Information processing device, information processing method, and program

Abstract

[Problem] It has been impossible to simulate processing in a brain in the case of sensing an object. [Solution] The problem can be solved by an information processing device 1 comprising: a cortex part 113 that stores one or more pieces of storage information having a firing pattern and image-related information; a feature acquisition part 131 that acquires one or more pieces of feature information from received character string information; a transfer part 132 that determines one or more node identifiers paired with a start point condition corresponding to the one or more pieces of feature information acquired by the feature acquisition part 131, and that performs processing of firing transfer from a fired node which is identified by each of the one or more node identifiers; a preliminary firing part 133 that acquires, from the cortex part 113, image-related information which is to be paired with a firing pattern that satisfies a first condition of similarity with a firing pattern based on the one or more node identifiers determined by the transfer part 132; a corpus callosum part 134 that acquires result information based on the image-related information; and an output unit 14 that outputs the result 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 that occurs in the brain when sensing an object.

[0002] Conventionally, there has been a system for performing neurofeedback treatment (see Patent Document 1).

[0003] Special table 2019-523108 publication

[0004] However, conventional techniques have not been able to simulate the processing that occurs in the brain when sensing an object.

[0005] More specifically, in the prior art, it has not been possible to simulate the processing that occurs in the brain when, for example, detecting an image corresponding to received character string information.Furthermore, in the prior art, it has not been possible to simulate the processing that occurs in the brain when, for example, detecting text corresponding to received character string information.

[0006] The information processing device of the first invention includes an NN storage unit storing 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 a connection between the nodes; a cortex unit storing one or more pieces of memory information each having a firing pattern and image-related information related to an image; a start point storage unit storing one or more pieces of start point information each having one or more node identifiers for identifying a node that will fire without passing through other nodes, 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 will fire without passing through other nodes; a firing condition storage unit storing firing conditions related to one or more pieces of feature information, which are firing conditions associated with each of one or more pieces of node information among the two or more pieces of node information; a reception unit receiving character string information related to a character string; The information processing device includes a feature acquisition unit that acquires one or more feature information from string information; a transmission unit that determines, from a start point storage unit, one or more node identifiers that pair with a start point condition that matches the one or more feature information acquired by the feature acquisition unit, and performs a transmission process that determines, for each of the one or more node identifiers that have fired, the node identifiers of nodes that are connected by edges to which the one or more feature information is passed and that will fire based on the firing condition corresponding to the node; a preliminary firing unit that acquires firing patterns of two or more nodes based on the one or more node identifiers determined by the transmission unit, and acquires image-related information that pairs with the firing pattern and the firing pattern that satisfies a first similarity condition from a cortex unit; a corpus call OSAM unit that acquires result information based on the image-related information acquired by the preliminary firing unit; and an output unit that outputs the result information acquired by the corpus call OSAM unit.

[0007] This configuration makes it possible to simulate the processing that occurs in the brain when sensing an object.

[0008] Furthermore, in the information processing device of the second invention, compared to the first invention, the reception unit receives string information and then receives one or more input images, the corpus call OSAM unit acquires image-related information based on the input image for each of the one or more input images received by the reception unit, determines whether the image-related information and the image-related information acquired by the preliminary firing unit satisfy a second similarity condition, acquires result information regarding the result of the determination, and the output unit outputs the result information for each of the one or more input images.

[0009] This configuration makes it possible to simulate the processing that occurs in the brain when sensing an object.

[0010] In addition, the information processing device of the third invention is an information processing device in which, compared to the second invention, the cortex unit stores one or more pieces of memory information having a firing pattern and image-related information which is one or more pieces of feature information of the image, and the corpus call OSAM unit acquires the image-related information which is one or more pieces of feature information from the input image accepted by the acceptance unit, determines whether the image-related information and the image-related information acquired by the preliminary firing unit satisfy a similarity condition, and acquires result information regarding the result of the judgment.

[0011] This configuration allows for the simulation of the processes that occur in the brain when detecting objects in an image.

[0012] Furthermore, 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 corpus callosum unit determines whether the firing state in the neural network satisfies a steady-state condition, obtains a firing pattern when it is determined that the steady-state condition is satisfied, determines whether a firing pattern that satisfies a similar condition to the firing pattern exists in the cortex unit, and obtains result information regarding the result of the determination.

[0013] This configuration makes it possible to simulate the processing that occurs in the brain when sensing an object.

[0014] Furthermore, 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 reception unit includes a first reception unit that receives first character string information from the right side and a second reception unit that receives second character string information from the left side, the feature acquisition unit acquires a first feature set, which is one or more pieces of feature information, from the first character string information and acquires a second feature set, which is one or more pieces of feature information, from the second character string information, and the transmission unit performs transmission processing using the first feature set and also performs transmission processing using the second feature set.

[0015] This configuration makes it possible to simulate the processing that occurs in the brain when information corresponding to a character string input through both ears or both eyes is perceived.

[0016] In addition, the information processing device of the sixth invention is an information processing device in which, compared to the second invention, the corpus call-OSM unit acquires image-related information based on an input image, which satisfies a second similarity condition, acquires an ignition pattern when the input image is received, and stores memory information having the ignition pattern and the image-related information in the cortex unit.

[0017] This configuration makes it possible to simulate the process of updating memory information in the brain.

[0018] The information processing device according to the present invention can simulate the processing that occurs in the brain when sensing an object.

[0019] a block diagram of the information processing device 1 according to the first embodiment; a flowchart illustrating a first operation example of the information processing device 1; a flowchart illustrating an example of the start node processing; a flowchart illustrating an example of the firing time processing; a flowchart illustrating an example of the simultaneous transmission processing; a flowchart illustrating an example of the firing determination processing; a flowchart illustrating an example of the preliminary firing processing; a flowchart illustrating an example of the result acquisition processing; a flowchart illustrating a second operation example of the information processing device 1; an overview diagram of the computer system; and a block diagram of the computer system.

