Information processing system, information processing method, and program

Abstract

The present disclosure pertains to an information processing system, an information processing method, and a program that enable the processing of tasks to be carried out by processing that is creative and has an increased degree of freedom. A task is processed on the basis of information pertaining to the task, and then, on the basis of the evaluation of the processing results, the task is further processed on the basis of information with low relevance to the task. The present invention can be applied to task processing devices.

Description

[Technical Field]

[0001] The present disclosure relates to an information processing system, an information processing method, and a program, and more particularly to an information processing system, an information processing method, and a program that enable creative and highly flexible task processing. [Background technology]

[0002] Technology that uses machine learning to present task processing is becoming more widespread.

[0003] The technology required to present the processing of this task is not just a standardized, generalized presentation of processing, but also a creative, flexible presentation of processing.

[0004] Therefore, for example, a technology has been proposed in which success cases and failure cases for task processing are compiled into a database, the success cases and failure cases are compared, and information on the differences is presented (see Patent Document 1).

[0005] Furthermore, a technology has been proposed for processing a diagnosis-related task, which presents both a diagnosis name that is an inference result based on the user's information and a diagnosis name that is a negative result of the inference result (see Patent Document 2).

[0006] In either case, it can be used as a hint for thinking about creative and flexible task processing. [Prior art documents] [Patent documents]

[0007] [Patent Document 1] Japanese Patent Application Publication No. 9-6619 [Patent Document 2] Japanese Patent Application Laid-Open No. 2013-165780 Summary of the Invention [Problem to be solved by the invention]

[0008] However, while both Patent Documents 1 and 2 provide hints for considering creative and highly flexible task processing, they do not actually realize specific processing.

[0009] The present disclosure has been made in light of such circumstances, and in particular, is directed to realizing creative and highly flexible task processing. [Means for solving the problem]

[0010] An information processing system and a program according to an embodiment of the present disclosure include: The information that can be used to process the recognized task includes first information having a relevance to the task higher than a predetermined standard and second information having a relevance lower than the predetermined standard, The task is processed based on first information, and if an evaluation of the processing result based on the first information is lower than a predetermined threshold, The first information and the second information, Mix at a mixing ratio based on the evaluation of the processing results Mixed The information processing system and the program further include a task processing unit that processes the task based on the information.

[0011] An information processing method according to one aspect of the present disclosure includes: The information that can be used to process the recognized task includes first information having a relevance to the task higher than a predetermined standard and second information having a relevance lower than the predetermined standard, The task is processed based on first information, and if an evaluation of the processing result based on the first information is lower than a predetermined threshold, The first information and the second information, Mix at a mixing ratio based on the evaluation of the processing results Mixed The information processing method further includes performing task processing for processing the task based on the information.

[0012] In one aspect of the present disclosure, The information that can be used to process the recognized task includes first information having a relevance to the task higher than a predetermined standard and second information having a relevance lower than the predetermined standard, The task is processed based on first information, and if an evaluation of the processing result based on the first information is lower than a predetermined threshold, The first information and the second information are Mix at a mixing ratio based on the evaluation of the processing results Mixed Based on the information, the task is further processed. [Brief explanation of the drawings]

[0013] [Figure 1] FIG. 2 is a diagram illustrating an example of the hardware configuration of an information processing device according to the present disclosure. [Figure 2]2 is a diagram illustrating a configuration example of a first embodiment of a task processing unit in FIG. 1; FIG. [Figure 3] 3 is a flowchart illustrating task processing by the task processing unit of FIG. 2. [Figure 4] FIG. 10 is a diagram illustrating a modified example of the first embodiment. [Figure 5] 1. FIG. 4 is a diagram illustrating an example of the configuration of a modified example of the first embodiment of the task processing unit in FIG. [Figure 6] 6 is a flowchart illustrating task processing by the task processing unit of FIG. 5. [Figure 7] 1. FIG. 4 is a diagram illustrating a configuration example of a second embodiment of the task processing unit in FIG. [Figure 8] 8 is a flowchart illustrating task processing by the task processing unit of FIG. 7. [Figure 9] FIG. 10 is a diagram illustrating a configuration example of a third embodiment of the task processing unit in FIG. [Figure 10] 10 is a flowchart illustrating task processing by the task processing unit of FIG. 9. [Figure 11] FIG. 1 is a diagram illustrating an example of the configuration of a general-purpose personal computer. DETAILED DESCRIPTION OF THE INVENTION

[0014] Preferred embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. In this specification and drawings, components having substantially the same functional configurations are designated by the same reference numerals, and redundant description will be omitted.

[0015] Hereinafter, embodiments of the present technology will be described in the following order. 1. First embodiment 2. Modification of the First Embodiment 3. Second Embodiment 4. Third Embodiment 5. Software implementation example

[0016] <<1. First Embodiment>> <Configuration example of information processing device of the present disclosure> This disclosure proposes and enables creative and flexible task processing as a process for solving a task. Here, "creative" means, for example, solving a problem using information that is remotely related to the task (information that is less related to the task).

[0017] First, an example of the hardware configuration of an information processing device according to the present disclosure will be described with reference to the block diagram of FIG.

[0018] An information processing device 11 in FIG. 1 is, for example, a personal computer, and constitutes part of a system for processing various tasks, processes the various tasks, and outputs the processing results to solve the various tasks.

[0019] The task may be, for example, object grasping (picking) by a robot, in which case the information processing device 11 realizes a robot having a manipulator that grasps objects, such as grasping parts in a factory or assisting users at home, or a system that controls the manipulator.

[0020] The task may be, for example, a route search (path planning), in which case the information processing device 11 realizes a system that presents a route from a set start point to a goal point. Route search is used, for example, to give route instructions to a moving body such as an automobile, or to plan the movement of the moving body itself.

[0021] Furthermore, the task may be, for example, recipe creation for cooking, etc. In this case, the information processing device 11 realizes a system that creates and outputs cooking recipes. A recipe is, for example, a procedure for combining, processing, and editing ingredients, and may be a craft procedure or a research procedure in addition to cooking.

[0022] Furthermore, the task may be, for example, the automatic generation of conversations in a system that communicates with users. In this case, the information processing device 11 realizes a system that, for example, provides system operations through conversations by financial institutions, etc., provides service information in stores, and conducts casual conversations in nursing homes and at home.

[0023] Furthermore, the task may be to support the user in making decisions, in which case the information processing device 11 generates and presents candidate behavioral options and recommends priorities for the options to the user, thereby realizing a system that provides behavioral navigation and business behavioral support.

[0024] Thus, the tasks may be of a wide variety and are not limited to the types of tasks described above.

[0025] The information processing device 11 in Figure 1 is composed of a control unit 31, an input unit 32, an output unit 33, a memory unit 34, a communication unit 35, a drive 36, and a removable storage medium 37, which are connected to each other via a bus 38 and can send and receive data and programs.

[0026] The control unit 31 is composed of a processor and a memory, and controls the overall operation of the information processing device 11 .

[0027] The control unit 31 also includes a task processing unit 51 .

[0028] The task processing unit 51 recognizes tasks that need to be processed based on information input via the input unit 32, performs processing to solve the recognized tasks (hereinafter also referred to as task processing), and outputs the processing results from the output unit 33.

[0029] The detailed configuration of the task processing unit 51 will be described later with reference to FIG.

[0030] The input unit 32 is composed of input devices such as a keyboard through which the user inputs operation commands and a microphone through which voice input is performed, as well as various sensors such as a camera, a distance sensor, a temperature sensor, a humidity sensor, an illuminance sensor, and a biometric sensor, and supplies various input or detected signals to the control unit 31.

[0031] The sensors constituting the input unit 32 are not limited to the above-mentioned sensors, and any sensors may be used as long as they detect information required for a task.

[0032] The output unit 33 is composed of an audio output unit such as a speaker, and an image display unit such as an LCD (Liquid Crystal Display) or an organic EL (Organic Electro-Luminescence), and outputs various task processing results.

[0033] The configuration of the output unit 33 is not limited to an audio output unit or an image display unit, as long as it is a configuration necessary for realizing the task.

[0034] Furthermore, if there is separate hardware required to process the task, a control signal for operating that hardware is output, and the task is processed by operating the hardware.

[0035] In this case, the connection to the hardware can be either wired or wireless, so if necessary, an interface that allows for wired connection can be connected to the output unit 33, and a control signal can be supplied to the hardware via the interface, so that the hardware performs an operation to realize task processing based on the control signal.

[0036] Alternatively, instead of the output unit 33, a control signal may be supplied to the hardware via wired or wireless communication via the communication unit 35 described later, and the control signal may cause the hardware to perform an operation to realize task processing.

[0037] The storage unit 34 is composed of a hard disk drive (HDD), a solid state drive (SSD), or a semiconductor memory, and is controlled by the control unit 31 to write or read various data and programs.

