A battlefield target recognition method, device, equipment and medium based on knowledge graph

Abstract

The present application relates to the field of image recognition, and in particular to a battlefield target recognition method, device, equipment and medium of a knowledge graph. The method includes: obtaining battlefield image information, then performing position detection on the battlefield image information, determining the image position information of the battlefield image information, then determining the processing device information based on the image position information, then summarizing the image feature information generated by the processing device information, and inputting the image feature information into the battlefield knowledge graph for feature recognition to obtain battlefield target information. The present application has the effect of improving the accuracy of battlefield target recognition.

Description

Technical Field

[0001] The present application relates to the field of image recognition, and in particular to a battlefield target recognition method, device, equipment and medium based on a knowledge graph. Background Art

[0002] Modern warfare is an information-based war. The entire battlefield presents a variety of combat methods, diversified combat targets, and a complex and changing combat environment, which makes command and combat increasingly difficult. How to command and guide combat deployment more efficiently and intelligently is an important process in the development of electronicization and automation of our military.

[0003] At present, when identifying battlefield targets (aircraft, tanks, ships, and communication vehicles, etc.), space-based infrared early warning satellite signal-level simulation systems and ground-based radar signal-level simulation systems are generally used. A distributed detection sensor network consisting of multiple satellites and multiple radars is used to integrate redundant and complementary information, which can collect battlefield targets to a greater extent, identify the collected battlefield targets, and timely estimate the subsequent situation and threats.

[0004] Regarding the above-mentioned related technologies, the inventors believe that when identifying battlefield targets, due to the remoteness of various distributed sensors, the collected target information is prone to certain uncertainty and ambiguity, thereby reducing the accuracy of battlefield target identification. Summary of the invention

[0005] In order to improve the accuracy of battlefield target recognition, the present application provides a battlefield target recognition method, device, equipment and medium based on a knowledge graph.

[0006] In the first aspect, the present application provides a battlefield target recognition method based on a knowledge graph, which adopts the following technical solution:

[0007] A battlefield target recognition method based on a knowledge graph, comprising:

[0008] Obtain battlefield image information;

[0009] Performing position detection on the battlefield image information to determine image position information of the battlefield image information;

[0010] determining processing device information based on the image position information;

[0011] The image feature information generated by the processing device information is summarized, and the image feature information is input into the battlefield knowledge graph for feature recognition to obtain battlefield target information.

[0012] By adopting the above technical solution, when identifying battlefield targets, battlefield image information of various positions is obtained, and then the position of the battlefield image information is detected to obtain image position information corresponding to the battlefield image information. According to the image position information, processing device information that can process the image information is obtained, and then a communication connection is established through the processing device corresponding to the processing device information, the image feature information generated by the processing device information is summarized and collected, and the image feature information is input into the battlefield knowledge graph for feature recognition to obtain the final battlefield target information. By adopting the same-region image processing and information aggregation and collection method, it is helpful to improve the uncertainty and ambiguity of target information, thereby improving the accuracy of battlefield target recognition.

[0013] In another possible implementation manner, determining the processing device information based on the image position information includes:

[0014] Scanning a preset area based on the image position information to obtain first device set information;

[0015] Performing signal detection on the processing device information in the first device set information respectively to determine the device signal state of the processing device information;

[0016] Determine whether the device signal state satisfies a preset signal state, and if not, filter out the processing device information corresponding to the device signal state to obtain second device set information;

[0017] respectively calculating the distance values ​​between the processing device information in the second device set information and the image position information to determine the signal transmission distance of the processing device information;

[0018] It is determined whether the signal transmission distance satisfies a preset distance condition, and if so, the processing device information corresponding to the signal transmission distance is determined.

[0019] Through the above technical scheme, when determining the processing device information, a preset area scan is performed according to the image position information to obtain the first device set information, and then the signal detection is performed on the processing device information in the first device set information respectively to obtain the device signal state of each processing device information, and then it is judged whether the device signal state satisfies the preset signal state. If not, the processing device information corresponding to the device signal state is screened out to obtain the second device set information, and then the distance value between the processing device information and the image position information in the second device set information is calculated respectively to determine the signal transmission distance of each processing device information, and then it is judged whether the signal transmission distance satisfies the preset distance condition. The preset distance condition represents the shortest distance value. Selecting the processing device information with the shortest distance to the image position information from the second device set information that satisfies the device signal state helps to improve the transmission efficiency of battlefield image information.

