WO2023084814A1 - Système de communication, serveur, procédé de communication et programme de communication - Google Patents

Système de communication, serveur, procédé de communication et programme de communication Download PDF

Info

Publication number
WO2023084814A1
WO2023084814A1 PCT/JP2022/015322 JP2022015322W WO2023084814A1 WO 2023084814 A1 WO2023084814 A1 WO 2023084814A1 JP 2022015322 W JP2022015322 W JP 2022015322W WO 2023084814 A1 WO2023084814 A1 WO 2023084814A1
Authority
WO
WIPO (PCT)
Prior art keywords
search
person
unit
spatio
server
Prior art date
Application number
PCT/JP2022/015322
Other languages
English (en)
Japanese (ja)
Inventor
淳 磯村
宣宏 沖
一兵衛 内藤
磯生 上野
直子 重松
デビッド アッシュ
ブラッド ダビジャ
シュムール アール
Original Assignee
日本電信電話株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 日本電信電話株式会社 filed Critical 日本電信電話株式会社
Publication of WO2023084814A1 publication Critical patent/WO2023084814A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/10—File systems; File servers
    • G06F16/18—File system types
    • G06F16/182—Distributed file systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/53—Querying
    • G06F16/532—Query formulation, e.g. graphical querying
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually

Definitions

  • the present invention relates to a communication system, a server, a communication method, and a communication program.
  • Non-Patent Document 1 a plurality of cameras are installed in an external environment such as a roadside strip, and a warning such as "the face recognition camera is in operation” is issued to a person who seems to be a suspicious person, or "face recognition It is disclosed that a crime is deterred by issuing a warning such as "You are being monitored by a camera.”
  • Non-Patent Document 2 discloses that machine learning improves the safety of public spaces in a smart city environment.
  • Non-Patent Document 3 describes a technique for recognizing a suspicious person by capturing an image of a person using CCTV (closed-circuit television), analyzing the behavior of the person who is considered to be a suspicious person, and comparing it with past behavior. is disclosed.
  • CCTV closed-circuit television
  • Patent Document 1 and Non-Patent Document 4 disclose techniques for quickly searching for data to be searched by setting spatio-temporal information consisting of time information and position information.
  • Non-Patent Documents 1 to 4 and Patent Document 1 mentioned above when there is a stranger in the neighborhood, the risk of crime by this person is immediately analyzed in light of time information and location information, and the analyzed information is There is no disclosure of informing the user.
  • the present invention has been made in view of the above circumstances, and its purpose is to improve the safety and security of nearby residents by immediately predicting the actions and intentions of actions of strangers. to prevent inaccurate or false profiling against strangers for unfair or wrong reasons, and to prevent unlawful (unfair) discrimination against unfamiliar persons, and vice versa.
  • a server, a communication method, and a communication program capable of preventing a claim for damages from a victim.
  • a communication system is a communication system including a communication terminal and a server, wherein the communication terminal includes an imaging unit that captures an image of the surroundings, and an image of a target person captured by the imaging unit. a search command unit that outputs search data to which search-side spatio-temporal information including time and position is added; and a terminal-side communication unit that communicates with the server, wherein the server includes person-related information and the person Storage-side spatio-temporal information including associated information collection time and collection location; a server-side communication unit for receiving stored data having; a database having a plurality of nodes; a storage processing unit that calculates a hash value and stores the stored data in a node set based on the first hash value among the plurality of nodes; a search processing unit that calculates a hash value and searches for stored data related to the search data from a node corresponding to the second hash value among the plurality of nodes; a risk value calculation unit that calculates the risk value of the target
  • a server includes stored data obtained by adding storage-side spatio-temporal information including the collection time and collection position of the person-related information to person-related information, and a search including the time and position in the image of the target person.
  • search data to which side spatio-temporal information is added a communication unit that receives search data; a database having a plurality of nodes; and a first hash value using the storage side spatio-temporal information; calculating a second hash value using a storage processing unit that stores the stored data in a node set based on the first hash value, and the search-side spatio-temporal information;
  • a search processing unit for searching stored data related to the search data from a node corresponding to the second hash value, and calculating a risk value of the target person based on the stored data searched by the search processing unit. and a risk value calculator.
  • a communication method is a communication method for a communication system including a communication terminal and a server, wherein the communication terminal captures an image of a target person with an imaging unit and includes a time and a position in the image of the target person. a step of transmitting search data to which spatial information is added to said server; and said server receives stored data comprising person-related information and storage-side spatio-temporal information including collection time and collection position of said person-related information. and calculating a first hash value using the storage-side spatio-temporal information, and storing the stored data in a node set based on the first hash value among a plurality of nodes of a database.
  • One aspect of the present invention is a communication program for causing a computer to function as the server.
  • One aspect of the present invention is a communication program installed on the server via a network, which causes a computer to function as the server.