[0020] 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.

[0021] (Embodiment 1) In this embodiment, an information processing device will be described that acquires a firing pattern in response to received character string information, uses the firing pattern to acquire image-related information corresponding to the firing pattern from two or more pieces of image-related information stored, and outputs result information based on the image-related information. Note that the information processing device can be said to be a device that realizes a perception model in the brain.

[0022] In this embodiment, an information processing device that simulates processing in the brain when sensing an object will be described. More specifically, the information processing device will be described, which receives an input of a character string, acquires a firing pattern corresponding to the character string, uses the firing pattern to search for image-related information corresponding to the firing pattern from two or more pieces of image-related information stored, acquires image-related information from each of the received one or more input images, and determines an input image corresponding to the received character string using the searched image-related information and image-related information corresponding to each of the one or more input images.

[0023] In addition, in this embodiment, an information processing device that simulates processing in the brain when information corresponding to a character string input through both ears or both eyes is perceived will be described.

[0024] 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.

[0025] 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.

[0026] 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 .

[0027] The storage unit 11 includes an NN storage unit 111, a firing condition storage unit 112, a cortex unit 113, a hypocampus unit 114, and a starting point storage unit 115. The reception unit 12 includes a first reception unit 121 and a second reception unit 122. The processing unit 13 includes a feature acquisition unit 131, a transmission unit 132, a preliminary firing unit 133, and a corpus call OSAM unit 134.

[0028] 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.

[0029] Various types of information are stored in the storage unit 11 that constitutes the information processing device 1. The various types of information include, for example, neural network information (hereinafter referred to as "NN information"), memory information, starting point information, firing information, and various conditions. The various conditions are, for example, firing conditions, starting point conditions, or steady-state conditions. It goes without saying that the various conditions may be embedded in the program.

[0030] The firing information is information about the result of firing. The firing information is information about the node that fired. Preferably, the firing information is information about the node that is firing. The firing information has a node identifier that identifies the node that fired. The firing information may 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 from which the firing is transmitted. It is preferable that the firing information in the storage unit 11 is automatically deleted by the processing unit 13 after a certain period of time has elapsed since storage. It is preferable that the firing information has transmission information. The transmission information is information transmitted between nodes via edges. The transmission information is one or more pieces of characteristic information, signal strength, or one or more pieces of characteristic information and signal strength.

[0031] The NN storage unit 111 stores NN information. The NN information is information that simulates a neural network (hereinafter referred to as "NN" where appropriate) in the brain. The NN information is information that identifies a NN having two or more nodes and one or more edges connecting the nodes. The NN information has two or more node information and one or more edge information. It is preferable that each node in the NN information is connected to one or more other nodes by an edge. In other words, it is preferable that the NN here does not have an input layer or an output layer.

[0032] Node information is information about the nodes that make up the NN. A node is usually connected by two or more edges. A node is connected to a certain node by an edge, and there may be two or more other nodes that transmit information to the node. A node is connected to a certain node by an edge, and there may be two or more other nodes to which the node transmits information. The node information has a node identifier. The node information has, for example, one or two or more node attribute values. The node information of a node may have the node identifier of another node that is connected to the node by an edge and transmits information to the node. The node information of a node may have the node identifier of another node that is connected to the node by an edge and transmits information to the node.

[0033] 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.

[0034] The node attribute values ​​include, for example, node position information, firing conditions, firing probability information, number of times information, and wait time.

[0035] The node position information is information about the position 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).

[0036] 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 112. The firing condition will be described in detail later.

[0037] The firing probability information is information about 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 the node may or may not fire at the probability specified by the firing probability information, even if the transmission information is the same.

[0038] 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."

[0039] The wait time is the waiting time from when a node receives transmission information until it transmits the information to the next node. The wait time may be common to two or more nodes. The wait time may also be common to all nodes.

[0040] 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 identifies 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 connected by the edge. 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 typically includes one or more edge attribute values. Edge attribute values ​​include, 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, the more likely the node beyond the edge will typically 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.

[0041] 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.

[0042] 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.

[0043] The DENDRITES identifier is information for identifying DENDRITES, such as the ID or name of DENDRITES.

[0044] 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.

[0045] 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.

[0046] 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.

[0047] The AXON identifier is information for identifying the AXON, such as the ID or name of the AXON.

[0048] 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.

[0049] 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.

[0050] 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.

[0051] The firing condition storage unit 112 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 transmission information or frequency information.

[0052] The firing condition storage unit 112 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.

[0053] The firing condition corresponding to a node may be common to all nodes. Furthermore, the firing condition may be "empty". If the firing condition of a node connected by an edge is "empty", the node connected by the edge may always fire. It is not necessary for all nodes to have a corresponding firing condition. In such a case, the firing condition storage unit 112 is not necessary.

[0054] The firing condition is, for example, a condition related to one or more pieces of feature information. The feature information is characteristic information in information. The feature information may also be called a feature amount. The feature information is, for example, image feature information or sound feature information.

[0055] Image feature information is feature information of image information (or simply "image"). Examples of image feature information include the amount of "R" information, the amount of "G" information, the amount of "B" information, SIFT features, HOG features, and Haar-Like features.

[0056] The sound feature information is feature information of sound information (or simply "sound"). The sound feature information is, for example, frequency or the amount of information in a specific frequency range.

[0057] The firing condition is, for example, a condition related to one or more pieces of image feature 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)".

[0058] The firing condition is, for example, a condition related to one or more pieces of sound feature 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 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.