[0020] In another possible implementation, the image feature information generated by the processing device information is aggregated and input into the battlefield knowledge graph for feature recognition, which also includes:

[0021] Acquiring battlefield data information, wherein the battlefield data information includes terrain image information and combat tool image information;

[0022] A battlefield knowledge graph is constructed based on the battlefield data information.

[0023] Through the above technical solution, before identifying the image feature information, the terrain image information and combat tool image information of the battlefield are pre-collected by using an image collection device (for example, a drone), and then the collected terrain image information and combat tool image information are obtained, and a battlefield map is built based on the terrain image information and combat tool image information, so as to facilitate the subsequent identification of the image feature information.

[0024] In another possible implementation manner, the performing position detection on the battlefield image information to determine the image position information of the battlefield image information further includes:

[0025] Determine regional level information based on the image location information, where the regional level information is used to indicate level information of the region where the image location information is located;

[0026] Comparing the regional level information with a standard regional level table to determine a collection frequency for collecting the battlefield image information;

[0027] A preset acquisition device is controlled according to the acquisition frequency to acquire the battlefield image information.

[0028] Through the above technical scheme, when controlling the preset acquisition device to collect battlefield image information, the regional level information of the battlefield is determined according to the image position information, and then the regional level information is compared with the standard regional level table to determine the acquisition frequency of the battlefield image information, and then the preset acquisition device is controlled to collect the battlefield image information according to the acquisition frequency, thereby achieving the effect of controlling the acquisition frequency of the preset acquisition device and improving the real-time nature of the information.

[0029] In another possible implementation manner, the determining the regional level information based on the image position information further includes:

[0030] It is determined whether the regional level information conforms to the preset regional level information, and if so, the image position information is marked.

[0031] Through the above technical solution, when the regional level information of the image location information is judged, the regional level information is matched with the preset regional level information to determine whether the current regional level information conforms to the preset regional level information. If it conforms, the image location information is marked, so as to facilitate informing battlefield personnel to pay more attention to the image location information.

[0032] In another possible implementation, the image feature information generated by the processing device information is aggregated, and the image feature information is input into a knowledge graph for feature recognition to obtain battlefield target information, and then the following is further included:

[0033] Counting the number of battlefield targets in the battlefield target information to obtain battlefield scale information;

[0034] Determine whether the scale in the battlefield scale information reaches a preset battlefield scale, and if so, perform a driving judgment on the battlefield target in the battlefield target information to obtain target travel information;

[0035] The battlefield target information is predicted in combination with the battlefield scale information and the target travel information to obtain characteristic intention information.

[0036] Through the above technical scheme, when predicting the characteristic intention information of the battlefield based on the battlefield target information, the number of battlefield targets in the battlefield target information is counted to obtain the battlefield scale information, and then it is judged whether the scale in the battlefield scale information reaches the preset battlefield scale. When it reaches the preset battlefield scale, the movement of the battlefield targets in the battlefield target information is judged to obtain the target travel information, and then the battlefield target information is predicted in combination with the battlefield scale information and the target travel information to obtain the characteristic intention information, so as to facilitate battlefield personnel to predict the enemy's movements.

[0037] In another possible implementation, the battlefield target information is predicted by combining the battlefield scale information and the target travel information to obtain characteristic intention information, and then the method further includes:

[0038] Assessing the hazard level of the characteristic intention information to generate a characteristic hazard level;

[0039] It is determined whether the characteristic hazard level exceeds the preset hazard level. If so, an early warning instruction is generated to control the early warning device to issue an early warning.

[0040] Through the above technical scheme, when conducting a hazard assessment on characteristic intention information, the characteristic hazard level is determined according to the characteristic intention of the enemy in the characteristic intention information, and then it is determined whether the characteristic hazard level exceeds the preset hazard level. When it is met, an early warning instruction is generated to control the early warning device to issue an early warning, thereby achieving the effect of early warning of the enemy's hazard.

[0041] In the second aspect, the present application provides a battlefield target recognition device based on a knowledge graph, which adopts the following technical solution:

[0042] A battlefield target recognition device based on a knowledge graph, comprising:

[0043] An information acquisition module, used to acquire battlefield image information;

[0044] A position determination module, used to perform position detection on the battlefield image information and determine image position information of the battlefield image information;

[0045] A device determination module, used to determine processing device information based on the image position information;

[0046] The feature recognition module is used to summarize the image feature information generated by the processing device information, and input the image feature information into the battlefield knowledge graph for feature recognition to obtain battlefield target information.

