Information processing device, information processing method and program

Abstract

To provide an information processing device capable of appropriately grasping a situation of an event, an information processing method and a program.SOLUTION: An information processing device 10 comprises an event information reception section 111, a context information extraction section 112, a reproduction information generation section 113, and an output section 114. The event information reception section 111 receives event information including information indicating a motion of a mobile that relates to a predetermined event occurring in the mobile. The context information extraction section 112 extracts context information indicating a content of the event from the event information. The reproduction information generation section 113 generates reproduction information including complementary information that complements the content of the event from the context information. The output section 114 outputs the reproduction information.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus, an information processing method, and a program.

Background Art

[0002] In the analysis of accidents, disasters, etc., reproducing these events is an important factor. For example, regarding the analysis of automobile accidents, a drive recorder that records images around the automobile with an in-vehicle camera is used.

[0003] For example, the system for detecting traffic violations described in Patent Document 1 includes a context camera assembly and a license plate recognition camera assembly, each having a housing, a mount, and a skirt for attachment inside the vehicle.

[0004] The system described in Patent Document 2 extracts traffic violation data and information and transmits it to a server. The server compares the received data to make a final determination of traffic violations and also constructs a semantically annotated map.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0006] However, for example, not all event situations are recorded in a drive recorder.

[0007] In view of the above problems, the present disclosure provides an information processing apparatus and the like capable of suitably grasping the situation of an event.

Means for Solving the Problem

[0008] The information processing apparatus according to the present disclosure includes an event information reception unit, a context information extraction unit, a reproduction information generation unit, and an output unit. The event information reception unit receives event information including information indicating the movement of a moving body related to a predetermined event that has occurred to the moving body. The context information extraction unit extracts context information indicating the content of the event from the event information. The reproduction information generation unit generates reproduction information including complementary information that complements the content of the event from the context information. The output unit outputs the reproduction information.

[0009] In the information processing method according to the present disclosure, a computer executes the following processes. The computer receives event information including information indicating the movement of a moving body related to a predetermined event that has occurred to the moving body. The computer extracts context information indicating the content of the event from the event information. The computer generates reproduction information including complementary information that complements the content of the event from the context information. The computer outputs the reproduction information.

[0010] The program according to the present disclosure causes a computer to execute the following information processing method. The computer receives event information including information indicating the movement of a moving body related to a predetermined event that has occurred to the moving body. The computer extracts context information indicating the content of the event from the event information. The computer generates reproduction information including complementary information that complements the content of the event from the context information. The computer outputs the reproduction information.

Advantages of the Invention

[0011] According to the present disclosure, it is possible to provide an information processing apparatus, an information processing method, and a program capable of suitably grasping the situation of an event.

Brief Description of the Drawings

[0012]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Mode for Carrying Out the Invention

[0013] Hereinafter, the present invention will be described through embodiments of the invention, but the invention according to the claims is not limited to the following embodiments. Also, not all of the configurations described in the embodiments are essential as means for solving the problems. For the sake of clarity of explanation, the following description and drawings are appropriately omitted and simplified. In each drawing, the same elements are denoted by the same reference numerals, and duplicate explanations are omitted as necessary.

[0014] <Embodiment 1> Hereinafter, the configuration of the information processing apparatus 10 will be described with reference to FIG. 1. FIG. 1 is a block diagram of an information processing apparatus according to the present disclosure. The information processing apparatus 10 receives predetermined information regarding an event such as a traffic accident, and generates and outputs reproduction information of the event from the received information. The information processing apparatus 10 is, for example, a computer having a CPU (Central Processing Unit).

[0015] In one embodiment, the information processing apparatus 10 generates and outputs reproduction information regarding an event such as a traffic accident of a moving object. The moving object is, for example, an automobile, a motorcycle, or a bicycle that travels on a road or a floor surface. The moving object may also be a ship that moves on the sea, or a drone or a flying car that moves in the air. The information processing apparatus 10 according to the present disclosure includes an event information reception unit 111, a context information extraction unit 112, a reproduction information generation unit 113, and an output unit 114.

[0016] The event information reception unit 111 receives event information including information indicating the movement of the moving object regarding a predetermined event that has occurred to the moving object. The event information includes, for example, an image of the event captured by a camera mounted on the moving object. In this case, the image as the event information is, for example, image data conforming to MPEG (Motion Picture Experts Group) or the like. The event information also includes character information indicating the date and time and the location where the event occurred. The event information may also include character information for explaining the situation of the event that has occurred. The event information may also include data of an arbitrary sensor or the like indicating the situation of the event that has occurred.

