Recognition device, recognition processing method, and program

Abstract

To easily reproduce a recognition environment used in past recognition processing.SOLUTION: A recognition device acquires recognition target information to be a target of recognition processing, acquires information output in the past recognition processing performed using a model and indicating the content of the past recognition processing, and performs the recognition processing using the model on the recognition target information according to the information indicating the content of the past recognition processing.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a recognition device, a recognition processing method, and a program, and relates to, for example, a deformation detection process for an image of a structure. [Background technology]

[0002] Recognition devices and recognition services are available that recognize targets, such as predetermined objects, from information such as images. These recognition devices use large amounts of training data to train models such as CNNs (Convolutional Neural Networks), and can recognize targets from input information using the trained models.

[0003] For example, Patent Document 1 discloses a technology for detecting cracks using a learning model from images captured by an unmanned aerial vehicle. In Patent Document 1, cracks are detected using two types of models: a specialized learning model that can identify specific types of cracks, and a non-specialized learning model that can identify multiple types of cracks other than the specific types of cracks. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 6807093 Summary of the Invention [Problem to be solved by the invention]

[0005] A user of a recognition device may want to compare the results of a recognition process performed on past information (e.g., a past image of a structure) with the results of a recognition process performed on current information (e.g., a current image of a structure). In such cases, it is desirable to maintain a recognition environment that can reproduce recognition results similar to those of past recognition processes and apply the environment to recognition processes on other information in order to compare the results. However, manually setting parameters for recognition processes so as to obtain recognition results similar to those of past recognition processes is cumbersome. In particular, in recognition devices, the learning model used for recognition processes may be updated. In such cases, using the same learning model as in the past requires the user to maintain multiple versions of the learning model and then select the learning model used in the past recognition processes from among the multiple versions, a cumbersome operation.

[0006] An object of the present invention is to make it possible to easily reproduce a recognition environment used in a past recognition process. [Means for solving the problem]

[0007] The recognition device according to the embodiment of the present invention has the following configuration: a first acquisition means for acquiring recognition target information to be subjected to recognition processing; a second acquisition means for acquiring information indicating the content of a past recognition process output during the past recognition process performed using the model; a recognition means for performing a recognition process using a model on the recognition target information in accordance with information indicating the content of the past recognition process; Equipped with. [Effects of the Invention]

[0008] The recognition environment used in the past recognition process can be easily reproduced. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing an example of the functional configuration of a recognition device according to an embodiment. [Figure 2]FIG. 1 is a diagram showing an example of the hardware configuration of a recognition device according to an embodiment. [Figure 3] FIG. 1 is a diagram showing an example of a processing flow of a recognition processing method according to an embodiment. [Figure 4] FIG. 10 is a diagram showing an example of a UI for a user to set model information. [Figure 5] FIG. 4 is a diagram for explaining the output and input of model information. [Figure 6] A diagram showing an example of the UI that is displayed when a hidden model is called. [Figure 7] FIG. 10 is a diagram showing an example of a model management table. [Figure 8] FIG. 3 is a diagram for explaining the operation of a switching unit 111. [Figure 9] FIG. 10 is a diagram showing an example of a processing flow for presenting a display target model. [Figure 10] FIG. 10 is a diagram showing an example of a lookup table showing model relationships. [Figure 11] FIG. 10 is a diagram showing an example of a UI that presents the results of recognition processing using each model. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. Note that the following embodiments do not limit the scope of the invention claimed. Although multiple features are described in the embodiments, not all of these multiple features are necessarily essential to the invention, and multiple features may be combined arbitrarily. Furthermore, in the accompanying drawings, the same reference numerals are used to designate the same or similar components, and redundant explanations will be omitted.

[0011] FIG. 1 shows the functional configuration of a recognition device according to an embodiment of the present invention. Information 102 to be recognized (recognition target information) is input to the recognition device 101, and a recognition result 103 obtained by performing the recognition process on the recognition target information 102 is output. The type of object of the recognition process is not particularly limited, and may be, for example, an image, text information, audio information, or signal information. The type of recognition process is also not particularly limited, and may include, for example, a process for recognizing a recognition target from an image, a process for recognizing a summary from text information, or a process for recognizing an abnormality from a knocking sound of a structure or a sensor signal from an instrument. In the following embodiment, a case will be described in which the recognition device 101 recognizes a defect, such as a crack, that has occurred in a structure in an image. The structure may be, for example, an infrastructure structure such as a tunnel or a bridge.