[0047] By adopting the above technical solution, when identifying battlefield targets, battlefield image information of various positions is obtained, and then the position of the battlefield image information is detected to obtain image position information corresponding to the battlefield image information. According to the image position information, processing device information that can process the image information is obtained, and then a communication connection is established through the processing device corresponding to the processing device information, the image feature information generated by the processing device information is summarized and collected, and the image feature information is input into the battlefield knowledge graph for feature recognition to obtain the final battlefield target information. By adopting the same-region image processing and information aggregation and collection method, it is helpful to improve the uncertainty and ambiguity of target information, thereby improving the accuracy of battlefield target recognition.

[0048] In a possible implementation manner, when the device determination module determines the processing device information based on the image position information, it is specifically configured to:

[0049] Scanning a preset area based on the image position information to obtain first device set information;

[0050] Performing signal detection on the processing device information in the first device set information respectively to determine the device signal state of the processing device information;

[0051] Determine whether the device signal state satisfies a preset signal state, and if not, filter out the processing device information corresponding to the device signal state to obtain second device set information;

[0052] respectively calculating the distance values ​​between the processing device information in the second device set information and the image position information to determine the signal transmission distance of the processing device information;

[0053] It is determined whether the signal transmission distance satisfies a preset distance condition, and if so, the processing device information corresponding to the signal transmission distance is determined.

[0054] In another possible implementation, the device further includes: a data acquisition module and a map construction module, wherein:

[0055] The data acquisition module is used to acquire battlefield data information, wherein the battlefield data information includes terrain image information and combat tool image information;

[0056] The graph building module is used to build a battlefield knowledge graph based on the battlefield data information.

[0057] In another possible implementation, the device further includes: a region determination module, a region comparison module, and a frequency control module, wherein:

[0058] The region determination module is used to determine region level information based on the image position information, wherein the region level information is used to indicate level information of the region where the image position information is located;

[0059] The region comparison module is used to compare the region level information with the standard region level table to determine the frequency of collecting the battlefield image information;

[0060] The frequency control module is used to control a preset acquisition device to acquire the battlefield image information according to the acquisition frequency.

[0061] In another possible implementation, the device further includes: a level determination module, wherein:

[0062] The level judgment module is used to judge whether the regional level information conforms to the preset regional level information, and if so, mark the image position information.

[0063] In another possible implementation, the device further includes: a quantity statistics module, a scale judgment module, and an intention prediction module, wherein:

[0064] The quantity statistics module is used to count the quantity of battlefield targets in the battlefield target information to obtain battlefield scale information;

[0065] The scale judgment module is used to judge whether the scale in the battlefield scale information reaches the preset battlefield scale. If it reaches, the battlefield target in the battlefield target information is judged to obtain the target travel information;

[0066] The intention prediction module is used to predict the battlefield target information in combination with the battlefield scale information and the target travel information to obtain characteristic intention information.

[0067] In another possible implementation, the device further includes: a level generating module and an early warning module, wherein:

[0068] The level generating module is used to evaluate the hazard level of the characteristic intention information and generate a characteristic hazard level;

[0069] The early warning module is used to determine whether the characteristic hazard level exceeds the preset hazard level. If it exceeds, a warning instruction is generated to control the early warning device to issue an early warning.

[0070] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0071] An electronic device, comprising:

[0072] at least one processor;

[0073] Memory;

[0074] At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the battlefield target recognition method based on the above-mentioned knowledge graph.

[0075] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0076] A computer-readable storage medium, comprising: a computer program storing a battlefield target identification method that can be loaded by a processor and execute the above-mentioned knowledge graph.