[0017] The context information extraction unit 112 extracts context information indicating the content of the event from the event information. The context information is used to generate the reproduction information. The context information extraction unit 112 extracts various information included in the event information along the time series. The context information extraction unit 112 also extracts the event information for each object that appears in the event. The object that appears in the event is, for example, an automobile, a road, and an object that the automobile has contacted in a traffic accident of an automobile. The object that the automobile has contacted may include, for example, another moving object such as another vehicle, a pedestrian, and a building.

[0018] The reproduction information generation unit 113 generates reproduction information including complementary information that supplements the content of the event from the context information. The reproduction information is information indicating the situation of the event along the time series. The reproduction information is, for example, virtual space information generated using computer graphics technology. Also, the reproduction information may be a superimposition of character information on an image captured by a camera and an image generated by computer graphics. The reproduction information may include character information.

[0019] The complementary information is virtual information supplemented by the reproduction information generation unit 113. When there is uncertain information in the context information, the reproduction information generation unit 113 infers this uncertain information from the relevant context information. Thereby, the reproduction information generation unit 113 generates reproduction information using the context information and the complementary information.

[0020] In order to realize the above functions, the reproduction information generation unit 113 has a function of integrating and organizing a plurality of context information to generate a series of reproduction information. This function can be realized by the reproduction information generation unit 113 using generative AI (artificial intelligence). Also, the reproduction information generation unit 113 can use generative AI when generating complementary information.

[0021] Here, generative AI will be explained. Generative AI is a type of artificial intelligence that has the ability to generate new and different data from a certain data. By using knowledge and experience for a specific task, generative AI can produce new information and ideas that do not exist in the original dataset. Generative AI mainly uses a generative model, which is a field of machine learning. The generative model learns a large amount of data and generates new data by understanding the structure and pattern of that data.

[0022] As an example of generative AI that generates images, there are generative adversarial networks (GANs). GANs pit two networks against each other: a generative network and a discriminative network. This enables GANs to generate high-quality and realistic data. The generative network generates data. The discriminative network discriminates whether the data is real data or generated data. This process allows the generative network to evolve to generate higher-quality and more realistic data.

[0023] Also, as an example of generative AI that generates language, there are large language models. A large language model is a model that generates related strings related to a target string from the target string by learning the relationships between words in a sentence. By learning sentences and texts in various contexts, a large language model can generate related strings with appropriate content related to the target string.

[0024] For example, the case of using a large language model in question-and-answer will be described. The large language model receives, as the target string, the input of the question "What kind of country is Japan?". The large language model generates a string such as "Japan is an island country in the Northern Hemisphere..." as an answer to the question.

[0025] The learning method of the large language model is not particularly limited. As an example, the learning method of the large language model may be one that is learned to output at least one sentence including the input string.

[0026] Moreover, the strings generated by large language models are not limited to natural languages. A large language model may output, for example, an artificial language (such as program source code) for a string input in a natural language. For example, a large language model receives, as a target string, an input of a question such as "How to retrieve data containing a specific string from a database?". In this case, the large language model may output program source code for performing database processing. Alternatively, a large language model may output a natural language corresponding to a string input in an artificial language. Also, the content generated by a large language model is not limited to strings. A large language model may generate, for example, image data, video data, audio data, or other data formats corresponding to the input string.

[0027] The output unit 114 outputs reproduction information. The destination to which the output unit 114 outputs is, for example, a user who uses the information processing apparatus 10 for the purpose of analyzing an event. The information processing apparatus 10 may be included in a computer used by the user. In that case, the output unit 114 outputs the reproduction information to a display connected to the computer used by the user. The user may use the information processing apparatus 10 via a network. In that case, the output unit 114 of the information processing apparatus 10 outputs the reproduction information to the user's computer via the network.

[0028] With the above configuration, the information processing apparatus 10 can present reproduction information for grasping the situation of an event to the user. Also, when there is uncertain information, the information processing apparatus 10 generates complementary information to generate reproduction information that enables the user to more preferably grasp the situation of the event.

[0029] Next, the processing executed by the information processing apparatus 10 will be described with reference to FIG. 2. FIG. 2 is a flowchart showing the information processing method according to the present disclosure. The information processing method according to the present disclosure is such that the information processing apparatus 10 executes the following processing.

