Information processing device, information processing method, and program

Abstract

[Problem] To solve the problem that movement in a brain cannot be simulated when performing an operation in consideration of an expectation value in the past. [Solution] The above problem can be solved by an information processing device 1 comprising: an operation management unit 115 in which operation information associated with two or more operation identifiers is stored; a cortex unit 116 in which one or more past operation identifiers are stored in association with a feature set, which is one or more pieces of feature information, and an expected value; a reception unit 12 for receiving information; a feature acquisition unit 131 for acquiring a feature set from the received information; and a corpus callosum unit which, for one or more candidate operation identifiers among one or more past operation identifiers, acquires the similarity between the feature set associated with the candidate operation identifier and the feature set acquired by the feature acquisition unit 131, acquires a score by using the similarity and an expectation value paired with the candidate operation identifier, acquires operation information paired with one or more operation identifiers whose scores satisfy the operation condition from the operation management unit 115, and performs an operation according to the one or more pieces of operation information.

Description

Information processing device, information processing method, and program

[0001] The present invention relates to an information processing device or the like that simulates processing in the brain.

[0002] Conventionally, there has been an augmented reality system that claims to be able to monitor an individual's brain state (see Patent Document 1).

[0003] Special table 2021-511612 publication

[0004] However, conventional techniques have not been able to simulate the behavior of the brain when performing actions that take expected values ​​into account.

[0005] The information processing device of the first invention is an information processing device comprising: an action management unit in which action information corresponding to each of two or more action identifiers that identify an action is stored; a cortex unit in which one or more past action identifiers that identify actions performed in the past are stored, each corresponding to one or more feature sets that are feature information and expected values; a reception unit that receives information; a feature acquisition unit that acquires one or more feature sets that are feature information from the information received by the reception unit; and a corpus call osmosis unit that, for one or more candidate action identifiers among the one or more past action identifiers, acquires a similarity between the feature set corresponding to the candidate action identifier and the feature set acquired by the feature acquisition unit, acquires a score using the similarity and the expected value paired with the candidate action identifier, determines one or more action identifiers from the one or more candidate action identifiers whose score satisfies an action condition, acquires action information paired with each of the one or more action identifiers from the action management unit, and performs an action according to each of the one or more action information.

[0006] This configuration makes it possible to simulate the movements in the brain when performing actions that take expected values ​​into account.

[0007] Furthermore, compared to the information processing device of the first invention, the information processing device of the second invention further includes a hippocampus unit in which one or more short-term action identifiers are stored, each of which corresponds to one or more feature sets that are feature information and identifies an action that was recently performed within a predetermined period of time; the corpus callosum unit acquires, for each of one or more candidate action identifiers among the one or more past action identifiers or the one or more short-term action identifiers, a similarity between the feature set associated with the candidate action identifier and the feature set acquired by the feature acquisition unit, acquires a score using the similarity or the similarity and an expected value paired with the candidate action identifier, determines one or more action identifiers from the one or more candidate action identifiers whose score satisfies the action condition, acquires action information paired with each of the one or more action identifiers from the action management unit, and performs an action according to each of the one or more action information.

[0008] This configuration makes it possible to more accurately simulate the movements in the brain when performing actions that take expected values ​​into account.

[0009] Furthermore, in the information processing device of the third invention, compared to the second invention, an expected value is associated with each of the one or more short-term action identifiers of the hippocampus section, and the corpus callosum section acquires a similarity between the feature set associated with the candidate action identifier and the feature set acquired by the feature acquisition section for each of the one or more past action identifiers and one or more candidate action identifiers among the one or more short-term action identifiers, acquires a score using the similarity and the expected value paired with the candidate action identifier, determines one or more action identifiers from the one or more candidate action identifiers whose score satisfies the action condition, acquires action information paired with each of the one or more action identifiers from the action management section, and performs an action according to each of the one or more action information.

[0010] This configuration makes it possible to more accurately simulate the movements in the brain when performing actions that take expected values ​​into account.

[0011] In addition, the information processing device of the fourth invention is an information processing device in which, compared to any one of the first to third inventions, the reception unit receives new information after the corpus call analysis unit performs an action according to the action information, the positive analysis unit acquires a positivity based on the new information received by the reception unit, the negative analysis unit acquires a negativity based on the new information received by the reception unit, the corpus call analysis unit acquires a reward related to the difference between the positivity acquired by the positive analysis unit and the negativity acquired by the negative analysis unit, and uses the reward to update an expected value corresponding to an action identifier that identifies the action performed by the corpus call analysis unit.

[0012] With this configuration, the expected value corresponding to the action identifier can be appropriately updated.

[0013] In addition, the information processing device of the fifth invention is an information processing device in which, compared to any one of the first to fourth inventions, the corpus call osmosis unit updates the feature set corresponding to each of the one or more determined action identifiers using the feature set acquired by the feature acquisition unit.

[0014] With this configuration, after an action is performed, the feature set corresponding to the action identifier can be appropriately updated.

[0015] Furthermore, the information processing device of the sixth invention is an information processing device in which, compared to any one of the first to fifth inventions, the corpus call OSAM unit stores an action identifier that identifies the action performed by the corpus call OSAM unit in the hippocampus unit.

[0016] Such a configuration allows for storing action identifiers for executed actions.

[0017] Furthermore, the information processing device of the seventh invention is an information processing device in which, compared to any one of the first to sixth inventions, the corpus call OSAM unit stores in the cortex unit an action identifier that identifies the action performed by the corpus call OSAM unit.

[0018] Such a configuration allows for storing action identifiers for executed actions.

[0019] Furthermore, an information processing device of the eighth invention is an information processing device according to any one of the first to seventh inventions, further comprising: an NN storage unit in which neural network information having two or more pieces of node information each having a node identifier and one or more pieces of edge information each having an edge identifier and specifying connections between the nodes is stored; a start point storage unit in which one or more pieces of start point information each having one or more node identifiers that identify a node that is to fire without passing through other nodes is stored, in association with a start point condition that is a condition related to one or more pieces of feature information of the received information and is a condition for determining a node that is to fire without passing through other nodes; a firing condition storage unit in which the firing conditions are associated with one or more pieces of node information among the two or more pieces of node information and the firing conditions related to the one or more pieces of feature information are stored; and a transmission unit that determines, from the start point storage unit, one or more node identifiers that pair with the start point condition that matches the one or more pieces of feature information acquired by the feature acquisition unit, and that determines the node identifiers of nodes that are connected by edges to the fired nodes identified by the one or more node identifiers and that are passed the one or more pieces of feature information, and that are to fire based on the firing condition corresponding to the node.

[0020] With this configuration, the activity inside the brain can be simulated using a neural network.

[0021] In addition, the information processing device of the ninth invention is an information processing device in which, compared to the eighth invention, the NN storage unit stores neural network information having two or more node information having node identifiers corresponding to an area identifier that identifies one of two or more areas including positive or negative areas, and one or more edge information having an edge identifier that identifies the connection between the nodes, the positive or negative area storage unit obtains the number of fired nodes among one or more nodes corresponding to the area identifier indicating positive or negative areas, and obtains the positivity using the number of nodes, and the negative or negative area storage unit obtains the number of fired nodes among one or more nodes corresponding to the area identifier indicating negative or negative areas, and obtains the negativity using the number of nodes.

[0022] With this configuration, it is possible to use a neural network to simulate the brain's internal processes when performing an action that takes into account a reward.

[0023] In addition, the information processing device of the tenth invention is an information processing device according to the ninth invention, wherein the edge information has an edge weight, the transmission unit is a node connected to the fired node by an edge, and when determining the node identifier of the node that will fire based on the firing condition corresponding to the node, the larger the edge weight, the more likely it is to be determined as the node that will fire, and the survival rule storage unit stores one or more survival rules that correspond to the feature set, the survival rules being positive rules corresponding to positive information indicating that the node is positive or negative rules corresponding to negative information indicating that the node is negative, a judgment unit determines a survival rule that corresponds to the feature set acquired by the feature acquisition unit and acquires judgment information that is positive information or negative information corresponding to the survival rule, and when the judgment information is positive information, the transmission unit increases the weight of the edge connecting the node that is the node ahead of the fired node and corresponds to the area identifier of the positive area, and when the judgment information is negative information, the transmission unit increases the weight of the edge connecting the node that is the node ahead of the fired node and corresponds to the area identifier of the negative area.

[0024] This configuration allows for the construction of an appropriate neural network using managed survival rules.

[0025] The information processing device according to the present invention can simulate the behavior of the brain when performing an action taking into account expected values.

[0026] a block diagram of an information processing device 1 according to a first embodiment; a flowchart illustrating an example of an operation of the information processing device 1; a flowchart illustrating an example of a firing transmission process; a flowchart illustrating an example of a start node process; a flowchart illustrating an example of a firing time process; a flowchart illustrating an example of a simultaneous transmission process; a flowchart illustrating an example of a firing determination process; a flowchart illustrating an example of a survival rule application process; a flowchart illustrating an example of a weight change process; a flowchart illustrating an example of a firing pattern process; a flowchart illustrating an example of an action determination process; a flowchart illustrating an example of a score acquisition process; a flowchart illustrating an example of a post-processing process; a flowchart illustrating an example of a degree of similarity acquisition process; an overview of the computer system; and a block diagram of the computer system.

[0027] Hereinafter, embodiments of an information processing device and the like will be described with reference to the drawings. Note that components with the same reference numerals in the embodiments perform similar operations, and therefore repeated description may be omitted.

[0028] First Embodiment In this embodiment, an information processing device capable of simulating the behavior in the brain when performing an action taking into account an expected value will be described.

[0029] In this embodiment, an information processing device will be described that selects an action identifier from among action identifiers corresponding to expected values ​​that satisfy a selection condition, and executes the action identified by the action identifier.

[0030] In this embodiment, an information processing device that can appropriately update an expected value corresponding to an action identifier will be described.

[0031] In this embodiment, an information processing device capable of storing action identifiers of executed actions will be described.

[0032] In addition, in this embodiment, an information processing device will be described that obtains a score for each action using an expected value and simulates, using a neural network, the activity in the brain when an action is performed for which the score satisfies a condition.