[0077] In summary, this application includes the following beneficial technical effects:

[0078] 1. When identifying battlefield targets, battlefield image information of different positions is obtained, and then the position of the battlefield image information is detected to obtain image position information corresponding to the battlefield image information. According to the image position information, processing device information that can process the image information is obtained, and then communication connection is established through the processing device corresponding to the processing device information, and the image feature information generated by the processing device information is collected and summarized, and the image feature information is input into the battlefield knowledge graph for feature recognition to obtain the final battlefield target information. By adopting the same-region image processing and information aggregation and collection method, it is helpful to improve the uncertainty and ambiguity of the target information, thereby improving the accuracy of battlefield target recognition;

[0079] 2. When determining the processing device information, perform a preset area scan based on the image position information to obtain the first device set information, then perform signal detection on the processing device information in the first device set information respectively to obtain the device signal status of each processing device information, then determine whether the device signal status satisfies the preset signal status, if not, screen out the processing device information corresponding to the device signal status to obtain the second device set information, then calculate the distance value between the processing device information in the second device set information and the image position information respectively, determine the signal transmission distance of each processing device information, then determine whether the signal transmission distance satisfies the preset distance condition, the preset distance condition represents the shortest distance value, and select the processing device information with the shortest distance to the image position information from the second device set information that satisfies the device signal status, which helps to improve the transmission efficiency of battlefield image information. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] Figure 1 It is a flowchart of a battlefield target recognition method based on a knowledge graph in an embodiment of the present application;

[0081] Figure 2 It is a block diagram of a battlefield target recognition method based on a knowledge graph in an embodiment of the present application;

[0082] Figure 3 It is a schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0083] The following is combined with Figure 1-3 This application is described in further detail.

[0084] After reading this specification, those skilled in the art may make non-creative modifications to this embodiment as needed, but such modifications are protected by patent law as long as they are within the scope of the claims of this application.

[0085] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0086] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0087] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0088] The embodiment of the present application provides a battlefield target recognition method based on a knowledge graph, which is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. Figure 1 As shown, the method includes:

[0089] Step S10, obtaining battlefield image information.

[0090] In an embodiment of the present application, image information is collected by an image acquisition device pre-set in each different battlefield. The image acquisition device includes a drone and an aircraft. The drone and the aircraft are respectively provided with cameras for image capture.

[0091] Specifically, the image acquisition device is connected to the communication end of the electronic device in the embodiment of the present application, so that the electronic device can directly obtain the battlefield image information collected by the image acquisition device. The specific connection method between the image acquisition device and the electronic device includes: the image acquisition device communicates with a base station at a short distance to send the battlefield image information to the base station, and then the electronic device communicates with the corresponding base station to obtain the battlefield image information.

[0092] Step S11, performing position detection on the battlefield image information to determine the image position information of the battlefield image information.

[0093] Specifically, battlefield image information includes terrain images, combat tool images, temperature information, and longitude and latitude information, wherein terrain images include: land, sky, and sea; combat tool images include: airplanes, tanks, armored vehicles, and aircraft carriers; temperature information indicates the temperature value of the image acquisition device; longitude and latitude information indicates the geographical location of the image acquisition device; and image position information of the battlefield image information is determined based on the specific longitude and latitude information.

[0094] Step S12: determining processing device information based on the image position information.

[0095] For the embodiment of the present application, the processing device information is an image processing device, specifically including: an image graphics processor and a computer. In addition, the information receiving end of the image processing device is connected to the base station described in step S10.

[0096] Specifically, the satellite positioning scanning technology is used to locate the accurate position in the image position information, and a regional scan is performed with the image position information as the center to determine the processing equipment information around the image position information.

[0097] Step S13, summarize the image feature information generated by the processing device information, and input the image feature information into the battlefield knowledge graph for feature recognition to obtain battlefield target information.

[0098] Specifically, the knowledge graph is a structured semantic knowledge base that is used to quickly describe concepts and their relationships in the physical world. The knowledge graph effectively processes, processes, and integrates the data of complex documents into simple and clear "entity, relationship, entity" triples, and finally aggregates a large amount of knowledge to achieve rapid response and reasoning of knowledge. There are two ways to build knowledge graphs: top-down and bottom-up. The so-called top-down construction is to extract ontology and pattern information from high-quality data with the help of structured data sources such as encyclopedia websites, and add it to the knowledge base; the so-called bottom-up construction is to extract resource patterns from publicly collected data with the help of certain technical means, select new patterns with higher confidence, and add them to the knowledge base after manual review.

[0099] In an embodiment of the present application, the battlefield knowledge graph includes terrain image information and combat tool image information. The image feature information generated by the image processing device is input into the battlefield knowledge graph for feature recognition to obtain battlefield target information.