[0059] The firing condition is, for example, a condition related to signal strength. In this case, the firing condition is called an intensity condition. The firing condition is, for example, that the signal strength is equal to or greater than a threshold. The signal strength here is the signal strength associated with the candidate node to be fired. The signal strength is usually the transmitted signal strength, but it may also be the signal strength reduced by the transmission.

[0060] 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. Frequency information is, for example, the time resolution at which a signal is transmitted and the number of times a signal is transmitted within a predetermined time. Note that this information typically includes one or more characteristic information of the received information or signal strength. The information here may also be referred to as a signal. Frequency conditions are, for example, a condition for a specific time resolution, a condition for a specific time resolution range, 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 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.

[0061] The firing condition may be, for example, a combination of two or more conditions selected from a sound feature condition, an image feature condition, an intensity condition, and a frequency condition.

[0062] The cortex unit 113 stores one or more pieces of memory information. The memory information here is typically long-term memory information. Long-term memory information is information that is stored over a long period of time. The memory information includes firing patterns and image-related information.

[0063] Image-related information is information about an image. For example, the image-related information is one or more pieces of image feature information or image information. For example, the image-related information is the amount of "R" information, the amount of "G" information, and the amount of "B" information.

[0064] The firing patterns included in the stored information are firing patterns corresponding to character string information. Character string information is information relating to a character string. The character string information is, for example, an image, sound, or text in which the character string is clearly indicated. The cortex unit 113 may also be referred to as "Cortex 113."

[0065] The hippocampus section 114 stores one or more firing patterns. The firing patterns stored in the hippocampus section 114 may be associated with signal strength. The firing patterns may be associated with one or more pieces of feature information. The firing patterns, etc. of the hippocampus section 114 may be referred to as short-term memory information. The firing patterns, etc. are one or more pieces of information selected from the firing pattern, or the firing pattern and signal strength, and one or more pieces of feature information. The storage of the firing patterns, etc. in the hippocampus section 114 may be temporary storage. The hippocampus section 114 may be referred to as "hippocampus114" or "HIP114."

[0066] The start point storage unit 115 stores one or more pieces of start point information in association with a start point condition.

[0067] The start condition is a condition for determining a node that will fire without passing through other nodes, and is a condition related to one or more characteristic information of the received information.

[0068] The starting point information includes one or more node identifiers that identify the node that fires without going through other nodes.

[0069] The reception unit 12 receives character string information. Here, reception refers to, for example, receiving information transmitted via a wired or wireless communication line, but may also include the concept of receiving information input from an input device such as a keyboard, mouse, or touch panel, or information read from a recording medium such as an optical disk, magnetic disk, or semiconductor memory.

[0070] After receiving the character string information, the receiving unit 12 receives, for example, one or more input images. The input images are image information. The input images are candidate images that may correspond to the character string information received by the receiving unit 12. The input images are images that are to be determined as to whether they correspond to the character string information.

[0071] The first receiving unit 121 receives first character string information from the right side. The first receiving unit 121 receives first character string information that is input from the right ear or the right eye.

[0072] The second receiving unit 122 receives second character string information from the left side. The first receiving unit 121 receives second character string information that is input from the left ear or the left eye. Note that the reception of information by the second receiving unit 122 corresponds to, for example, reception of information via the right ear and the left ear. The reception of information by the second receiving unit 122 corresponds to, for example, reception of information via the right eye and the left eye.

[0073] The means for inputting the first character string information and the second character string information is, for example, a microphone or a camera.

[0074] The processing unit 13 performs various types of processing, such as processing performed by a feature acquisition unit 131, a transmission unit 132, a preliminary firing unit 133, and a corpus call OSAM unit 134.

[0075] The processing unit 13 deletes the ignition information stored in the storage unit 11, for example, when the deletion condition is met. The deletion condition is that a time equal to or longer than a threshold has elapsed since the ignition information was accumulated. Deleting the ignition information may involve actually deleting the ignition information, or may involve processing such as adding a deletion flag to the ignition information. Deleting the ignition information means putting the ignition information into an unused state.

[0076] The feature acquisition unit 131 acquires one or more pieces of feature information from the character string information accepted by the acceptance unit 12. Such one or more pieces of feature information may be referred to as a feature set. Each of the one or more pieces of feature information is, for example, feature information of an image acquired from the character string information. Note that the process of acquiring one or more pieces of feature information of an image, sound, or text is a well-known technique.

[0077] The feature acquisition unit 131 acquires, for example, a first feature set, which is one or more pieces of feature information, from the first character string information. Also, the feature acquisition unit 131 acquires, for example, a second feature set, which is one or more pieces of feature information, from the second character string information.

[0078] The transmission unit 132 performs a firing transmission process. The firing transmission process is a process in which firing is transmitted between nodes. The process in which firing is transmitted between nodes is usually a process in which transmission information is transmitted between nodes. It is preferable that the transmission unit 132 executes the process in which transmission information is transmitted at each node in parallel or in parallel.

[0079] More specifically, the transmission unit 132 determines, from the start point storage unit 115, one or more node identifiers that are paired with a start point condition that matches the one or more pieces of feature information acquired by the feature acquisition unit 131. The transmission unit 132 is connected by an edge to the fired node identified by the one or more node identifiers, is passed one or more pieces of feature information, and performs transmission processing to determine the node identifier of the node that will fire based on the firing condition corresponding to the node.

[0080] The transmission unit 132 performs, for example, a transmission process using the first feature set and a transmission process using the second feature set. Note that it is preferable that such transmission processes are performed in parallel or in parallel.

[0081] For example, the transmission unit 132 may receive transmission information from two or more edges for one node. Receiving transmission information is the transmission of a signal.