[0012] The recognition device 101 includes an information input unit (first acquisition unit) 104, a model information input unit (second acquisition unit) 110, and a recognition unit 105. The first acquisition unit 104 acquires recognition target information 102 to be subjected to recognition processing. The second acquisition unit 110 acquires information indicating the content of past recognition processing, which was output during past recognition processing performed using a model. The information indicating the content of recognition processing may include information identifying the model, such as a model ID, which is identification information for the model. The information indicating the content of recognition processing may also include processing parameters used in the recognition processing using the model. Furthermore, the information indicating the content of recognition processing may include information indicating the recognition target. Hereinafter, the information indicating the content of recognition processing will be referred to as model information, and the second acquisition unit 110 acquires model information 109.

[0013] Here, the information indicating the content of the past recognition processing may be associated with the result of the past recognition processing. For example, the information indicating the result of the past recognition processing may include information indicating the content of the past recognition processing. In this case, when a user inputs the result of the past recognition processing to the second acquisition unit 110, the second acquisition unit 110 can acquire the information indicating the content of the past recognition processing. Note that the recognition device 101 may be realized as a server or a cloud service. In this case, the first acquisition unit 104 and the second acquisition unit 110 can acquire the recognition target information 102 and the model information 109 via a network.

[0014] The recognition unit 105 performs recognition processing on the recognition target information using a model. Here, the recognition unit 105 can perform recognition processing according to information indicating the content of past recognition processing acquired by the second acquisition unit 110, as will be described later. For example, the recognition unit 105 can use a model used in past recognition processing for the recognition target information, and can also use processing parameters used in the past recognition processing. As will be described later, the recognition device 101 may include multiple recognition units 105, and in this case, each recognition unit 105 corresponds to one or more of the multiple models.

[0015] The recognition device 101 may further include a model management unit 106, a setting unit 107, an output unit 108, and a switching unit 111. The model management unit 106 manages one or more models used by the recognition unit 105 to perform recognition processing on recognition target information. The model management unit 106 may also select a model to be used for recognition processing from the models it manages in accordance with model information. For example, the model management unit 106 can select a model identified by the model information from among the models it manages.

[0016] The setting unit 107 can set model information according to user input. The output unit 108 can output the result of the recognition process performed by the recognition unit 105 on the recognition target information 102. The output unit 108 can also output information (model information) indicating the content of the recognition process performed by the recognition unit 105 in association with the result of the recognition process. The switching unit 111 switches the recognition unit 105 that performs the recognition process according to the model information.

[0017] The recognition device 101 according to this embodiment can be realized by a computer including a processor and a memory. FIG. 2 shows an example of the hardware configuration of the recognition device 101 according to one embodiment. A CPU (Central Processing Unit) 201 executes a control program for the recognition device 101. A ROM 202 stores the control program and the like. A RAM 203 provides a work area for the CPU 201. A network IF 204 is used to communicate with applications outside the recognition device 101. A storage device 205 is, for example, a hard disk, and stores data or programs. In this way, a processor such as the CPU 201 executes a program stored in a memory such as the ROM 202, the RAM 203, or the storage device 205, thereby realizing the functions of each unit shown in FIG. 1 and the like.

[0018] 3 shows a processing flow of a recognition processing method performed by a recognition device according to one embodiment of the present invention. In S301, the first acquisition unit 104 acquires an image, which is recognition target information. In S302, the setting unit 107 determines whether or not to use model information 109 indicating the contents of past recognition processing. If past model information is not to be used, the process proceeds to S303; if it is to be used, the process proceeds to S307.