[0030] First, the event information reception unit 111 receives event information including information indicating the movement of the mobile body related to a predetermined event that has occurred in the mobile body (step S11). The event information reception unit 111 supplies the received event information to the context information extraction unit 112.

[0031] Next, the context information extraction unit 112 extracts context information indicating the content of the event from the event information (step S12). The context information extraction unit 112 supplies the extracted context information to the context information extraction unit 112.

[0032] Next, the reproduction information generation unit 113 generates reproduction information (step S13). The reproduction information includes complementary information that complements the content of the event from the context information. The reproduction information generation unit 113 supplies the generated reproduction information to the output unit 114.

[0033] Next, the output unit 114 outputs the reproduction information received from the reproduction information generation unit 113 (step S14).

[0034] The information processing method executed by the information processing apparatus 10 has been described above. By the above method, the information processing apparatus 10 can output reproduction information in a manner that enables the user to appropriately grasp the situation of the event.

[0035] Incidentally, the information processing apparatus 10 may have a processor and a storage device as a configuration not shown. The storage device included in the information processing apparatus 10 includes a storage device including a non-volatile memory such as a flash memory or an SSD (Solid State Drive). In this case, the storage device included in the information processing apparatus 10 stores a computer program (hereinafter, also simply referred to as a program) for executing the above method. Further, the processor causes the buffer memory such as a DRAM (Dynamic Random Access Memory) to read the computer program from the storage device and executes the program.

[0036] Each component of the information processing apparatus 10 may be implemented by dedicated hardware. Also, some or all of each component may be implemented by general-purpose or dedicated circuitry, a processor, etc., or a combination thereof. These may be configured by a single chip, or may be configured by a plurality of chips connected via a bus. Some or all of each component of each device may be implemented by a combination of the circuitry etc. described above and a program. Also, as the processor, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (field-programmable gate array), etc. can be used. Further, the processing executed by the information processing apparatus 10 may be provided as SaaS (Software as a Service). Note that the description regarding the configuration described here can also be applied to other devices or systems described below in the present disclosure.

[0037] As described above, according to the present embodiment, it is possible to provide an information processing apparatus, an information processing method, and a program that can suitably grasp the situation of an event.

[0038] <Embodiment 2> Next, the information processing apparatus 20 will be described with reference to FIG. 3. FIG. 3 is a block diagram of the information processing apparatus 20 according to the present disclosure. The information processing apparatus 20 is communicably connected to a user terminal 400 via a network N1.

[0039] The user terminal 400 is a terminal managed by a user who uses the information processing apparatus 20. The user terminal 400 is, for example, a computer, a server, a tablet PC, or a smartphone. The user who manages the user terminal 400 supplies, for example, event information stored in the user terminal 400 to the information processing apparatus 20. Also, the user who manages the user terminal 400 is, for example, a police, an insurance company, a driving school, or a court.

[0040] The information processing apparatus 20 generates reproduction information from the event information received from the user terminal 400, and supplies the generated reproduction information to the user terminal 400. The information processing apparatus 20 includes an event information reception unit 111, a context information extraction unit 112, a reproduction information generation unit 113, an output unit 114, and a storage unit 120.

[0041] The event information reception unit 111 according to the present embodiment receives event information including one or more pieces of image information. The image information is, for example, an image (event image) captured and recorded by a drive recorder in the event of a car accident. The event image usually includes images over a period of several tens of seconds before and after the event. The event image also includes the time when the drive recorder captured the event image. The event image also includes information regarding the location where the drive recorder captured the event image. The information regarding the location is, for example, latitude and longitude. By receiving such information, the information processing apparatus 20 can suitably extract context information.

[0042] The event information reception unit 111 may receive event information including sensor data acquired by a moving body at a plurality of times. The sensor data acquired by the moving body may include, for example, the accelerator opening of an automobile or the braking amount of an automobile. Thereby, when the context information extraction unit 112 extracts context information, the information processing apparatus 20 can suitably process the attributes of the moving body.

[0043] The attributes of the moving body include the type of the moving body. The attributes of the moving body may also include the position, moving direction, moving speed, or moving acceleration of the moving body at each time. Information regarding the attributes of the moving body is referred to as attribute information. The attributes can also be associated with each of the objects related to the event.

[0044] Thereby, the context information extraction unit 112 recognizes various objects from the combination of the image information and the sensor data, and determines the attributes of the recognized objects. The information processing apparatus 20 uses the attributes determined by the context information extraction unit 112 for generating reproduction information.