[0082] For example, when transmitting information from one node to another node connected by an edge, the transmitter 132 may reduce the signal strength corresponding to the one node before transmitting the information to the other node. Note that transmitting information such as signal strength corresponds to associating the transmission information with the other node.

[0083] The pre-firing unit 133 acquires firing patterns of two or more nodes based on one or more node identifiers determined by the transmission unit 132, and acquires image-related information that pairs the acquired firing patterns with firing patterns that satisfy the first similarity condition from the cortex unit 113. It is preferable that the pre-firing unit 133 temporarily stores the acquired firing patterns in the hippocampus unit 114. The image-related information here is, for example, one or more pieces of image feature information or image information. The processing performed by the pre-firing unit 133 is referred to as pre-firing processing.

[0084] An firing pattern is information that identifies two or more firing nodes. The firing pattern has, for example, two or more node identifiers. The firing pattern is, for example, a vector having elements corresponding to each of the two or more node identifiers, and has a value indicating whether the node identified by each of the two or more node identifiers is firing (for example, "1") or not firing (for example, "0").

[0085] The first similarity condition is that the similarity between the two firing patterns is equal to or greater than a threshold value. The similarity between the two firing patterns is, for example, the similarity between the vectors of the two firing patterns, a value obtained by an increasing function that uses as a parameter the number of common node identifiers shared by the two firing patterns, or the ratio of common node identifiers shared by the two firing patterns.

[0086] The corpus call OSAM unit 134 acquires result information based on the image-related information acquired by the preliminary firing unit 133 .

[0087] The result information is, for example, image-related information acquired by the preliminary firing unit 133, or result information that pairs with the image-related information acquired by the preliminary firing unit 133, and is result information in the stored information that includes the image-related information.

[0088] The result information is, for example, image-related information based on the input image that satisfies the second similarity condition with the image-related information acquired by the preliminary firing unit 133. The result information based on the image-related information acquired by the preliminary firing unit 133 is, for example, image-related information that satisfies the second similarity condition with the image-related information acquired by the preliminary firing unit 133 and is information indicating whether or not image-related information based on the input image exists.

[0089] That is, for example, for each of one or more input images accepted by the accepting unit 12, the corpus call OSAM unit 134 acquires image-related information based on the input image, determines whether the image-related information and the image-related information acquired by the preliminary firing unit 133 satisfy the second similarity condition, and acquires result information. The result information is, for example, information indicating whether an input image corresponding to the character string information accepted by the accepting unit 12 has been accepted.

[0090] The second similarity condition is that the similarity between the two pieces of image-related information is equal to or greater than a threshold value.

[0091] The corpus call OSAM unit 134, for example, determines whether the firing state in the neural network satisfies steady-state conditions, acquires the firing pattern when it is determined that the steady-state conditions are satisfied, determines whether there is a firing pattern in the cortex unit 113 that satisfies similar conditions to the firing pattern, and acquires the result information.

[0092] The corpus call OSAM unit 134 acquires image-related information, which is one or more pieces of feature information, from the input image accepted by the accepting unit 12, determines whether the image-related information and the image-related information acquired by the preliminary firing unit 133 satisfy similarity conditions, and acquires the result information.

[0093] A steady state condition is a condition for determining that the firing state in a NN is steady. For example, the steady state condition is that the variation information is equal to or less than a threshold value. For example, the steady state condition is that a predetermined time or more has passed since the firing transmission process was started. For example, the steady state condition is that a predetermined time or more has passed since character string information was accepted. For example, the steady state condition is that a predetermined time or more has passed since an input image was accepted. The predetermined time is usually a constant, and its value is not important. The firing state in a NN is usually determined using a firing pattern. However, the steady state condition is not important.

[0094] The variation information is information about the variation in the number of fired nodes over time, such as the variance of the number of fired nodes at two or more time points, the reciprocal of the difference between the numbers of fired nodes at two time points, or the reciprocal of the sum of the differences between the numbers of fired nodes at two consecutive time points among three or more consecutive time points.

[0095] The corpus call osm unit 134 may perform a reconstruction process. The reconstruction process is a process of updating the cortex unit 113. The reconstruction process is, for example, the following process. Note that the reconstruction process may also be performed by a reconstruction unit (not shown).

[0096] The corpus call OSAM unit 134 acquires one or more pieces of feature information corresponding to an input image, which satisfy a similarity condition, or image-related information that is the input image that satisfies the similarity condition. Next, the corpus call OSAM unit 134 acquires an ignition pattern when the input image is received. The corpus call OSAM unit 134 constructs stored information containing the image-related information and the ignition pattern. The corpus call OSAM unit 134 stores the constructed stored information in the cortex unit 113. Note that the corpus call OSAM unit 134 may add the stored information to the cortex unit 113 or may update it. Updating the stored information means rewriting the stored information in the cortex unit 113, which is stored information having a feature set that satisfies the similarity condition, with the constructed stored information.

[0097] The output unit 14 outputs the result information acquired by the corpus call summing unit 134. For example, the output unit 14 outputs the result information for each of one or more input images.

[0098] Here, output is a concept that includes displaying on a display, projection using a projector, printing on a printer, sound output, transmission to an external device, storage on a recording medium, and delivery of processing results to other processing devices or other programs.

[0099] The storage unit 11, NN storage unit 111, firing condition storage unit 112, cortex unit 113, hypocampus unit 114, and starting point storage unit 115 are preferably non-volatile recording media, but can also be realized with volatile recording media.

[0100] 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.

[0101] The reception unit 12, the first reception unit 121, and the second reception unit 122 can be realized by a wireless or wired communication means, a means for receiving broadcasts, a device driver for an input means such as a microphone, touch panel, or keyboard, or control software for a menu screen.

[0102] The processing unit 13, the feature acquisition unit 131, the transmission unit 132, the preliminary firing unit 133, and the corpus call OSAM unit 134 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.

