Military scenario generation method, system and equipment and readable storage device

Abstract

The invention discloses a military scenario generation method, system and device and a readable storage medium. The method comprises the following steps: carrying out entity modeling on military units and combat missions expected to be contained in military scenario; converting the attribute information of the military units and the combat missions into vectorized data, and storing the vectorized data in a preset vector database; in response to a configuration operation of a user, mapping a military unit into a Gantt chart Y-axis element, mapping a combat task into a Gantt chart X-axis time-axis element, and editing starting and ending time, duration and a dependency relationship between tasks of the combat task; and inputting a Gantt chart generated in response to the user configuration operation into a preset neural network model, and outputting a military scenario. Compared with the prior art, the method has the advantages that the specialty of generation scenarios can be improved; the learning cost of the user and the economic cost of the desired generation are reduced; and meanwhile, the method adapts to most disclosed large models, so that the adaptability and flexibility of the scheme are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of simulation scenarios, and in particular relates to a military scenario generation method, system, equipment and a readable storage device. Background Art

[0002] A military scenario, a core tool in military operations research, combat simulation, and command decision-making, is a highly structured, detailed hypothetical situation or scenario carefully designed and constructed to systematically study, analyze, evaluate, train, or optimize the feasibility, effectiveness, risks, and potential consequences of different courses of action (COAs) within the context of a pre-determined war or military operation. Rather than a simple storytelling, it is a comprehensive virtual framework that integrates the enemy and friendly situation, the operational environment (geographic, meteorological, electromagnetic, cyber, humanities, etc.), available resources (troops, equipment, logistics, intelligence), timelines, rules of action, and specific operational objectives.

[0003] Existing techniques for generating military operational scenarios cannot precisely control the results. This can lead to the creation of scenarios that do not meet actual requirements, particularly in complex military missions. Furthermore, existing techniques lack an effective connection between task management and intelligent generation, failing to fully leverage the strengths of both. Furthermore, existing techniques suffer from high learning costs, heavy user burdens, and slow scenario framework development.

[0004] Therefore, in response to the above technical problems, it is necessary to provide a military scenario generation method, system, equipment and readable storage device.

[0005] The information disclosed in this background technology section is only intended to enhance understanding of the overall background of the invention and should not be regarded as an admission or any form of suggestion that the information constitutes the prior art already known to a person skilled in the art. Summary of the Invention

[0006] The purpose of the present invention is to provide a military scenario generation method, system, device and readable storage device, which can reduce the user's learning cost and generate military scenarios more accurately in line with user needs.

[0007] In order to achieve the above object, a specific embodiment of the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides a military scenario generation method, comprising:

[0009] Conduct entity modeling of the military units and combat missions expected to be included in the military scenario to define the attributes of the military units and combat missions;

[0010] Converting the attribute information of the military unit and the combat mission into vectorized data, and storing the vectorized data in a preset vector database;

[0011] In response to the user's configuration operation, the military unit is mapped to the Y-axis element of the Gantt chart, the combat mission is mapped to the X-axis timeline element of the Gantt chart, and the start and end time, duration and inter-task dependency of the combat mission are edited;

[0012] The Gantt chart generated in response to user configuration operations is input into a preset neural network model to output military scenarios.

[0013] In one or more embodiments of the present invention, the attributes of the military unit and combat mission include:

[0014] Military unit name, military unit composition, and military unit capabilities;

[0015] The name of the combat mission, the type of combat mission, the restrictive factors of the combat mission, and the prerequisites for executing the combat mission.

[0016] In one or more embodiments of the present invention, inputting the Gantt chart generated in response to the user configuration operation into a preset neural network model to output a military scenario includes:

[0017] Extracting vectorized data corresponding to military units and combat tasks in the Gantt chart, and generating a scenario setting text based on a preset scenario setting template;

[0018] Based on the vectorized data corresponding to the military units and combat tasks in the Gantt chart, traverse a preset vector database to obtain associated knowledge of the military units and / or the combat tasks, and generate supplementary knowledge text;

[0019] Based on the assumption setting text and the supplementary knowledge text information, prompt words are generated and input into the preset neural network model, so that the neural network model generates and outputs military assumptions based on the prompt words.