  • FIG. 1 is a block diagram showing the configuration of a communication system and its peripherals according to an embodiment.
  • FIG. 2 is an explanatory diagram showing an example of stored data.
  • FIG. 3 is an explanatory diagram showing an example of the data structure of stored data stored in each of the nodes N1 to Nn included in the database.
  • FIG. 4 is a block diagram showing the detailed configuration of the risk value calculator.
  • FIG. 5 is a flowchart showing the procedure of data storage processing in the communication system according to this embodiment.
  • FIG. 6 is a flowchart showing the procedure of data search processing in the communication system according to this embodiment.
  • FIG. 7 is a block diagram showing the hardware configuration of this embodiment.
  • FIG. 1 is a block diagram showing the configuration of the communication system and its peripheral devices according to this embodiment.
  • a communication system 100 according to this embodiment includes a communication terminal 1 and a server 2 connected to the communication terminal 1 via a network.
  • a data collection device 3 is connected to the server 2 .
  • the data collection device 3 is, for example, an IoT device and is connected to a network.
  • the data collection device 3 is a surveillance camera installed in roads, commercial facilities, residences, parking lots, etc., or a camera mounted on a vehicle or drone, a smart phone, a digital camera, or the like.
  • the data collection device 3 adds the person-related information (hereinafter referred to as “person-related information”) captured by surveillance cameras and cameras mounted on vehicles, drones, and smartphones to images of people and their related information (hereinafter referred to as “person-related information”). and data to which spatio-temporal information (storage-side spatio-temporal information) including the collection position is added (hereinafter referred to as “stored data”) is transmitted to the server 2 via the network. Collection locations can be set by longitude and latitude.
  • Person-related information includes information that indicates the characteristics of a person, such as an image of a person captured by a camera, information about a person's behavior, information about biometrics, information about walking and gestures such as gait, and information about clothing. Images include still images and moving images.
  • the number of data collection devices 3 may be one or plural.
  • FIG. 2 is an explanatory diagram showing an example of stored data.
  • the stored data transmitted from the data collection device 3 includes time information indicating data acquisition time, position information indicating longitude and latitude, and person-related information acquired by the data collection device 3 ( data part) are associated with each other.
  • the data collection device 3 stores the person-related information “data1” acquired at the time “2017/1/1, 10:15:30” at the position of longitude “27.1984°” and latitude “-15.2958°”. is transmitted to the server 2 as
  • the communication terminal 1 for example, an in-vehicle device mounted on a mobile object such as a smartphone or a vehicle can be used.
  • the communication terminal 1 includes a camera 11 (imaging section), a search command section 12, an information presentation section 13, and a communication section 14 (terminal side communication section).
  • the camera 11 captures an image of a person existing around the communication terminal 1.
  • the camera 11 is a camera built in a smart phone, an in-vehicle camera, or the like. Images captured by the camera 11 include still images and moving images. A user can use the camera 11 to capture an image of a surrounding person. An image (still image, moving image) captured by the camera 11 is output to the search command section 12 .
  • the camera 11 is an example of an imaging unit that captures images of the surroundings.
  • the search command unit 12 When the user inputs a search request for an image of a person captured by the camera 11, the search command unit 12 includes the person's image and spatio-temporal information (search-side spatio-temporal information) in the server 2. Data (hereinafter referred to as “retrieval data”) is output.
  • the spatio-temporal information includes time and position information.
  • the search command unit 12 may transmit search data including an image of a person to the server 2 when a person is detected by the camera 11 regardless of whether or not the user has input a search command. That is, the search command unit 12 outputs search data obtained by adding search-side spatio-temporal information including time and position information to the image captured by the camera 11 .
  • the information presentation unit 13 includes a display for image display or a speaker for audio output.
  • the information presentation unit 13 presents the information transmitted from the server 2 to the user in the form of images or sounds.
  • the information presenting unit 13 presents the risk value calculated by the risk value calculating unit 236, which will be described later, to the user of the communication terminal 1.
  • FIG. The information presentation unit 13 presents the risk value in real time after the search command unit 12 outputs the search data.
  • the communication unit 14 (terminal-side communication unit) communicates with the server 2.
  • the communication unit 14 transmits search data to the server 2 via the network.
  • the communication unit 14 receives the determination result by the risk value calculation unit 236, which will be described later.
  • the server 2 includes a communication unit 21, a storage unit 22, a search unit 23, and a database 25.
  • the database 25 has a plurality of nodes N1, N2, . . . , Nn in the form of a KVS (Key-Value Store).
  • KVS Key-Value Store
  • "KVS” is a method of setting a unique indicator (key) corresponding to data (value) to be saved and storing the key and value in pairs.
  • the communication unit 21 (server-side communication unit) communicates with the communication terminal 1 and the data collection device 3 via the network.
  • the communication unit 21 receives stored data transmitted from the data collection device 3 and outputs the stored data to the storage unit 22 . That is, the communication unit 21 receives stored data including person-related information and storage-side spatio-temporal information including information on the collection time and collection position of the person-related information.