[0045] The event information reception unit 111 may receive, as event information, in addition to the above-described information, for example, information related to the driver's behavior. The information related to the driver's behavior may include the driver's perspective, the driver's actions, and the content of the driver's speech. Further, the event information reception unit 111 may include, as event information, the situation of the event testified by a person who witnessed the event.

[0046] The event information reception unit 111 may include, as event information, in addition to the above-described information, for example, information related to the content and degree of damage to an object or a human body caused as a result of the event.

[0047] The context information extraction unit 112 extracts, as context information, the attribute information of each object including the moving body at a plurality of times of the event. Thereby, the information processing apparatus 20 can appropriately process the relationship between each object. The context information extraction unit 112 may extract the context information as text data. Thereby, the information processing apparatus 20 can handle the context information as input information for the generation AI. Note that the context information may include image data in addition to the text data.

[0048] The reproduction information generation unit 113 causes the learned model trained to generate the complementary information for complementing the attribute information to generate the complementary information, and generates the reproduction information based on the context information and the complementary information in the event for each predetermined period. In order to realize such a function, the reproduction information generation unit 113 calculates the relevance of the attribute information. That is, in this case, the reproduction information generation unit 113 calculates the degree of relevance between the respective pieces of attribute information, and uses the calculated degree of relevance for the generation of the complementary information.

[0049] The reproduction information generation unit 113 generates the reproduction information with reference to the map information of the place where the event occurred. The reproduction information generation unit 113 refers to the map information database 122 stored in the storage unit 120. At this time, the reproduction information generation unit 113 uses the information related to the position of the event included in the context information. By referring to the map information, the reproduction information generation unit 113 can generate high-precision reproduction data.

[0050] The map information database 122 may include various accompanying data associated with the map data. For example, the map information database 122 may include data of SNS (Social Networking Service) associated with the map data. When a specific accident occurs, a third party present at the location may post videos, photos, and comments on SNS or other Internet platforms. These data are very useful for more clearly understanding the situation of the accident. The reproduction information generation unit 113 collects these SNS data from the map information database 122 and combines them with the map data. Thereby, the reproduction information generation unit 113 can reproduce the situation of the accident with high accuracy.

[0051] Furthermore, various data included in the map information database 122 can provide the environment at the time of the accident and other related information. Therefore, the map information database 122 can improve the reliability and accuracy of the reproduction data. Also, the SNS data includes time information. Therefore, the map information database 122 can also be used to reproduce the time progression of the accident. In this way, by combining the map data and the SNS data, the reproduction information generation unit 113 can reproduce the situation of the accident more accurately and in detail.

[0052] The reproduction information generation unit 113 may generate reproduction information in a manner in which the complementary information can be identified. That is, the information processing device 20 outputs in a recognizable manner to the user that the reproduction information is generated based on the attributes complemented. More specifically, for example, when the reproduction information is an image by computer graphics that reproduces an event in a virtual space, the information processing device 20 may highlight the complemented area or the like. Thereby, the information processing device 20 can increase the degree of freedom in modifying the reproduction information and the like.

[0053] Based on the generated reproduction information, the reproduction information generation unit 113 may confirm the factuality of the generated part and send an instruction to re-acquire data to an arbitrary terminal device as necessary. The method for determining the factuality of the reproduction information generated by the reproduction information generation unit 113 is not particularly limited. For example, the reproduction information generation unit 113 acquires the feature amount (such as an image feature amount) of the part generated by the generation AI and compares the feature amount with the feature amount in another piece of data to be compared. Thereby, the reproduction information generation unit 113 determines the factuality.

[0054] For example, the reproduction information generation unit 113 compares the image information of the road at a specific position generated by the generation AI with the image information of the road registered in the public database. Thereby, the reproduction information generation unit 113 determines the fact of the image information of the road generated by the generation AI. In this case, the greater the distance between the feature amounts of the generated road image information and the road image information registered in the public database, the lower the factuality. By using such a factuality determination, the reproduction information generation unit 113 improves the reliability of the reproduction information. Also, when the factuality is low, the reproduction information generation unit 113 re-acquires the data. By re-acquiring the data, the reproduction information generation unit 113 can improve the accuracy of the reproduction information.

[0055] The reproduction information generation unit 113 may generate reproduction information that three-dimensionally shows the movement of a moving body in a virtual space that virtually reproduces an event. Thereby, the information processing apparatus 20 can present reproduction information that is easy to understand to the user.