[0019] In S303, the setting unit 107 sets model information. In this example, the setting unit 107 sets the model information based on user input. FIG. 4 shows a user interface (UI) for a user of the recognition device 101 to set model information. The UI shown in FIG. 4 includes a list 401 for selecting a recognition target and a list 402 for selecting a model to be used in recognition processing. The user can use the list 402 to select a model to be used in recognition processing from one or more models corresponding to the recognition target. Furthermore, the UI shown in FIG. 4 includes a slider 403 for specifying processing parameters to be used in recognition processing. The processing parameters may include, for example, a detection amount parameter that controls the amount of the recognition target detected in the recognition processing (e.g., making the recognition target more or less detectable). Furthermore, the processing parameters may include a noise reduction parameter that indicates the strength of noise reduction processing as preprocessing for the recognition target information. However, the types of processing parameters are not limited to these.

[0020] Based on user input to such a UI, the setting unit 107 can generate model information 404 indicating the details of the recognition process. The model information 404 shown in FIG. 4 indicates a model ID, which is identification information of the model, a recognition target, and processing parameters. In this way, in S303, the user can select a model or tune processing parameters to obtain better recognition processing results. However, the method of setting the model information by the setting unit 107 is not limited to this method. For example, the setting unit 107 may automatically set the model information based on attributes of the recognition target information (e.g., acquisition time zone, image brightness, GPS information, etc.) and the type of recognition target.

[0021] In S304, the recognition unit 105 performs recognition processing using a model on the recognition target information. The recognition unit 105 can perform recognition processing in accordance with the model information set by the setting unit 107 in S303. The recognition unit 105 can also perform recognition processing in accordance with model information indicating the content of past recognition processing acquired by the second acquisition unit 110 in S307. In this embodiment, the recognition unit 105 performs processing to recognize anomalies in the image.

[0022] In S305, the output unit 108 outputs the results of the recognition processing in S304. In this embodiment, the output unit 108 can superimpose the position of the recognized deformation, such as a crack, on the image that is the recognition target information, and output the superimposed image. The output unit 108 may also output vector data of the crack. However, as described above, the recognition processing performed by the recognition device according to the present invention is not particularly limited, and the output of the output unit 108 can take various forms.

[0023] In S306, the output unit 108 outputs model information indicating the content of the recognition processing performed in S304. For example, the output unit 108 can output the model information 404 in FIG. 4 as text or binary data in a predetermined format. The output unit 108 can output the model information in association with the result of the recognition processing. For example, information indicating the result of the recognition processing may include the model information. With this configuration, the user of the recognition device 101 can manage the model information used in the recognition processing along with the result of the recognition processing, and can know the model information used to obtain a specific recognition processing result. Note that the output unit 108 can output the result of the recognition processing and the model information to an external device via a network or the like in S305 and S306. Alternatively, the output unit 108 may store the result of the recognition processing and / or the model information in a storage device provided in the recognition device 101 in S305 and S306. In this case, the result of the recognition processing and / or the model information can be output to an external device at any time in accordance with a user request.

[0024] In S307, the second acquisition unit 110 acquires model information indicating the content of past recognition processing. This model information is the model information output by the output unit 108 in S306 during the past recognition processing. That is, as shown in FIG. 5, at a certain point in time, a user of the recognition device 101 inputs an image to the recognition device 101, and the recognition device 101 outputs a recognition result 501 for this image and model information 502. The recognition result 501 is obtained by superimposing the result of the recognition processing on the input image. By the second acquisition unit 110 acquiring the model information 502, the recognition device 101 can restore the settings used in the past recognition processing. Thereafter, in S304, the recognition unit 105 can perform recognition processing on the recognition target information in accordance with the model information acquired in S307.

[0025] On the other hand, in one embodiment, the model management unit 106 can distinguish between and manage a first model group and a second model group. For example, the model management unit 106 can select a model to be used for recognition processing from the first model group based on the model information set by the setting unit 107 (e.g., according to user input), regardless of the model information acquired by the second acquisition unit 110. On the other hand, the model management unit 106 can select a selectable model to be used for recognition processing from the second model group according to the model information acquired by the second acquisition unit 110. In one embodiment, the model management unit 106 can perform both a process of determining a model to be used for recognition processing from the first model group according to user input and a process of selecting a model identified according to the model information from the second model group. Here, the models managed by the model management unit 106 can include display models that are presented to the user in S303 and from which the user can select from a list, and hidden models that are not presented to the user in S303 and from which the user cannot select from a list. In this case, the first model group is the display target models, the second model group is a collection of the display target models and the non-display models, and the first model group is smaller than the second model group.