[0038] If necessary, the storage unit 34 may be configured as a server on a network that can communicate via a communication unit 35, which will be described later.

[0039] The communication unit 35 is controlled by the control unit 31 and transmits and receives various data and programs to and from various devices via a wired (or wireless (not shown)) communication network such as a LAN (Local Area Network).

[0040] The drive 36 reads and writes data from and to a removable storage medium 37 such as a magnetic disk (including a flexible disk), an optical disk (including a CD-ROM (Compact Disc-Read Only Memory) and a DVD (Digital Versatile Disc)), a magneto-optical disk (including an MD (Mini Disc)), or a semiconductor memory.

[0041] Although the present specification will describe an example in which the technology of the present disclosure is realized by the information processing device 11, it may also be realized by a system made up of multiple devices.

[0042] That is, the technology of the present disclosure may be realized, for example, by configuring multiple personal computers or servers on a network that have the functions of the control unit 31, input unit 32, output unit 33, memory unit 34, drive 36, and removable storage medium 37 of the information processing device 11, or by configuring them using cloud computing, thereby realizing an information processing system that is configured to be able to communicate with each other.

[0043] <First configuration example of task processing unit> Next, a first configuration example of the function of the task processing unit 51 realized by the control unit 31 will be described with reference to the functional block diagram of FIG.

[0044] The task processing unit 51 includes a task input unit 71 , a task processing module 72 , a processing result evaluation module 73 , an output unit 74 , a bias value setting unit 75 , an input data processing unit 76 , and a storage module 77 .

[0045] The task input unit 71 receives the input results and detection results from the input unit 32 and grasps the content of the task to be solved. The task input unit 71 recognizes a specific task and grasps its content by receiving input from sensors, interpreting the input information, and recognizing the environment as necessary. Here, "recognizing" and "understanding" a specific task means retaining the information of the specific task in a state that can be handled by the system by applying the data format, pattern, and model that the system handles based on the input or detected signal.

[0046] Furthermore, the task input unit 71 outputs information relating to the content of the task that has been grasped to the task processing module 72 and the processing result evaluation module 73 .

[0047] More specifically, for example, in the case of a task related to conversation recognition, the task input unit 71 converts the voice input result from the user into text, performs semantic analysis, recognizes it as the "content of the user's question," and grasps the generation of a conversation in response to the recognized "content of the user's question" as the content of the task.

[0048] At this time, the task input unit 71 may take into account the user model, the user's behavioral history, and environmental information as necessary, and recognize the "user's question content" according to the context including information such as the user's location, time, and surrounding circumstances.

[0049] Furthermore, for example, in the case of a task relating to grasping an object, the task input unit 71 recognizes the external shape of the object in three dimensions based on information from the camera, ultrasonic sensor, etc. that constitutes the input unit 32, recognizes it as "three-dimensional information of the object to be grasped," and understands the grasping of the recognized object as the content of the task.

[0050] At this time, the task input unit 71 may estimate the position of the center of gravity, the hardness of the object surface, and the like, as necessary.

[0051] When an object is required to be grasped and then moved, the task input unit 71 may acquire information such as the destination position and grasp the grasping and movement as part of the task content.

[0052] The task processing module 72 requests and acquires input data required for task processing from the input data processing unit 76, processes the task supplied from the task input unit 71 by applying the acquired input data to a specific processing pattern or processing model, and outputs the processing result to the processing result evaluation module 73.

[0053] More specifically, for example, in the case of a task related to conversation recognition, the task processing module 72 generates suitable answer candidates for the task, "user's question content," as the processing result and outputs them to the processing result evaluation module 73.

[0054] Furthermore, in the case of a task related to grasping an object, the task processing module 72 generates candidates for manipulator control information as processing results, such as the object grasping position by the manipulator constituting the output unit 33, torque, and the manipulator's approach to grasping, and outputs these to the processing result evaluation module 73.

[0055] In the case of a task relating to object grasping, the manipulator is the hardware required to realize the processing of the task.

[0056] The input data processing unit 76 extracts information belonging to the first data group 91 and information belonging to the second data group 92 stored in the memory module 77 according to the bias value supplied from the bias value setting unit 75, and supplies the extracted information to the task processing module 72.

[0057] Here, information belonging to the first data group 91 is information related to the identified task, information that has a higher relevance to the identified task than a predetermined value, or information that has a higher relevance to the identified task relative to the second data group 92.

[0058] For example, if the task is related to conversation recognition, the information belonging to the first data group 91 is a group of terms related to the understood task and a conversation sequence model.For example, if the content of the conversation is a conversation related to an operator agent of a financial institution, the information would be information related to finance, the service content of the financial institution, and a standard conversation sequence model related to the operator's conversation.

[0059] Furthermore, in the case of a task related to object grasping, the information belonging to the first data group 91 includes information such as three-dimensional model information of the object to be grasped, surface information, center of gravity information, and bias values optimized for the situation in environmental recognition, which frequently appear in situations adapted to realizing object grasping.

[0060] Furthermore, information belonging to the second data group 92 is information that is not related to the recognized task, information that has a relevance to the recognized task lower than a predetermined value, or information that has a lower relationship to the recognized task compared to the first data group 91.

[0061] For example, if the task is related to conversation recognition, the information belonging to the second data group 92 is a group of terms unrelated to the task and a conversation sequence model. For example, if the processing content of the task is an operator agent of a financial institution, the information would be words unrelated to finance, casual conversation topics, a typical conversation sequence model in the medical field, an atypical conversation sequence model, etc.

[0062] Furthermore, in the case of an object grasping task, the information belonging to the second data group 92 is information used in a situation different from the situation in which it is applied to realize object grasping, or information unrelated to object grasping. For example, in the case of a task performed in an electronic parts manufacturing factory, the information includes information related to object grasping of a car body transport robot, shape models and hardness models of food, and driving information of a mobile robot.

[0063] The processing result evaluation module 73 evaluates, as an evaluation value, whether the candidate output information generated as a processing result by the task processing module 72 is information that appropriately solves the input task, and when the evaluation result is higher than a predetermined threshold and the processing result can be considered to appropriately solve the task, outputs the processing result to the output unit 74.

[0064] Furthermore, when the evaluation result is lower than a predetermined threshold and the processing result is deemed not to be able to solve the task appropriately, the processing result evaluation module 73 outputs the evaluation value to the bias value setting unit 75 .

[0065] More specifically, the processing result evaluation module 73 evaluates the task processing result by calculating an evaluation value based on, for example, task achievement prediction or reward amount prediction in a reinforcement learning model.

[0066] More specifically, in the case of a task related to speech recognition, the processing result evaluation module 73 evaluates whether an appropriate amount of reward can be obtained for the candidate answers that are the candidate output results, in light of the user model and the question content.

[0067] In addition, if the task is related to object grasping, the processing result evaluation module 73 calculates and evaluates the probability of success in grasping the object based on the candidate control for grasping the object that is the candidate output result as an evaluation value.

[0068] The bias value setting unit 75 sets a bias value based on the evaluation value, which is the evaluation result supplied from the processing result evaluation module 73 .

[0069] Based on the bias value, the input data processing unit 76 selectively extracts information belonging to a first data group 91 and information belonging to a second data group 92 that are necessary for processing the identified task stored in the memory module 77, and supplies them to the task processing module 72.

[0070] When the task processing module 72 requests information necessary for processing a task, if it is the first time, the input data processing unit 76 does not receive a bias value from the bias value setting unit 75, so by default, it extracts information belonging to the first data group 91 that is related to the task or highly related to the task, and supplies it to the task processing module 72.

[0071] Furthermore, when the task processing module 72 requests information necessary for processing a task, the input data processing unit 76 extracts not only information belonging to a first data group 91 that is related to the task or highly related to the task, but also information belonging to a second data group 92 that is not related to the task or has a low relevance to the task, depending on the bias value from the bias value setting unit 75, and supplies this information to the task processing module 72.

[0072] The bias value is, for example, information (mixing ratio) supplied to the task processing module 72 that specifies the ratio at which information belonging to the first data group 91 and information belonging to the second data group 92 should be mixed and extracted.

[0073] For example, the bias value setting unit 75 may set the bias value so that, if the evaluation value continues to be lower than a predetermined threshold, the proportion of information belonging to the first data group 91 that is extracted gradually decreases and the proportion of information belonging to the second data group 92 that is extracted gradually increases.

[0074] As a result, the task processing module 72 initially processes the task based on information related to the task, but if the evaluation value for the processing result is low and the state in which appropriate processing is not achieved continues, the processing will be based on information unrelated to the task.

[0075] In addition, when the evaluation value continues to be lower than a predetermined threshold, the bias value setting unit 75 sets a bias value such that information belonging to the first data group 91 is extracted until a predetermined number of times is exceeded, but after the predetermined number of times is exceeded, the bias value may be set so that information belonging to the second data group 92 is extracted.