[0056] The storage unit 120 includes a non-volatile memory such as a flash memory, an SSD (Solid State Drive), or an HDD (Hard Disk Drive). The storage unit 120 stores an attribute information database 121 and a map information database 122. The attribute information database 121 includes attribute information of a plurality of objects referred to by the context information extraction unit 112 and the reproduction information generation unit 113. For example, the attribute information database 121 may include, as attribute information of an event related to a car accident, the size of the car, the shape of the car, the friction coefficient between the car tire and the road, the power performance of the car, and the braking performance of the car, etc.

[0057] The map information database 122 is information of a map including the location where the event occurs. The map information may be two-dimensional information or three-dimensional information. When the map information database 122 is three-dimensional information, the information processing apparatus 20 can reproduce the occurred event in a virtual space.

[0058] Next, the reproduction information generation unit 113 will be further described with reference to FIG. 4. FIG. 4 is a diagram for explaining the processing of the reproduction information generation unit 113. The reproduction information generation unit 113 receives context information as an input, generates reproduction information, and outputs it. When generating the reproduction information, the reproduction information generation unit 113 refers to the attribute information and the map information.

[0059] The context information received by the reproduction information generation unit 113 is composed of a plurality of attributes. The reproduction information generation unit 113 generates reproduction information using the context information. Also, the reproduction information generation unit 113 generates reproduction information by referring to the attribute information database 121 and the map information database 122.

[0060] An example of the procedure for the reproduction information generation unit 113 to generate reproduction information is shown below. For example, the reproduction information generation unit 113 first reads the context information received from the context information extraction unit 112 and refers to the attribute information database 121 for the attribute information related to the extracted context information. Similarly, the reproduction information generation unit 113 refers to the map information database 122 for the map information related to the context information. Next, the reproduction information generation unit 113 attempts to generate reproduction information from the context information, the attribute information database 121, and the map information database 122. Next, the reproduction information generation unit 113 performs a complementation process for the attributes that do not exist in the context information and are not referred to from the attribute information database 121.

[0061] The example of the process executed by the reproduction information generation unit 113 has been described above. Note that the process executed by the reproduction information generation unit 113 is not limited to the above content.

[0062] Next, the complementation process performed by the reproduction information generation unit 113 will be described with reference to FIG. 5. FIG. 5 is a diagram for explaining the concept of the complementation process according to the present disclosure. FIG. 5 shows the states of attributes 1 to 4 at times T = T1 to T4 by A, B, or C. Here, state A indicates that the corresponding attribute is included in the context information. State B indicates that it has been complemented by the reproduction information generation unit 113. Also, state C indicates a state where it is not included in the context information and has not been complemented.

[0063] For example, assume that attribute 1 is the position information of an automobile. In this case, attribute 1 at time T1 is included in the context information. On the other hand, although attribute 2 at time T2 was not included in the context information, it has been complemented from attribute 1 at time T1 and attribute 1 at time T3. In this way, the reproduction information generation unit 113 can complement the attributes that have not been extracted as context information by using the same attributes at adjacent times.

[0064] Also, although Attribute 3 at time T2 was not extracted as context information, it is complemented from Attribute 2 and Attribute 4 at time T2. Thus, the reproduction information generation unit 113 can complement attributes that have not been extracted as context information by using other related attributes.

[0065] Note that the reproduction information generation unit 113 does not need to complement all attributes that have not been extracted as context information. For example, Attribute 2 at time T1 has not been complemented. The reproduction information generation unit 113 can generate reproduction information while including attributes in such a state C. Also, the reproduction information generation unit 113 can combine the above-described complementation processes. That is, for example, the reproduction information generation unit 113 may complement attributes by a combination of attributes at adjacent times and related attributes at the same time.

[0066] Thus, the information processing apparatus 20 identifies attribute information that needs to be complemented. Also, the information processing apparatus 20 performs complementation for attribute information that needs to be complemented from information on attributes with a high degree of relevance. Thereby, the information processing apparatus 20 can suitably perform complementation and generate reproduction information.

[0067] Next, referring to FIG. 5, FIG. 5 is a block diagram of a user terminal 400 according to the present disclosure. The user terminal 400 mainly includes an operation reception unit 411, a display unit 412, a communication unit 413, a control unit 414, and a storage unit 420.

[0068] The operation reception unit 411 is an interface that receives operations from the user. The user performs various operations using information input devices such as buttons, switches, and touch panels provided in the user terminal 400. The operation reception unit 411 supplies a signal regarding the received operation to the control unit 414.