[0026] The provider of the recognition device 101 may update the model for purposes such as improving recognition performance. In this case, the model management unit 106 can manage the model before the update as a hidden model and the updated model as a display target model. In this way, a model that was previously a display target model can be managed as a hidden model when updated. Then, when the recognition device 101 is used for a new purpose or when a new user uses the recognition device 101, the hidden model is hidden from the user when setting model information in S303. With this configuration, a new display target model is usually used, thereby preventing the use of old models. Furthermore, since the models presented to the user are limited to new models and the number of presented models is reduced, usability is improved. On the other hand, when model information is acquired in S307 to reproduce a recognition environment used in the past, the recognition device 101 can use the hidden model indicated by the model information.

[0027] Therefore, in S308, the model management unit 106 determines whether the model indicated by the model information acquired in S307 is a display target model. The model management unit 106 can determine whether the model is a display target model or a non-display model according to the model ID included in the model information. If the model is a display target model, the process proceeds to S304, and the recognition unit 105 performs recognition processing on the recognition target information according to the model and processing parameters indicated by the model information acquired in S307. On the other hand, if the model is not a display target model, the process proceeds to S309.

[0028] In S309, the model management unit 106 calls the hidden model indicated by the model information acquired in S307. FIG. 6 shows the UI that is displayed when the second acquisition unit 110 acquires model information in S307 and the model management unit 106 calls the hidden model in S309. The model indicated by the model information acquired in S307 is "crackModel2021-1." However, as a result of updating the model, the display target models that can be selected for the recognition target "crack" at this time are "crackModel2023-1," "crackModel2023-2," and "crackModel2023-3." However, because "crackModel2021-1" has not been deleted from the model management unit 106, the model used in the past is called in FIG. 6 by inputting past model information. On the other hand, as shown in Fig. 4, in S303, three selectable display target models for the recognition target "crack" are displayed: "crackModel2023-1," "crackModel2023-2," and "crackModel2023-3." In this way, in S303, the hidden model "crackModel2021-1" is not displayed as an option. Note that in S309, the recognition target, model, and / or processing parameters may be further changed based on user input.

[0029] In S310, the switching unit 111 switches the recognition unit 105 according to the model to be used. Depending on the model used in the recognition process, different recognition algorithms, libraries, and OSSs may be used. Therefore, the recognition device 101 can use multiple recognition units 105. Here, each of the multiple recognition units 105 corresponds to one or more models managed by the model management unit 106. In other words, one recognition unit 105 can be associated with each model. The switching unit 111 can switch the recognition unit 105 so that the recognition unit 105 corresponding to the model ID indicated by the model information is used in the recognition process.

[0030] In this way, when the hidden model is called according to the model ID indicated by the model information and the recognition unit 105 corresponding to this model is determined, the process proceeds to S304, where the recognition unit 105 performs recognition processing according to the called model and the processing parameters indicated by the model information. The processing from S304 onwards is as described above.

[0031] By the above processing, model information indicating the contents of the recognition processing is output, and the settings of the past recognition processing, i.e., the recognition environment, can be reproduced according to the output model information. Note that it is not essential for the switching unit 111 to switch the recognition unit 105, and the same recognition unit 105 may perform recognition processing using various models.

[0032] (More about model management) The processes of S307 to S310 will be described in more detail. FIG. 7 shows a model management table used by the model management unit 106 to manage models. In the table of FIG. 7, a model ID is associated with a flag indicating whether the model is a display target model and the ID (recognition unit ID) of the recognition unit 105 that performs recognition processing using the model. The model management unit 106 also manages the entity of the model corresponding to the model ID. In this specification, the entity of the model refers to the structure and / or parameters that represent the model. For example, when a convolutional neural network is used as a model, the entity of the model can be represented by structural information indicating the size and number of each layer, and / or parameters such as filter coefficients used in convolution processing performed between layers. When the recognition unit 105 performs recognition processing in S305, the model management unit 106 can supply information representing the entity of the model corresponding to the model ID to the recognition unit 105, and the recognition unit 105 can construct a model using the supplied information.