[0103] 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 the output device, or by a combination of driver software for the output device and the output device, etc.

[0104] Next, a first operation example of the information processing device 1 will be described with reference to the flowchart of FIG.

[0105] (Step S201) The accepting unit 12 determines whether or not character string information has been accepted. If character string information has been accepted, the process proceeds to step S202, and if not, the process returns to step S201.

[0106] (Step S202) The feature acquisition unit 131 acquires one or more pieces of feature information from the character string information received in step S201 and temporarily stores the acquired information in a buffer (not shown). Such feature information may be, for example, image feature information.

[0107] (Step S203) The transmission unit 132 performs start node processing. The start node processing is processing for determining the node that will be fired first in response to the reception of information. An example of the start node processing will be described with reference to the flowchart in FIG. 3.

[0108] (Step S204) The transmission unit 132 assigns 1 to the counter i.

[0109] (Step S205) The transmission unit 132 determines whether the i-th start node exists among the start nodes determined in step S203. If the i-th start node exists, the process proceeds to step S206; if not, the process proceeds to step S208.

[0110] (Step S206) The transmission unit 132 performs next transmission processing. An example of the next transmission processing will be described using the flowchart in FIG. 5. The next transmission processing is processing that imitates the transmission of firing from one node to another node connected to the node via 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.

[0111] (Step S207) The transmission unit 132 increments the counter i by 1. The process returns to step S205.

[0112] (Step S208) The preliminary firing unit 133 performs preliminary firing processing. An example of the preliminary firing processing will be described with reference to the flowchart of FIG.

[0113] (Step S209) The corpus call summing unit 134 acquires the result information. An example of the result acquisition process will be described with reference to the flowchart in FIG.

[0114] (Step S210) The output unit 14 outputs the result information acquired in step S209. The process returns to step S201.

[0115] In the flowchart of FIG. 2, if there are two or more start nodes determined in step S203, it is preferable to perform the next transmission process in step S206 in parallel or in parallel for each start node.

[0116] Furthermore, in the flowchart of FIG. 2, the process ends when the power is turned off or an interrupt occurs to end the process.

[0117] Next, an example of the start node process in step S203 will be described with reference to the flowchart in FIG.

[0118] (Step S301) The transmission unit 132 assigns 1 to a counter i.

[0119] (Step S302) The transmission unit 132 determines whether or not the i-th start point information exists in the start point storage unit 115. If the i-th start point information exists, the process proceeds to step S303; if not, the process returns to the upper level process.

[0120] (Step S303) The transmitter 132 acquires the start point condition included in the i-th start point information from the start point storage unit 115.

[0121] (Step S304) The transmission unit 132 determines whether or not one or more pieces of feature information stored in a buffer (not shown) in step S202 match the i-th start point condition acquired in step S303. If the one or more pieces of feature information match the i-th start point condition, the process proceeds to step S305; if not, the process proceeds to step S310.

[0122] (Step S305) The transmitter 132 acquires, from the start point storage unit 115, one or more node identifiers that are paired with the i-th start point condition.

[0123] (Step S306) The transmission unit 132 assigns 1 to the counter j.

[0124] (Step S307) The transmitter 132 determines whether or not the jth node identifier exists among the one or more node identifiers acquired in step S305. If the jth node identifier exists, the process proceeds to step S308; if not, the process proceeds to step S310.

[0125] (Step S308) 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.

[0126] (Step S309) The transmission unit 132 increments the counter j by 1. The process returns to step S307.

[0127] (Step S310) The transmission unit 132 increments the counter i by 1. The process returns to step S302.

[0128] 4, if there is no start point condition in the start point storage unit 115, the transmission unit 132 proceeds to step S306 after acquiring one or more node identifiers from the start point storage unit 115. In this case, the node that will fire first has already been determined.

[0129] Next, an example of the firing process in steps S308 and S512 will be described with reference to the flowchart of FIG.

[0130] (Step S401) 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 S307.

[0131] (Step S402) The transmitter 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 S401.

[0132] 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.

[0133] (Step S403) 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 S401 and the timer information. The transmission unit 132 stores the firing information in the storage unit 11.

[0134] 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.

[0135] (Step S404) The transmission unit 132 updates one or more node attribute values ​​paired with the node identifier acquired in step S401, and returns to the upper-level processing.

[0136] Here, the transmission unit 132 increments, for example, the number of times information paired with the node identifier acquired in step S401 by 1. The transmission unit 132 increments, for example, the firing probability information paired with the node identifier acquired in step S401. 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.

[0137] Next, an example of the next transmission process in steps S206 and S513 will be described with reference to the flowchart of FIG.

[0138] (Step S501) The transmission unit 132 acquires the node identifier of a node of interest. The node of interest is, for example, the j-th firing node of step S307.

[0139] (Step S502) The transmitter 132 acquires one or more pieces of feature information paired with the node identifier acquired in step S501. 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.

[0140] (Step S503) The transmission unit 132 obtains one or more edge identifiers that pair with the node identifier obtained in step S501 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.

[0141] (Step S504) The transmission unit 132 determines whether or not one or more edge identifiers were acquired in step S503. If an edge identifier was acquired, the process proceeds to step S505; 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.

[0142] (Step S505) The transmission unit 132 assigns 1 to the counter i.

[0143] (Step S506) The transmission unit 132 determines whether or not the i-th edge identifier exists among the edge identifiers acquired in step S503. If the i-th edge identifier exists, the process proceeds to step S507; if not, the process returns to the upper level process.

[0144] (Step S507) 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.

[0145] (Step S508) 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 S507. If the signal is to be transmitted, the process proceeds to step S509; if not, the process proceeds to step S514.