[0076] In either case, processing is performed based on information that is not related to the task or that has a low relevance to the task, making it possible to solve tasks that cannot be solved by processing based on information that is related to the task or that has a high relevance to the task through creative and flexible processing.

[0077] The memory module 77 stores, as information required for task processing, model information to be adapted (e.g., conversation template information, object grasping pattern information), element information constituting output information (e.g., conversation topic, travel route), information generated in real time based on sensor information and environmental information, learning models to be applied in each situation, and learned models as a first data group 91 and a second data group 92.

[0078] The output unit 74 has a configuration corresponding to the output unit 33 (FIG. 1), and outputs a processing result that has been evaluated by the processing result evaluation module 73 as an appropriate processing result for solving the task and has a higher evaluation value than a predetermined evaluation value.

[0079] The processing results output by the output unit 74 are output in an appropriate manner depending on the situation to which they are applied, and include voice output, text output, information presentation, manipulator control, equipment control, movement and modification of the system itself, etc.

[0080] More specifically, for example, in the case of a task related to speech recognition, the processing result is a response to the "user's question" in the form of text, audio, or the presentation of appropriate information (for example, the presentation of map information in response to a question about directions).

[0081] Furthermore, in the case of a task relating to object grasping, the processing result is the output of manipulator control information for actually grasping the object, or manipulator control itself.

[0082] After the processing result is output, feedback based on the processing result may be recognized based on a sensor or new input information, and fed back to the task processing module 72 and the processing result evaluation module 73. In this case, the task processing module 72 and the processing result evaluation module 73 execute processing and evaluate the processing result in accordance with the feedback.

[0083] Furthermore, in the case of a task related to speech recognition, the feedback may be, for example, the user's reaction (facial expressions and emotions) based on user sensing, evaluation input information by the user, or an estimation result of whether the user was able to achieve their goal based on the user's behavior.

[0084] Furthermore, in the case of a task involving grasping an object, the feedback may include, for example, the result of whether or not the object was grasped without any problems, the number of attempts until the object was successfully grasped, and information about the actual stress applied to the object.

[0085] <Task processing by the task processing unit in Figure 2> Next, task processing by the task processing unit 51 in FIG. 2 will be described with reference to the flowchart in FIG.

[0086] In step S11, the task input unit 71 receives various data relating to the input result input by the input unit 32 or the detected result.

[0087] In step S12, the task input unit 71 determines the content of the task to be solved based on the input results of the input unit 32 and data related to the detection results, and supplies the determined task information to the task processing module 72.

[0088] In step S13, the task processing module 72 requests the input data processing unit 76 for data required for processing the task based on the information on the task that has been grasped and that has been supplied from the task input unit 71.

[0089] In step S14, in response to a request from the task processing module 72, the input data processing unit 76 reads data relating to the processing of the recognized task from the storage module 77 and supplies the data to the task processing module 72.

[0090] More specifically, the input data processing unit 76 accesses the memory module 77, extracts information belonging to a first data group 91 that is supplied by the task processing module 72 and consists of information related to the recognized task or information that is highly relevant to the task, and supplies the information to the task processing module 72.

[0091] In step S15, the task processing module 72 processes the task based on the information belonging to the first data group 91 supplied from the input data processing unit 76, and outputs the processing result to the processing result evaluation module 73.

[0092] In step S16, the processing result evaluation module 73 calculates an evaluation value for evaluating whether the processing result solves the task appropriately, and evaluates the processing result.

[0093] In step S17, the processing result evaluation module 73 determines whether the evaluation value for the processing result of the task processing module 72 is higher than a predetermined threshold value and whether the processing result appropriately solves the task.

[0094] In step S17, if the evaluation value is lower than the predetermined threshold and the processing result is deemed not to solve the task appropriately, the process proceeds to step S18.

[0095] In step S18, the processing result evaluation module 73 outputs the calculated evaluation value that is lower than the predetermined threshold to the bias value setting unit 75. Then, based on the evaluation value that is an evaluation of the processing result of the task processing module 72 and the number of times the evaluation value is considered to be lower than the predetermined threshold, the bias value setting unit 75 sets a bias value that indicates the mixing ratio (proportion) of the data extracted as information belonging to each of the first data group 91 and the second data group 92, and outputs the bias value to the input data processing unit 76.

[0096] In step S19, the input data processing unit 76 accesses the memory module 77, extracts the data belonging to the first data group 91 and the second data group 92 in a mixing ratio based on the bias value as data necessary for processing the task, and supplies it to the task processing module 72, and the processing returns to step S15.

[0097] That is, the processes of steps S15 to S19 are repeated until the evaluation value for the processing result of the task processing module 72 is higher than a predetermined threshold and the processing result is deemed to solve the task appropriately.

[0098] Then, in step S17, if the evaluation value is higher than a predetermined threshold and the processing result is deemed to be an appropriate solution to the task, the process proceeds to step S20.

[0099] In step S20, the processing result evaluation module 73 outputs to the output unit 74 the processing result whose evaluation value is higher than a predetermined threshold and which is deemed to solve the task appropriately.

[0100] The output unit 74 (output unit 33) outputs a processing result whose evaluation value is higher than a predetermined threshold and which is deemed to solve the task appropriately.

[0101] In step S21, task input section 71 determines whether or not new task data has been input and whether or not an instruction to end the process has been given. If an instruction to end the process has not been given, the process returns to step S11.

[0102] That is, steps S11 to S21 are repeated until an instruction to end the process is given.

[0103] Then, in step S21, if it is determined that an instruction to end the process has been given, the process ends.

[0104] Through the above processing, the task processing module 72 first receives data required for processing from the first data group 91, which is information related to the task or information highly related to the task, and then processes the task.

[0105] Here, if the evaluation value of the processing result of the task processing module 72 is lower than a predetermined threshold and the processing result is deemed not to solve the task appropriately, the bias value setting unit 75 sets a bias value to be supplied to the task processing module 72 by mixing, in a predetermined ratio, data from the first data group 91, which is data related to the task, and data from the second data group 92, which is data not related to the task, as data necessary for the task processing realized by the task processing module 72, and supplies the bias value to the input data processing unit 76.

[0106] As a result, the input data processing unit 76 supplies the task processing module 72 with data from the second data group 92, which is data that is not related to the task (has low relevance), in addition to data from the first data group 91, which is data that is related to the task (high relevance), as data required for the task processing realized in the task processing module 72.

[0107] When processing a task, the task processing module 72 uses data belonging to a first data group 91 that is related (highly related) to the task, as well as data from a second data group 92 that is not related (lowly related) to the task, so processing is different from processing using data related to the task.

[0108] As a result, it becomes possible to explore and realize a method for solving a task that cannot be solved using data belonging to the first data group 91 that is related to the task (highly related), through creative and flexible processing using data from the second data group 92 that is not related to the task (lowly related).

[0109] In addition, the bias value setting unit 75 may mix data from a first data group 91, which is data related to (highly related to) the task, with data from a second data group 92, which is data not related to (lowly related to) the task, as data required for task processing realized in the task processing module 72, and set a bias value such that the mixing ratio of data from the second data group gradually increases each time a state in which the evaluation value is lower than a predetermined threshold is repeated, and supply the bias value to the input data processing unit 76.

[0110] In addition, when the evaluation value is repeatedly kept lower than a predetermined threshold, the data used to process the task may be gradually switched from data belonging to the first data group 91 to data belonging to the second data group, depending on the number of times the evaluation value is repeatedly kept lower than the predetermined threshold.

[0111] Furthermore, when the state in which the evaluation value is lower than a predetermined threshold is repeated a predetermined number of times, the data used to process the task may be switched from data belonging to the first data group 91 to data belonging to the second data group.

[0112] In either case, if such processing causes the evaluation value to remain lower than a predetermined threshold, the processing of the task will gradually change to processing using data unrelated to the task, and the processing of the task will change to processing that is more creative and has a higher degree of freedom.

[0113] Furthermore, if the evaluation value continues to be lower than a predetermined threshold, the data used to process the task will be switched to data that is not (has low relevance to) the task, and the task will be processed using that data, which will result in the task being processed in a more creative and flexible manner.

[0114] In either case, by changing the data required to process a task from one that is highly relevant to the task to one that is less relevant, it becomes possible to change the processing of the task to one that is more creative and has a higher degree of freedom.

[0115] As a result, even if a task cannot be solved using only task-related data, it is possible to search for and implement a process to solve the task appropriately.

[0116] For example, in the case of tasks such as navigation systems or mobile robots (including autonomous vehicles) searching for their own routes, among various evaluation functions, it is possible to search for a more suitable solution by setting a new evaluation function (data belonging to second data group 92) based on a wider range of information and models, rather than just the initially assumed evaluation function or the input evaluation function (data belonging to first data group 91).