[0100] An embodiment of the present application provides a battlefield target recognition method based on a knowledge graph. When identifying battlefield targets, battlefield image information of different positions is obtained, and then the position of the battlefield image information is detected to obtain image position information corresponding to the battlefield image information. Processing device information that can process the image information is obtained based on the image position information. Then, a communication connection is established through a processing device corresponding to the processing device information, and image feature information generated by the processing device information is summarized and collected. The image feature information is input into the battlefield knowledge graph for feature recognition to obtain the final battlefield target information. By adopting the same-region image processing and information aggregation and collection method, it helps to improve the uncertainty and ambiguity of target information, thereby improving the accuracy of battlefield target recognition and the efficiency of information query.

[0101] In a possible implementation of the embodiment of the present application, step S12 specifically includes step S121 (not shown in the figure), step S122 (not shown in the figure), step S123 (not shown in the figure), step S124 (not shown in the figure) and step S125 (not shown in the figure), wherein:

[0102] Step S121: Scan a preset area based on the image position information to obtain first device set information.

[0103] Specifically, the preset area is a circular area with the image location information as the center and a radius of 5 kilometers. The processing device information in the circular area is scanned to obtain multiple processing devices, and then the device information corresponding to the processing devices is put into a set to form the first device set information. For example: A represents the first device set information, and multiple processing devices are represented by (a, b, c, d, e...), then A={a, b, c, d, e...}.

[0104] Step S122: performing signal detection on the processing device information in the first device set information respectively to determine the device signal status of the processing device information.

[0105] Specifically, the signal status of the device that processes the device information is determined by a signal detector that is pre-set in a preset area.

[0106] Step S123, determining whether the device signal state satisfies the preset signal state, if not, filtering out the processing device information corresponding to the device signal state to obtain the second device set information.

[0107] Specifically, after the signal detection of the processing device information in the first device set information is completed by the signal detector, the device signal state corresponding to the processing device information is obtained, and the device signal state is represented by "1, 0, X, Z" respectively, where 1 and 0 are undoubtedly real signal states, while Z is used to represent a high impedance state and X is used to represent an uncertain state. The preset signal state is "1", and by judging whether the device signal state satisfies the preset signal state, the signal state that does not satisfy "1" is screened out, and the remaining second device set information of the first device set information is obtained.

[0108] Step S124, respectively calculating the distance values ​​between the processing device information in the second device set information and the image position information, and determining the signal transmission distance of the processing device information.

[0109] In the embodiment of the present application, the processing device information includes: the name of the processing device, the type of the processing device, the status of the processing device, and the longitude and latitude of the processing device.

[0110] Specifically, the processing device information in the second device set information is listed, and the distance between the longitude and latitude of the processing device and the longitude and latitude of the battlefield image information is calculated one by one. For example, the longitude and latitude of the processing device is (X1, Y1), and the longitude and latitude of the battlefield image information is (X2, Y2), where X1 and X2 are longitudes, and Y1 and Y2 are latitudes, which are converted into radians (*3.1415926 / 180) according to the calculation program. The radius of the earth is R=6371.0KM, then the signal transmission distance D=R*arcos[cos(Y1)*cos(Y2)*cos(X1-X2)+sin(Y1)*sin(Y2)].

[0111] Step S125, determining whether the signal transmission distance satisfies a preset distance condition, and if so, determining the processing device information corresponding to the signal transmission distance.

[0112] Specifically, the preset distance condition is the shortest distance, and by comparing the calculated signal transmission distances one by one, the processing equipment information with the shortest longitude and latitude from the battlefield image information is obtained.

[0113] In a possible implementation of the embodiment of the present application, step S13 may further include step Sa (not shown in the figure) and step Sb (not shown in the figure), wherein:

[0114] Step Sa, obtaining battlefield data information, the battlefield data information includes terrain image information and combat tool image information.

[0115] Specifically, the methods of obtaining battlefield data information include: directly collecting and obtaining electronic data, and importing non-electronic data by means of regional scanning and recognition. For example, through the mode of turning pages of a textbook, regional image features are recognized and matching keywords are extracted for verification and import.

[0116] Step Sb, building a battlefield knowledge graph based on battlefield data information.