[0020] In one or more embodiments of the present invention, the acquiring of the associated knowledge of the military unit and / or the combat mission includes:

[0021] Calculating cosine similarity between the vectorized data corresponding to the military units and / or the combat missions collected in the Gantt chart and each vectorized data stored in the vector database;

[0022] If the cosine similarity is less than or equal to a preset similarity threshold, the vectorized data stored in the vector database is the associated knowledge of the military unit and / or the combat mission in the Gantt chart;

[0023] If the cosine similarity is greater than a preset similarity threshold, the vectorized data stored in the vector database is not associated knowledge of the military unit and / or the combat mission in the Gantt chart.

[0024] In one or more embodiments of the present invention, generating prompt words for input into the preset neural network model based on the assumption setting text and the supplementary knowledge text information includes:

[0025] Extracting the scenario setting text and the supplementary knowledge text information based on a preset prompt word template;

[0026] The extracted information is used to replace the placeholders in the preset prompt word template to generate prompt words for input into the preset neural network model.

[0027] In one or more embodiments of the present invention, the method further comprises:

[0028] Constructing a neural network model and setting relevant parameters of the neural network model;

[0029] Acquire a training sample set, wherein the training sample set includes a preset template, information to be extracted, and expected information, wherein the preset template includes one or more placeholders, and the expected information included in the information to be extracted is expected to be written into the placeholders;

[0030] The neural network model is trained based on the training sample set, and the parameters of the neural network model are corrected until the similarity between the expected information output by the neural network model based on the input preset template and the information to be extracted and the input expected information is greater than a preset threshold.

[0031] In one or more embodiments of the present invention, the method further comprises:

[0032] Traversing the start and end time, duration and inter-task dependencies of the combat missions configured by the user;

[0033] If the start and end time and / or duration and / or inter-task dependency of the combat mission configured by the user is in logical conflict with the information stored in the vector database, an alarm signal is returned.

[0034] In a second aspect, the present invention provides a military scenario generation system, comprising:

[0035] A definition module is used to perform entity modeling on the military units and combat missions expected to be included in the military scenario, so as to define the attributes of the military units and combat missions;

[0036] a conversion module, configured to convert the attribute information of the military unit and the combat mission into vectorized data, and store the vectorized data in a preset vector database;

[0037] a construction module, configured to map the military units to Y-axis elements of the Gantt chart, map the combat tasks to X-axis timeline elements of the Gantt chart, and edit the start and end times, durations, and dependencies between tasks of the combat tasks in response to a user's configuration operation;

[0038] The output module is used to input the Gantt chart generated in response to the user configuration operation into the preset neural network model and output the military scenario.

[0039] In a third aspect, the present invention also provides a computer device comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the military scenario generation method by executing the computer instructions.

[0040] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer instructions for enabling a computer to execute the military scenario generation method.

[0041] Compared with the existing technology, the military scenario generation method provided by the present invention displays the time interval, length and prerequisite relationship of the task through a Gantt chart. The generated scenario will be repeatedly verified to meet user expectations and avoid the AI ​​hallucination phenomenon caused by direct dialogue; a large amount of preset vectorized data avoids the user's colloquial prompt words, thereby improving the professionalism of the generated scenario; military content is converted into Gantt chart items, and users can modify the task content through a simple graphical interface, avoiding the need to learn large model prompt words and improving the convenience of use; the present invention can simultaneously adapt to large models disclosed on the market, without the need for additional neural network model training, which can reduce the cost of military scenarios and improve the adaptability and flexibility of the plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 is a schematic diagram of a military scenario generation scenario in one embodiment of the present invention;

[0044] Figure 2is a flow chart of a military scenario generation method according to one embodiment of the present invention;

[0045] Figure 3 is a block diagram of a military scenario generation system according to one embodiment of the present invention;

[0046] Figure 4 It is a structural block diagram of an electronic device in one embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to enable those skilled in the art to better understand the technical solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0048] Unless expressly stated otherwise, throughout the specification and claims, the term "comprise" or variations such as "include" or "comprising", etc., will be understood to include the stated elements or components but not to exclude other elements or other components.