[0117] Furthermore, in the case of a task involving grasping an object that was not initially anticipated, applying the technology of the present disclosure makes it possible to achieve more flexible grasping.

[0118] In other words, by referring not only to information about the intended object (shape, center of gravity position, hardness, fragility, suitable grasping approach model, movement approach model) (data belonging to the first data group 91), but also to other information and models (data belonging to the second data group 92), it becomes possible to expand the trial method and respond more flexibly, making it possible to achieve grasping even if the object deviates from the range originally expected.

[0119] In addition, in the case of the above-mentioned tasks related to navigation systems, mobile robots (including autonomous vehicles) searching for their own paths, or tasks related to grasping objects that were not initially anticipated, by also referring to data sources and models (data belonging to the second data group 92) other than the initially anticipated situation (data belonging to the first data group 91), it becomes possible to search for a wider range of solutions or escape from local solutions when processing gets stuck.

[0120] Furthermore, in the case of a task related to generating a cooking recipe, it is possible to output a more creative recipe by referring to the target cooking category and approaches (data belonging to the second data group 92) other than those normally assumed in cooking (data belonging to the first data group 91).

[0121] That is, when creating a Chinese recipe, it is possible to refer to a Japanese recipe, and when plating a dish, it is possible to incorporate art-related information unrelated to cooking.

[0122] It is not enough to combine more distant information; it is also possible to have an evaluation function that evaluates whether the dish is viable (taste, appearance, whether it meets certain standards for human consumption, etc.), and the processing result evaluation module 73 may evaluate the candidate output results based on this standard.

[0123] Furthermore, cooking is an example, and the invention is effective for all processing tasks that involve combining elements and methods to create something. For example, it may be possible to search for novel writing, automatic generation of video scenes, etc.

[0124] Furthermore, when the task involves conversation generation, the conversation is usually generated using the terms, discourse, and conversation generation logic that make up the conversation based on the initially expected usage situation and target user (data belonging to the first data group 91). However, there are many cases where the user makes unexpected utterances, the situation changes, or more flexible conversation responses are required. In such unexpected situations and cases, more flexible conversation generation can be achieved by also referring to unexpected terminology groups, discourse examples, and conversation generation models (data belonging to the second data group 92).

[0125] In addition, it is possible to set a wider variety of options, such as conservative solutions (data belonging to the first data group 91) and more ambitious solutions (data belonging to the second data group 92), for all tasks, including general tasks, not just the above-mentioned series of tasks such as navigation systems, tasks related to route finding by mobile robots (including autonomous vehicles), tasks related to grasping objects that were not initially anticipated, tasks related to generating cooking recipes, and tasks related to generating conversations.

[0126] Here, "conservative" and "ambitious" refer to the degree of risk to the user and the likelihood of selection calculated based on the user's past selection trends. More specifically, a conservative solution is, for example, a solution that poses a relatively low risk to the user or a solution that is likely to be selected by the user. An ambitious solution is, for example, a solution that poses a relatively high risk to the user or a solution that may be selected by the user but is unlikely to be selected.

[0127] Furthermore, when a task is interpreted as an optimization problem, flexible problem solving may be achieved by gradually relaxing constraints and conducting trials.

[0128] In other words, the initially set constraints (data belonging to the first data group 91) may be too strict and limit the tasks that can be handled, but for events that are broader than the conditions initially anticipated, gradually relaxing the conditions (by gradually using data belonging to the second data group 92) makes it possible to respond more flexibly.

[0129] In the above, an example has been described in which the processing result evaluation module 73 outputs to the output unit 74 one processing result whose evaluation value is higher than a predetermined threshold and which is deemed to solve the task appropriately, but multiple processing results with different evaluation values may be output together with the evaluation values and presented to the user so that the user can select one. This type of processing makes it possible to present to the user, for example, multiple processing results higher than a predetermined threshold, and realizes flexible responses including user judgment based on the evaluation values.

[0130] Furthermore, when there are multiple solutions to a task, a normal trial search (search using data belonging to the first data group 91) may result in the search being limited to the closest local solution (making it impossible to search for any further solutions); however, by applying the technology disclosed herein, it is possible to temporarily suspend the local solution and conduct a wider range of search (search using data belonging to the second data group 92), thereby arriving at a more optimal solution.

[0131] That is, for example, in the case of a task involving path planning for a robot, in a situation where there are multiple possible evaluation functions (shortest route, route that is comfortable for the user, route with less risk, etc.), rather than ending the search with the output of a solution based only on the evaluation function that was initially assumed, by also applying evaluation functions that were not initially assumed, it becomes possible to search for a more optimal solution that was not initially assumed.

[0132] In reinforcement learning, learning is performed according to an evaluation function (reward), and the setting of the evaluation function is important. The evaluation function is usually set in advance (by human design), but there is a demand for automation of the setting of the evaluation function (reward amount).

[0133] By applying the technology disclosed herein, it becomes possible to flexibly use evaluation functions related to the task (there may be multiple evaluation functions), evaluation functions not related to the task, or evaluation functions that are automatically generated each time, thereby enabling more flexible problem solving.

[0134] <<2. Modification of the First Embodiment>> In the above, we have described an example in which the processing in the task processing module 72 is changed by mixing (or switching) two types of data, namely, a first data group consisting of data related to the task (highly related to the task) and a second data group consisting of data not related to the task (lowly related to the task), based on a bias value.

[0135] However, the data required for task processing may be classified into three or more types based on its relevance to the task, and data with progressively lower relevance may be used for task processing depending on the number of times the evaluation value of the processing result of the task processing module 72 is deemed to be lower than a predetermined threshold.

[0136] That is, for example, data required for processing a task is classified into a first data group 111 to an n-th data group as shown in FIG.

[0137] 4, the first data group 111 is the data group most relevant to the task, the second data group 112 is the data group second most relevant to the task after the first data group 111, the third data group 113 is the data group second most relevant to the task after the second data group 112, and so on up to the n-th data group n according to the degree of relevance to the task. That is, the n-th data group n is the least relevant to the task.

[0138] Then, when the first data group 111 is used to process a task and the evaluation value of the processing result is lower than a predetermined threshold, in the next processing, in addition to the first data group 111, the second data group 112 is also used, and thereafter, data up to the nth data group n are used sequentially to process the task until the evaluation value becomes higher than the predetermined threshold.

[0139] This type of processing allows the data used to process a task to be used in order of the most relevant data to the task, making it possible to properly solve tasks that cannot be solved using only the data group related to the task.

[0140] <Modification of the first configuration example of the task processing unit> Next, a modification of the first exemplary configuration of the task processing unit will be described with reference to FIG.

[0141] In FIG. 5, components having the same functions as those in FIG. 2 are denoted by the same reference numerals, and the description thereof will be omitted as appropriate.

[0142] That is, the task processing unit 51 in FIG. 5 differs from the task processing unit 51 in FIG. 2 in that a bias value setting unit 101, an input data processing unit 102, and a storage module 103 are provided instead of the bias value setting unit 75, the input data processing unit 76, and the storage module 77.

[0143] The bias value setting unit 101 has the same basic function as the bias value setting unit 75, but further sets a bias value so that the data groups supplied to the task processing module 72 are changed so that the number of data groups with low relevance to the task increases depending on the number of times that the evaluation value is lower than a predetermined threshold and it is determined that the task cannot be properly solved.

[0144] The input data processing unit 102 extracts data based on the bias value supplied from the bias value setting unit 101 from the first data group 111 to the nth data group stored in the memory module 103, and supplies the extracted data to the task processing module 72.

[0145] The storage module 103 stores the first data group 111 and the n-th data group n described with reference to FIG. 4, instead of the first data group 91 and the second data group 92 in the storage module 77.

[0146] That is, of the first data group 111 to the nth data group, the first data group 111 is the data group most relevant to the task, followed by the second data group 112, the third data group 113, ..., the nth data group n, in that order.

[0147] <Task processing by the task processing unit in Figure 5> Next, task processing by the task processing unit 51 in Fig. 5 will be described with reference to the flowchart in Fig. 6. Note that the processing of steps S32 to S38 in Fig. 6 is similar to the processing of steps S11 to S17 in Fig. 3, and therefore the description thereof will be omitted as appropriate.

[0148] In step S31, the bias value setting unit 101 initializes a counter m, which identifies a data group stored in the storage module 103, to 1.

[0149] In steps S32 to S38, the task processing module 72 processes the task using the first data group 111, and the processing result is supplied to the processing result evaluation module 73, which calculates an evaluation value.

[0150] If the evaluation value is lower than the predetermined threshold in step S38, the process proceeds to step S39.

[0151] In step S39, the bias value setting unit 101 increments the counter m by one.