[0117] Specifically, the concept of knowledge graph was first proposed by Google. Its purpose is to describe various entities and concepts in the real world and the relationships between them. In the actual construction process, it mainly includes six steps: knowledge modeling, knowledge storage, knowledge extraction, knowledge fusion, knowledge computing and knowledge application. Among them, knowledge modeling is based on the application attributes, knowledge characteristics and actual needs of the industry, and business abstraction and business modeling are carried out according to the knowledge graph model, mainly entity definition, relationship definition and attribute definition. Knowledge storage, the original data types of knowledge graphs are generally divided into three categories: structured data (Structed Data), such as relational databases; unstructured data, such as pictures, audio, video; semi-structured data, such as XML, JSON, encyclopedia. At present, the mainstream knowledge storage solutions include single and hybrid storage. There are generally two options for its storage method. One is to store it through a standardized storage format such as RDF (Resource Description Framework), and Jena is more commonly used. The other is to use a graph database for storage, such as Neo4j. Information extraction (infromation extraction) Information extraction is a technology that automatically extracts structured information such as entities, relationships, and entity attributes from semi-structured and unstructured data. Key technologies include: entity extraction, relationship extraction, and attribute extraction. Knowledge fusion, after obtaining entities, relationships, and entity attribute information from the original data through information extraction, it is necessary to logically attribute and filter redundant / error data through knowledge fusion. That is, it requires two processes: entity linking and knowledge merging. Knowledge computing, after information extraction and knowledge fusion, a series of basic factual expressions have been obtained from the original messy data. The next step is to obtain a structured, networked knowledge system and update mechanism through knowledge computing. Knowledge application, after the above five links, the knowledge graph of the special field has been constructed. In its unique application form, combined with domain data and business scenarios, it will actually help enterprises achieve actual business value in this field.

[0118] In a possible implementation of the embodiment of the present application, step S11 further includes step S111 (not shown in the figure), step S112 (not shown in the figure) and step S113 (not shown in the figure), wherein:

[0119] Step S111, determining the region level information based on the image location information, where the region level information is used to indicate the level information of the region where the image location information is located.

[0120] Specifically, the battlefield area is pre-classified into levels, for example: severe battlefield situation is level 5, relatively severe battlefield situation is level 4, moderate battlefield situation is level 3, relatively moderate battlefield situation is level 2, and stable battlefield situation is level 1. The location of the battlefield is determined according to the image location information, and then the regional level information corresponding to the battlefield location is determined.

[0121] Step S112, comparing the regional level information with the standard regional level table to determine the frequency of collecting battlefield image information.

[0122] Specifically, the acquisition frequencies of different battlefield image information corresponding to different regional level information are specifically reflected in the standard regional level table, and each different level of regional level corresponds to a different image acquisition frequency.

[0123] Step S113, controlling a preset acquisition device to acquire battlefield image information according to an acquisition frequency.

[0124] In a possible implementation manner of the embodiment of the present application, step S111 (not shown in the figure) further includes step S1111 (not shown in the figure), wherein:

[0125] Step S1111, determining whether the regional level information conforms to the preset regional level information, and if so, marking the image position information.

[0126] Specifically, the preset regional level information is level 4 and level 5.

[0127] In a possible implementation of the embodiment of the present application, step S13 further includes step S131 (not shown in the figure), step S132 (not shown in the figure), and step S133 (not shown in the figure), wherein:

[0128] Step S131, counting the number of battlefield targets in the battlefield target information to obtain battlefield scale information.

[0129] Specifically, the battlefield scale information is obtained by performing scale statistics based on the number of combat tools reflected in the battlefield target information.

[0130] Step S132, determine whether the scale in the battlefield scale information reaches the preset battlefield scale. If it reaches it, perform driving judgment on the battlefield target in the battlefield target information to obtain target travel information.

[0131] Specifically, the direction and speed of the battlefield target are determined by battlefield image information collected twice adjacently.

[0132] Step S133, predicting battlefield target information by combining battlefield scale information and target travel information to obtain characteristic intention information.

[0133] Specifically, based on the battlefield scale information and target movement information, the characteristic intention information of the battlefield target information is predicted. For example, if the scale of the battlefield target is 1,000 tanks and the direction of travel is toward a friendly base, the predicted characteristic intention information is that the enemy is launching an attack on the friendly base.

[0134] In a possible implementation of the embodiment of the present application, step S133 (not shown in the figure) further includes step S1331 (not shown in the figure) and step S1332 (not shown in the figure), wherein:

[0135] Step S1331, assess the hazard level of the characteristic intention information and generate a characteristic hazard level.