[0033] Furthermore, in this embodiment, an information processing device capable of constructing an appropriate neural network using managed survival rules will be described.

[0034] In this specification, information X being associated with information Y means that information Y can be obtained from information X, or information X can be obtained from information Y, and the method of association is not important. Information X and information Y may be linked, may exist in the same buffer, information X may be included in information Y, or information Y may be included in information X, etc.

[0035] Furthermore, in this specification, selecting or determining information Z means obtaining information Z, obtaining a pointer to information Z, obtaining the ID of information Z, setting a flag on information Z, etc., and it is sufficient if information Z can be accessed.

[0036] 1 is a block diagram of an information processing device 1 according to this embodiment. The information processing device 1 includes a storage unit 11, a reception unit 12, a processing unit 13, and an output unit .

[0037] The storage unit 11 includes an NN storage unit 111, a starting point storage unit 112, a firing condition storage unit 113, an operation management unit 114, a cortex unit 115, a hypocampus unit 116, and a survival rule storage unit 117. The reception unit 12 includes an information reception unit 121. The processing unit 13 includes a feature acquisition unit 131, a transmission unit 132, a pattern acquisition unit 133, a corpus call analysis unit 134, a positive association unit 135, a negative association unit 136, a judgment unit 137, and a rule application unit 138.

[0038] The information processing device 1 is, for example, a terminal, but may also be a server. When the information processing device 1 is a terminal, the information processing device 1 is, for example, a personal computer, a tablet terminal, or a smartphone, but may also be a robot, etc. When the information processing device 1 is a robot, the robot may be a human-shaped robot. When the information processing device 1 is a server, the information processing device 1 is, for example, a cloud server or an ASP server, but this does not matter.

[0039] Various types of information are stored in the storage unit 11 constituting the information processing device 1. The various types of information include, for example, neural network information (hereinafter referred to as "NN information"), starting point information, firing conditions, action information, past action identifiers, short-term action identifiers, firing information, and various conditions. The various conditions include, for example, action conditions and selection conditions. It goes without saying that the various conditions may be embedded in the program.

[0040] Firing information is information about the result of firing. The firing information has a node identifier that identifies the node that fired. The firing information may usually have timer information that indicates the time of firing. The timer information may be information that indicates relative time or time information that indicates absolute time. The timer information may be considered to be a node attribute value. The firing information may have a node identifier of the node from which the firing is transmitted. The firing information may have an edge identifier of the edge when the firing is transmitted. Note that the firing information may be automatically deleted by the processing unit 13 after a certain time has passed since it was accumulated.

[0041] The NN storage unit 111 stores NN information. The NN information is information that simulates a neural network (hereinafter referred to as "NN" as appropriate) in the brain. The NN information is information that identifies an NN that has two or more nodes and one or more edges connecting the nodes. The NN information has two or more pieces of node information and one or more pieces of edge information.

[0042] Node information is information about the nodes that make up the NN. The node information has a node identifier. The node information has, for example, one or more node attribute values. Each of the two or more pieces of node information that make up the NN information corresponds to an area identifier. The area identifier is information that identifies an area in the brain. The area identifier is, for example, an area name or an area ID. The area identifier is, for example, "positive" or "negative." It is preferable that the area identifier is information that identifies one of two or more areas including "positive" or "negative." One or more pieces of node information among the two or more pieces of node information may be associated with two area identifiers, "positive" and "negative." The "positive" area is the area of ​​a node that fires in positive cases. The "negative" area is the area of ​​a node that fires in negative cases. Note that the NN information may also include node information that does not correspond to an area identifier.

[0043] A node identifier is information that identifies a node that constitutes a network. A node identifier is, for example, a node ID or node name. A node may also be called a soma. A node identifier may also be called a soma identifier.

[0044] The node attribute values ​​include, for example, node position information, firing conditions, firing probability information, and number of times information.

[0045] The node position information is the position information of a node, and is, for example, three-dimensional coordinate values ​​(x, y, z), two-dimensional coordinate values ​​(x, y), or four-dimensional quaternion (x, y, x, w).

[0046] The firing condition is a condition under which a node fires. The firing condition may be considered to be the firing condition stored in the firing condition storage unit 113. The firing condition will be described in detail later.

[0047] The firing probability information is information relating to the probability of firing. The firing probability information may be the firing probability itself, or a value obtained by converting the firing probability using a function or the like. It is preferable that the firing probability information is referenced, and a node may or may not fire at the probability specified by the firing probability information, even if the feature information is the same.

[0048] The number of times information is information based on the number of times a node has fired. The number of times information is, for example, the number of times a node fired or the firing rate. The number of times a node fired is, for example, the number of times a node fired in a specific period of time, or the cumulative number of times a node fired. The firing rate is, for example, the rate of a node fired in a specific period of time, or the rate of a node fired over the entire period of time. The firing rate of a node is the "number of times a node fired / number of times a signal was transmitted to the node."

[0049] Edge information is information about the edges that make up a neural network. Edge information is information that identifies edges that connect nodes. Edge information typically includes an edge identifier. Edge identifiers are information that identify edges. The edge identifier is, for example, the edge ID or the edge name. Edge information is, for example, the node identifier of each of the two nodes that the edge connects. Edge information is, for example, the node identifier of one connecting node. When edge information includes only one node identifier, the edge is in the growth process before connecting the two nodes. Edge information includes one or more edge attribute values. The edge attribute values ​​are, for example, weight and edge position information. Weight can be considered information based on the thickness of the edge. The larger the weight, the more easily information is transmitted via the edge. The larger the edge weight, typically, the more likely the node beyond the edge is to fire. Edge position information is edge position information. Edge position information is information that identifies the position of the endpoint of the edge. When edge information includes two node identifiers, for example, edge position information is not included. When edge information has two node identifiers, the edge specified by the edge information connects two nodes.

[0050] The edge information includes, for example, dendrites information and AXON information. In this case, the edge includes dendrites and AXON. Note that the edge may be considered to be a single line or two or more branched lines. The edge may also be called a synapse.

[0051] Dendrites information is information about DENDRITES. DENDRITES are also called dendrites and are parts of nerve cells. They are multiple projections that branch out from the cell body like the branches of a tree in order for nerve cells to receive external stimuli and information sent from the axons (AXONs) of other nerve cells. DENDRITES are elements that make up edges in this case. DENDRITES information includes a DENDRITES identifier and DENDRITES position information.

[0052] The DENDRITES identifier is information for identifying DENDRITES, such as the ID or name of DENDRITES.

[0053] DENDRITES position information is information about the position of DENDRITES. DENDRITES position information is information that specifies the position of DENDRITES, and is, for example, one or more three-dimensional coordinate values ​​(x, y, z) or one or more two-dimensional coordinate values ​​(x, y). When the DENDRITES position information has two or more coordinate values, DENDRITES is a line connecting the points of the two or more coordinate values.

[0054] It is also preferable that the dendrites information includes information on the amount of energy held by the dendrites, which indicates the amount of energy held by the dendrites.It is also preferable that the dendrites information includes information on the amount of energy required to transmit information using the dendrites.

[0055] The axon information is information about an axon. An axon, also known as an axon, is a protruding structure extending from a cell body and responsible for signal output in a nerve cell. Here, an axon is an element that constitutes an edge. The axon information includes an axon identifier and axon position information.

[0056] The AXON identifier is information for identifying the AXON, such as the ID or name of the AXON.

[0057] AXON position information is information about the position of the AXON. The AXON position information is information that specifies the position of the AXON, and is, for example, one or more three-dimensional coordinate values ​​(x, y, z) or one or more two-dimensional coordinate values ​​(x, y). When the AXON position information has two or more coordinate values, the AXON is a line connecting the points of the two or more coordinate values.

[0058] Preferably, the AXON information includes information on the amount of energy stored in the AXON, and information on the amount of energy required to transmit information using the AXON.

[0059] Note that dendrites and AXON may be branched. When dendrites and AXON are branched, the position information of each may be expressed by three or more coordinate values. However, the method of expressing dendrite position information and AXON position information does not matter.

[0060] The start point storage unit 112 stores one or more pieces of start point information. The start point information is information for determining the node that will fire first when information is received. The start point information corresponds to a start point condition. The start point information usually has a node identifier that identifies the node that can fire first. The node that can fire first is a node that does not receive information from other fired nodes. The node that can fire first is usually a node in the input layer. The start point information has, for example, one or more node identifiers and a start point condition. The start point condition is a condition for determining the node that will fire without going through other nodes. The start point condition is a condition related to one or more pieces of feature information obtained from the information received by the information receiving unit 121. Note that the one or more pieces of feature information are referred to as a "feature set" as appropriate.

[0061] The firing condition storage unit 113 stores one or more firing conditions. The firing condition corresponds to the node information. The firing condition may be included in the node information. The firing condition is a condition for a node to fire. The firing condition is information related to one or more pieces of feature information.

[0062] The firing condition storage unit 113 stores firing conditions corresponding to one or more pieces of node information among the two or more pieces of node information. Note that node information not corresponding to a firing condition may or may not exist. Node information not corresponding to a firing condition is information about a node that will always fire when a signal is transmitted.

[0063] The firing condition is, for example, a condition related to one or more feature information of the sound information. In such a case, the firing condition is called a sound feature condition. The sound feature condition is, for example, a condition related to a specific frequency of the sound information. In such a case, the firing condition is called a frequency condition. The frequency condition is, for example, information specifying a frequency range (e.g., "first threshold <= frequency <= second threshold"), information specifying an upper frequency limit (e.g., "frequency <= second threshold"), or information specifying a lower frequency limit (e.g., "first threshold <= frequency"). Examples of frequency conditions are "<information identifier> frequency = Fa <condition> information amount > = 100", "<information identifier> Fa <= frequency <Fb <condition> information amount > = 100", or "<information identifier> R <condition> information amount > = 150 & <information identifier> frequency = Fa <condition> information amount > = 180". Note that the frequencies Fa and Fb are values ​​indicating specific frequencies. Also, "<information identifier> frequency=Fa <condition> information amount>=100" means that the information amount (for example, volume) of the frequency "Fa" is 100 or more.