[0152] In step S40, the bias value setting unit 101 sets a bias value so that the data of the data group corresponding to the counter m is supplied to the processing of the task processing module 72, and outputs the bias value to the input data processing unit .

[0153] In step S41, the input data processing unit 102 accesses the memory module 103 and extracts data necessary for processing the task from the data belonging to, for example, the first data group to the mth data group m among the first data group to the nth data group n based on the bias value, and supplies the extracted data to the task processing module 72, and the processing returns to step S36.

[0154] That is, the processing results of the task processing module 72 are deemed to be processing results that properly solve the task, and the processing of steps S36 to S41 is repeated until the evaluation value for the processing results becomes higher than a predetermined threshold value, and the processing of the task using data from data groups that are progressively less relevant to the task from among the first data group to the nth data group n is repeated according to the number of repetitions.

[0155] Then, in step S41, if the evaluation value is higher than a predetermined threshold and the processing result is deemed to be an appropriate solution to the task, the process proceeds to step S42.

[0156] Then, in step S42, the output unit 74 outputs a processing result whose evaluation value is higher than a predetermined threshold and which is deemed to solve the task appropriately.

[0157] Through the above processing, the task processing module 72 first receives data required for processing from the first data group 91, which is data related to the task, and then processes the task.

[0158] Here, if the processing result of the task processing module 72 does not solve the task appropriately and the evaluation value is lower than a predetermined threshold, the bias value setting unit 75 gradually includes data from a data group that is not related to the task (has lower relevance to the task) as data necessary for the task processing realized by the task processing module 72 and supplies this data to the task processing module 72.

[0159] As a result, when processing a task, the task processing module 72 gradually processes data from data groups unrelated to the task until the processing result is deemed to adequately resolve the task, thereby enabling creative and highly flexible processing.

[0160] With this type of processing, if the evaluation value continues to be lower than a predetermined threshold, the task will gradually be processed using data that is not related to the task, making it possible to process the task while gradually changing the processing to one that is more creative and has a higher degree of freedom.

[0161] In this way, the data required to process a task gradually changes from highly relevant to the task to less relevant, making it possible to properly solve tasks that cannot be solved using only the data relevant to the task.

[0162] In the above, we have explained an example in which, if the evaluation value continues to remain lower than a predetermined threshold, data that is not relevant to the task is gradually included and used to process the task. However, it is also possible to gradually extract only less relevant data and use it in task processing as the evaluation value continues to remain lower than the predetermined threshold.

[0163] <<3. Second Embodiment>> The above has described an example in which the input data processing unit 76 or 102 accesses the memory module 77 or 103, mixes data belonging to the first data group 91 and the second data group 92, or data belonging to the first data group 111 and the nth data group n, according to the bias value, and supplies the data to the task processing module 72.

[0164] However, the main memory module may be configured to store data belonging to the first data group by default, the task processing module may read the data stored in the main memory module to process the task, and if the processing result does not properly resolve the task, the main memory module may be increased in amount with data belonging to the second data group according to the bias value.

[0165] FIG. 7 shows an example configuration of a task processing unit 51 in which a main memory module is provided that stores data belonging to a first data group by default and gradually increases and stores data belonging to a second data group according to a bias value, and a task processing module processes a task based on the data stored in the main memory module.

[0166] The task processing unit 51 in Figure 7 includes a task input unit 171, a task processing module 172, a processing result evaluation module 173, an output unit 174, a bias value setting unit 175, an input data processing unit 176, a main memory module 177, a first sub-memory module 178, and a second sub-memory module 179.

[0167] The task input unit 171, task processing module 172, processing result evaluation module 173, and output unit 174 have the same configuration as the task input unit 71, task processing module 72, processing result evaluation module 73, and output unit 74 in Figure 2, so their explanation will be omitted as appropriate.

[0168] However, while task processing module 172 is similar to task processing module 72 in terms of basic functions, it differs from task processing module 72 in that task processing module 72 requests and obtains the data necessary for processing from input data processing unit 76 and processes the task, whereas task processing module 172 processes the task based on data stored in main memory module 177.

[0169] Furthermore, the configurations of the main memory module 177, the first sub-memory module 178, and the second sub-memory module 179 are basically the same as that of the memory module 77, and may be configured within the memory unit 34, or may be configured as separate memory units, or may be configured by an external server via a network.

[0170] Furthermore, the first sub-storage module 178 stores a first data group 191 corresponding to the first data group 91, and the second sub-storage module 179 stores a second data group 192 corresponding to the second data group 92.

[0171] The bias value setting unit 175 sets a bias value that specifies the amount of data that the input data processing unit 176 reads out from the second data group 192 stored in the second sub-storage module 179 and stores in the main memory module, based on the evaluation value supplied from the processing result evaluation module 173.

[0172] More specifically, the bias value setting unit 175 sets the bias value so that the amount of data belonging to the second data group 192 to be extracted increases as the number of times the evaluation value is lower than a predetermined threshold increases.

[0173] The input data processing unit 176 extracts the data of the second data group stored in the second sub-storage module 179 based on the bias value supplied from the bias value setting unit 175, and stores the extracted data in the main storage module 177.

[0174] With this configuration, initially, data related to the task (highly relevant to the task) belonging to the first data group 191 stored by default in the first sub-storage module 178 is extracted and stored in the main memory module 177, and is used in task processing by the task processing module 172, and the processing results are output.

[0175] Then, when the evaluation value of the processing result of the task processing module 172 is lower than a predetermined threshold and it is determined that the task cannot be properly solved due to the processing result, the input data processing unit 176 extracts data that is not related to the task and belongs to the second data group 192 from the second sub-storage module 179 based on the bias value set by the bias value setting unit 175, and stores the data in the main memory module 177.

[0176] As a result, in addition to the data belonging to the first data group 191, the main storage module 177 stores data belonging to the second data group 192, which is used by the task processing module 172 to process the task.

[0177] As this process is repeated and the evaluation value of the processing result of the task processing module 172 is lower than a predetermined threshold value and the number of times the processing result does not properly solve the task increases, the amount of data stored in the main memory module 177 that is not related to the task (has low relevance to the task) and belongs to the second data group 192 gradually increases.

[0178] In other words, if the processing result continues to be deemed not to adequately resolve the task, data unrelated to the task will gradually be stored in the main memory module 177, and the task processing will change to data unrelated to the task (highly related to the task).

[0179] As a result, for tasks that cannot be solved using only task-related (highly relevant to the task) data, by changing the processing to include more task-irrelevant (lowly relevant to the task) data, it becomes possible to solve the task using creative and flexible processing.

[0180] <Task processing by the task processing unit in Figure 7> Next, task processing by the task processing unit 51 in FIG. 7 will be described with reference to the flowchart in FIG.

[0181] In step S51, the task input unit 171 receives various data relating to the input result input by the input unit 32 or the detected result.

[0182] In step S52, the task input unit 171 determines the content of the task to be solved based on the input result of the input unit 32 and data related to the detection result, and supplies the determined task information to the task processing module 172.

[0183] In step S53, the task processing module 72 supplies the information on the recognized task supplied from the task input unit 71 to the main storage module 177. In response to this, the main storage module 177 accesses the first sub-storage module 178, and extracts and stores data related to the task that belongs to the first data group 191.

[0184] In step S54, the task processing module 72 processes the task based on the data stored in the main storage module 177, and outputs the processing result to the processing result evaluation module 173.

[0185] In the initial processing, only the data related to the task that belongs to the first data group 191, which is the default, is stored in the main storage module 177, so the task is processed using only the data related to the task.

[0186] In step S55, the processing result evaluation module 173 calculates an evaluation value for evaluating whether the processing result solves the task appropriately, and evaluates the processing result.

[0187] In step S56, the processing result evaluation module 173 determines whether the evaluation value for the processing result of the task processing module 172 is higher than a predetermined threshold value and whether the processing result appropriately resolves the task.

[0188] In step S56, if the evaluation value is lower than the predetermined threshold and the processing result is deemed not to solve the task appropriately, the process proceeds to step S57.

[0189] In step S57, the processing result evaluation module 173 outputs an evaluation value that is lower than the calculated predetermined threshold to the bias value setting unit 175. Then, the bias value setting unit 175 sets a bias value that indicates the amount of extraction of data belonging to the second data group 192 stored in the second sub-storage module 179 based on the evaluation value that is an evaluation of the processing result of the task processing module 172, and outputs the bias value to the input data processing unit 176.

[0190] In step S58, the input data processing unit 176 accesses the second sub-storage module 179, extracts data that is not related to the task (has low relevance to the task) from the second data group 192 based on the bias value, supplies the extracted data to the main storage module 177 for storage, and the processing returns to step S54.

[0191] That is, steps S54 to S58 are repeated until the evaluation value of the processing result of the task processing module 172 becomes higher than a predetermined threshold value and the processing result is deemed to solve the task appropriately, and task processing is repeated with the amount of data in the second data group 192 stored in the main memory module 177 gradually increasing.