[0136] Specifically, the characteristic intention information is evaluated for hazard level. For example, the characteristic intention information containing the intention to invade a friendly base has a hazard level of 5, and the characteristic intention information containing the intention to invade a friendly garrison has a hazard level of 4.

[0137] Step S1332, determine whether the characteristic hazard level exceeds the preset hazard level. If it exceeds, generate an early warning instruction to control the early warning device to issue an early warning.

[0138] Specifically, the preset hazard level is level 4. When the characteristic hazard level exceeds level 4, the early warning device is controlled to issue an early warning alarm. The early warning device includes a buzzer and a warning light.

[0139] The above-mentioned embodiment introduces a battlefield target recognition method based on a knowledge graph from the perspective of method flow. The following embodiment introduces a battlefield target recognition device based on a knowledge graph from the perspective of a virtual module or a virtual unit. Please see the following embodiment for details.

[0140] The present application embodiment provides a battlefield target recognition device based on a knowledge graph, such as Figure 2 As shown, the device 20 may specifically include: an information acquisition module 21, a location determination module 22, a device determination module 23 and a feature recognition module 24, wherein:

[0141] An information acquisition module 21 is used to acquire battlefield image information;

[0142] A position determination module 22, used to detect the position of the battlefield image information and determine the image position information of the battlefield image information;

[0143] A device determination module 23, used to determine processing device information based on image position information;

[0144] The feature recognition module 24 is used to summarize the image feature information generated by the processing equipment information, and input the image feature information into the battlefield knowledge graph for feature recognition to obtain battlefield target information.

[0145] In a possible implementation manner of the embodiment of the present application, when the device determination module 23 determines the processing device information based on the image position information, it is specifically used to:

[0146] Scanning a preset area based on the image position information to obtain first device set information;

[0147] Perform signal detection on the processing device information in the first device set information respectively to determine the device signal state of the processing device information;

[0148] Determine whether the device signal state satisfies the preset signal state, and if not, filter out the processing device information corresponding to the device signal state to obtain the second device set information;

[0149] respectively calculating the distance values ​​between the processing device information in the second device set information and the image position information, and determining the signal transmission distance of the processing device information;

[0150] It is determined whether the signal transmission distance meets the preset distance condition. If so, the processing device information corresponding to the signal transmission distance is determined.

[0151] In another possible implementation of the embodiment of the present application, the device 20 further includes: a data acquisition module and a graph construction module, wherein:

[0152] A data acquisition module is used to acquire battlefield data information, which includes terrain image information and combat tool image information;

[0153] The graph building module is used to build a battlefield knowledge graph based on battlefield data information.

[0154] In another possible implementation of the embodiment of the present application, the device 20 further includes: a region determination module, a region comparison module, and a frequency control module, wherein:

[0155] A region determination module, used to determine region level information based on the image location information, where the region level information is used to indicate level information of the region where the image location information is located;

[0156] A region comparison module is used to compare the region level information with the standard region level table to determine the frequency of collecting battlefield image information;

[0157] The frequency control module is used to control the preset acquisition device to acquire battlefield image information according to the acquisition frequency.

[0158] In another possible implementation of the embodiment of the present application, the device 20 further includes: a level determination module, wherein:

[0159] The level judgment module is used to judge whether the regional level information conforms to the preset regional level information. If it conforms, the image position information is marked.

[0160] In another possible implementation of the embodiment of the present application, the device 20 further includes: a quantity statistics module, a scale judgment module and an intention prediction module, wherein:

[0161] A quantity statistics module is used to count the number of battlefield targets in the battlefield target information to obtain battlefield scale information;

[0162] A scale judgment module is used to judge whether the scale in the battlefield scale information reaches the preset battlefield scale. If it reaches, a driving judgment is performed on the battlefield target in the battlefield target information to obtain target travel information;

[0163] The intention prediction module is used to predict battlefield target information by combining battlefield scale information and target movement information to obtain characteristic intention information.

[0164] In another possible implementation of the embodiment of the present application, the device 20 further includes: a level generation module and an early warning module, wherein:

[0165] A level generation module is used to evaluate the hazard level of feature intention information and generate a feature hazard level;

[0166] The early warning module is used to determine whether the characteristic hazard level meets the preset hazard level. If so, an early warning instruction is generated to control the early warning device to issue an early warning.