[0033] When adding or updating a model used by the recognition device 101, the model ID and recognition unit ID of the new model can be added to the model management table. At this time, the model management unit 106 can set a flag indicating that only the latest model is a display target model to Yes, and set the flag of an older model to No. In this case, the older model cannot be selected when setting normal model information in S303.

[0034] When such a model management table is used, in S308 the model management unit 106 can use the model ID indicated in the model information and the table to determine whether the model indicated by the model ID is a model to be displayed. Furthermore, in S309, the model management unit refers to the table and calls the model corresponding to the model ID. Furthermore, in S310, the switching unit 111 refers to the table and switches the recognition unit 105 so as to use the recognition unit 105 having the recognition unit ID corresponding to the model ID. FIG. 8 is a diagram showing how the switching unit 111 switches the recognition unit 105 depending on the model. The recognition unit 105 may be a library within the recognition device 101, or may be a server or container that accepts recognition processing. Furthermore, each recognition unit 105 may be realized by a different cloud service or the like.

[0035] In the example of FIG. 8, each of the multiple recognition units 105 operates on a corresponding container. Each container executes recognition processing as a batch process. Container 802 is a container for the recognition unit 105 corresponding to the model to be displayed, and is normally running. In addition, the model management unit 106 manages snapshots (e.g., container images) of the containers corresponding to each of the multiple recognition units 105. Containers, which are the execution environments of applications such as the recognition unit 105, and snapshots that retain the states of the containers can be provided, for example, using a cloud service.

[0036] In this case, the switching unit 111 can switch the recognition unit 105 to be called based on the model ID. Specifically, the switching unit 111 can start the recognition unit 105 by using a snapshot of a container corresponding to the model selected by the model management unit 106 in accordance with the model information. In Fig. 8, the switching unit 111 starts the recognition unit 105 to be used for recognition processing on the container 803 by using a snapshot of a recognition unit having a recognition unit ID corresponding to the model ID.

[0037] In the example of Figure 8, the model management unit 106 manages the latest models "crackModel2023-001," "crackModel2023-002," and "crackModel2023-003" as models to be displayed. A recognition unit started on the container 802 using a snapshot having a recognition unit ID "Recognizer003" corresponding to these models is normally running. When model information is set based on user input in S303, and when it is determined in S308 that the model information indicates a model to be displayed, recognition processing is performed using this recognition unit.

[0038] On the other hand, if the model information indicates the model ID "crackModel2021-001" of the hidden model, the switching unit 111 refers to the model management table and determines that the recognition unit ID corresponding to this model ID is "Recognizer001". Based on this, the switching unit 111 uses the snapshot of the recognition unit ID "Recognizer001" to start up the recognition unit corresponding to this model on the container 803. Then, the switching unit 111 switches the recognition unit used for recognition processing from the recognition unit running on the container 802 to the recognition unit running on the container 803. Then, the recognition unit 803 started up on the container 803 performs recognition processing on the recognition target information in S305.

[0039] In this way, in the recognition device 101, the recognition unit 105 that performs recognition processing using a display object model may normally operate. Then, when performing recognition processing using a non-display model, the switching unit 111 activates the recognition unit 105 that performs recognition processing using a non-display model, and recognition processing can be performed by this recognition unit 105. In other words, the recognition unit 105 that uses a non-display model does not normally operate and is activated as needed, while the recognition unit 105 that uses a display object model may always operate.

[0040] In the above embodiment, the correspondence between the model and the recognition unit 105 is managed using the model management table shown in FIG. 7. However, the method of determining the recognition unit 105 corresponding to a model is not limited to this method. For example, the model information may indicate a recognition unit ID corresponding to the model to be used. Furthermore, when the setting unit 107 sets the model information in S303, it may acquire a user input to select the recognition unit 105 from one or more options, and determine the recognition unit 105 to be used based on this user input.