[0049] Existing technical solutions include methods for intelligently generating military scenario combat plans based on user-provided keywords. However, due to varying degrees of understanding of the content and structure of combat missions, developers must train neural network models tailored to each user to accommodate different types of user prompts. Even so, maintaining the accuracy of generated scenarios remains difficult. On the user's side, scenario prompts are input into the neural network model, which then outputs a corresponding military scenario plan. The model then verifies whether the scenario matches expectations, adjusts the input prompt text, and iteratively generates new scenarios.

[0050] Understandably, existing techniques for directly generating military combat scenarios cannot precisely control the generated results. The generated scenarios are based on the user's subjective descriptions, and particularly in complex military missions, the generated results may not meet actual requirements. When generating mission scenarios using models, users must master complex prompt word techniques and model invocation methods, which imposes a high learning curve for military personnel or experts in related fields. Furthermore, developing scenarios requires a considerable knowledge base and the need to search through various documentation, placing a significant burden on users. Since the external large model base frequently changes, achieving optimal performance requires continuously pre-training the large model with the latest base, which is costly.

[0051] The inventors of this invention identified the major shortcomings of existing technologies and, based on these shortcomings, proposed a novel technical implementation strategy: converting military operational entities and mission information into items in a Gantt chart, thereby vectorizing military knowledge. This approach converts Gantt chart items into text, filters keywords from the text, and then extracts additional knowledge from a vector database. This process then reconstructs the text to generate professional prompts. This vectorization of military knowledge also provides professional assurance for scenarios generated using large models. This invention allows users to generate prompts simply by operating the Gantt chart, enabling the creation of professional operational scenarios. This simplifies user operations and reduces the learning cost of prompts.

[0052] Please refer to Figure 1 , which is a schematic diagram of an application scenario of the military scenario generation method provided by the present invention under one embodiment, and the scenario specifically includes: a vector database 101, a server 102 and a user terminal 103.

[0053] It should be noted that communication connections are provided between the vector database 101, the server 102, and the user terminal 103. The communication network extended from the communication connection can include various connection types, including but not limited to: wired connection, wireless connection, or fiber optic cable connection. At the same time, the communication network can be a local area network, a metropolitan area network, a wide area network, or any combination of the three.

[0054] It should be noted that server 102 is configured with the neural network model and / or second neural network model required for the military scenario generation method. Based on user configuration, server 102 can call upon the vectorized data in the vector database to form a Gantt chart. It then applies the neural network model and / or second neural network model to ultimately generate a military scenario solution.

[0055] The user terminal 103 is installed with a computer software program that matches the military scenario generation method provided by this method; the user terminal 103 may include but is not limited to a desktop computer (PC), a desktop computer, a smart phone, a handheld computer, a tablet computer, a personal digital assistant (PDA), and other portable electronic devices or wearable electronic devices, and the embodiments of the present invention do not limit the above content.

[0056] It should also be noted that server 102 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. The embodiments of the present invention do not limit this.

[0057] It should also be noted that the military scenario generation method of the embodiments of the present invention can be applied to the military scenario generation system of the embodiments of the present invention. The military scenario generation system can be deployed on a terminal. The terminal may include, but is not limited to, a PC (Personal Computer), a PDA (Tablet Computer), a smartphone, a smart wearable device, and the like.

[0058] Please refer to Figure 2 FIG. 1 is a flow chart of military scenario generation in accordance with an embodiment of the present invention. The military scenario generation method specifically includes the following steps:

[0059] S201: Perform entity modeling on the military units and combat missions expected to be included in the military scenario to define the attributes of the military units and combat missions;

[0060] It should be noted that the defined attributes refer to the properties and relationships between the military unit, the combat mission, and the combat. These may include, but are not limited to: the military unit name, military unit composition, and military unit capabilities; the combat mission name, combat mission type, combat mission constraints, and combat mission execution prerequisites. The attribute information defined in the modeling in specific embodiments should depend on factors such as the actual usage scenario and the desired scenario. This invention does not limit the specific selection of defined attributes.