  • the communication unit 21 receives search data output from the communication terminal 1 and outputs the data to the search unit 23 .
  • the communication unit 21 transmits various types of information searched by the search unit 23 (such as the determination result of the risk value calculation unit 236 ) to the communication terminal 1 .
  • the storage unit 22 includes a first generation unit 221 , a first division unit 222 , a first calculation unit 223 , a storage destination node calculation unit 224 and a storage processing unit 225 .
  • the storage unit 22 distributes and stores the stored data transmitted from the data collection device 3 in the KVS format to a plurality of nodes N1 to Nn of the database 25, so that the stored data is concentrated in a specific node. avoid being stored.
  • the first generation unit 221 generates a spatio-temporal index based on the stored data transmitted from the data collection device 3. As described above, the stored data includes spatio-temporal information (storage-side spatio-temporal information) and person-related information. The first generator 221 generates a spatio-temporal index by converting the spatio-temporal information into a one-dimensional bit string.
  • the first dividing unit 222 divides the one-dimensional bit string generated by the first generating unit 221 into a forward bit string and a backward bit string.
  • the first calculation unit 223 calculates a hash value (first hash value) from the forward bit string divided by the first division unit 222 . Since the hash value calculation method is a known technique, detailed description thereof is omitted.
  • the storage destination node calculation unit 224 sets the node as the storage destination of the stored data based on the first hash value calculated by the first calculation unit 223 .
  • the storage processing unit 225 stores the storage data in the KVS format in the node set by the storage destination node calculation unit 224 .
  • FIG. 3 is a diagram showing an example of the data structure of stored data stored in each of the nodes N1 to Nn included in the database 25. As shown in FIG. As shown in FIG. 3, the key is set based on the forward bit string and the value is set based on the backward bit string. Person-related information (data part: data1, data2, . . . ) is stored in association with the value. That is, the storage processing unit 225 calculates the first hash value using the storage-side spatio-temporal information, and stores the stored data in the node set based on the first hash value among the plurality of nodes. I do.
  • the data structure of the stored data stored in the nodes N1 to Nn is a key-value type having a secondary index part.
  • the nodes N1 to Nn store data in a configuration having items of node identification information, key, and value as in the list L2.
  • the value is provided with a secondary index portion and a data portion in which event information data is stored.
  • the key stores the forward bit string when the spatio-temporal information is bit string-converted.
  • the secondary index of the value stores the backward bit string when the spatio-temporal information is bit string-converted.
  • the search unit 23 includes a second generation unit 231, a second division unit 232, a second calculation unit 233, a search destination node calculation unit 234, a search processing unit 235, a risk value A calculation unit 236 is provided.
  • the second generation unit 231 generates a spatio-temporal index based on the search data transmitted from the communication terminal 1.
  • the search data includes spatio-temporal information (search-side spatio-temporal information) and images.
  • the image is, for example, an image of a person captured by a camera 11 mounted on a vehicle or a smartphone.
  • the second generation unit 231 generates a spatio-temporal index by converting the spatio-temporal information included in the search data into a one-dimensional bit string.
  • the second dividing unit 232 divides the one-dimensional bit string generated by the second generating unit 231 into a forward bit string and a backward bit string.
  • the second calculation unit 233 calculates a hash value (second hash value) from the forward bit string divided by the second division unit 232 .
  • the search destination node calculation unit 234 sets the node to be the search destination for information related to the search data.
  • the search processing unit 235 searches for the node set by the search destination node calculation unit 234. Specifically, as shown in FIG. 3, a key is set based on the forward bit string, and a value is set based on the backward bit string. Search stored data related to the search item from the stored data stored corresponding to the value.
  • the search processing unit 235 stores event information that occurred in the past near this location and time, and related storage Search data.
  • the search processor 235 outputs stored data acquired from the database 25 to the risk value calculator 236 .
  • the search processing unit 235 acquires stored data that matches the search data. For example, a person who matches the person in the image included in the search data (hereinafter referred to as "target person") and information related to this person are searched.
  • the search processing unit 235 identifies a person who matches the target person by face recognition processing, which is a well-known technique.
  • the search processing unit 235 calculates a second hash value using the search-side spatio-temporal information, and searches for stored data related to the search data from the node set based on the second hash value among the plurality of nodes. process.
  • the search processor 235 outputs information related to the specified person to the risk value calculator 236 .
  • the risk value calculation unit 236 calculates the risk value of the target person based on the stored data searched by the search processing unit 235.
  • the risk value calculation unit 236 calculates the risk value of the target person based on the image data of the target person and various data related to the target person searched by the search processing unit 235 .