[0146] 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.

[0147] (Step S509) 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.

[0148] (Step S510) The transmission unit 132 performs firing determination processing for the node using the node information acquired in step S509. An example of the firing determination processing will be described with reference to the flowchart of FIG.

[0149] (Step S511) If the determination result in step S510 is "fire", the communication unit 132 proceeds to step S512, and if the determination result is "not fire", the communication unit 132 proceeds to step S514.

[0150] (Step S512) The transmission unit 132 performs an in-fire process for the node identified by the node information acquired in step S509. The in-fire process is the process shown in the flowchart of FIG.

[0151] (Step S513) The transmission unit 132 performs a next transmission process for the node identified by the node information acquired in step S509. The next transmission process is the process of the flowchart in FIG.

[0152] (Step S514) The transmission unit 132 increments the counter i by 1. The process returns to step S506.

[0153] Next, an example of the firing determination process in step S510 will be described with reference to the flowchart of FIG.

[0154] (Step S601) The transmission unit 132 acquires a firing condition corresponding to a node of interest. For example, the transmission unit 132 acquires the firing condition corresponding to the node of interest from the firing condition storage unit 112. For example, the transmission unit 132 acquires from the firing condition storage unit 112 a firing condition that is paired with a node identifier included in the node information of the node of interest.

[0155] (Step S602) The transmission unit 132 acquires one or more pieces of feature information corresponding to the node of interest.

[0156] (Step S603) The transmission unit 132 determines whether or not the one or more pieces of feature information acquired in step S602 satisfy the firing condition acquired in step S601. If the firing condition is satisfied, the process proceeds to step S604, and if the firing condition is not satisfied, the process proceeds to step S605.

[0157] (Step S604) The communication unit 132 assigns "fire" to the variable "determination result" and returns to the upper level process.

[0158] (Step S605) The communication unit 132 assigns "not fired" to the variable "determination result" and returns to the upper level process.

[0159] In the flowchart of FIG. 6, 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.

[0160] Next, an example of the preliminary firing process in step S208 will be described with reference to the flowchart of FIG.

[0161] (Step S701) The preliminary firing unit 133 acquires a firing pattern that identifies one or more nodes that have fired in the next transmission process of step S206, and stores the pattern in the hypocampus unit 114. This firing pattern is called a first firing pattern.

[0162] (Step S702) The preliminary firing unit 133 assigns 1 to the counter i.

[0163] (Step S703) Prefire unit 133 determines whether or not the i-th stored information exists in cortex unit 113. If the i-th stored information exists, the process proceeds to step S704; if not, the process proceeds to step S707.

[0164] (Step S704) The preliminary firing unit 133 acquires the firing pattern contained in the i-th stored information from the cortex unit 113. This firing pattern is called a second firing pattern.

[0165] (Step S705) The pre-firing unit 133 acquires the similarity between the first firing pattern and the i-th second firing pattern, associates it with the i-th stored information, and temporarily stores it in a buffer (not shown). Note that the pre-firing unit 133 may store the similarity in the hippocampus unit 114 instead of in a buffer (not shown).

[0166] (Step S706) The preliminary firing unit 133 increments the counter i by 1. The process returns to step S703.

[0167] (Step S707) The pre-firing unit 133 acquires from the cortex unit 113 image-related information contained in the stored information paired with one or more similarities that satisfy the first similarity condition among the similarities acquired in step S705, and temporarily stores the information in a buffer (not shown). The process returns to the upper level processing. Note that the pre-firing unit 133 may store one or more image-related information in the hippocampus unit 114 instead of a buffer (not shown).

[0168] The first similarity condition is, for example, "the degree of similarity is maximum" or "the degree of similarity is equal to or greater than a threshold value."

[0169] Next, an example of the result acquisition process in step S209 will be described with reference to the flowchart in Fig. 8. In the flowchart in Fig. 8, the description of the same steps as in the flowchart in Fig. 2 will be omitted.

[0170] (Step S801) The reception unit 12 determines whether or not an input image has been received. If an input image has been received, the process proceeds to step S802, and if not, the process returns to step S801.

[0171] (Step S802) The corpus call summing unit 134 acquires one or more feature information of the input image accepted in step S801. The process proceeds to step S203. The one or more feature information is referred to as a first feature set. This process may be performed by the feature acquisition unit 131.

[0172] (Step S808) The corpus call summing unit 134 acquires one or more pieces of image-related information acquired in step S707. The image-related information here is one or more pieces of feature information. Such one or more pieces of feature information are referred to as a second feature set. In other words, in this step, the corpus call summing unit 134 acquires one or more second feature sets.

[0173] (Step S809) The corpus call summing unit 134 assigns 1 to a counter j.

[0174] (Step S810) The corpus call summing unit 134 determines whether the jth second feature set exists. If the jth second feature set exists, the process proceeds to step S811; if not, the process proceeds to step S815.

[0175] (Step S811) The corpus call summing unit 134 acquires the similarity between the first feature set and the jth second feature set, associates the similarity with the jth second feature set, and temporarily stores the similarity in a buffer (not shown).

[0176] (Step S812) The corpus call summing unit 134 increments the counter j by 1. The process returns to step S810.

[0177] (Step S813) The corpus call summing unit 134 determines whether or not one or more similarities that satisfy the second similarity condition exist among the similarities temporarily stored in a buffer (not shown). If a similarity that satisfies the second similarity condition exists, the process proceeds to step S814; if not, the process proceeds to step S815.

[0178] (Step S814) The corpus call summing unit 134 acquires the result information and returns to the upper-level process. The result information is, for example, "information indicating that an input image corresponding to the accepted character string information exists" or "an input image corresponding to the j-th second feature set."