[0061] For example, in one specific embodiment, a military unit might be named "Mechanized Infantry Battalion," with its composition consisting of "3 Tank Companies, 3 Mechanized Infantry Companies, and 1 Fire Support Company," its equipment consisting of "42 Main Battle Tanks, 28 Infantry Fighting Vehicles," and its capabilities as "Deep Penetration, Position Defense." Similarly, a combat mission might be named "Amphibious Assault," with its prerequisites being "air superiority and completion of fire preparation," and its limiting factors being "tidal window and landing beach capacity."

[0062] Furthermore, users can edit "doctrines" based on actual use cases. Doctrines are deterministic rules used to ensure the proper functioning of combat plans, improve efficiency, and maintain good order. Using the amphibious assault example above, a doctrinal rule like "No fire without orders" could be edited.

[0063] Furthermore, in order to make the defined information recognizable and applicable, the attribute information should be converted into a recognizable encoding form, that is, to achieve the "entity modeling" of the present invention. Continuing with the above specific embodiment, the modeling results are as follows:

[0064] {

[0065] "unit":{

[0066] "id":"A1B2",

[0067] "type":"Mechanized Infantry Battalion",

[0068] "composition":["Tank Company × 3","Mechanized Infantry Company × 2","Fire Support Company"],

[0069] "equipment":["Main battle tank × 42","Infantry fighting vehicle × 28"],

[0070] "capability":["deep breakthrough","position defense"],

[0071] "detail":"{detailed description of the unit}"

[0072] },

[0073] "Task":[{

[0074] "id":"OP-2024",

[0075] "type":"Amphibious Assault",

[0076] "prerequisites":["Air supremacy","Fire preparation completed"],

[0077] "constraints":["tidal window period","landing beach capacity"],

[0078] "detail":"{detailed description of the task}"

[0079] }],

[0080] "Order": [{"Do not fire without orders"}]

[0081] }

[0082] It should be noted that when performing entity modeling of the military units and combat missions expected to be included in the military scenario, they can be added manually; in another embodiment, the corpus can also be quickly formatted to comply with military standards based on the large model to achieve the entity modeling.

[0083] S202: Converting the attribute information of the military unit and the combat mission into vectorized data, and storing the vectorized data in a preset vector database;

[0084] It's important to note that data sources like text, images, and sound typically can't serve as input for direct analysis and calculation in large models. Therefore, when generating combat scenarios based on large models, some deviations arise from the model's inability to understand text and other information. Therefore, in this embodiment of the present invention, the attribute information of military units and combat missions is converted into a set of numbers describing their characteristics, i.e., vectorized data.

[0085] Vectorization is essentially the process of converting human-understandable information (text, images, sounds, etc.) into machine-computable mathematical expressions. Specifically, it involves converting complex objects into multidimensional vectors of numbers (i.e., a set of ordered values, such as [0.25, -1.7, 0.03, ...]). This allows computers to understand the relationships between objects through mathematical operations and adapt to the input requirements of large models.

[0086] In an exemplary embodiment of the present invention, the attribute information of the military unit and the combat mission can be further divided into structured data and unstructured data. Structured data is highly organized and neatly formatted data, which is information that can be represented by data or a unified structure, such as numbers, symbols, etc. In military hypothetical scenarios, it mostly refers to performance parameters, military unit composition, etc. For structured data, it is preferably encoded according to its feature weight. For example, {"maximum range": 800km, "bomb load": 6t} is vectorized to [0.8, 0.6]. On the other hand, unstructured data is essentially all data other than structured data. In the military hypothetical scenario, it mostly represents custom regulations, combat case reports, etc. It is preferred to perform word segmentation on this type of data to form corresponding vectorized data.

[0087] It should also be noted that the vector database contains vectorized military data such as military units, equipment, and missions from historical battles. When using the present invention, users can generate Gantt charts based on the vector data in the vector database. Furthermore, in subsequent implementation steps of the present invention, the data in the vector database can assist in scenario generation based on similarity with the data for the scenario to be generated.

[0088] S203: In response to the user's configuration operation, the military unit is mapped to the Y-axis element of the Gantt chart, the combat mission is mapped to the X-axis timeline element of the Gantt chart, and the start and end time, duration, and inter-task dependency of the combat mission are edited;

[0089] A Gantt chart, also known as a horizontal bar chart or bar chart, uses a bar chart to display the internal relationships between projects, schedules, and other time-related system developments over time. Based on the aforementioned vector database, users can directly access existing resources and generate a Gantt chart to represent the desired task execution process.