[0192] Then, in step S56, if the evaluation value is higher than the predetermined threshold and the processing result is deemed to be an appropriate solution to the task, the process proceeds to step S59.

[0193] In step S59, the processing result evaluation module 173 outputs to the output unit 174 the processing result whose evaluation value is higher than a predetermined threshold and which is deemed to solve the task appropriately.

[0194] The output unit 174 outputs a processing result whose evaluation value is higher than a predetermined threshold and which is deemed to solve the task appropriately.

[0195] In step S60, task input section 171 determines whether or not new task data has been input and an instruction to end the process has been given. If an instruction to end the process has not been given, the process returns to step S51.

[0196] That is, steps S51 to S60 are repeated until an instruction to end the process is given.

[0197] Then, in step S60, if it is determined that an instruction to end the process has been given, the process ends.

[0198] Through the above processing, in the initial processing, task processing module 172 processes the task using only data from first data group 191, which is data related to the task (highly related to the task) and stored in main storage module 177.

[0199] Here, if the processing result of the task processing module 172 does not solve the task appropriately and the evaluation value is lower than a predetermined threshold, the bias value setting unit 175 sets a bias value such that the data of the second data group 192, which is data that is not related to the task (has low relevance to the task) and is stored in the second sub-storage module 179, is supplied to the main storage module 177, and supplies it to the input data processing unit 176.

[0200] As a result, the input data processing unit 176 supplies the data of the second data group 192, which is data that is not related to the task (has low relevance to the task), as data required for the task processing realized by the task processing module 72 to the main storage module 177 for storage.

[0201] When processing a task, the task processing module 72 uses data belonging to a first data group 191 that is related to the task (highly related to the task) stored by default, as well as data belonging to a second data group 192 that is not related to the task (lowly related to the task).

[0202] If the evaluation value of the processing result remains lower than a predetermined threshold, the amount of data stored in the main memory module 177 that belongs to the second data group 192 and is not related to the task will increase, resulting in processing that is different from processing using data related to the task, and as a result, it will be possible to achieve creative and flexible processing.

[0203] <<4. Third Embodiment>> In the above, we have explained an example of realizing creative and flexible processing by setting up the main memory module 177 to store data belonging to the first data group 191 related to the task by default, having the task processing module 172 process the task based on the data stored in the main memory module 177, and if the evaluation value of the processing result remains lower than a predetermined threshold, increasing the amount of data belonging to the second data group 192 not related to the task in the main memory module 177.

[0204] However, a task processing module may be provided with a first task processing module that performs data processing based on a specific processing pattern or processing model, and a second task processing module that performs processing to switch between processing patterns or processing models used for specific task processing in the first task processing module, and the second task processing module may switch between processing patterns or processing models depending on the bias value.

[0205] FIG. 9 shows an example configuration of a task processing unit 51 in which a task processing module is provided with a first task processing module that performs data processing based on a specific processing pattern or processing model, and a second task processing module that performs processing to switch between processing patterns or processing models used for specific task processing in the first task processing module, and the second task processing module switches between processing patterns or processing models depending on a bias value.

[0206] The task processing unit 51 in FIG. 9 includes a task input unit 371, a task processing module 372, a processing result evaluation module 373, an output unit 374, a bias value setting unit 375, and a storage module 376.

[0207] The task input unit 371, processing result evaluation module 373, and output unit 374 have the same configurations as the task input unit 71, processing result evaluation module 73, and output unit 74 in FIG. 2, and therefore their description will be omitted as appropriate.

[0208] The storage module 376 has basically the same configuration as the storage module 77, and stores processing patterns and processing models for processing tasks.

[0209] The storage module 376 may be configured in the storage unit 34, or may be configured by an external server via a network.

[0210] The processing pattern and processing model are, for example, functions and various parameters used in specific task processing executed by the first task processing module 381. The processing pattern and processing model also include a machine learning learning model, a trained model, a database describing the gradient of feature quantities, and a network structure of a machine learning algorithm.

[0211] The storage module 376 stores processing patterns and processing models with various levels of relevance to the task, from processing patterns and processing models with high relevance to the task to processing patterns and processing models with low relevance to the task.

[0212] The task processing module 372 basically processes the task recognized by the task input unit 371 in the same manner as the task processing module 72 , and outputs the processing result to the processing result evaluation module 373 .

[0213] However, task processing module 372 includes first task processing module 381 and second task processing module 382, and realizes the following task processing.

[0214] That is, first task processing module 381 realizes specific task processing based on the processing pattern and processing model set by second task processing module 382, and outputs the processing results to processing result evaluation module 373.

[0215] The second task processing module 382 extracts processing patterns and processing models that are related to the task (highly related to the task) by default from the storage module 376 and supplies them to the first task processing module 381.

[0216] Furthermore, if the evaluation value for the processing result of the first task processing module is lower than a predetermined threshold and the task is deemed unable to be solved appropriately, the second task processing module 382 extracts processing patterns or processing models that are unrelated to the task (have low relevance to the task) from the memory module 376 based on the bias value set by the bias value setting unit 375, and supplies them to the first task processing module 381.

[0217] If the evaluation value for the processing result of the first task processing module is lower than a predetermined threshold and the task is deemed not to have been properly resolved, the bias value setting unit 375 sets a bias value and supplies it to the second task processing module 382 of the task processing module 372.

[0218] More specifically, the bias value setting unit 375 sets the bias value to 0 to 1, and for example, when the default value is 0, sets the bias value to 0 so that processing patterns and processing models that are relevant to the task are extracted from the memory module 376.

[0219] Furthermore, if the evaluation value for the processing result is lower than a predetermined threshold and the state in which the task has not been properly solved continues, the bias value is gradually changed to a value closer to 1.

[0220] In this case, the second task processing module 382 reads out from the storage module 376 a processing pattern or processing model that is less relevant to the task as the bias value approaches 1, and supplies this to the first task processing module 381.

[0221] With this configuration, when the bias value is set to 0 by default, the second task processing module 382 supplies the first task processing module 381 with processing patterns and processing models that are related to the task (highly related to the task) from among the processing patterns and processing models used to process the task stored in the memory module 376.

[0222] As a result, the first task processing module 381 processes the task using a processing pattern or processing model that is highly relevant to the task.

[0223] Furthermore, if the evaluation value for the processing result of first task processing module 381 continues to be lower than a predetermined threshold, bias value setting section 375 gradually sets the bias value to a value closer to 1.

[0224] As a result, the second task processing module 382 gradually extracts processing patterns and processing models that are less relevant to the task, and supplies them to the first task processing module 381.

[0225] As a result, the first task processing module 381 gradually changes to perform task processing based on processing patterns and processing models that are less relevant to the task.

[0226] Furthermore, for tasks that cannot be solved using task-related processing patterns and processing models, the processing is changed so that processing patterns and processing models that are not task-related are increased, making it possible to explore and solve task processing using creative and flexible processing.

[0227] <Task processing by the task processing unit in Figure 9> Next, task processing by the task processing unit 51 in FIG. 9 will be described with reference to the flowchart in FIG.

[0228] In step S81, the task input unit 371 receives various data relating to the input result input by the input unit 32 or the detected result.

[0229] In step S82, the task input unit 371 determines the content of the task to be solved based on the input result of the input unit 32 and data related to the detection result, and supplies the determined task information to the task processing module 372.

[0230] In step S83, the task processing module 372 acquires information on the recognized tasks supplied from the task input unit 371.

[0231] In response to this, the second task processing module 382 extracts from the storage module 376 processing patterns and processing models that are in a state where the default bias value is 0, i.e., that are relevant to the task, and supplies them to the first task processing module 381.

[0232] In step S84, the first task processing module 381 processes the task based on the processing pattern and processing model supplied from the second task processing module 382, and outputs the processing result to the processing result evaluation module 373.

[0233] In step S85, the processing result evaluation module 373 calculates an evaluation value for evaluating whether the processing result solves the task appropriately, and evaluates the processing result.

[0234] In step S86, the processing result evaluation module 173 determines whether the evaluation value for the processing result of the first task processing module 381 is higher than a predetermined threshold value and whether the processing result appropriately resolves the task.

[0235] In step S86, if the evaluation value is lower than the predetermined threshold and the processing result is deemed not to solve the task appropriately, the process proceeds to step S87.

[0236] In step S87, the processing result evaluation module 373 outputs the calculated evaluation value that is lower than the predetermined threshold to the bias value setting unit 375. Then, based on the evaluation value that is the evaluation of the processing result of the first task processing module 381 and the number of times that the evaluation value is considered to be lower than the predetermined threshold, the bias value setting unit 375 sets a bias value that indicates the relevance to the task of the processing pattern or processing model extracted from the storage module 376 by the second task processing module 382, and outputs the bias value to the task processing module 372.