[0179] (Step S815) The corpus call sum unit 134 acquires one or more pieces of feature information corresponding to the input image or image-related information that is the input image. The corpus call sum unit 134 acquires an ignition pattern when the input image is accepted. The corpus call sum unit 134 creates stored information that includes the image-related information and the ignition pattern.

[0180] (Step S816) The corpus call sum unit 134 stores the stored information constructed in step S815 in the cortex unit 113. The corpus call sum unit 134 may add or update the stored information in the cortex unit 113. Updating the stored information means rewriting the stored information having the second feature set that satisfies the second similarity condition with the stored information constructed in step S815.

[0181] (Step S817) The corpus call OSAM unit 134 determines whether or not to end the acceptance of input images. If the acceptance of input images is to be ended, the process proceeds to step S818, and if not, the process returns to step S801.

[0182] The corpus call OSAM unit 134 determines to end the acceptance of input images, for example, when a predetermined time or more has elapsed since the start of acceptance of input images. The corpus call OSAM unit 134 determines to end the acceptance of input images, for example, when the acceptance of input images equal to or greater than a threshold has been completed.

[0183] (Step S818) The corpus call summing unit 134 acquires result information indicating "no match" and returns to the upper process.

[0184] In the flowchart of FIG. 8, if there are two or more start nodes determined in step S203, it is preferable to perform the next transmission process in step S206 in parallel or in parallel for each start node.

[0185] Next, a second operation example of the information processing device 1 will be described with reference to the flowchart of Fig. 9. In the flowchart of Fig. 9, explanations of steps that are the same as those in the flowchart of Fig. 2 will be omitted. The second operation example of the information processing device 1 is a case where character string information is received from both the right ear and the left ear.

[0186] (Step S901) The reception unit 12 determines whether or not first character string information and second character string information have been received. If such character string information has been received, the process proceeds to step S202; if not, the process returns to step S901. Note that if character string information has been received, the first reception unit 121 receives the first character string information, and the second reception unit 122 receives the second character string information.

[0187] In addition, in the flowchart of Figure 9, the processing of steps S202 to S207 for the first character string information received by the right ear and the processing of steps S202 to S207 for the second character string information received by the left ear are performed in parallel or in parallel.

[0188] As described above, according to this embodiment, it is possible to simulate the processing that occurs in the brain when sensing an object.

[0189] Furthermore, according to this embodiment, it is possible to simulate the processing that occurs in the brain when detecting an object in an input image.

[0190] Furthermore, according to this embodiment, it is possible to simulate the processing that occurs in the brain when information corresponding to a character string input through both ears or both eyes is perceived.

[0191] 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. That is, this program comprises a computer that can access an NN storage unit that stores 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 a connection between nodes, a cortex unit that stores one or more pieces of memory information each having a firing pattern and image-related information related to an image, a start point storage unit that stores one or more pieces of start point information each having one or more node identifiers that identify a node that will fire without passing through other nodes 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 will fire without passing through other nodes, and a firing condition storage unit that stores a firing condition related to one or more pieces of feature information that is a firing condition associated with one or more pieces of node information out of the two or more pieces of node information, a reception unit that receives character string information related to a character string, and a program that receives one or more pieces of character string information from the character string information received by the reception unit. a transmission unit that performs a transmission process that determines, from the starting point storage unit, one or more node identifiers that pair with a starting point condition that matches the one or more pieces of feature information acquired by the feature acquisition unit, and determines, for each fired node identified by the one or more node identifiers, the node identifiers of the nodes that are connected by edges, to which the one or more pieces of feature information are passed, and that fire based on the firing condition corresponding to the node; a preliminary firing unit that acquires firing patterns of two or more nodes based on the one or more node identifiers determined by the transmission unit, and acquires image-related information that pairs with the firing pattern and a firing pattern that satisfies a first similarity condition from the cortex unit; a corpus call OSAM unit that acquires result information based on the image-related information acquired by the preliminary firing unit; and an output unit that outputs the result information acquired by the corpus call OSAM unit.

[0192] 10 shows the appearance of a computer that executes the programs described herein to realize the information processing device 1 according to the various embodiments described above. The above-described embodiments can be realized by computer hardware and a computer program executed thereon. FIG. 10 is an overview of this computer system 300, and FIG. 11 is a block diagram of the system 300.

[0193] In FIG. 10, a computer system 300 includes a computer 301 including a CD-ROM drive, a keyboard 302, a mouse 303, and a monitor 304.

[0194] 11, in addition to a CD-ROM drive 3012, the computer 301 includes 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.

[0195] A program that causes computer system 300 to execute the functions of information processing device 1 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.

[0196] The program does not necessarily include an operating system (OS) or a third-party program that causes the computer 301 to execute the functions of the information processing device of the above-described embodiment. The program only needs to include instructions that call appropriate functions (modules) in a controlled manner to achieve the desired results. How the computer system 300 operates is well known, and a detailed description thereof will be omitted.

[0197] 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).

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] As described above, the information processing device 1 according to the present invention has the effect of being able to simulate the processing that occurs in the brain when sensing an object, and is useful as a robot or the like.