[0167] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0168] The present application also introduces an electronic device from the perspective of a physical device, such as Figure 3 As shown, Figure 3 The electronic device 300 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0169] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0170] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0171] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0172] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0173] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0174] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0175] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A battlefield target recognition method based on knowledge graph, characterized in that: include Obtain battlefield image information; Performing position detection on the battlefield image information to determine image position information of the battlefield image information; determining processing device information based on the image position information; Summarize the image feature information generated by the processing device information, and input the image feature information into the battlefield knowledge graph for feature recognition to obtain battlefield target information; Wherein, determining the processing device information based on the image position information includes: Scanning a preset area based on the image position information to obtain first device set information; Performing signal detection on the processing device information in the first device set information respectively to determine the device signal state of the processing device information; Determine whether the device signal state satisfies a preset signal state, and if not, filter out the processing device information corresponding to the device signal state to obtain second device set information; respectively calculating the distance values ​​between the processing device information in the second device set information and the image position information to determine the signal transmission distance of the processing device information; It is determined whether the signal transmission distance satisfies a preset distance condition, and if so, the processing device information corresponding to the signal transmission distance is determined.

2. The method according to claim 1, characterized in that The step of aggregating the image feature information generated by the processing device information and inputting the image feature information into the battlefield knowledge graph for feature recognition also includes: Acquiring battlefield data information, wherein the battlefield data information includes terrain image information and combat tool image information; A battlefield knowledge graph is constructed based on the battlefield data information.

3. The method according to claim 1, characterized in that The step of detecting the position of the battlefield image information to determine the image position information of the battlefield image information further comprises: Determine regional level information based on the image location information, where the regional level information is used to indicate level information of the region where the image location information is located; Comparing the regional level information with a standard regional level table to determine a collection frequency for collecting the battlefield image information; A preset acquisition device is controlled according to the acquisition frequency to acquire the battlefield image information.

4. The method according to claim 3, characterized in that The step of determining the regional level information based on the image position information further includes: It is determined whether the regional level information conforms to the preset regional level information, and if so, the image position information is marked.

5. The method according to claim 1, characterized in that The image feature information generated by the processing device information is aggregated, and the image feature information is input into the knowledge graph for feature recognition to obtain battlefield target information, and then the following is further included: Counting the number of battlefield targets in the battlefield target information to obtain battlefield scale information; Determine whether the scale in the battlefield scale information reaches a preset battlefield scale, and if so, perform a driving judgment on the battlefield target in the battlefield target information to obtain target travel information; The battlefield target information is predicted in combination with the battlefield scale information and the target travel information to obtain characteristic intention information.

6. The method according to claim 5, characterized in that The battlefield target information is predicted by combining the battlefield scale information and the target travel information to obtain characteristic intention information, and then further includes: Assessing the hazard level of the characteristic intention information to generate a characteristic hazard level; It is determined whether the characteristic hazard level exceeds the preset hazard level. If so, an early warning instruction is generated to control the early warning device to issue an early warning.

7. A battlefield target recognition device based on knowledge graph, characterized in that: include: An information acquisition module, used to acquire battlefield image information; A position determination module, used to perform position detection on the battlefield image information and determine image position information of the battlefield image information; A device determination module, used to determine processing device information based on the image position information; A feature recognition module is used to summarize the image feature information generated by the processing device information, and input the image feature information into the battlefield knowledge graph for feature recognition to obtain battlefield target information; Wherein, when the device determination module determines the processing device information based on the image position information, it is specifically used to: Scanning a preset area based on the image position information to obtain first device set information; Performing signal detection on the processing device information in the first device set information respectively to determine the device signal state of the processing device information; Determine whether the device signal state satisfies a preset signal state, and if not, filter out the processing device information corresponding to the device signal state to obtain second device set information; respectively calculating the distance values ​​between the processing device information in the second device set information and the image position information to determine the signal transmission distance of the processing device information; It is determined whether the signal transmission distance satisfies a preset distance condition, and if so, the processing device information corresponding to the signal transmission distance is determined.

8. An electronic device, characterized in that: The electronic device includes: at least one processor; Memory; At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the battlefield target recognition method based on the knowledge graph described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the battlefield target recognition method based on the knowledge graph described in any one of claims 1 to 6.

Images