[0237] In step S88, the second task processing module 382 of the task processing module 372 accesses the memory module 376, extracts processing patterns and processing models that are relevant to the task based on the bias value, and supplies them to the first task processing module 381, and the processing returns to step S84.

[0238] That is, the processing result of the first task processing module 381 is deemed to be a processing result that solves the task appropriately, and the processing of steps S84 to S88 is repeated until the evaluation value for the processing result becomes higher than a predetermined threshold, and the processing is repeated while gradually changing to processing the task using processing patterns and processing models stored in the memory module 376 that are less relevant to the task.

[0239] Then, in step S86, if the evaluation value is higher than a predetermined threshold and the processing result is deemed to be an appropriate solution to the task, the process proceeds to step S89.

[0240] In step S89, the processing result evaluation module 373 outputs to the output unit 374 the processing result whose evaluation value is higher than a predetermined threshold and which is deemed to solve the task appropriately.

[0241] The output unit 374 outputs a processing result whose evaluation value is higher than a predetermined threshold and which is deemed to solve the task appropriately.

[0242] In step S90, the task input unit 371 determines whether or not there is no new task data input and an instruction to end the process has been given. If an instruction to end the process has not been given, the process returns to step S81.

[0243] That is, steps S81 to S90 are repeated until an instruction to end the process is given.

[0244] Then, in step S90, if it is determined that an instruction to end the process has been given, the process ends.

[0245] Through the above processing, in the initial processing, first task processing module 381 of task processing module 372 processes the task using the processing pattern and processing model related to the task that are stored in memory module 376 by second task processing module 382.

[0246] Here, if the processing result of the first task processing module 381 does not solve the task appropriately and the evaluation value is lower than a predetermined threshold, the bias value setting unit 375 sets a bias value for the second task processing module 382 such that processing patterns and processing models that are less relevant to the task are extracted from the memory module 177, based on the evaluation value or the number of times the evaluation value was deemed to be lower than the predetermined threshold, from the processing patterns and processing models stored in the memory module 376, and supplied to the first task processing module 381, and supplies the bias value to the task processing module 372.

[0247] As a result, the second task processing module 382 extracts processing patterns and processing models required for task processing, which have relevance to the task according to the bias value, from the memory module 376 and supplies them to the first task processing module 381.

[0248] When processing a task, the first task processing module 381 processes the task by using a processing pattern or processing model that has a relevance to the task based on the bias value.

[0249] At this time, if the evaluation value of the processing result remains lower than a predetermined threshold, the processing pattern or processing model stored in the memory module 376 will change to a processing pattern or processing model that is less relevant to the task, and the processing will change to a processing different from the processing that uses the processing pattern or processing model that is relevant to the task, and as a result, it will be possible to realize creative and flexible processing.

[0250] In any of the first to third embodiments of the present disclosure described above, when setting the bias value, a processing pattern or processing model that is less relevant to the task may be selected or its weighting may be changed depending on the conditions related to the task processing.

[0251] The conditions for task processing include, for example, the risk of task processing. In other words, when the risk of failure of a task is low, it is possible to actively select processing patterns or processing models that are less relevant to the task, thereby enabling the search for task processing with greater creativity and freedom.

[0252] Here, tasks with low risk in case of failure include, for example, tasks with a low limit on the number of attempts, tasks with a low possibility of destroying an object or making the user uncomfortable compared to other situations, tasks that involve communication with the user or presenting information and are performed when the user is in a positive state based on behavior recognition, facial expression recognition, and emotion estimation based on voice and biological information, and tasks that require processing with a virtual personality such as an agent model and are performed when the emotional state of the agent model is positive, etc. This makes it possible to present solutions that include the possibility of destroying an object or making the user uncomfortable when the risk of task processing is low, and to present only solutions that are likely to avoid such possibilities when the risk is high.

[0253] <<5. Example of execution by software>> The above-described series of processes can be executed by hardware, but can also be executed by software. When the series of processes are executed by software, the programs constituting the software are installed from a recording medium into a computer incorporated in dedicated hardware, or into, for example, a general-purpose computer that can execute various functions by installing various programs.

[0254] 11 shows an example of the configuration of a general-purpose computer. This personal computer has a built-in CPU (Central Processing Unit) 1001. An input / output interface 1005 is connected to the CPU 1001 via a bus 1004. A ROM (Read Only Memory) 1002 and a RAM (Random Access Memory) 1003 are connected to the bus 1004.

[0255] Connected to the input / output interface 1005 are an input unit 1006 including input devices such as a keyboard and a mouse through which a user inputs operation commands, an output unit 1007 that outputs a processing operation screen and images of processing results to a display device, a storage unit 1008 including a hard disk drive or the like that stores programs and various data, and a communication unit 1009 including a LAN (Local Area Network) adapter or the like that executes communication processing via a network typified by the Internet. Also connected to the input / output interface 1005 is a drive 1010 that reads and writes data from / to removable storage media 1011 such as a magnetic disk (including a flexible disk), an optical disk (including a CD-ROM (Compact Disc-Read Only Memory) and a DVD (Digital Versatile Disc)), a magneto-optical disk (including an MD (Mini Disc)), or a semiconductor memory.

[0256] The CPU 1001 executes various processes in accordance with a program stored in a ROM 1002 or a program read from a removable storage medium 1011 such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, installed in a storage unit 1008, and loaded from the storage unit 1008 into a RAM 1003. The RAM 1003 also stores data necessary for the CPU 1001 to execute various processes as appropriate.

[0257] In a computer configured as described above, the CPU 1001 performs the above-described series of processes by, for example, loading a program stored in the memory unit 1008 into the RAM 1003 via the input / output interface 1005 and the bus 1004 and executing it.

[0258] The program executed by the computer (CPU 1001) can be provided by being recorded on a removable storage medium 1011 such as a package medium, for example. The program can also be provided via a wired or wireless transmission medium such as a local area network, the Internet, or digital satellite broadcasting.

[0259] In a computer, a program can be installed in the storage unit 1008 via the input / output interface 1005 by inserting a removable storage medium 1011 into the drive 1010. The program can also be received by the communication unit 1009 via a wired or wireless transmission medium and installed in the storage unit 1008. Alternatively, the program can be installed in the ROM 1002 or the storage unit 1008 in advance.

[0260] The program executed by the computer may be a program that processes in chronological order according to the order described in this specification, or may be a program that processes in parallel or at the required timing, such as when called.

[0261] 11. The CPU 1001 in FIG. 11 realizes the functions of the control unit 31 in FIG.

[0262] In this specification, a system refers to a collection of multiple components (devices, modules (components), etc.), regardless of whether all the components are contained in the same housing. Therefore, multiple devices housed in separate housings and connected via a network, and a single device housed in a single housing with multiple modules, are both systems.

[0263] The embodiments of the present disclosure are not limited to the above-described embodiments, and various modifications are possible within the scope of the gist of the present disclosure.

[0264] For example, the present disclosure can be configured as a cloud computing system in which a single function is shared and processed collaboratively by multiple devices via a network.

[0265] Furthermore, each step described in the above flowchart can be executed by one device, or can be shared and executed by multiple devices.

[0266] Furthermore, when one step includes multiple processes, the multiple processes included in that one step can be executed by one device or can be shared and executed by multiple devices.

[0267] The present disclosure can also be configured as follows.