[0041] As described above, the recognition device according to this embodiment can reproduce previously used recognition processing settings based on model information output during past recognition processing. Furthermore, in the above-described embodiment, when a model is added or updated, a display target model and a previous version of a hidden model that is normally not selectable are managed separately. Even when the model information indicates a hidden model, it is possible to reproduce past settings using the hidden model when performing recognition processing according to model information previously output. According to this method, only new display target models are normally presented as options for the user to use, while older hidden models can be used when it is desired to reproduce past settings.

[0042] In the above-described embodiment, the model information output by the output unit 108 indicates a model ID, a recognition target, and processing parameters used in the recognition process, and the model management unit 106 manages the model corresponding to the model ID. Then, when the second acquisition unit 110 acquires the model information, the recognition process is performed using the model corresponding to the model ID indicated by the model information. On the other hand, the model information may also include information indicating the entity of the model as described above.

[0043] In this case, in response to the second acquisition unit 110 acquiring model information indicating the entity of the model, the recognition unit 105 can perform recognition processing on the recognition target information using a model according to the model information. For example, the output unit 108 can output a model information file having information indicating the entity of the model (e.g., structural information and / or parameters of the model) in a predetermined format. When the second acquisition unit 110 acquires this file, the model management unit 106 can restore the entity of the model based on the model information and pass it to the recognition unit 105. In this case, the second acquisition unit 110 can acquire model information indicating the entity of a model different from the model managed by the model management unit 106, and the recognition unit 105 can perform recognition processing using a model according to this model information.

[0044] According to this configuration, the model information output from the recognition device 101 contains information representing the entity of the model used in the recognition process, and when it is desired to reproduce the recognition environment, the model can be restored from the model information. Therefore, even if the recognition device 101 deletes an old model when updating a model, the past recognition environment can be reproduced. In this embodiment as well, the switching unit 111 can switch between the recognition units 105 that perform recognition processing using a model. In this case, information identifying the recognition unit corresponding to the model (for example, a recognition unit ID) can be held in the model management unit 106 or the model information.

[0045] (Presenting a different model to display based on model information) In the above-described embodiment, a past recognition environment is reproduced using a hidden model according to model information output in the past. On the other hand, if it is sufficient to reproduce a recognition environment that will yield roughly similar recognition results, the recognition device 101 may present a display target model that corresponds to the hidden model indicated by the model information. With this configuration, when the model information indicates a model before an update, the updated model can be presented to the user, thereby promoting replacement of the pre-update model with the updated model.

[0046] Such an embodiment can be realized by performing the processing shown in FIG. 9 when it is determined in S308 that the model information indicates a hidden model and that the model identified by the model information is not included in the display target models. That is, first, in S1004, the model management unit 106 presents a model selected from the display target models to the user. Here, the model management unit 106 can present a display target model corresponding to the hidden model indicated by the model information. For example, the model management unit 106 may manage information indicating the association between the hidden model and the display model. Based on such information, the model management unit 106 may determine a display target model to be presented to the user that corresponds to the hidden model identified by the model information. Specifically, updated models similar to the pre-update model are determined in advance, a lookup table indicating the relationship between them is created, and the updated display target model corresponding to the pre-update hidden model can be selected based on this lookup table. FIG. 10 shows an example of such a lookup table, in which a display target model ID is uniquely determined for each hidden model ID.

[0047] As another example, a display target model corresponding to the hidden model indicated by the model information may be determined based on the similarity of the recognition results. In this case, the recognition unit 105 can perform recognition processing on the recognition target information, a part of it, or other information using each of the hidden model indicated by the model information and the multiple display target models. Then, the display target model that gives the recognition result closest to the hidden model is determined to be the display target model corresponding to the hidden model.

[0048] In S1005, the recognition unit 105 performs a recognition process using the hidden model identified by the model information and a recognition process using the display target model presented to the user in S1004. The recognition unit 105 can perform these recognition processes on the recognition target information, a part of it, or other information. In addition, the model management unit 106 can present the results of the recognition processes thus obtained to the user.