[0064] The firing condition is, for example, a condition related to one or more feature information of the image information. Such a firing condition is called an image feature condition. An example of the image feature condition is "<information identifier>R <condition> information amount >= 150". An example of the initial firing condition is "information amount of 'R' >= 150", "(information amount of 'R' >= 150) & (information amount of 'G' >= 80)", or "(information amount of 'R' >= 150) & (information amount of 'G' >= 80) & (information amount of 'B' >= 120)".

[0065] The firing condition is, for example, a condition related to the frequency at which a signal is transmitted to a node. Such a firing condition is called a frequency condition. The frequency condition is a condition related to frequency information. Frequency information is information related to the frequency at which information is transmitted to a node. For example, frequency information is the time resolution at which a signal is transmitted and the number of times a signal is transmitted within a predetermined time. Note that the information here is typically one or more characteristic pieces of information about the received information. The information here may also be referred to as a signal. For example, frequency conditions are a condition for a specific time resolution, a condition for a specific range of time resolution, a condition for specific rhythm information, a condition for a range of similarity with a reference specific rhythm information, etc. The time resolution is the number of times a signal fires per unit time. The rhythm information is a vector whose elements are the values ​​of two or more intervals (times) during which a signal is transmitted. Note that the transmission of a signal to a node means, for example, that another node connected to the node by an edge fires. When a signal is transmitted to a node, the node in question is, for example, a node connected to the edge determined to transmit the signal.

[0066] The firing condition may be, for example, a combination of two or more conditions selected from a sound feature condition, an image feature condition, and a frequency condition.

[0067] The operation management unit 114 stores two or more pieces of operation information. An operation identifier corresponds to each of the two or more pieces of operation information. Operation information is information that identifies an operation. The operation information is, for example, a program, a module, an operation name, etc. The operation information may have a positive or negative degree. Such a positive or negative degree may not be fixed, but may change dynamically. An operation identifier is information that identifies an operation. The operation identifier is, for example, an operation ID, an operation name (for example, a function name, a method name, a module name), etc.

[0068] The cortex unit 115 stores one or more past action identifiers. A past action identifier is an action identifier that identifies an action performed in the past. Examples of past action identifiers include "laugh" and "cry." The cortex unit 115 may also be referred to as "Cortex 115." Each of the one or more past action identifiers in the cortex unit 115 typically corresponds to a feature set and an expected value. Each of the one or more past action identifiers may correspond to two or more pairs of feature sets and expected values. Each of the one or more past action identifiers may correspond to one expected value and two or more feature sets. The feature set here is a feature set acquired from information input when the action specified by the past action identifier is performed. The expected value is the degree of expectation when the action specified by the action identifier is performed. The expected value may also be referred to as information that specifies a reward to be obtained when the action specified by the action identifier is performed. The reward may also be referred to as a benefit, etc.

[0069] The hippocampus section 116 stores one or more short-term action identifiers. A short-term action identifier is an action identifier that identifies a recently performed action. "Recently" typically refers to a predetermined period of time. The predetermined period of time refers to a predetermined period of time from the current point in time. Note that the predetermined period of time may change. An example of a short-term action identifier is "raise hand." Note that the hippocampus section 116 may also be referred to as "hippocampus116" or "HIP116." Each of the one or more short-term action identifiers in the hippocampus section 116 is associated with a feature set. Each of the one or more short-term action identifiers may be associated with two or more pairs of feature sets and expected values. Each of the one or more short-term action identifiers may be associated with one expected value and two or more feature sets. The feature set here is a feature set acquired from information input when the action identified by the short-term action identifier is performed. Preferably, each of the one or more short-term action identifiers of the hippocampus section 116 has an expected value associated with it.

[0070] When a predetermined period of time has elapsed since the action identified by the short-term action identifier of the hippocampus unit 116 was performed, for example, the short-term action identifier is deleted from the hippocampus unit 116. Note that the deleted short-term action identifier may be written to the cortex unit 115 as a past action identifier.

[0071] It is also possible that the hippocampus unit 116 does not exist, and the unit that manages the action identifiers of the performed actions is the cortex unit 115 alone.

[0072] The survival rule storage unit 117 stores one or more survival rules. Each of the one or more survival rules is associated with judgment information. Each of the one or more survival rules is associated with a feature set. Judgment information is information that specifies the type of survival rule. Judgment information is positive information or negative information. Positive information is information that indicates positive, for example, "1". Negative information is information that indicates negative, for example, "0". Each of the one or more survival rules may be associated with both positive information and negative information. Each of the one or more survival rules is associated with one or more feature sets. A feature set is one or more pieces of feature information.

[0073] A survival rule is, for example, a rule used by a person to survive. Each of the one or more survival rules is a positive rule or a negative rule. A positive rule is a rule that defines something as positive. A positive rule is a rule that corresponds to positive information. A negative rule is a rule that defines something as negative. A negative rule is a rule that corresponds to negative information. Here, rules are usually information. A positive rule is, for example, a feature set of images of delicious food or a feature set of laughter. A negative rule is, for example, a feature set of images of cockroaches.

[0074] The receiving unit 12 receives various types of information and instructions. The various types of information and instructions include, for example, images, voice, sounds, character strings, and operation instructions. An operation instruction is an instruction to start an operation.

[0075] The receiving unit 12 receives the information after the corpus call processing unit 134 performs an operation according to the operation information. Such information is new information.

[0076] The information receiving unit 121 receives information, such as an image, a voice, a sound, or a character string.

[0077] Here, reception is a concept that includes, for example, reception of information input from an input device such as a keyboard, mouse, or touch panel, acquisition by a microphone, acquisition by a camera, reception of information transmitted via a wired or wireless communication line, and reception of information read from a recording medium such as an optical disk, magnetic disk, or semiconductor memory.

[0078] The means for inputting information may be any means, such as a touch panel, keyboard, mouse, menu screen, microphone, or camera.

[0079] The processing unit 13 performs various processes, such as processes performed by a feature acquisition unit 131, a transmission unit 132, a pattern acquisition unit 133, a corpus call analysis unit 134, a positive analysis unit 135, a negative analysis unit 136, a judgment unit 137, and a rule application unit 138.

[0080] The feature acquisition unit 131 acquires a feature set, which is one or more pieces of feature information, from the information received by the reception unit 12. The feature information may also be referred to as a feature amount.

[0081] When the received information is sound information, the acquired feature information is called sound feature information. It is preferable that the one or more pieces of sound feature information include frequency. The one or more pieces of sound feature information may include volume. The one or more pieces of sound feature information may be, for example, MFCC or Mel spectrum, but this is not important. When the received information is image information, the acquired feature information is called image feature information. The one or more pieces of image feature information are typically R, G, and B values. The one or more pieces of image feature information may include brightness, lightness, and saturation. When the received information is a character string, the acquired feature information is, for example, one or more independent words.

[0082] The transmission unit 132 determines one or more node identifiers corresponding to the start point conditions that match the one or more pieces of feature information acquired by the feature acquisition unit 131. This determination is to determine the node that will fire first when the information is accepted. Determining a node identifier, for example, is to obtain a node identifier. Determining a node identifier is to cause the node identified by the node identifier to fire. When a node fires, conceptually, for example, one or more pieces of feature information are passed to other nodes connected to the node by edges. Such one or more pieces of feature information are information that the node holds at least temporarily.

[0083] The transmission unit 132 is a node that is connected to the fired node by an edge, receives one or more pieces of feature information from the fired node, and determines the node identifier of the node that will fire based on the firing condition corresponding to the node. This processing is a firing transmission processing.

[0084] It is preferable that the transmission unit 132 recursively determines the node to be fired and acquires the node identifier of the node.

[0085] The transmitter 132 is a node connected to the fired node by an edge, and when determining the node identifier of a node that will fire based on the firing condition corresponding to the node, it is preferable to perform processing such that the greater the weight of the edge, the more likely the node is to be determined as a node that will fire. Note that the processing for making it easier to determine a node is, for example, using the weight of the edge to determine that the greater the weight, the more likely the node is to fire. The processing for making it easier to determine a node is, for example, processing for making it easier to determine a node is, for example, processing for making the firing probability information included in the node information of a node connected to the edge greater, the greater the weight of the edge.

[0086] After determining the node to be fired, the transmission unit 132, for example, obtains timer information that specifies the time of firing, composes firing information having the node identifier of the fired node and the timer information, and stores the firing information in the storage unit 11.

[0087] The pattern acquisition unit 133 acquires a firing pattern. The firing pattern is information about one or more firing nodes. The firing pattern includes, for example, one or more node identifiers determined by the transmission unit 132.

[0088] The pattern acquisition unit 133 acquires, for example, a firing pattern that can be acquired from the firing information in the storage unit 11. The pattern acquisition unit 133 acquires, for example, a firing pattern that includes a node identifier included in one or more pieces of firing information in the storage unit 11. Such firing information is, for example, firing information that has been stored in the storage unit 11 and has not been deleted. Such firing information is, for example, firing information that has been stored in the storage unit 11 within a predetermined time. Such firing information is, for example, information on fired nodes among the nodes in the output layer.

[0089] The pattern acquisition unit 133 acquires, for example, a firing pattern that identifies a node in the output layer from among the one or more nodes determined by the transmission unit 132. In this case, the node identified by the one or more node identifiers included in the firing pattern is the node in the output layer.

[0090] For each of one or more candidate action identifiers among the one or more past action identifiers in the cortex unit 115, the corpus call OSAM unit 134 acquires a similarity between a feature set associated with the candidate action identifier and the feature set acquired by the feature acquisition unit 131. Next, for each of the one or more candidate action identifiers, the corpus call OSAM unit 134 acquires a score using the similarity and an expected value paired with the candidate action identifier. Next, the corpus call OSAM unit 134 determines, from the one or more candidate action identifiers, one or more action identifiers whose acquired score satisfies the action condition, and acquires action information paired with each of the one or more action identifiers from the action management unit 114. Next, the corpus call OSAM unit 134 performs an action corresponding to each of the one or more action information.