  • the risk value is the degree to which a target person is likely to cause dangerous behavior in a specific place. Probability is high.
  • a risk value is quantified and calculated based on various kinds of information such as whether or not the posture and gait during walking or other behaviors (behavior history) are abnormal.
  • the risk value calculator 236 transmits the calculated risk value to the communication terminal 1 .
  • FIG. 4 is a block diagram showing the detailed configuration of the risk value calculator 236.
  • the risk value calculation unit 236 includes a personal information determination unit 51 , an expression determination unit 52 , a stay time determination unit 53 , a behavior determination unit 54 and a point addition unit 55 .
  • the personal information determination unit 51 determines the personal information of the target person based on various data searched by the search processing unit 235, and sets a risk value according to the determination result. If the target person has a criminal record, the personal information determination unit 51 acquires information such as the number and content of crimes from a crime database provided by the police, etc., and determines the risk according to the number and content of the crimes. Calculate the value. In addition to the criminal database, the information related to the criminal record can also be obtained via a network from a database other than the criminal database, cloud search, or the like.
  • the point is "+1", if multiple times, "+2", and if there is no criminal record, the point is "0". Also, if the content of the criminal history is a serious crime such as an injury incident, "+1" is added to the points. Also, information is acquired as to whether the position where the target person is confirmed is near or far from the residence of this target person, and if it is far, the point is increased by "+1".
  • the facial expression determination unit 52 determines the facial expression of the target person from the image of the target person, and sets a risk value according to the determination result. Specifically, the facial expression determination unit 52 determines whether or not the target person is nervous and whether or not the target person is drinking. ”, and when it is determined that the person is drinking, the point is set to “+1”.
  • the stay time determination unit 53 determines the place and time that the target person stays nearby from the image of the target person. For example, it is determined whether or not the user stays in the same area (for example, in a park or in a commercial facility) for a long time.
  • the staying time determining unit 53 gives a point of "+1" when the staying time is long, for example, when the staying time exceeds a predetermined time.
  • the behavior determination unit 54 determines the behavior of the target person from the image of the target person.
  • the behavior determination unit 54 determines, for example, whether or not the target person is interacting with others in an unnatural manner, or whether or not the person behaves in an unnatural manner.
  • the behavior determination unit 54 gives a point of "+1" when it is determined that the target person is having unnatural interactions with others, or when the target person has an unnatural behavior.
  • behaviors such as people stopping, sitting, and going back and forth are not natural behaviors. That is, a stranger's behaviors such as stopping, sitting, and going back and forth are natural behaviors around train stations, but are unnatural behaviors around elementary and junior high schools, and are factors that increase the risk value.
  • the behavior determination unit 54 calculates the degree of "unnatural behavior” as follows. First, we search for multiple places that have the same characteristics as the "specific place” where the target person is, and then search for people's flow, human gestures and behavior, human gait, clothing, etc. common to multiple "specific places”. The average value and average features of are calculated in advance. Next, the "specific place” where the target person is located and its movements, gestures, gaits, and clothes are compared with the average values and average characteristics described above. If the comparison result exceeds a predetermined value, it is determined that the behavior of the target person is unnatural, and points are added. For example, let the point be "+1".
  • the behavior determination unit 54 combines (a) detection of the difference between normal behavior and specific behavior at a specific location, and (b) detection of the history and characteristics of the target person.
  • points are added if it is determined to be unnatural. If the degree of unnaturalness is large, the points to be added may be increased, such as "+2".
  • the points to be added may be increased, such as "+2".
  • people near the target person and the vicinity of the target person A store clerk in the store may be notified that there is a person behaving unnaturally.
  • the presence of a person acting unnaturally may be reported to a preset reporting destination such as the police.
  • the point addition unit 55 adds the points calculated by the personal information determination unit 51, the facial expression determination unit 52, the stay time determination unit 53, and the behavior determination unit 54 described above, and uses the total as a risk value. Point adder 55 transmits the calculated risk value to communication terminal 1 .
  • the risk value calculation unit 236 stores the stored data including the behavior of a person statistically detected at a specific location and the spatio-temporal information (storage-side spatio-temporal information) added to the behavior of the person in the database 25. Search from The risk value calculation unit 236 calculates a risk value based on the retrieved stored data, the behavior of a specific person in a specific location recognized in real time by the communication terminal 1, and the past behavior history of the specific person. calculate.
  • FIG. 5 is a flowchart showing a process of storing stored data in the database 25
  • FIG. 6 is a flowchart showing a process of searching information related to search data from the stored data stored in the database 25.
  • step S11 the data collection device 3 acquires stored data. For example, still images or moving images captured by surveillance cameras installed in roads, commercial facilities, residences, parking lots, and the like are acquired.
