025 determines that the preprocessing contents satisfy the preconditions (S34) and ends the flow. The results of the processes in this flow (S31, S33, S34) are to be stored in the compatibility management table 1023 in S23 of the flow in Figure 9.

[0066] The final results of the above flow are set and output by the compatibility determination unit 1025 on a compatibility determination result display screen 1044, and presented to the developer. This compatibility determination result display screen 1044 includes a determination result display section 10441 and a detailed result display section 10442. Of these, the determination result display section 10441 indicates whether or not there is compatibility, with "OK" for compatibility and "NG" for incompatibility. The detailed result display section 10442 shows a breakdown of the determination results shown in the determination result display section 10441, and in the example of FIG. 14, it shows that although the pre-processing "doCalibration" is required, it does not match the prerequisites for the task data extraction process specified on the compatibility determination execution screen 1043.

[0067] As described above, the development support system of this embodiment makes it possible to easily determine whether or not a developed recognition process can be reused, and makes it possible to improve the efficiency of development when the developed recognition process can be reused.

[0068] The present invention is not limited to the above-described embodiments, and includes various modifications and equivalent configurations within the spirit of the appended claims. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to configurations including all of the described configurations. Furthermore, part of the configuration of one embodiment may be replaced with the configuration of another embodiment. Furthermore, the configuration of another embodiment may be added to the configuration of one embodiment. Furthermore, part of the configuration of each embodiment may be added, deleted, or replaced with other configurations.

[0069] Furthermore, the aforementioned configurations, functions, processing units, processing means, etc. may be realized in part or in whole in hardware, for example by designing them as integrated circuits, or may be realized in software by having a processor interpret and execute a program that realizes each function.

[0070] Information such as programs, tables, and files that realize each function can be stored in a storage device such as a memory, a hard disk, or an SSD (Solid State Drive), or in a recording medium such as an IC card, an SD card, or a DVD.

[0071] In addition, the control lines and information lines shown are those that are considered necessary for explanation, and do not necessarily represent all the control lines and information lines that are necessary for implementation. In reality, it can be assumed that almost all components are interconnected.

[0072] The above various explanations can be summarized as follows: The following summary may include supplementary explanations and explanations of variations of the above explanations.

[0073] In the development support system of this embodiment, when making the determination, the computing device may compare information regarding the preprocessing referenced in the first setting file with information regarding the prerequisites referenced in the second setting file, and determine whether the preprocessing required prior to executing the recognition process is consistent with the necessity and content of the preprocessing referenced in the first setting file.

[0074] This makes it possible to accurately determine whether a sensor can be used for recognition processing, based on the presence and content of preprocessing that should be performed on the target data. This in turn makes it easier to determine whether a previously developed recognition process can be reused, improving the efficiency of development work.

[0075] Furthermore, in the development support system of this embodiment, the storage device may include, in the first setting file, information regarding the pre-processing, information regarding the necessity and content of at least one of calibration, filtering, and normalization, and in the second setting file, information regarding the prerequisites, information regarding the necessity and content of at least one of calibration, filtering, and normalization, and in making the determination, the arithmetic device may compare the necessity and content of at least one of calibration, filtering, and normalization, which is the information regarding the pre-processing referenced in the first setting file, with the necessity and content of at least one of calibration, filtering, and normalization, which is the information regarding the prerequisites referenced in the second setting file, and determine whether the pre-processing required prior to execution of the recognition process is consistent with the necessity and content of at least one of the calibration, filtering, and normalization, which is referenced in the first setting file.

[0076] This makes it possible to efficiently obtain a more accurate judgment result on the suitability of a planned sensor from the perspective of the presence or absence and content of more specific processing such as calibration and filtering as pre-processing that should be performed on target data during recognition processing.Furthermore, it becomes possible to more easily determine whether or not a developed recognition process can be reused, thereby improving the efficiency of development work. [Explanation of symbols]

[0077] 100: Development support system, 101: CPU (processing unit), 102: Memory, 1021: Sensor data management table, 1022: Work data management table, 1023: Conformity management table, 1025: Conformity determination unit, 1026: Work data extraction unit, 1027: Sensor data collection unit, 103: External storage device

Claims

1. a storage device storing a first setting file that specifies information regarding preprocessing of sensor data by a sensor to be adopted, and a second setting file that specifies information regarding prerequisites for recognition processing of a predetermined event based on sensor data by a sensor different from the first setting file; a computing device that executes a process of referring to information on the pre-processing from the first setting file, a process of referring to information on the prerequisites from the second setting file, and a process of determining whether the content of the pre-processing satisfies the prerequisites, thereby specifying whether the collection process of the sensor to be adopted or the sensor data and the recognition process are mutually applicable; A development support system equipped with:

2. The computing device In making the determination, information relating to the preprocessing referred to in the first setting file is compared with information relating to the prerequisites referred to in the second setting file, and it is determined whether the preprocessing required prior to the execution of the recognition process conforms to the necessity and content of the preprocessing referred to in the first setting file. The development support system according to claim 1 .

3. The storage device includes: In the first setting file, the information regarding the preprocessing includes information regarding the necessity and content of at least one of calibration, filtering, and normalization, and in the second setting file, the information regarding the prerequisites includes information regarding the necessity and content of at least one of calibration, filtering, and normalization, The computing device In making the determination, the information on the pre-processing referenced in the first setting file, which is the information on the pre-processing, including the necessity and content of at least one of calibration, filtering, and normalization, is compared with the information on the prerequisites referenced in the second setting file, which is the information on the prerequisites, including the necessity and content of at least one of calibration, filtering, and normalization, and it is determined whether the pre-processing required prior to the execution of the recognition process conforms to the necessity and content of at least one of the calibration, filtering, and normalization referenced in the first setting file. The development support system according to claim 2 .

4. A first setting file that specifies information regarding preprocessing of sensor data by a sensor to be adopted, and a second setting file that specifies information regarding prerequisites for recognition processing of a predetermined event based on sensor data by another sensor different from the sensor are stored in a storage device; executes a process of referencing information on the pre-processing from the first setting file, a process of referencing information on the prerequisites from the second setting file, and a process of determining whether the content of the pre-processing satisfies the prerequisites, thereby identifying whether the sensor to be adopted or the collection process of the sensor data and the recognition process are mutually applicable; A development support method that uses computers to do this.

Images