[0091] The corpus call OSAM unit 134 acquires a higher score as the similarity increases. The corpus call OSAM unit 134 acquires a higher score as the expected value increases. The operating conditions are conditions for selecting an operating identifier. The operating conditions are conditions related to the score. Examples of operating conditions are "the score is the maximum," "the score is equal to or greater than a threshold," "the score is in the top N (N is a natural number equal to or greater than 1)," and "the score is Nth (N is a natural number equal to or greater than 1)." The operating conditions may be fixed or may change dynamically.

[0092] Furthermore, the operation according to the operation information is the operation specified by the operation information, such as executing a program or module included in the operation information, or performing an operation identified by an operation identifier associated with the operation information.

[0093] The corpus call summing unit 134 may use any algorithm to obtain the similarity between two feature sets. For example, the corpus call summing unit 134 obtains the distance between two feature sets, which are vectors, as the similarity. For example, the corpus call summing unit 134 calculates the similarity using an increasing function that uses the number of identical elements in the two feature sets, which are vectors, as a parameter.

[0094] When the receiving unit 12 receives information, the corpus call OSAM unit 134, for example, acquires one or more past action identifiers from the cortex unit 115 and one or more short-term action identifiers from the hippocampus unit 116. Each of these one or more past action identifiers and each of these one or more short-term action identifiers are candidate action identifiers. In other words, when the receiving unit 12 receives information, the corpus call OSAM unit 134 acquires two or more candidate action identifiers. Next, for each of the two or more candidate action identifiers, the corpus call OSAM unit 134 acquires a score for when the action identified by the candidate action identifier is performed. For example, the corpus call OSAM unit 134 acquires the similarity between the feature set paired with the candidate action identifier and the feature set acquired by the feature acquisition unit 131, and acquires a score using an increasing function with the similarity as a parameter. For example, the corpus call OSAM unit 134 acquires an expected value paired with each of the two or more candidate action identifiers as a score. The corpus call OSAM unit 134, for example, acquires the similarity between the feature set paired with the candidate action identifier and the feature set acquired by the feature acquisition unit 131, and acquires a score using an increasing function with parameters of the similarity and the expected value paired with the candidate action identifier.

[0095] The corpus callosum unit 134 may also be called "Corpus Callosum 134."

[0096] The corpus call osm unit 134 preferably acquires from the cortex unit 115 one or more past action identifiers associated with expected values ​​that satisfy a selection condition, acquires two or more candidate action identifiers that are one or more short-term action identifiers stored in the hippocampus unit 116 in conjunction with the one or more action identifiers, acquires a score for each of the two or more candidate action identifiers when the action identified by the candidate action identifier is performed, determines one or more candidate action identifiers whose scores satisfy the action condition, acquires action information paired with each of the one or more candidate action identifiers from the action management unit 114, and performs an action corresponding to each of the one or more action information. The selection condition is a condition for selecting a candidate action identifier. The selection condition is a condition related to an expected value paired with a past action identifier. For example, the selection condition is that the expected value is equal to or greater than a threshold.

[0097] The corpus callOSM unit 134 may acquire one or more past action identifiers corresponding to expected values ​​that satisfy the selection conditions from the cortex unit 115, acquire one or more short-term action identifiers corresponding to expected values ​​that satisfy the selection conditions from the hippocampus unit 116, acquire a score for each of two or more candidate action identifiers that are the one or more past action identifiers and the one or more short-term action identifiers, determine one or more candidate action identifiers whose score satisfies the action conditions, acquire action information paired with each of the one or more candidate action identifiers from the action management unit 114, and perform an action according to each of the one or more action information.

[0098] Furthermore, the corpus call summing unit 134 obtains a reward related to the difference between the positivity obtained by the positive assessment unit 135 and the negativity obtained by the negative assessment unit 136. Then, the corpus call summing unit 134 preferably uses the reward to update the expectation value corresponding to the action performed by the corpus call summing unit 134.

[0099] When the corpus call OSAM unit 134 updates the expected value using the reward, it may be by adding a new expected value or by updating the expected value associated with the action identifier.

[0100] When a new expected value is added, the corpus call summing unit 134 uses the acquired reward to acquire a new expected value and associates the new expected value with the action identifier. In such a case, it is preferable that the corpus call summing unit 134 associates the feature set acquired by the feature acquisition unit 131 with the action identifier in addition to the acquired new expected value. Note that the new expected value to be added may be the reward, or may be a value calculated by an increasing function with the reward as a parameter.

[0101] When updating an expected value associated with an action identifier, the corpus call OSAM unit 134, for example, adds a reward to the expected value associated with the action identifier. The corpus call OSAM unit 134, for example, calculates a new expected value using an increasing function with the expected value associated with the action identifier and the reward as parameters, and associates the new expected value with the action identifier.

[0102] When updating an expected value associated with an action identifier, the corpus call summing unit 134 preferably also updates a feature set corresponding to the action identifier, for example. The corpus call summing unit 134 also updates the feature set corresponding to the action identifier, for example, using the feature set acquired by the feature acquisition unit 131. Specifically, the corpus call summing unit 134 acquires, for each element of the feature set, a representative value (e.g., average or weighted average) between the element values ​​of the feature set acquired by the feature acquisition unit 131 and the element values ​​of the feature set corresponding to the action identifier, acquires a feature set that is a vector whose elements are the representative values ​​of each element, and associates the feature set with the action identifier.

[0103] The reward may be the difference between the positivity and negativity, or a value obtained by an increasing function that uses the difference between the positivity and negativity as a parameter, or a value obtained by a function that is an increasing function that uses the positivity as a parameter and a decreasing function that uses the negativity as a parameter. The greater the positivity, the greater the value of the reward, and the greater the negativity, the smaller the value.

[0104] Preferably, the corpus call sum unit 134 stores in the hippocampus unit 116 an action identifier that identifies the action taken by the corpus call sum unit 134 .

[0105] Corpus call summing unit 134 may store in cortex unit 115 an action identifier that identifies the action performed by corpus call summing unit 134 .

[0106] The corpus call OSAM unit 134 may store action identifiers that identify actions performed by the corpus call OSAM unit 134 in both the hippocampus unit 116 and the cortex unit 115, or may store them only in the hippocampus unit 116, or may store them only in the cortex unit 115. When the corpus call OSAM unit 134 stores action identifiers only in the hippocampus unit 116, for example, the processing unit 13 moves the action identifiers from the hippocampus unit 116 to the cortex unit 115 when a predetermined time or more has passed since the action identifiers were stored in the hippocampus unit 116. When the corpus call OSAM unit 134 stores action identifiers in both the hippocampus unit 116 and the cortex unit 115, for example, the processing unit 13 deletes the action identifiers from the hippocampus unit 116 when a predetermined time or more has passed since the action identifiers were stored.

[0107] The positivity calculator 135 obtains the positivity level when a movement identified by one or more candidate movement identifiers is performed based on the information received by the receiver 12 .

[0108] The positivity calculator 135 obtains a positivity level based on the new information received by the receiver 12 .

[0109] The positivity calculator 135 preferably uses the firing pattern when the receiving unit 12 receives information to obtain the number of fired nodes among one or more nodes corresponding to the area identifier indicating the positivity, and obtains the positivity using the number of nodes. The positivity calculator 135 obtains a larger positivity as the number of nodes increases. The positivity calculator 135 calculates the positivity using, for example, an increasing function with the number of nodes as a parameter. The positivity calculator 135 obtains the positivity corresponding to the number of nodes from, for example, a correspondence table. The correspondence table has two or more pieces of correspondence information each representing a range of node numbers and a positivity.

[0110] The positivity calculator 135, for example, acquires a positivity level paired with a candidate action identifier from the action management unit 114. In such a case, if the action management unit 114 does not have a positivity level paired with the candidate action identifier, the positivity calculator 135 acquires a positivity level of "0" corresponding to the candidate action identifier. Note that it is preferable that the positivity level paired with an action identifier change dynamically.

[0111] The negativity assessment unit 136 acquires the degree of negativity when a movement identified by one or more candidate movement identifiers is performed based on the information received by the receiving unit 12 .

[0112] The negative feedback unit 136 acquires the degree of negativity based on the new information received by the receiving unit 12 .

[0113] Preferably, the negativity unit 136 acquires the number of fired nodes among one or more nodes corresponding to the area identifier indicating the negativity using the firing pattern when the receiving unit 12 receives information, and acquires the negativity degree using the number of fired nodes. The larger the number of nodes, the larger the negativity degree acquired by the negativity unit 136. For example, the negativity unit 136 calculates the positivity degree using an increasing function with the number of nodes as a parameter. For example, the negativity unit 136 acquires the negativity degree corresponding to the number of nodes from a correspondence table. Such a correspondence table has two or more pieces of correspondence information each having a range of the number of nodes and a negativity degree.

[0114] The negativity unit 136, for example, acquires a negativity degree paired with a candidate action identifier from the action management unit 114. In such a case, if the action management unit 114 does not have a negativity degree paired with the candidate action identifier, the negativity unit 136 acquires a negativity degree of "0" corresponding to the candidate action identifier. Note that it is preferable that the negativity degree paired with an action identifier change dynamically.

[0115] The determination unit 137 determines a survival rule that is satisfied by the information received by the reception unit 12 from one or more survival rules in the survival rule storage unit 117, and obtains determination information associated with the survival rule from the survival rule storage unit 117.

[0116] The judgment unit 137 determines a survival rule corresponding to the feature set acquired by the feature acquisition unit 131 from one or more survival rules in the survival rule storage unit 117, and acquires judgment information, which is positive information or negative information, associated with the survival rule.

[0117] If the judgment information acquired by the judgment unit 137 is positive, the rule application unit 138 increases the weight of the edge connecting the node that is the node ahead of the node that was fired by the transmission unit 132 and that corresponds to the area identifier of the area of ​​the positive area. The amount by which the edge weight is increased does not matter.

[0118] If the determination information acquired by the determination unit 137 is negative information, the rule application unit 138 increases the weight of the edge connecting the node that is the node ahead of the node that was fired by the transmission unit 132 and that corresponds to the area identifier of the negative area. The amount by which the edge weight is increased does not matter.