[0268] <1> a task processing unit that processes the task based on first information having a relevance to the recognized task higher than a predetermined standard and second information having a relevance to the task lower than a predetermined standard; An information processing system comprising: <2> The task processing unit processes the task based on the first information, and further processes the task based on an evaluation of a processing result and the second information. <1> An information processing system according to claim 1. <3> further including an input data processing unit that supplies at least one of the first information and the second information to the task processing unit; When an evaluation of a processing result based on the first information by the task processing unit is lower than a predetermined threshold, the input data processing unit supplies the second information to the task processing unit. <2> An information processing system according to claim 1. <4> the input data processing unit mixes the first information and the second information at a predetermined mixing ratio and supplies the mixed information to the task processing unit; When an evaluation by the task processing unit of a processing result based on the first information and the second information mixed at the predetermined mixing ratio is lower than a predetermined threshold, the input data processing unit mixes the first information and the second information at a new mixing ratio in which the mixing ratio of the second information is increased, and supplies the mixed information to the task processing unit. <3> An information processing system according to claim 1. <5> a bias value setting unit that sets a bias value indicating a mixing ratio of the first information and the second information to be supplied to the task processing unit based on the evaluation of the processing result, and supplies the bias value to the input data processing unit; The input data processing unit mixes the first information and the second information at a mixing ratio based on the bias value and supplies the mixed information to the task processing unit. <4> An information processing system according to claim 1. <6> When the evaluation of the processing result by the task processing unit is deemed to be lower than a predetermined threshold, the bias value setting unit sets the bias value so that the mixing ratio of the second information is increased. <5> An information processing system according to claim 1. <7> the second information is composed of a plurality of hierarchical information having a plurality of hierarchical structures according to the degree of relevance to the task, When an evaluation of a processing result based on the first information by the task processing unit is deemed to be lower than a predetermined threshold, the bias value setting unit sets the bias value so as to increase a mixing ratio of the second information including the hierarchical information less relevant to the task. <6> An information processing system according to claim 1. <8> the task processing unit further includes a main information storage unit that stores main information used when processing the task, the primary information storage unit stores the first information as the primary information; When an evaluation of a processing result based on the first information by the task processing unit is lower than a predetermined threshold, the second information is stored in the main information storage unit as new main information in addition to the first information already stored. <2> An information processing system according to claim 1. <9> a bias value setting unit that sets a bias value indicating an amount of information of the second information to be stored in the primary information storage unit based on the evaluation of the processing result; The main information storage unit stores the second information by an amount of information set based on the bias value. <8> An information processing system according to claim 1. <10> When the evaluation of the processing result by the task processing unit is deemed to be lower than a predetermined threshold, the bias value setting unit sets the bias value so as to increase the amount of the second information to be stored in the primary information storage unit. <9> An information processing system according to claim 1. <11> The task processing unit processes the task based on a processing pattern or a processing model having a higher relevance to the task as the first information than a predetermined standard, and a processing pattern or a processing model having a lower relevance to the task as the second information than a predetermined standard. <1> An information processing system according to claim 1. <12> The task processing unit processes the task based on a processing pattern or a processing model having a higher relevance to the task than a predetermined standard as first information related to the task, and further processes the task based on an evaluation of a processing result based on a processing pattern or a processing model having a lower relevance to the task than a predetermined standard as second information. <11> An information processing system according to claim 1. <13> The task processing unit a supply processing unit that supplies at least one of the plurality of processing patterns or processing models with different associations; a task pattern model processing unit that processes the task based on the processing pattern or processing model supplied by the supply processing unit, the task pattern model processing unit processes the task based on a processing pattern or a processing model having a higher relevance to the task as the first information than a predetermined standard; When the evaluation by the task pattern model processing unit of the processing result based on a processing pattern or a processing model having a higher relevance to the task than a predetermined standard is lower than a predetermined threshold, the supply processing unit supplies, as the second information, a processing pattern or a processing model having a lower relevance to the task than a predetermined standard. <12> An information processing system according to claim 1. <14> When the evaluation by the task pattern model processing unit of the processing result based on a processing pattern or processing model whose relevance to the task as second information is lower than a predetermined standard is lower than a predetermined threshold, the supply processing unit supplies the task pattern model processing unit with a new processing pattern or processing model whose relevance to the task as second information is lower than another predetermined value that is even lower than the predetermined standard. <13> An information processing system according to claim 1. <15> a bias value setting unit that sets a bias value indicating a degree of relevance with the task corresponding to the processing pattern or processing model to be supplied based on the evaluation of the processing result, and supplies the bias value to the supply processing unit; The supply processing unit supplies the task pattern model processing unit with a processing pattern or a processing model having a high degree of relevance to the task corresponding to the bias value. <14> An information processing system according to claim 1. <16> The bias value setting unit sets the bias value so as to supply a processing pattern or a processing model that is highly related to the task when the evaluation of the processing result by the task pattern model processing unit is deemed to be lower than a predetermined threshold. <15> An information processing system according to claim 1. <17> an output unit that outputs a processing result of the task processing unit; <1> ~ <16> 10. An information processing system according to claim 9, wherein: <18> The output unit outputs a processing result for which the evaluation of the processing result is deemed to be higher than a threshold. <17> An information processing system according to claim 1. <19> Processing the task based on first information having a relevance to the recognized task higher than a predetermined standard and second information having a relevance to the task lower than a predetermined standard. An information processing method comprising the steps. <20> a task processing unit that processes the task based on first information having a relevance to the recognized task higher than a predetermined standard and second information having a relevance to the task lower than a predetermined standard; A program that makes a computer function as a [Explanation of symbols]

[0269] 11 information processing device, 31 control unit, 32 input unit, 33 output unit, 34 memory unit, 35 communication unit, 36 drive, 37 removable storage medium, 51 task processing unit, 71 task input unit, 72 task processing module, 73 processing result evaluation module, 74 output unit, 75 bias value setting unit, 76 input data processing unit, 77 storage module, 91 first data group, 92 second data group, 101 bias value setting unit, 102 input data processing unit, 103 storage module, 111 to n first data group to nth data group, 171 task input unit, 172 task processing module, 173 processing result evaluation module, 174 output unit, 175 bias value setting unit, 176 input data processing unit, 177 main storage module, 178 First sub-storage module, 179 Second sub-storage module, 191 First data group, 192 Second data group, 371 Task input unit, 372 Task processing module, 373 Processing result evaluation module, 374 Output unit, 375 Bias value setting unit, 376 Storage module, 381 First task processing module, 382 Second task processing module

Claims

1. Information that can be used to process a recognized task includes first information having a relevance to the task higher than a predetermined standard and second information having a relevance lower than the predetermined standard, a task processing unit that processes the task based on the first information, and if an evaluation of the processing result based on the first information is lower than a predetermined threshold, further processes the task based on mixed information obtained by mixing the first information and the second information at a mixing ratio based on the evaluation of the processing result. An information processing system comprising:

2. further including an input data processing unit that supplies at least one of the first information and the second information to the task processing unit; the input data processing unit supplies the first information to the task processing unit, and when an evaluation of a processing result by the task processing unit based on the first information is lower than a predetermined threshold, mixes the first information and the second information at the mixing ratio and supplies the result as the mixed information to the task processing unit; If the evaluation of the processing result based on the mixed information by the task processing unit is lower than a predetermined threshold, the input data processing unit mixes the first information and the second information at a new mixing ratio in which the mixing ratio of the second information is increased, and supplies the new mixed information to the task processing unit. The information processing system according to claim 1 .

3. a bias value setting unit that sets a bias value indicating a mixing ratio of the first information and the second information to be supplied to the task processing unit based on the evaluation of the processing result, and supplies the bias value to the input data processing unit; The input data processing unit mixes the first information and the second information at a mixing ratio based on the bias value and supplies the mixed information to the task processing unit. The information processing system according to claim 2 .

4. When the evaluation of the processing result by the task processing unit is deemed to be lower than a predetermined threshold, the bias value setting unit sets the bias value so that the mixing ratio of the second information is increased. The information processing system according to claim 3 .

5. the second information is composed of a plurality of hierarchical information having a plurality of hierarchical structures according to the degree of relevance to the task, When an evaluation of a processing result based on the first information by the task processing unit is deemed to be lower than a predetermined threshold, the bias value setting unit sets the bias value so as to increase a mixing ratio of the second information including the hierarchical information less relevant to the task. The information processing system according to claim 4 .

6. the task processing unit further includes a main information storage unit that stores main information used when processing the task, the primary information storage unit stores the first information as the primary information; When an evaluation of a processing result based on the first information by the task processing unit is lower than a predetermined threshold, the second information is stored in the main information storage unit as new main information in addition to the first information already stored. The information processing system according to claim 1 .

7. a bias value setting unit that sets a bias value indicating an amount of information of the second information to be stored in the primary information storage unit based on an evaluation of the processing result; The main information storage unit stores the second information by an amount of information set based on the bias value. The information processing system according to claim 6.

8. When the evaluation of the processing result by the task processing unit is deemed to be lower than a predetermined threshold, the bias value setting unit sets the bias value so as to increase the amount of the second information to be stored in the primary information storage unit. The information processing system according to claim 7 .

9. an output unit that outputs a processing result of the task processing unit; The information processing system according to claim 1 .

10. The output unit outputs a processing result for which the evaluation of the processing result is deemed to be higher than a threshold. The information processing system according to claim 9 .

11. Information that can be used to process a recognized task includes first information having a relevance to the task higher than a predetermined standard and second information having a relevance lower than the predetermined standard, The task is processed based on the first information, and if an evaluation of the processing result based on the first information is lower than a predetermined threshold, the task is further processed based on mixed information obtained by mixing the first information and the second information at a mixing ratio based on the evaluation of the processing result. An information processing method including:

12. Information that can be used to process a recognized task includes first information having a relevance to the task higher than a predetermined standard and second information having a relevance lower than the predetermined standard; a task processing unit that processes the task based on the first information, and if an evaluation of the processing result based on the first information is lower than a predetermined threshold, further processes the task based on mixed information obtained by mixing the first information and the second information at a mixing ratio based on the evaluation of the processing result. A program that makes a computer function as a

Images