[0069] The display unit 412 includes a display device such as a liquid crystal panel or an organic electroluminescence device. The display unit 412 displays the reproduction information supplied from the information processing device 20. The communication unit 413 is an interface for communicating between the user terminal 400 and the information processing device 20. The control unit 414 includes an arithmetic device such as a CPU and controls each component of the user terminal 400. The control unit 414 reads the program 421 from the storage unit 420 and realizes a predetermined function according to the read program in the present embodiment.

[0070] The storage unit 420 is a storage device including a non-volatile memory and stores a program 421 for realizing the functions in the present embodiment in the user terminal 400. The storage unit 420 also stores event information 422. The event information 422 may include, for example, images of events captured by the user terminal 400 or a drive recorder, and information about events input by the user.

[0071] Next, an example of event information will be described with reference to FIG. 7. FIG. 7 is a diagram showing an example of an image of an in-vehicle camera. FIG. 7 shows images P1 to P3 captured by an in-vehicle camera provided in the automobile 51 arranged vertically. The uppermost image P1 is an image at 15:45:21 on October 12, 2023.

[0072] The image P1 shows a situation where the automobile 51 is traveling on the road. The middle image P2 is an image at 15:45:22 on October 12, 2023. The image P2 shows a situation where the automobile 52 is approaching from the side road to the road on which the automobile 51 is traveling. It is an image at 15:45:23 on October 12, 2023. The image P3 shows a situation where the automobile 51 and the automobile 52 are approaching.

[0073] In the above situation, the event information reception unit 111 acquires the images P1 to P3 and receives information such as the times when the images P1 to P3 are captured and the locations where the images P1 to P3 are captured.

[0074] Next, the reproduction information will be described with reference to FIG. 8. FIG. 8 is a diagram showing an example of the reproduction information. A virtual space image V1 is shown in FIG. 8. The virtual space image V1 is an image of a virtual space generated by the reproduction information generation unit 113. The virtual space image V1 includes a road, and automobiles 51 and 52 traveling on the road. The road in the virtual space image V1 is generated by the reproduction information generation unit 113 on the virtual space. The reproduction information generation unit 113 generates a road having attributes equivalent to those of the actual road by collating the information on the place where the automobile 51 actually traveled with the map information database 122 that the information processing apparatus 20 has. Here, the attributes of the road are the shape of the road, the friction coefficient of the road surface, and the like.

[0075] The reproduction information generation unit 113 further generates the automobiles 51 and 52 traveling on the road on the virtual space. The virtual space image V1 is an image including information corresponding to, for example, the time T2 in FIG. 5. The reproduction information generation unit 113 generates a plurality of such images along with time. Thereby, the reproduction information generation unit 113 generates reproduction information that reproduces the movement of the automobile 51 and the movement of the automobile 52. Although FIG. 8 shows an image of observing the situation of the event from the information, the virtual space image V1 can change the observation viewpoint. Since the observation viewpoint can be changed, the information processing apparatus 20 can provide the user with information that is easy to grasp the situation of the event.

[0076] Next, with reference to FIG. 9, variations of the information processing method will be described. FIG. 9 is a flowchart showing the information processing method according to the present disclosure. The flowchart shown in FIG. 9 is different from the flowchart shown in FIG. 2 in that it further has steps S21, S22, and S23.

[0077] In step S14, the output unit 114 of the information processing apparatus 20 outputs the reproduction information to the user terminal 400.

[0078] Next, the information processing apparatus 20 determines whether there is a correction instruction from the user terminal 400 (step S21). If the information processing apparatus 20 determines that there is no correction instruction (step S21: NO), the information processing apparatus 20 ends the series of processes. On the other hand, when receiving a correction instruction from the user terminal 400, the information processing apparatus 20 determines that there is a correction instruction. In that case (step S21: YES), the information processing apparatus 20 proceeds to step S22.

[0079] In step S22, the event information reception unit 111 receives the event information related to the correction instruction (step S22). The event information related to the correction instruction may change the content of the event information that has already been received. Also, the event information related to the correction instruction may add to the content of the event information.

[0080] After receiving the event information related to the correction instruction, the context information extraction unit 112 corrects the context information according to the received event information (step S23). Next, the information processing apparatus 20 proceeds to step S13 to generate reproduction information.