[0119] The output unit 14 outputs various types of information. The various types of information are, for example, the results of operations performed by the corpus call summing unit 134. Note that the corpus call summing unit 134 may output the results of operations performed by the corpus call summing unit 134. In such a case, the output unit 14 is not necessary.

[0120] Output is a concept that includes displaying on a display, projecting using a projector, printing on a printer, outputting sound, transmitting to an external device, storing on a recording medium, and handing over processing results to other processing devices or other programs.

[0121] The storage unit 11, NN storage unit 111, starting point storage unit 112, firing condition storage unit 113, operation management unit 114, cortex unit 115, hypocampus unit 116, and survival rule storage unit 117 are preferably non-volatile recording media, but can also be realized using volatile recording media.

[0122] There is no restriction on the process by which information is stored in the storage unit 11 etc. For example, information may be stored in the storage unit 11 etc. via a recording medium, information transmitted via a communication line etc. may be stored in the storage unit 11 etc., or information input via an input device may be stored in the storage unit 11 etc.

[0123] The reception unit 12 and the information reception unit 121 are realized by, for example, a device driver for an input means such as a touch panel or keyboard, control software for a menu screen, wireless or wired communication means, or means for receiving broadcasts.

[0124] The processing unit 13, feature acquisition unit 131, transmission unit 132, pattern acquisition unit 133, corpus call analysis unit 134, positive and negative analysis unit 135, negative and positive analysis unit 136, judgment unit 137, and rule application unit 138 can typically be realized by a processor, memory, etc. The processing procedures of the processing unit 13, etc. are typically realized by software, and the software is recorded on a recording medium such as a ROM. However, they may also be realized by hardware (dedicated circuitry). The processor may be a CPU, MPU, GPU, etc., and the type does not matter.

[0125] The output unit 14 may or may not include an output device such as a display, a speaker, etc. The output unit 14 may be realized by driver software for an output device, or a combination of driver software for an output device and the output device, etc.

[0126] Next, an example of the operation of the information processing device 1 will be described with reference to the flowchart of FIG.

[0127] (Step S201) The information receiving unit 121 determines whether or not information has been received. If information has been received, the process proceeds to step S202, and if information has not been received, the process proceeds to step S204.

[0128] (Step S202) The transmission unit 132 and the like perform the firing transmission process. Return to step S201. An example of the firing transmission process will be described using the flowchart in Fig. 3. The firing transmission process is a process that imitates the transmission of a signal within a neural network in response to the reception of information.

[0129] (Step S203) The rule application unit 138 etc. performs a survival rule application process. An example of the survival rule application process will be described with reference to the flowchart in Fig. 8. The survival rule application process is a process of determining a survival rule corresponding to the received information and increasing the weight of the edge in accordance with the determined survival rule.

[0130] (Step S204) The processing unit 13 determines whether it is time to perform firing pattern processing. If it is time to perform firing pattern processing, the processing proceeds to step S205, and if it is not time to perform firing pattern processing, the processing returns to step S201.

[0131] The timing for performing the firing pattern processing may be, for example, when a node fires, periodically, constantly, or when a node that has fired exists within a predetermined time from the current time. The timing for performing the firing pattern processing is not important. When a node fires, it is usually when the firing information is accumulated in the storage unit 11.

[0132] (Step S205) The corpus call OSAM unit 134 and the like perform firing pattern processing. Return to step S201. An example of the firing pattern processing will be described with reference to the flowchart of FIG.

[0133] The firing pattern processing is a process of detecting a firing pattern related to a fired node and executing an operation corresponding to the firing pattern.

[0134] In the flowchart of FIG. 2, the process ends when the power is turned off or an interrupt occurs to end the process.

[0135] Next, an example of the firing transmission process in step S202 will be described with reference to the flowchart of FIG.

[0136] (Step S301) The transmission unit 132 assigns 1 to a counter i.

[0137] (Step S302) The transmission unit 132 determines whether the i-th information exists among the information received in S201. If the i-th information exists, the process proceeds to step S303; if not, the process proceeds to step S306.

[0138] The information accepted in S201 is, for example, one or two types of information from among audio information and image information.

[0139] (Step S303) The feature acquisition unit 131 acquires one or more pieces of feature information of the i-th information and temporarily stores them in a buffer (not shown). If the i-th information is audio information, it is preferable that the one or more pieces of feature information include frequency. If the i-th information is image information, it is preferable that the one or more pieces of feature information include the amount of information for each of "R", "G", and "B".

[0140] (Step S304) The transmission unit 132 increments the counter i by 1. The process returns to step S302.

[0141] (Step S305) The transmission unit 132 performs start node processing using one or more pieces of feature information stored in a buffer (not shown). An example of the start node processing will be described with reference to the flowchart in Fig. 4. The start node processing is processing for determining the node that will be fired first based on the received information.

[0142] (Step S306) The transmission unit 132 assigns 1 to the counter i.

[0143] (Step S307) The transmission unit 132 determines whether or not the i-th ignition node exists among the nodes determined to ignite in step S305. If the i-th ignition node exists, the process proceeds to step S308; if not, the process returns to the upper level process.

[0144] (Step S308) The transmission unit 132 performs next transmission processing. An example of the next transmission processing will be described using the flowchart in FIG. 6. The next transmission processing is processing that imitates the transmission of firing from one node to a next node connected to the first node by an edge. The next transmission processing is processing that determines the node that will fire next, which is a node to which one or more pieces of feature information are passed from the firing node of interest.

[0145] (Step S309) The transmission unit 132 increments the counter i by 1. The process returns to step S307.

[0146] Next, an example of the start node process in step S305 will be described with reference to the flowchart of FIG.

[0147] (Step S401) The transmission unit 132 assigns 1 to a counter i.

[0148] (Step S402) The transmission unit 132 determines whether or not the i-th start point information exists in the start point storage unit 112. If the i-th start point information exists, the process proceeds to step S403; if not, the process returns to the upper level process.

[0149] (Step S403) The transmitter 132 acquires the start point condition included in the i-th start point information from the start point storage unit 112.

[0150] (Step S404) The transmission unit 132 determines whether or not one or more pieces of feature information stored in a buffer (not shown) in step S303 match the i-th start point condition acquired in step S403. If the one or more pieces of feature information match the i-th start point condition, the process proceeds to step S405; if not, the process proceeds to step S410.

[0151] (Step S405) The transmitter 132 acquires, from the start point storage unit 112, one or more node identifiers that are paired with the i-th start point condition.

[0152] (Step S406) The transmission unit 132 assigns 1 to the counter j.

[0153] (Step S407) The transmission unit 132 determines whether or not the j-th node identifier exists among the one or more node identifiers acquired in step S405. If the j-th node identifier exists, the process proceeds to step S408; if not, the process proceeds to step S410.

[0154] (Step S408) The transmission unit 132 performs an ignition process for the node identified by the j-th node identifier. An example of the ignition process will be described with reference to the flowchart in Fig. 5. The ignition process is a process that is performed when a node ignites.

[0155] (Step S409) The transmission unit 132 increments the counter j by 1. The process returns to step S407.

[0156] (Step S410) The transmission unit 132 increments the counter i by 1. The process returns to step S402.

[0157] 4, if there is no start point condition in the start point storage unit 112, the transmission unit 132 proceeds to step S406 after acquiring one or more node identifiers from the start point storage unit 112. In this case, the node that will fire first has already been determined.

[0158] Next, an example of the firing process in steps S408 and S612 will be described with reference to the flowchart of FIG.

[0159] (Step S501) The transmission unit 132 acquires the node identifier of the node that will fire. Note that this node identifier is, for example, the j-th node identifier of step S407.

[0160] (Step S502) The transmission unit 132 acquires one or more pieces of characteristic information and associates the one or more pieces of characteristic information with the node identifier acquired in step S501.

[0161] The one or more pieces of characteristic information are characteristic information acquired from the received information or characteristic information associated with the node from which the firing is transmitted. The characteristic information associated with the node from which the firing is transmitted is usually the same as the characteristic information acquired from the received information. The characteristic information associated with the node from which the firing is transmitted is characteristic information among the characteristic information acquired from the received information, and may be only the characteristic information used to determine the firing condition.

[0162] (Step S503) The transmission unit 132 acquires timer information that identifies the time of firing. The transmission unit 132 generates firing information that includes the node identifier acquired in step S501 and the timer information. The transmission unit 132 stores the firing information in the storage unit 11.

[0163] The transmission unit 132 may obtain, for example, timer information specifying the time of firing from a clock (not shown). The transmission unit 132 may obtain, for example, the node identifier of the node that caused the firing and the edge identifier of the edge that was passed through when the firing occurred, and may form firing information having the node identifier and the edge identifier, and store the firing information in the storage unit 11.

[0164] (Step S504) The transmission unit 132 updates one or more node attribute values ​​paired with the node identifier acquired in step S501, and returns to the upper-level processing.

[0165] Here, the transmission unit 132 increments, for example, the number of times information paired with the node identifier acquired in step S501 by 1. The transmission unit 132 increments, for example, the firing probability information paired with the node identifier acquired in step S501. Note that the amount of increment is not important. For example, the transmission unit 132 substitutes the original firing probability information into an increasing function that uses the firing probability information as a parameter, executes the increasing function, acquires new firing probability information, and rewrites the original firing probability information with the new firing probability information.

[0166] Next, an example of the next transmission process in step S308 will be described with reference to the flowchart of FIG.

[0167] (Step S601) The transmission unit 132 acquires the node identifier of a node of interest. The node of interest is the i-th firing node of step S307.

[0168] (Step S602) The transmitter 132 acquires one or more pieces of feature information paired with the node identifier acquired in step S601. The one or more pieces of feature information paired with the node identifier are nodes connected by edges to the node identified by the node identifier, and may be one or more pieces of feature information paired with a node that fired previously.