  • the data collection device 3 generates stored data including spatio-temporal information and person-related information, and transmits the stored data to the server 2.
  • the spatio-temporal information includes time information and position information consisting of longitude and latitude.
  • Person-related information includes an image of a person and information related to this person.
  • the stored data transmitted from the data collection device 3 is received by the communication unit 21 of the server 2 .
  • step S12 the first generation unit 221 generates a spatio-temporal index by converting the spatio-temporal information included in the stored data into a one-dimensional bit string. Specifically, the time, longitude, and latitude information is converted into a one-dimensional bit string.
  • step S13 the first dividing unit 222 divides the one-dimensional bit string into a forward bit string and a backward bit string.
  • step S14 the first calculation unit 223 calculates the hash value (first hash value) of the forward bit.
  • step S15 the storage destination node calculation unit 224 sets the node of the database 25 that stores the stored data based on the first hash value calculated in the process of S14.
  • the storage destination node calculation unit 224 sets the node of the database 25 that stores the stored data based on the first hash value calculated in the process of S14.
  • step S16 the storage processing unit 225 stores the forward bit string in the KVC format key and the backward bit string in the value, as shown in FIG.
  • step S17 the storage processing unit 225 stores the person-related information in the value.
  • the stored data output from the data collection device 3 is stored in each node included in the database 25 in the KVS format. At this time, it is possible to avoid concentration of stored data in a specific node.
  • step S31 the communication terminal 1 transmits search data to the server 2, and the communication section 21 of the server 2 receives the search data.
  • image data of a person captured by the camera 11 of the communication terminal 1 is acquired, and when a search command operation is input by the user in the search command unit 12, spatio-temporal information is added to the image data.
  • the added search data is sent.
  • step S32 the second generation unit 231 generates a spatio-temporal index by converting the spatio-temporal information included in the stored data into a one-dimensional bit string. Specifically, the time, longitude, and latitude information is converted into a one-dimensional bit string.
  • step S33 the second dividing unit 232 divides the one-dimensional bit string into a forward bit string and a backward bit string.
  • step S34 the second calculation unit 233 calculates the hash value (second hash value) of the forward bit.
  • step S35 the search destination node calculation unit 234 calculates the node number of the database 25 as the search destination based on the second hash value calculated in the process of S34.
  • the search destination node calculation unit 234 calculates the node number of the database 25 as the search destination based on the second hash value calculated in the process of S34.
  • step S36 the search processing unit 235 searches for a node using the forward bit string extracted by the second dividing unit 232 as a key and the backward bit string as a value.
  • step S37 the search processing unit 235 extracts stored data including information related to the search data from the search destination node.
  • the risk value calculation unit 236 refers to stored data including information related to the search data, and calculates the risk value of the target person included in the search data. As described above, the risk value calculator 236 calculates the risk value according to the target person's personal information, facial expression, staying time at a predetermined place, and behavior.
  • step S ⁇ b>39 the risk value calculator 236 outputs the calculated risk value, and the risk value data is transmitted from the communication unit 21 to the communication terminal 1 .
  • the risk value is presented by the information presentation unit 13 of the communication terminal 1. FIG. In this way, the user of the communication terminal 1 can know the risk value of the target person by transmitting the image of the target person (suspicious person, etc.) acquired by the communication terminal 1 to the server 2 as search data.
  • the communication system 100 is a communication system including the communication terminal 1 and the server 2.
  • the communication terminal 1 includes the camera 11 (imaging unit) that captures an image of the surroundings, and the camera 11
  • a search command unit 12 that outputs search data obtained by adding search-side spatio-temporal information including time and position to an image of a target person imaged in
  • a communication unit 14 terminal-side communication unit
  • the server 2 includes a communication unit 21 (server-side communication unit) that receives stored data having person-related information and storage-side spatio-temporal information including the collection time and collection position of the person-related information
  • a storage that calculates a first hash value using a database 25 having nodes and storage-side spatio-temporal information, and stores stored data in a node set based on the first hash value among a plurality of nodes
  • data such as a person's face, behavior, biometrics, etc. collected by the data collection device 3 is stored in a database.
  • the node number is calculated using the forward bit string, backward bit string, and hash value, and the stored data is stored in the calculated node. Therefore, it is possible to more reliably prevent a large amount of data from concentrating on a specific node.
  • the user of the communication terminal 1 can quickly recognize whether the stranger is a criminal or a person who behaves suspiciously by searching for images of strangers around him. can. For example, when there is a person who behaves abnormally near an elementary school, it is possible to prevent an incident from occurring by reporting the person to the police.