[0081] The variations of the information processing method have been described above. By such a method, for example, the user can add information lacking in the reproduction information. More specifically, for example, the user can supply the information processing apparatus 20 with images taken from a plurality of angles at the location where the event occurred as additional event information. Therefore, the information processing apparatus 20 can suitably generate and correct the reproduction information.

[0082] The above describes the embodiments. Note that the information processing apparatus according to the present disclosure is not limited to the above-described configuration. For example, the event information reception unit 111 may receive, as event information related to one event, images captured by cameras respectively possessed by a plurality of automobiles. In addition to the above-described information, the event information may include images captured by surveillance cameras or smartphones. The event information reception unit 111 may receive, as event information, the temperature, weather, etc. at the location where the event occurred at the time when the event occurred. The event information reception unit 111 may receive, as event information, information generated by remote sensing technology using various sensors mounted on artificial satellites, aircraft, etc. The remote sensing technology includes, for example, image analysis including SAR (Synthetic Aperture Radar), optical fiber sensor analysis, multi-satellite image analysis, cross-view image matching between on-site images and satellite images, etc.

[0083] With the above configuration, the information processing apparatus realizes a digital twin that suitably reproduces an event that occurred in the real space in the virtual space. Further, the information processing apparatus can reproduce an event such as a traffic accident in the virtual space. In this case, for example, an automobile insurance company can use the reproduction information generated by the information processing apparatus in calculating the insurance premium related to the accident. Thereby, the automobile insurance company can suitably calculate the insurance premium or the liability ratio.

[0084] As described above, according to the present disclosure, it is possible to provide an information processing apparatus, an information processing method, and a program that can suitably grasp the situation of an event.

[0085] <Example of hardware configuration> Hereinafter, an example in which each functional configuration of the information processing apparatus in the present disclosure is realized by a combination of hardware and software will be described.

[0086] FIG. 10 is a block diagram illustrating the hardware configuration of a computer. The information processing apparatus in the present disclosure can implement the above-described functions by a computer 500 including the hardware configuration shown in the figure. The computer 500 may be a portable computer such as a smartphone or a tablet terminal, or may be a stationary computer such as a PC. The computer 500 may be a dedicated computer designed to implement each device, or may be a general-purpose computer. The computer 500 can implement a desired function by installing a predetermined application.

[0087] The computer 500 includes a bus 502, a processor 504, a memory 506, a storage device 508, an input / output interface (I / F) 510, and a network interface (I / F) 512. The bus 502 is a data transmission path for the processor 504, the memory 506, the storage device 508, the input / output interface 510, and the network interface 512 to transmit and receive data to and from each other. However, the method of connecting the processor 504 and the like to each other is not limited to bus connection.

[0088] The processor 504 is various processors such as a CPU, a GPU, or an FPGA. The memory 506 is a main storage device realized using a RAM (Random Access Memory) or the like.

[0089] The storage device 508 is an auxiliary storage device realized using a hard disk, an SSD, a memory card, or a ROM (Read Only Memory). The storage device 508 stores a program for implementing a desired function. The processor 504 reads out and executes this program in the memory 506 to implement each functional component of each device.

[0090] The input / output interface 510 is an interface for connecting the computer 500 and an input / output device. For example, an input device such as a keyboard and an output device such as a display device are connected to the input / output interface 510. The network interface 512 is an interface for connecting the computer 500 to a network.

[0091] Note that the present disclosure is not limited to the above-described embodiments. Various changes that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. And each embodiment can be combined with other embodiments as appropriate.

[0092] Each drawing is merely an example for explaining one or more embodiments. Each drawing is not associated with only one specific embodiment, but may be associated with one or more other embodiments. As can be understood by those skilled in the art, various features or steps described with reference to any one drawing can be combined with the features or steps shown in one or more other drawings to create, for example, embodiments not explicitly illustrated or described. Not all of the features or steps shown in any one drawing for explaining exemplary embodiments are necessarily essential, and some features or steps may be omitted. The order of the steps described in any drawing may be changed as appropriate.