[0169] (Step S603) The transmission unit 132 obtains one or more edge identifiers that are paired with the node identifier obtained in step S601 from the NN storage unit 111. Note that these one or more edge identifiers are identifiers of edges ahead of the node. The node ahead refers to the destination to which a signal is transmitted from the node. The transmission of a signal can be considered as the passing of one or more pieces of feature information.

[0170] (Step S604) The transmission unit 132 determines whether or not one or more edge identifiers were acquired in step S603. If an edge identifier was acquired, the process proceeds to step S605; if an edge identifier was not acquired, the process returns to the upper level processing. If an edge identifier paired with the node identifier was not acquired, this means that the node identified by the node identifier is a node in the output layer of the NN node group.

[0171] (Step S605) The transmission unit 132 assigns 1 to the counter i.

[0172] (Step S606) The transmission unit 132 determines whether or not the i-th edge identifier exists among the edge identifiers acquired in step S603. If the i-th edge identifier exists, the process proceeds to step S607; if not, the process returns to the upper level process.

[0173] (Step S607) The transmission unit 132 acquires one or more edge attribute values ​​paired with the i-th edge identifier from the NN storage unit 111. The one or more edge attribute values ​​include, for example, a weight.

[0174] (Step S608) The transmission unit 132 determines whether or not to transmit a signal via the edge, using one or more edge attribute values ​​(e.g., weights) acquired in step S607. If the signal is to be transmitted, the process proceeds to step S609; if not, the process proceeds to step S614.

[0175] Note that the transmission unit 132 normally increases the probability of determining to transmit a signal as the weight increases. The transmission unit 132 obtains the probability of determining to transmit a signal, for example, using an increasing function with the weight as a parameter, and determines whether to transmit a signal in accordance with the probability. The transmission unit 132 generates a random number, for example, and uses the random number to determine whether to transmit a signal in accordance with the probability.

[0176] (Step S609) The transmission unit 132 acquires node information of the node at the end of the edge. More specifically, the transmission unit 132 acquires the node identifier of the node to which the signal is to be transmitted, which is a node identifier that pairs with the i-th edge identifier, and acquires the node information of the node identified by the node identifier from the NN storage unit 111.

[0177] (Step S610) The transmission unit 132 performs firing determination processing for the node using the node information acquired in step S609. An example of the firing determination processing will be described with reference to the flowchart of FIG.

[0178] (Step S611) If the determination result in step S610 is "fire", the communication unit 132 proceeds to step S612, and if the determination result is "not fire", the communication unit 132 proceeds to step S614.

[0179] (Step S612) The transmission unit 132 performs an in-fire process for the node identified by the node information acquired in step S609. The in-fire process is the process shown in the flowchart of FIG.

[0180] (Step S613) The transmission unit 132 performs a next transmission process for the node identified by the node information acquired in step S609. The next transmission process is the process shown in the flowchart in FIG.

[0181] (Step S614) The transmission unit 132 increments the counter i by 1. The process returns to step S606.

[0182] Next, an example of the firing determination process in step S610 will be described with reference to the flowchart of FIG.

[0183] (Step S701) The transmission unit 132 acquires a firing condition corresponding to a node of interest from the firing condition storage unit 113. For example, the transmission unit 132 acquires from the firing condition storage unit 113 a firing condition paired with a node identifier included in the node information of the node of interest.

[0184] (Step S702) The transmission unit 132 acquires one or more pieces of feature information corresponding to the node of interest.

[0185] (Step S703) The transmission unit 132 determines whether or not the one or more pieces of feature information acquired in step S702 satisfy the firing condition acquired in step S701. If the firing condition is satisfied, the process proceeds to step S704, and if the firing condition is not satisfied, the process proceeds to step S705.

[0186] (Step S704) The communication unit 132 assigns "fire" to the variable "determination result" and returns to the upper level process.

[0187] (Step S705) The communication unit 132 assigns "not fired" to the variable "determination result" and returns to the upper level process.

[0188] In the flowchart of FIG. 7, the transmission unit 132 may determine whether or not to fire based on the probability according to the firing probability information included in the node information.

[0189] Next, an example of the survival rule application process in step S203 will be described with reference to the flowchart of FIG.

[0190] (Step S801) The determination unit 137 assigns 1 to a counter i.

[0191] (Step S802) The judgment unit 137 judges whether or not the i-th survival rule exists in the survival rule storage unit 117. If the i-th survival rule exists, the process proceeds to step S803; if not, the process returns to the upper process.

[0192] (Step S803) The determination unit 137 acquires the i-th survival rule from the survival rule storage unit 117.

[0193] (Step S804) The judgment unit 137 judges whether the i-th survival rule corresponds to the feature set acquired by the feature acquisition unit 131. If they correspond, the process proceeds to step S805, and if they do not correspond, the process proceeds to step S807. It is assumed that the i-th survival rule corresponds to the feature set acquired by the feature acquisition unit 131, which means that the i-th survival rule is matched.

[0194] In this step, the determination unit 137 acquires the feature set acquired by the feature acquisition unit 131. This feature set is, for example, a feature set paired with the ignition node. This feature set may be a part of one or more pieces of feature information acquired by the feature acquisition unit 131. Next, the determination unit 137 acquires a feature set paired with the i-th survival rule. Next, the determination unit 137 determines whether the feature set acquired by the feature acquisition unit 131 and the feature set paired with the i-th survival rule satisfy a predetermined condition. If the predetermined condition is satisfied, the process proceeds to step S805; if not, the process proceeds to step S807. The predetermined condition is, for example, that the similarity between the two feature sets is equal to or greater than a threshold.

[0195] (Step S805) The rule application unit 138 acquires, from the survival rule storage unit 117, the judgment information paired with the i-th survival rule.

[0196] (Step S806) The rule application unit 138 performs edge weight change processing in accordance with the determination information. An example of such weight change processing will be described with reference to the flowchart of FIG.

[0197] (Step S807) The determination unit 137 increments the counter i by 1. The process returns to step S802.

[0198] Next, an example of the weight change process in step S806 will be described with reference to the flowchart in FIG.

[0199] (Step S901) The rule application unit 138 acquires the obtained firing pattern.

[0200] (Step S902) The rule application unit 138 determines whether the obtained judgment information is positive or negative. If it is positive, the process proceeds to step S903, and if it is negative, the process proceeds to step S912.

[0201] (Step S903) The rule application unit 138 assigns 1 to a counter i.

[0202] (Step S904) The rule application unit 138 determines whether the i-th ignition node exists in the ignition pattern acquired in step S901. If the i-th ignition node exists, the process proceeds to step S905; if not, the process returns to the upper level process.

[0203] (Step S905) The rule application unit 138 acquires the area identifier paired with the i-th firing node from the NN storage unit 111. The area identifier paired with the i-th firing node is the area identifier paired with the node identifier of the i-th firing node.

[0204] (Step S906) The rule application unit 138 determines whether the area identifier acquired in step S905 is a positive area identifier. If it is a positive area identifier, the process proceeds to step S907, and if it is not a positive area identifier, the process proceeds to step S911.

[0205] (Step S907) The rule application unit 138 assigns 1 to a counter j.

[0206] (Step S908) The rule application unit 138 determines whether or not there is a jth edge connected to the ith firing node by referring to the NN storage unit 111. If there is a jth edge, the process proceeds to step S909; if there is no jth edge, the process proceeds to step S911.

[0207] (Step S909) The rule application unit 138 increases the weight of the edge information of the j-th edge. The amount of increase is, for example, "1," but is not critical. Increasing the weight means changing the "weight" of the attribute value of the edge information.

[0208] (Step S910) The rule application unit 138 increments the counter j by 1. The process returns to step S908.

[0209] (Step S911) The rule application unit 138 increments the counter i by 1. The process returns to step S904.

[0210] (Step S912) The rule application unit 138 assigns 1 to a counter i.

[0211] (Step S923) The rule application unit 138 determines whether the i-th ignition node exists in the ignition pattern acquired in step S901. If the i-th ignition node exists, the process proceeds to step S905; if not, the process returns to the upper level process.

[0212] (Step S914) The rule application unit 138 acquires from the NN storage unit 111 the area identifier paired with the i-th firing node.

[0213] (Step S915) The rule application unit 138 determines whether the area identifier acquired in step S905 is a negative area identifier. If it is a negative area identifier, the process proceeds to step S916, and if it is not a negative area identifier, the process proceeds to step S920.

[0214] (Step S916) The rule application unit 138 assigns 1 to a counter j.

[0215] (Step S917) The rule application unit 138 refers to the NN storage unit 111 and determines whether or not there is a jth edge connected to the ith firing node. If there is a jth edge, the process proceeds to step S918; if there is no jth edge, the process proceeds to step S920. Note that the edge connected to the firing node is identified by an edge identifier that pairs with the node identifier of the firing node.

[0216] (Step S918) The rule application unit 138 increases the weight of the edge information of the j-th edge. Note that the amount of increase is, for example, "1", but is not critical.

[0217] (Step S919) The rule application unit 138 increments the counter j by 1. The process returns to step S917.

[0218] (Step S920) The rule application unit 138 increments the counter i by 1. The process returns to step S913.

[0219] Next, an example of the firing pattern processing in step S205 will be described with reference to the flowchart of FIG.

[0220] (Step S1001) The corpus call OSAM unit 134 determines one or more actions to be executed according to the firing pattern, and acquires an action identifier that identifies each of the one or more actions. An example of such action determination processing will be described with reference to the flowchart in FIG. 11.

[0221] (Step S1002) The corpus call summing unit 134 assigns 1 to a counter i.

[0222] (Step S1003) The corpus call sum unit 134 determines whether the i-th action identifier exists among the one or more action identifiers acquired in step S1001. If the i-th action identifier exists, the process proceeds to step S1004; if not, the process returns to the upper level process.

[0223] (Step S1004) The corpus call summing unit 134 acquires the action information paired with the i-th action identifier from the action management unit 114.

[0224] (Step S1005) The corpus call OSAM unit 134 executes an operation using the operation information acquired in step S1004.

[0225] (Step S1006) The corpus call summing unit 134 performs post-processing. An example of the post-processing will be described with reference to the flowchart in Fig. 13. Note that the post-processing is processing performed after the execution of an operation.