  • the image of this person is captured by the camera 11, and the search data including the image of this person is sent to the server 2, thereby making it possible to recognize the information of this person, It is possible to determine whether or not this person is a suspicious person.
  • this person's information and risk value can be obtained in real time. can be recognized and can be used to prevent crime. That is, in the present embodiment, it is possible to improve safety and security by immediately predicting the actions and intentions of actions of strangers and eliminating unfair profiling of strangers.
  • the user of the communication terminal 1 can recognize the risk value of the target person in the vicinity, he or she can recognize whether or not this target person is safe. Also, when the risk value exceeds a certain value, by reporting to the police or a nearby convenience store, it is possible to prevent a crime by a suspicious person.
  • the storage unit 22 and the search unit 23 employed in the communication system 100 according to the present embodiment store spatio-temporal information at high speed, and search, calculation, and judgment can be performed at high speed. It is possible to notify the surrounding people, the police, etc. in real time that there is a person.
  • the communication system 100 accesses the server 2 at high speed, stores various kinds of information collected by the data collection device 3 in the database 25, and accesses the server 2 at high speed to obtain necessary information. Search for information. Therefore, the information stored in the database 25 is highly reliable, and it is possible to avoid the inclusion of inaccurate information and intentional erroneous information. Avoid the occurrence of problems such as incorrect information being treated as fact, inappropriate treatment of others, encouragement of unfair discrimination, and acts that lead to legal risks. can be done. That is, in this embodiment, it is possible to help people and their businesses by making better decisions based only on valid and legal reasons.
  • the server 2 of the embodiment described above includes, for example, a CPU (Central Processing Unit, processor) 901, a memory 902, and a storage 903 (HDD: HardDisk Drive, SSD: Solid State Drive). , a communication device 904, an input device 905, and an output device 906, a general-purpose computer system can be used.
  • Memory 902 and storage 903 are storage devices.
  • each function of the server 2 is realized by the CPU 901 executing a predetermined program loaded on the memory 902 .
  • server 2 may be implemented by one computer, or may be implemented by a plurality of computers. Also, the server 2 may be a virtual machine implemented in a computer.
  • a method may be adopted in which the server 2 is remotely controlled via a network using a communication program that causes a computer to function as the server 2 .
  • a method may be adopted in which a communication program for causing the server 2 to function as a computer is installed on the server via a network.
  • the program for server 2 can be stored in a computer-readable recording medium such as HDD, SSD, USB (Universal Serial Bus) memory, CD (Compact Disc), DVD (Digital Versatile Disc), etc., or via a network. can also be delivered.
  • a computer-readable recording medium such as HDD, SSD, USB (Universal Serial Bus) memory, CD (Compact Disc), DVD (Digital Versatile Disc), etc., or via a network. can also be delivered.
  • a communication system including a communication terminal and a server,
  • the communication terminal includes a first memory and a first processor coupled to the first memory;
  • the server includes a second memory, a second processor connected to the second memory, and a hard disk having a plurality of nodes;
  • the first processor Capturing an image of the surroundings, and outputting search data obtained by adding search-side spatio-temporal information including time and position to the captured image of the target person, the second processor, receiving stored data having person-related information and storage-side spatio-temporal information including the collection time and collection position of the person-related information; calculating a first hash value using the storage-side spatio-temporal information, and storing the stored data in a node set based on the first hash value among the plurality of nodes; calculating a second hash value using the search-side spatio-temporal information, searching for stored data related to the search data from a node corresponding to the second hash value among the plurality of nodes; calculating a risk value of the
  • (Appendix 2) A non-temporary storage medium storing a program executable by a computer so as to execute processing by a communication terminal and a server constituting a communication system,
  • the processing is
  • the communication terminal captures an image of the surroundings, outputs search data obtained by adding search-side spatio-temporal information including time and position to the captured image of the target person,
  • the server receives stored data having person-related information and storage-side spatio-temporal information including the collection time and collection position of the person-related information, and generates a first hash using the storage-side spatio-temporal information.
  • Appendix 3 a memory, at least one processor coupled to the memory, and a database having a plurality of nodes;
  • the processor Stored data in which storage-side spatio-temporal information including the collection time and collection position of the person-related information is added to the person-related information, and search data in which search-side spatio-temporal information including the time and position is added to the image of the target person.
  • a non-temporary storage medium storing a program that can be executed by a computer for processing by a server, The processing is Stored data in which storage-side spatio-temporal information including the collection time and collection position of the person-related information is added to the person-related information, and search data in which search-side spatio-temporal information including the time and position is added to the image of the target person.
  • a non-temporary storage medium that calculates the risk value of the target person based on the retrieved stored data.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Library & Information Science (AREA)
  • Alarm Systems (AREA)