[0093] Some or all of the above embodiments can be described as follows in the appended claims, but are not limited thereto. (Appended Claim 1) An event information receiving unit that receives event information including information indicating the movement of the moving body related to a predetermined event that has occurred in the moving body, A context information extraction unit that extracts context information indicating the content of the event from the event information, A reproduction information generation unit that generates reproduction information including complementary information that complements the content of the event from the context information, An output unit that outputs the reproduction information, and An information processing apparatus. (Appendix 2) The event information reception unit receives the event information including one or more pieces of image information. The information processing apparatus according to Appendix 1. (Appendix 3) The event information reception unit receives the event information including data of sensors acquired by the moving body at a plurality of times. The information processing apparatus according to Appendix 2. (Appendix 4) The context information extraction unit extracts, as the context information, attribute information for each object including the moving body at a plurality of times of the event. The information processing apparatus according to Appendix 1. (Appendix 5) The reproduction information generation unit causes the learned model trained to generate complementary information for complementing the attribute information to generate the complementary information, and generates the reproduction information based on the context information and the complementary information in the event for each predetermined period. The information processing apparatus according to Appendix 4. (Appendix 6) The reproduction information generation unit generates the reproduction information with reference to map information of the location where the event occurred. The information processing apparatus according to Appendix 1. (Appendix 7) The reproduction information generation unit generates the reproduction information in a manner in which the complementary information can be identified. The information processing apparatus according to Appendix 1. (Appendix 8) The reproduction information generation unit generates the reproduction information that three-dimensionally shows the movement of the moving body in a virtual space in which the event is reproduced. The information processing apparatus according to any one of Appendices 1 to 7. (Appendix 9) A computer receives event information including information indicating the movement of the moving body related to a predetermined event that has occurred in the moving body, extracts context information indicating the content of the event from the event information, Generate reproduction information including complementary information that supplements the content of the event from the context information, and output the reproduction information. An information processing method. (Appendix 10) Receive event information including information indicating the movement of the mobile body related to a predetermined event that has occurred in the mobile body, extract context information indicating the content of the event from the event information, generate reproduction information including complementary information that supplements the content of the event from the context information, and output the reproduction information. A program for causing a computer to execute an information processing method.

[0094] Some or all of the elements (for example, configurations and functions) described in Appendices 2 to 8 that are subordinate to Appendix 1 may be subordinate to Appendices 9 and 10 in the same subordinate relationship as Appendices 2 to 8. Some or all of the elements described in any appendix may be applied to various hardware, software, recording means for recording software, systems, and methods.

Description of Reference Numerals

[0095] 10 Information processing apparatus 20 Information processing apparatus 111 Event information reception unit 112 Context information extraction unit 113 Reproduction information generation unit 114 Output unit 120 Storage unit 121 Attribute information database 122 Map information database 400 User terminal 411 Operation reception unit 412 Display unit 413 Communication unit 414 Control unit 420 Storage unit 421 Program 422 Event information 400 User terminal 500 Computer 502 Bus 504 Processor 506 Memory 508 Storage Device 510 Input / Output I / F 512 Network I / F 900 User Terminal

Claims

1. an event information receiving unit that receives event information including information indicating a movement of the moving object related to a predetermined event that has occurred in the moving object; a context information extraction unit that extracts context information indicating a content of the event from the event information; a reenactment information generating unit for generating reenactment information including supplementary information for supplementing the content of the event from the context information; and an output unit that outputs the reproduction information. Information processing device.

2. the event information receiving unit receives the event information including one or more pieces of image information; The information processing device according to claim 1 .

3. the event information receiving unit receives the event information including sensor data acquired by the moving object at a plurality of times; The information processing device according to claim 2 .

4. the context information extraction unit extracts attribute information for each object including the moving object at a plurality of times of the event as the context information; The information processing device according to claim 1 .

5. The reproduction information generation unit causes a trained model trained to generate complementary information that complements the attribute information to generate the complementary information; generating the reproduction information based on the context information and the complementary information for the event for each predetermined period; The information processing device according to claim 4.

6. the reproduction information generating unit generates the reproduction information by referring to map information of a location where the event occurred. The information processing device according to claim 1 .

7. the reproduction information generating unit generates the reproduction information in a manner in which the complementary information can be identified. The information processing device according to claim 1 .

8. the reproduction information generation unit generates the reproduction information three-dimensionally indicating a movement of the moving object in a virtual space in which the event is reproduced. The information processing device according to any one of claims 1 to 7.

9. The computer receiving event information including information indicating a movement of the moving object related to a predetermined event occurring in the moving object; extracting context information indicating a content of the event from the event information; generating replay information including supplementary information that supplements the content of the event from the context information; outputting the reproduction information; Information processing methods.

10. receiving event information including information indicating a movement of the moving object related to a predetermined event occurring in the moving object; extracting context information indicating a content of the event from the event information; generating replay information including supplementary information that supplements the content of the event from the context information; outputting the reproduction information; A program that causes a computer to execute an information processing method.

Images