[0226] (Step S1007) The corpus call summing unit 134 increments the counter i by 1. The process returns to step S1003.

[0227] Next, an example of the operation determination process in step S1001 will be described with reference to the flowchart in FIG.

[0228] (Step S1101) The corpus call OSAM unit 134 acquires one or more short-term action identifiers from the hippocampus unit 116 and temporarily stores them in a buffer (not shown).

[0229] (Step S1102) The corpus call summing unit 134 acquires the selection conditions from the storage unit 11.

[0230] (Step S1103) The corpus call summing unit 134 assigns 1 to a counter i.

[0231] (Step S1104) Corpus call OSAM unit 134 determines whether or not the i-th past action identifier exists in cortex unit 115. If the i-th past action identifier exists, the process proceeds to step S1105; if not, the process proceeds to step S1109.

[0232] (Step S1105) The corpus call OSAM unit 134 acquires from the cortex unit 115 an expected value paired with the i-th past action identifier.

[0233] (Step S1106) The corpus call OSAM unit 134 determines whether the expected value acquired in step S1105 satisfies the selection condition acquired in step S1102. If the expected value satisfies the selection condition, the process proceeds to step S1107; if not, the process proceeds to step S1108.

[0234] (Step S1107) The corpus call summing unit 134 acquires the i-th past action identifier and temporarily stores it in a buffer (not shown).

[0235] (Step S1108) The corpus call summing unit 134 increments the counter i by 1. The process returns to step S1104.

[0236] (Step S1109) The corpus call summing unit 134 acquires the operating conditions of the storage unit 11.

[0237] (Step S1110) The corpus call summing unit 134 assigns 1 to a counter j.

[0238] (Step S1111) The corpus call OSAM unit 134 determines whether the jth action identifier is present among the action identifiers acquired in steps S1101 and S1107. If the jth action identifier is present, the process proceeds to step S1112; if not, the process proceeds to step S1114.

[0239] (Step S1112) The corpus call OSAM unit 134 performs a score acquisition process. An example of the score acquisition process will be described using the flowchart in FIG. 12. The score acquisition process is a process for acquiring a score predicted when an action corresponding to the action identifier is performed. The score may also be referred to as a reward.

[0240] (Step S1113) The corpus call summing unit 134 increments the counter i by 1. The process returns to step S1111.

[0241] (Step S1114) The corpus call OSAM unit 134 acquires from a buffer (not shown) one or more action identifiers that are paired with scores that satisfy the action conditions acquired in step S1109, among the action identifiers acquired in steps S1101 and S1107. The process returns to the upper level process.

[0242] Next, an example of the score acquisition process in step S1112 will be described with reference to the flowchart in FIG.

[0243] (Step S1201) The corpus call summing unit 134 acquires the feature set acquired by the feature acquisition unit 131. This feature set is called a first feature set.

[0244] (Step S1202) The corpus call OSAM unit 134 acquires one or more feature sets paired with the action identifier of interest from the cortex unit 115 or the hippocampus unit 116. The action identifier of interest is the j-th action identifier of step S1111.

[0245] (Step S1203) The corpus call summing unit 134 assigns 1 to a counter i.

[0246] (Step S1204) The corpus call summing unit 134 determines whether the i-th feature set exists among the feature sets acquired in step S1202. If the i-th feature set exists, the process proceeds to step S1205; if not, the process proceeds to step S1210.

[0247] (Step S1205) The corpus call summing unit 134 acquires the i-th feature set from the feature sets acquired in step S1202. This feature set is called the second feature set.

[0248] (Step S1206) The corpus call summing unit 134 determines whether an expected value corresponding to the i-th feature set of the action identifier of interest exists. If an expected value exists, the process proceeds to step S1207; if not, the process proceeds to step S1208.

[0249] (Step S1207) The corpus call summing unit 134 acquires an expected value corresponding to the i-th feature set of the action identifier of interest.

[0250] (Step S1208) The corpus call summing unit 134 obtains a score using the similarity obtained in step S1205, or the similarity obtained in step S1205 and the expected value obtained in step S1207.

[0251] (Step S1209) The corpus call summing unit 134 increments the counter i by 1. The process returns to step S1204.

[0252] (Step S1210) The corpus call summing unit 134 associates the maximum score among the scores acquired in step S1208 with the action identifier of interest, and stores the score in a buffer (not shown). The process returns to the upper level process.

[0253] Next, an example of the post-processing in step S1006 will be described with reference to the flowchart in FIG.

[0254] (Step S1301) The corpus call sum unit 134 stores an action identifier that identifies the performed action. The corpus call sum unit 134 typically stores the action identifier in the hippocampus unit 116. The corpus call sum unit 134 may also store the action identifier in the cortex unit 115.

[0255] (Step S1302) The information receiving unit 121 determines whether new information has been received after the operation. If new information has been received, the process proceeds to step S1304, and if not, the process proceeds to step S1303.

[0256] (Step S1303) The processing unit 13 determines whether a timeout has occurred. If a timeout has occurred, the processing returns to the upper processing, and if a timeout has not occurred, the processing returns to step S1302. Note that, for example, the processing unit 13 determines that a timeout has occurred if a predetermined time or more has elapsed since the execution of the operation.

[0257] (Step S1304) The transmission unit 132 etc. performs the ignition transmission process using the new information received in step S1302. An example of the ignition transmission process has been described with reference to the flowchart of FIG.

[0258] (Step S1305) The processing unit 13 performs the degree acquisition process. An example of the degree acquisition process has been described with reference to the flowchart in FIG.

[0259] (Step S1306) The corpus call OSAM unit 134 acquires a reward using the positivity and negativity acquired in step S1305. The corpus call OSAM unit 134 acquires the reward in combination with the action identifier of the performed action.

[0260] (Step S1307) The corpus call OSAM unit 134 updates the expected value paired with the action identifier of the performed action using the reward acquired in step S1306. Note that updating the expected value may involve adding a new expected value. For example, the corpus call OSAM unit 134 adds the acquired reward to the expected value paired with the action identifier. Here, it is preferable that the corpus call OSAM unit 134 also updates the feature set paired with the action identifier of the performed action. For example, the corpus call OSAM unit 134 updates the feature set corresponding to the action identifier using the feature set acquired by the feature acquisition unit 131. Furthermore, the corpus call OSAM unit 134 may associate a pair of a new expected value and the feature set acquired by the feature acquisition unit 131 with the action identifier of the performed action.

[0261] Next, an example of the degree acquisition process in step S1305 will be described with reference to the flowchart in FIG.

[0262] (Step S1401) The processing unit 13 acquires the obtained firing pattern.

[0263] (Step S1402) The processing unit 13 initializes the positivity and negativity. Note that the initialization usually involves setting the positivity to "0" and the negativity to "0", but this is not limiting.

[0264] (Step S1403) The processing unit 13 assigns 1 to the counter i.

[0265] (Step S1404) The processing unit 13 uses the firing pattern acquired in step S1401 to determine whether or not the i-th firing node exists. If the i-th firing node exists, the process proceeds to step S1405; if not, the process returns to the upper level process. Note that the i-th firing node exists when, for example, the i-th firing node identifier exists in the firing pattern.

[0266] (Step S1405) The processing unit 13 acquires a node identifier for identifying the i-th firing node.

[0267] (Step S1406) The processing unit 13 acquires from the NN storage unit 111 an area identifier that is paired with the node identifier acquired in step S1405.

[0268] (Step S1407) The processing unit 13 determines whether the area identifier acquired in step S1406 is "Pojiamigudara." If it is "Pojiamigudara," the processing proceeds to step S1408, and if it is not "Pojiamigudara," the processing proceeds to step S1409.

[0269] (Step S1408) The positive feedback unit 135 increases the positivity level. For example, the positive feedback unit 135 increases the positivity level by a predetermined amount (for example, "1").

[0270] (Step S1409) The processing unit 13 determines whether the area identifier acquired in step S1406 is "Negaamigudara." If it is "Negaamigudara," the processing proceeds to step S1410, and if it is not "Negaamigudara," the processing proceeds to step S1411.

[0271] (Step S1410) The negativity unit 136 increases the degree of negativity. For example, the negativity unit 136 increases the degree of negativity by a predetermined amount (for example, "1").

[0272] (Step S1411) The processing unit 13 increments the counter i by 1. The process returns to step S1404.

[0273] As described above, according to this embodiment, it is possible to simulate the behavior of the brain when performing an action taking into consideration a reward.

[0274] Furthermore, according to this embodiment, an action identifier is selected from among action identifiers whose expected values ​​correspond to the selection conditions, and an appropriate action is executed to execute the action identified by the action identifier.

[0275] Furthermore, according to this embodiment, the expected value corresponding to the action identifier can be updated appropriately.

[0276] Furthermore, according to this embodiment, it is possible to store the action identifier of the executed action.

[0277] Furthermore, according to this embodiment, it is possible to use a neural network to simulate the behavior in the brain when performing an action taking into consideration a reward.

[0278] Furthermore, according to this embodiment, an appropriate neural network can be constructed using managed survival rules.

[0279] The processing in this embodiment may be realized by software. This software may be distributed by software download or the like. This software may also be recorded on a recording medium such as a CD-ROM and distributed. This also applies to the other embodiments in this specification. The software that realizes the information processing device 1 in this embodiment is the following program. In other words, this program is a program for causing a computer that can access an action management unit in which action information corresponding to each of two or more action identifiers that identify an action is stored, and a cortex unit in which one or more past action identifiers that identify actions performed in the past are stored, each corresponding to one or more feature sets that are one or more pieces of feature information and expected values, to function as a corpus call OSAM unit that: a reception unit that receives information; a feature acquisition unit that acquires one or more feature sets that are one or more pieces of feature information from the information received by the reception unit; and, for each of one or more candidate action identifiers among the one or more past action identifiers, acquires a similarity between the feature set corresponding to the candidate action identifier and the feature set acquired by the feature acquisition unit, acquires a score using the similarity and the expected value paired with the candidate action identifier, determines one or more action identifiers from the one or more candidate action identifiers whose score satisfies an action condition, acquires action information paired with each of the one or more action identifiers from the action management unit, and performs an action according to each of the one or more pieces of action information.