Abstract

Un terminal de communication (1) comprend une caméra (11) qui capture une image des environs et une unité d'instruction de recherche (12) qui délivre des données de recherche obtenues par attribution d'informations temps/espace côté recherche, incluant un temps et une position, à une image d'une personne sujette capturée par la caméra (11). Un serveur (2) comprend une unité de communication (21), une base de données (25), qui stocke une pluralité de nœuds, et une unité de traitement de stockage (225) qui calcule une première valeur de hachage à l'aide d'informations temps/espace côté stockage et stocke des données de stockage dans un nœud qui fait partie de la pluralité de nœuds et qui est défini sur la base de la première valeur de hachage. Le serveur (2) comprend en outre une unité de traitement de recherche (235) qui calcule une seconde valeur de hachage à l'aide d'informations temps/espace côté recherche et recherche des données de stockage pertinentes aux données de recherche dans un nœud qui fait partie de la pluralité de nœuds et qui correspond à la seconde valeur de hachage, et une unité de calcul de valeur de risque (236) qui calcule une valeur de risque de la personne sujette sur la base des données de stockage récupérées par l'unité de traitement de recherche (235).
PCT/JP2022/015322 2021-11-10 2022-03-29 Système de communication, serveur, procédé de communication et programme de communication WO2023084814A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US202163277861P 2021-11-10 2021-11-10
US63/277,861 2021-11-10

Publications (1)

Publication Number Publication Date
WO2023084814A1 true WO2023084814A1 (fr) 2023-05-19

Family

ID=86335529

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2022/015322 WO2023084814A1 (fr) 2021-11-10 2022-03-29 Système de communication, serveur, procédé de communication et programme de communication

Country Status (1)