Claims

1. An NN storage unit that stores 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 identifying connections between nodes; a cortex unit that stores one or more pieces of memory information each having a firing pattern and image-related information related to an image; a start point storage unit that stores one or more pieces of start point information each having one or more node identifiers that identify nodes that will fire without passing through other nodes, 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 will fire without passing through other nodes; a firing condition storage unit that stores firing conditions related to one or more pieces of feature information, which are firing conditions associated with each of one or more pieces of node information among the two or more pieces of node information; a reception unit that receives character string information related to character strings; and a feature acquisition unit that acquires one or more pieces of feature information from the character string information received by the reception unit. an information processing device comprising: a transmission unit that performs a transmission process to determine, from the starting point storage unit, one or more node identifiers that pair with a starting point condition that matches the one or more pieces of feature information acquired by the feature acquisition unit, and to determine the node identifiers of nodes that are connected by edges to fired nodes identified by the one or more node identifiers, are passed the one or more pieces of feature information, and will fire based on the firing condition corresponding to the node; a pre-firing unit that acquires firing patterns of two or more nodes based on the one or more node identifiers determined by the transmission unit, and acquires image-related information that pairs with the firing pattern and a firing pattern that satisfies a first similarity condition from the cortex unit; a corpus call OSAM unit that acquires result information based on the image-related information acquired by the pre-firing unit; and an output unit that outputs the result information acquired by the corpus call OSAM unit.

2. The information processing device described in claim 1, wherein the reception unit receives one or more input images after receiving the character string information, the corpus call osmosis unit acquires image-related information based on the input image for each of the one or more input images received by the reception unit, determines whether the image-related information and the image-related information acquired by the preliminary firing unit satisfy a second similarity condition, and acquires result information regarding the result of the determination, and the output unit outputs the result information for each of the one or more input images.

3. The information processing device of claim 2, wherein the cortex unit stores one or more pieces of memory information having a firing pattern and image-related information which is one or more pieces of characteristic information of the image, and the corpus call osm unit acquires the image-related information which is one or more pieces of characteristic information from the input image accepted by the acceptance unit, determines whether the image-related information and the image-related information acquired by the preliminary firing unit satisfy a similarity condition, and acquires result information regarding the result of the judgment.

4. An information processing device as claimed in any one of claims 1 to 3, wherein the corpus callosum unit determines whether the firing state in the neural network satisfies a steady-state condition, acquires a firing pattern when it is determined that the steady-state condition is satisfied, determines whether a firing pattern that satisfies a similar condition to the firing pattern exists in the cortex unit, and acquires result information regarding the result of the determination.

5. An information processing device as described in any one of claims 1 to 4, wherein the reception unit comprises a first reception unit that receives first character string information from the right side and a second reception unit that receives second character string information from the left side, the feature acquisition unit acquires a first feature set, which is one or more pieces of feature information, from the first character string information and acquires a second feature set, which is one or more pieces of feature information from the second character string information, and the transmission unit performs the transmission process using the first feature set and also performs the transmission process using the second feature set.

6. An information processing device as described in claim 2, wherein the corpus call-OSM unit acquires image-related information based on the input image and that satisfies the second similarity condition, acquires an ignition pattern when the input image is received, and stores memory information having the ignition pattern and the image-related information in the cortex unit.

7. An information processing method realized by an NN storage unit storing 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 identifying connections between nodes, a cortex unit storing one or more pieces of memory information each having a firing pattern and image-related information related to an image, a start point storage unit storing one or more pieces of start point information each having one or more node identifiers that identify nodes that will fire without passing through other nodes, in association with a start point condition that is a condition related to one or more pieces of feature information of received information and is a condition for determining a node that will fire without passing through other nodes, a firing condition storage unit storing firing conditions related to one or more pieces of feature information that are firing conditions associated with each of one or more pieces of node information among the two or more pieces of node information, a reception unit, a feature acquisition unit, a transmission unit, a preliminary firing unit, a corpus call summing unit, and an output unit, comprising: the reception unit, a reception step of receiving character string information related to a character string; a feature acquisition step of the feature acquisition unit acquiring one or more pieces of feature information from the character string information received by the reception unit, a transmission step in which the transmission unit determines, from the starting point storage unit, one or more node identifiers that pair with a starting point condition that matches the one or more pieces of feature information acquired by the feature acquisition unit, and performs a transmission process to determine the node identifiers of nodes that are connected by edges to fired nodes identified by the one or more node identifiers, are passed the one or more pieces of feature information, and will fire based on the firing condition corresponding to the node; a preliminary firing step in which the pre-firing unit acquires firing patterns of two or more nodes based on the one or more node identifiers determined by the transmission unit, and acquires image-related information that pairs with the firing pattern and a firing pattern that satisfies a first similarity condition from the cortex unit; a corpus call OSAM step in which the corpus call OSAM unit acquires result information based on the image-related information acquired by the pre-firing unit; and an output step in which the output unit outputs the result information acquired by the corpus call OSAM unit.

8. A computer that can access an NN storage unit that stores 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 identifying connections between nodes, a cortex unit that stores one or more pieces of memory information each having a firing pattern and image-related information related to an image, a start point storage unit that stores one or more pieces of start point information each having one or more node identifiers that identify nodes that will fire without passing through other nodes, 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 will fire without passing through other nodes, and a firing condition storage unit that stores firing conditions related to one or more pieces of feature information, the firing conditions being firing conditions associated with each of one or more pieces of node information among the two or more pieces of node information; a reception unit that receives character string information related to a character string; a feature acquisition unit that acquires one or more pieces of feature information from the character string information received by the reception unit; a transmission unit that performs a transmission process to determine, from the starting point storage unit, one or more node identifiers that pair with a starting point condition that matches the one or more pieces of feature information acquired by the feature acquisition unit, and to determine the node identifiers of nodes that are connected by edges to fired nodes identified by the one or more node identifiers, are passed the one or more pieces of feature information, and fire based on the firing condition corresponding to the node; a preliminary firing unit that acquires firing patterns of two or more nodes based on the one or more node identifiers determined by the transmission unit, and acquires image-related information that pairs with the firing pattern and a firing pattern that satisfies a first similarity condition from the cortex unit; a corpus call OSAM unit that acquires result information based on the image-related information acquired by the preliminary firing unit; and a program for functioning as an output unit that outputs the result information acquired by the corpus call OSAM unit.

Images