[0280] 15 shows the appearance of a computer that executes the programs described herein to realize the information processing device 1 and the like according to the various embodiments described above. The above-described embodiments can be realized by computer hardware and a computer program executed thereon. FIG. 15 is an overview of this computer system 300, and FIG. 16 is a block diagram of the system 300.

[0281] In FIG. 15, a computer system 300 includes a computer 301 including a CD-ROM drive, a keyboard 302, a mouse 303, and a monitor 304.

[0282] 16, the computer 301 includes, in addition to a CD-ROM drive 3012, an MPU 3013, a bus 3014 connected to the CD-ROM drive 3012 etc., a ROM 3015 for storing programs such as a boot-up program, a RAM 3016 connected to the MPU 3013 for temporarily storing instructions for application programs and providing temporary storage space, and a hard disk 3017 for storing application programs, system programs, and data. Although not shown here, the computer 301 may further include a network card for providing connection to a LAN.

[0283] A program that causes computer system 300 to execute the functions of information processing device 1 and the like of the above-described embodiment may be stored on CD-ROM 3101, inserted into CD-ROM drive 3012, and then transferred to hard disk 3017. Alternatively, the program may be transmitted to computer 301 via a network (not shown) and stored on hard disk 3017. The program is loaded into RAM 3016 when executed. The program may also be loaded directly from CD-ROM 3101 or the network.

[0284] The program does not necessarily have to include an operating system (OS) or a third-party program that causes the computer 301 to execute the functions of the information processing device 1 of the above-described embodiment. The program only needs to include instructions that call appropriate functions (modules) in a controlled manner and achieve the desired results. How the computer system 300 operates is well known, and a detailed description thereof will be omitted.

[0285] In addition, in the above program, the steps of transmitting information and receiving information do not include processing performed by hardware, such as processing performed by a modem or interface card in the transmission step (processing that can only be performed by hardware).

[0286] The computer that executes the program may be a single computer or a plurality of computers, that is, it may perform centralized processing or distributed processing.

[0287] Furthermore, in each of the above embodiments, it goes without saying that two or more communication means present in one device may be physically realized by one medium.

[0288] Furthermore, in each of the above embodiments, each process may be realized by centralized processing in a single device, or may be realized by distributed processing in a plurality of devices.

[0289] The present invention is not limited to the above-described embodiment, and various modifications are possible, and it goes without saying that these modifications are also included within the scope of the present invention.

[0290] As described above, the information processing device 1 according to the present invention has the effect of being able to simulate the movements in the brain when performing an action taking into consideration a reward, and is useful as a brain simulation device or the like.

Claims

1. An information processing device comprising: an action management unit in which action information corresponding to each of two or more action identifiers that identify an action is stored; a cortex unit in which one or more past action identifiers that identify actions performed in the past are stored in correspondence with one or more feature sets that are feature information and expected values; a reception unit that receives information; a feature acquisition unit that acquires one or more feature sets that are feature information from the information received by the reception unit; and a corpus call osmosis unit that acquires, for one or more candidate action identifiers among the one or more past action identifiers, a similarity between the feature set corresponding to the candidate action identifier and the feature set acquired by the feature acquisition unit, acquires a score using the similarity and an expected value paired with the candidate action identifier, determines one or more action identifiers from the one or more candidate action identifiers whose score satisfies an action condition, acquires action information paired with each of the one or more action identifiers from the action management unit, and performs an action according to each of the one or more action information.

2. An information processing device as described in claim 1, further comprising a hippocampus unit in which one or more short-term action identifiers are stored, which are associated with one or more feature sets that are feature information, and which identify actions that have been performed recently and within a predetermined period of time, and wherein the corpus callosum unit acquires, for each of one or more candidate action identifiers among the one or more past action identifiers or the one or more short-term action identifiers, a similarity between the feature set associated with the candidate action identifier and the feature set acquired by the feature acquisition unit, acquires a score using the similarity or the similarity and an expected value paired with the candidate action identifier, determines one or more action identifiers from the one or more candidate action identifiers, whose score satisfies an action condition, acquires action information paired with each of the one or more action identifiers from the action management unit, and performs an action corresponding to each of the one or more action information.

3. An information processing device as described in claim 2, wherein an expected value is associated with each of the one or more short-term action identifiers of the hippocampus unit, and the corpus callosum unit acquires a similarity between a feature set associated with the candidate action identifier and the feature set acquired by the feature acquisition unit for each of the one or more past action identifiers and one or more candidate action identifiers among the one or more short-term action identifiers, acquires a score using the similarity and an expected value paired with the candidate action identifier, determines one or more action identifiers from the one or more candidate action identifiers whose score satisfies an action condition, acquires action information paired with each of the one or more action identifiers from the action management unit, and performs an action corresponding to each of the one or more action information.

4. An information processing device as described in any one of claims 1 to 3, wherein the reception unit receives new information after the corpus call analysis unit performs an action corresponding to the action information, the positivity analysis unit obtains a positivity based on the new information received by the reception unit, the negativity analysis unit obtains a negativity based on the new information received by the reception unit, and the corpus call analysis unit obtains a reward related to the difference between the positivity acquired by the positivity analysis unit and the negativity acquired by the negativity analysis unit, and uses the reward to update an expected value corresponding to an action identifier that identifies the action performed by the corpus call analysis unit.

5. An information processing device as described in any one of claims 1 to 4, wherein the corpus call osmosis unit updates the feature set corresponding to each of the one or more determined action identifiers using the feature set acquired by the feature acquisition unit.

6. An information processing device according to any one of claims 1 to 5, wherein the corpus call OSAM unit stores in the hippocampus unit the action identifier that identifies the action performed by the corpus call OSAM unit.

7. An information processing device according to any one of claims 1 to 6, wherein the corpus call OSAM unit stores in the cortex unit the action identifier that identifies the action performed by the corpus call OSAM unit.

8. An information processing device according to any one of claims 1 to 7, further comprising: an NN storage unit in which neural network information having two or more node information having node identifiers and one or more edge information having an edge identifier and identifying connections between nodes is stored; a starting point storage unit in which one or more starting point information having one or more node identifiers that identify nodes that will fire without passing through other nodes is stored in association with a starting point condition that is a condition related to one or more feature information of the received information and is a condition for determining a node that will fire without passing through other nodes; an ignition condition storage unit in which an ignition condition related to one or more feature information is stored, the ignition condition being associated with each of one or more node information among the two or more node information; and a transmission unit that determines from the starting point storage unit one or more node identifiers that are paired with a starting point condition that matches the one or more feature information acquired by the feature acquisition unit, and determines the node identifier of the node that is connected by an edge to the ignited node identified by the one or more node identifiers, is passed on to the one or more feature information, and will fire based on the ignition condition corresponding to the node.

9. The information processing device of claim 8, wherein the NN storage unit stores neural network information having two or more node information having node identifiers corresponding to an area identifier that identifies one of two or more areas including positive amygdala or negative amygdala, and one or more edge information having an edge identifier that specifies connections between the nodes; the positive amygdala unit obtains the number of fired nodes among one or more nodes corresponding to the area identifier indicating positive amygdala, and obtains a positivity degree using the number of nodes; and the negative amygdala unit obtains the number of fired nodes among one or more nodes corresponding to the area identifier indicating negative amygdala, and obtains a negativity degree using the number of nodes.

10. The edge information has edge weights, the transmission unit is a node connected to the fired node by an edge, and when determining a node identifier of the node that will fire based on a firing condition corresponding to the node, performs processing such that the greater the weight of the edge, the more likely the node is to be determined as the node that will fire; a survival rule storage unit in which one or more survival rules corresponding to a feature set are stored, the survival rule being a positive rule corresponding to positive information indicating a positive state or a negative rule corresponding to negative information indicating a negative state; a judgment unit that determines a survival rule corresponding to the feature set acquired by the feature acquisition unit and acquires judgment information that is positive information or negative information corresponding to the survival rule; The information processing device of claim 9, further comprising a rule application unit that, when the judgment information is positive information, increases a weight of an edge connecting a node that is a node ahead of the fired node and corresponds to an area identifier of a positive area, and, when the judgment information is negative information, increases a weight of an edge connecting a node that is a node ahead of the fired node and corresponds to an area identifier of a negative area.

11. An information processing method realized by an action management unit in which action information corresponding to each of two or more action identifiers that identify actions is stored, a cortex unit in which one or more past action identifiers that identify actions performed in the past are stored in association with one or more feature sets that are feature information and expected values, a reception unit, a feature acquisition unit, and a corpus call osmosis unit, comprising: a reception step in which the reception unit receives information; a feature acquisition step in which the feature acquisition unit acquires one or more feature sets that are feature information from the information received by the reception unit; an information processing method comprising: a corpus call OSAM step in which, for each of one or more candidate action identifiers among the one or more past action identifiers, the corpus call OSAM unit acquires a similarity between a feature set corresponding to the candidate action identifier and the feature set acquired by the feature acquisition unit, acquires a score using the similarity and an expected value paired with the candidate action identifier, determines one or more action identifiers from the one or more candidate action identifiers, the score of which satisfies an action condition, acquires action information paired with each of the one or more action identifiers from the action management unit, and performs an action according to each of the one or more action information.

12. A program for causing a computer that can access an action management unit in which action information corresponding to each of two or more action identifiers that identify an action is stored, and a cortex unit in which one or more past action identifiers that identify actions performed in the past are stored, the program comprising: a reception unit that receives information; a feature acquisition unit that acquires one or more feature sets that are one or more pieces of feature information from the information received by the reception unit; and a corpus callosum unit that acquires, for one or more candidate action identifiers among the one or more past action identifiers, a similarity between the feature set corresponding to the candidate action identifier and the feature set acquired by the feature acquisition unit, acquires a score using the similarity and an expected value paired with the candidate action identifier, determines one or more action identifiers from the one or more candidate action identifiers whose score satisfies an action condition, acquires action information paired with each of the one or more action identifiers from the action management unit, and performs an action according to each of the one or more pieces of action information.

Images