Country Link
WO (1) WO2023084814A1 (fr)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005119539A1 (fr) * 2004-06-04 2005-12-15 Mitsubishi Denki Kabushiki Kaisha Serveur d’émission de certificat et système de certification pour certifier un environnement d’exploitation
JP2019095872A (ja) * 2017-11-20 2019-06-20 Ｎｅｃソリューションイノベータ株式会社 捜索システム、捜索装置、端末装置、捜索方法、及びプログラム
US10360668B1 (en) * 2018-08-13 2019-07-23 Truepic Inc. Methods for requesting and authenticating photographic image data
WO2020065708A1 (fr) * 2018-09-25 2020-04-02 株式会社ウフル Système informatique, procédé de notification de conduite imprudente de véhicule et programme
WO2020100326A1 (fr) * 2018-11-12 2020-05-22 株式会社Ｎｅｘｐｏｉｎｔ Système de traitement d'informations
JP2020149518A (ja) * 2019-03-15 2020-09-17 オムロン株式会社 特定映像収集システム、特定映像収集方法
KR102174611B1 (ko) * 2019-08-12 2020-11-06 한성대학교 산학협력단 블랙박스 장치 및 이를 이용한 영상 생성 방법

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005119539A1 (fr) * 2004-06-04 2005-12-15 Mitsubishi Denki Kabushiki Kaisha Serveur d’émission de certificat et système de certification pour certifier un environnement d’exploitation
JP2019095872A (ja) * 2017-11-20 2019-06-20 Ｎｅｃソリューションイノベータ株式会社 捜索システム、捜索装置、端末装置、捜索方法、及びプログラム
US10360668B1 (en) * 2018-08-13 2019-07-23 Truepic Inc. Methods for requesting and authenticating photographic image data
WO2020065708A1 (fr) * 2018-09-25 2020-04-02 株式会社ウフル Système informatique, procédé de notification de conduite imprudente de véhicule et programme
WO2020100326A1 (fr) * 2018-11-12 2020-05-22 株式会社Ｎｅｘｐｏｉｎｔ Système de traitement d'informations
JP2020149518A (ja) * 2019-03-15 2020-09-17 オムロン株式会社 特定映像収集システム、特定映像収集方法
KR102174611B1 (ko) * 2019-08-12 2020-11-06 한성대학교 산학협력단 블랙박스 장치 및 이를 이용한 영상 생성 방법

Similar Documents

Publication Publication Date Title
US11410001B2 (en) Method and apparatus for object authentication using images, electronic device, and storage medium
US11010254B2 (en) System and method for prioritization of data file backups
US11025693B2 (en) Event detection from signal data removing private information
JP6915542B2 (ja) 情報処理装置、通知システム、情報送信方法及びプログラム
CN111680535B (zh) 在视频监控中实时预测一个或多个潜在威胁的方法和系统
US9285868B2 (en) Camera device, communication system, and camera system
JP6151085B2 (ja) サービス提供システム、サービス提供方法およびサービス提供管理装置
WO2021180004A1 (fr) Procédé d'analyse de vidéo, procédé de gestion d'analyse de vidéo, et dispositif associé
KR20180118979A (ko) 다중로그 데이터 기반의 공공안전 위험상황 감지, 예측, 대응 방법 및 장치
KR101979375B1 (ko) 감시 영상의 객체 행동 예측 방법
US11348367B2 (en) System and method of biometric identification and storing and retrieving suspect information
US10970184B2 (en) Event detection removing private information
TW202125332A (zh) 一種目標運動軌跡構建方法、設備以及計算機存儲介質
US20230229152A1 (en) Processing system for dynamic event verification & sensor selection
KR102054930B1 (ko) 영상 공유 방법 및 이를 위한 장치
Chen et al. Trusting the computer in computer vision: A privacy-affirming framework
JP6542819B2 (ja) 画像監視システム
US11100784B2 (en) Method and system for detecting and notifying actionable events during surveillance
WO2023084814A1 (fr) Système de communication, serveur, procédé de communication et programme de communication
JP2019053381A (ja) 画像処理装置、情報処理装置、方法およびプログラム
WO2023124451A1 (fr) Procédé et appareil de génération d'événement d'alarme, dispositif et support de stockage
US20220335154A1 (en) Predictive response-generation systems to facilitate timely compliance with information-disclosure laws
Mahmood Ali et al. Strategies and tools for effective suspicious event detection from video: a survey perspective (COVID-19)
CN112241671B (zh) 一种人员身份识别方法、装置及系统
JP2018142137A (ja) 情報処理装置、情報処理方法、及びプログラム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22892318

Country of ref document: EP

Kind code of ref document: A1