[0049] Figure 11 shows an example of a UI that presents the model ID of the display target model corresponding to the hidden model indicated by the model information, and the results of the recognition process using this display target model. Here, the display target model (ID: "crackModel2023-3") corresponding to the hidden model (ID: "crackModel2021-1") indicated by the model information, and the recognition results using each model, are presented. Based on these recognition results, the user can decide whether or not to change the model.

[0050] In S1006, the model management unit 106 acquires a user instruction indicating whether or not the user agrees to the model change. For example, if the user agrees to the model change, the user can press the "Change Model" button on the UI shown in Fig. 11. If the user agrees to the model change, the process proceeds to S1007, and the model management unit 106 determines that the display target model presented in S1004 will be used for recognition processing.

[0051] The model management unit 106 may further delete the hidden model indicated by the model information in S1008. That is, in accordance with an instruction in S1007 from the user to whom the display target model was presented, the model management unit 106 may delete the model identified by the model information. As a result of such deletion, even if the model information acquired by the second acquisition unit 110 indicates this hidden model, the hidden model becomes unusable. Various methods for deleting a model are possible. For example, the model may be physically deleted from the model management unit 106, or the model may be logically deleted from the model management unit 106 so that it becomes unavailable. On the other hand, if the recognition device 101 provides services to multiple users or organizations, the model may be logically deleted only for users or organizations that agree to the change or deletion of the model so that these users or organizations cannot use the model. Then, the process proceeds to S304, and the recognition unit 105 performs recognition processing using the display target model presented in step S1004.

[0052] On the other hand, if the user does not agree to the model change, the process proceeds to S1009, where the model management unit 106 decides to use the hidden model indicated by the model information for the recognition process. Thereafter, the process proceeds to S304, where the recognition unit 105 performs the recognition process using this hidden model. Note that if the hidden model indicated by the model information is no longer supported, for example, because a predetermined time has passed since it became a hidden model, the model management unit 106 may issue a warning in S1009 and terminate the process.

[0053] According to this embodiment, a past recognition environment is reproduced based on model information output during past recognition processing, and after a model update, a model similar to the model before the update and the recognition result are presented, thereby making it possible to propose a recognition environment similar to the past recognition environment. With this configuration, it is possible to encourage the user to switch to a new model.

[0054] A recognition device according to another embodiment of the present invention includes a recognition unit 105 that performs a recognition process using a model on recognition target information to be subjected to the recognition process, and an output unit 108 that outputs information indicating the content of the recognition process performed by the recognition unit 105 in association with the result of the recognition process. By using the information indicating the content of the recognition process output by such a recognition device, it becomes possible to easily reproduce the recognition environment in future recognition processes. The configurations of the recognition unit 105 and the output unit 108 are the same as those of the above embodiment, and this recognition device may further include the above-mentioned functional units.

[0055] The above-described recognition device may be configured with multiple devices. For example, a recognition device according to an embodiment may be configured with multiple information processing devices connected via a network. In particular, when the recognition device 101 is a server that receives requests from user terminals, the function of the recognition unit 105 may be executed by another server. With such a configuration, even if the processing of the recognition unit 105 takes time, the processing of the recognition unit 105 can be performed asynchronously with the request. Furthermore, although the functions of the information processing device shown in FIG. 2 can be realized by a computer, some or all of the functions of the information processing device may be realized by dedicated hardware.

[0056] As described above, the recognition unit 105 can take various forms, such as a library in the recognition device 101, or a server or cloud service separate from the recognition device 101. The recognition unit snapshot 801 shown in FIG. 8 can also take various forms, such as a container image, a server image, a dynamic link library, a cloud service version, or a script, depending on the form of the recognition unit 105.

[0057] (Other Examples) The present invention can also be realized by supplying a program that realizes one or more functions of the above-described embodiments to a system or device via a network or a storage medium, and having one or more processors in the computer of the system or device read and execute the program. It can also be realized by a circuit (e.g., ASIC) that realizes one or more functions.

[0058] The invention is not limited to the above-described embodiments, and various changes and modifications can be made without departing from the spirit and scope of the invention. Accordingly, the following claims are appended to apprise the public of the scope of the invention. [Explanation of symbols]

[0059] 101: recognition device, 104: first acquisition unit, 105: recognition unit, 106: model management unit, 107: setting unit, 108: output unit, 110: second acquisition unit, 111: switching unit

Claims

1. a first acquisition means for acquiring recognition target information to be subjected to recognition processing; a second acquiring means for acquiring information indicating the content of a past recognition process outputted during the past recognition process performed using the model; a recognition means for performing a recognition process using a model on the recognition target information in accordance with information indicating the content of the past recognition process; A recognition device comprising:

2. 2. The recognition device according to claim 1, wherein the information indicating the content of the past recognition processing is associated with the result of the past recognition processing.

3. 3. The recognition device according to claim 1, further comprising output means for outputting information indicating the content of the recognition process performed by said recognition means in association with the result of said recognition process.

4. the information indicating the content of the past recognition processing includes model information for identifying a model for the recognition processing used in the past recognition processing, the recognition device further comprises a management means for managing models to be used in the recognition process and selecting a model to be used in the recognition process from the managed models in accordance with the model information; 4. The recognition device according to claim 1, wherein the recognition means performs recognition processing on the recognition target information using the model selected by the management means.

5. 5. The recognition device according to claim 4, wherein said management means selects a model identified by said model information from among the models being managed.

6. the management means is capable of performing both a process of selecting a model to be used in the recognition process from a first model group in accordance with a user input and a process of selecting a model identified by the model information from a second model group; 6. The recognition device according to claim 4, wherein the first model group is smaller than the second model group.

7. 7. The recognition device according to claim 6, wherein the management means, when the model identified by the model information is not included in the first model group, presents a model selected from the first model group to the user.

8. 8. The recognition device according to claim 7, wherein the management means presents to the user a result of the recognition process using the model identified by the model information and a result of the recognition process using the model presented to the user.

9. 9. The recognition device according to claim 8, wherein the management means deletes the model identified by the model information in accordance with an instruction from the user to whom a model selected from the first model group has been presented.

10. 10. The recognition device according to claim 7, wherein the management means manages information indicating an association between a model identified by the model information and a model selected from the first model group and presented to the user.

11. the recognition device includes a plurality of recognition means, each of which corresponds to one or more of the models it manages; 11. The recognition device according to claim 4, further comprising a switching unit for switching between recognition units that perform the recognition process in accordance with the model information.

12. 12. The recognition device according to claim 11, wherein each of the plurality of recognition means operates on a corresponding container.

13. 13. The recognition device according to claim 12, wherein the management means manages snapshots of containers corresponding to the plurality of recognition means, and the switching means starts the recognition means using the snapshot of a container corresponding to the model selected by the management means.

14. 14. The recognition device according to claim 4, wherein, in response to the second acquisition means acquiring the model information indicating an entity of a model different from the model being managed, the recognition means performs recognition processing on the recognition target information using the different model according to the model information.

15. the information indicating the content of the past recognition processing further indicates processing parameters used in the past recognition processing; 15. The recognition device according to claim 1, wherein the recognition means uses processing parameters used in the past recognition process for the recognition target information.

16. 16. The recognition device according to claim 1, wherein an object of the recognition process is an image, and the recognition process is a process for recognizing the recognition object in the image.

17. 17. The recognition device according to claim 16, wherein the recognition target is a deformation occurring in a structure in the image.

18. a recognition means for performing a recognition process using a model on recognition target information that is the subject of the recognition process; an output means for outputting information indicating the content of the recognition processing performed by the recognition means in association with the result of the recognition processing; A recognition device comprising:

19. A recognition processing method performed by a recognition device, a step of acquiring recognition target information to be subjected to recognition processing; acquiring information indicating the content of a past recognition process outputted during the past recognition process performed using the model; performing a recognition process using a model on the recognition target information in accordance with information indicating the content of the past recognition process; A recognition processing method comprising:

20. A program for causing a computer to function as the recognition device according to any one of claims 1 to 18.

Images