[0090] The Gantt chart's core advantage is that it transforms an abstract operational timeline into a visual bar chart. It conveniently displays the relative timing of combat operations. It can also break down complex operations into a series of specific, executable tasks, clearly demonstrating the sequence and logical dependencies between players. Furthermore, the Gantt chart can quickly expose resource and time conflicts, allowing for timely adjustments and optimizations during the user's planning phase. This prevents logical conflicts from entering the model and generating scenarios with hidden risks, facilitating the subsequent development of scenario documentation and plans.

[0091] S204: Input the Gantt chart generated in response to the user configuration operation into a preset neural network model to output a military scenario.

[0092] In an exemplary embodiment of the present invention, a Gantt chart generated in response to a user configuration operation is input into a preset neural network model to output a military scenario, including: extracting vectorized data corresponding to military units and combat tasks in the Gantt chart, and generating a scenario setting text based on a preset scenario setting template; traversing a preset vector database based on the vectorized data corresponding to the military units and combat tasks in the Gantt chart, obtaining associated knowledge of the military units and / or the combat tasks, and generating a supplementary knowledge text; based on the scenario setting text and the supplementary knowledge text information, generating a prompt word for input into the preset neural network model, so that the neural network model generates and outputs a military scenario based on the prompt word.

[0093] It is understood that, using a user-configured Gantt chart instance as a blueprint for the scenario the user desires to generate, the Gantt chart theoretically contains all the elements necessary for scenario formation. However, to enable the large model to generate more accurate military scenarios, one embodiment of the present invention desirably generates prompt words using similar data in the vector database and data collected in the Gantt chart.

[0094] Specifically, obtaining the associated knowledge of the military unit and / or the combat mission includes: calculating the cosine similarity between the vectorized data corresponding to the military unit and / or the combat mission collected in the Gantt chart and the respective vectorized data stored in the vector database; if the cosine similarity is less than or equal to a preset similarity threshold, the vectorized data stored in the vector database is the associated knowledge of the military unit and / or the combat mission in the Gantt chart; if the cosine similarity is greater than the preset similarity threshold, the vectorized data stored in the vector database is not the associated knowledge of the military unit and / or the combat mission in the Gantt chart.

[0095] Among them, the method of calculating the degree of association of vectorized data based on cosine similarity can also be adjusted to calculate the Euclidean distance, Manhattan distance, etc. of the vectorized data based on different usage scenarios. The embodiment of the present invention does not limit this.

[0096] For example, in a specific embodiment, based on the Gantt chart configured by the user, the scenario setting text is formed in the following format:

[0097] [{

[0098] "task_id":"T01",

[0099] "duration":[t_start,t_end],

[0100] "dependencies":["T00"],

[0101] "unit_assignment":{"Armored Battalion A":0.8,"Artillery Company B":0.2},

[0102] "spatial_constraints":{"region X":true}

[0103] }]

[0104] In a specific embodiment, based on the vectorized data corresponding to the military units and / or the combat missions collected in the Gantt chart, the supplementary knowledge text formed by traversing the vector database is in the following format:

[0105] [{

[0106] "id":1001,

[0107] "distance":0.23,

[0108] "metadata":{

[0109] "text":"The J-20's electronic warfare capabilities include jamming enemy radar...",

[0110] "source": "Section 5.3 of the Air Force Technical White Paper",

[0111] "related_entities":["J-20","Electronic Countermeasures System","PL-15 Missile"]

[0112] }]

[0113] Furthermore, in an exemplary embodiment of the present invention, generating prompt words for input into the preset neural network model based on the scenario setting text and the supplementary knowledge text information includes: extracting the scenario setting text and the supplementary knowledge text information based on a preset prompt word template; and replacing the placeholders in the preset prompt word template with the extracted information to generate prompt words for input into the preset neural network model. The prompt word template includes one or more placeholders, and the information to be written into the placeholders includes, but is not limited to, engagement level, combat unit, combat mission, and knowledge dictionary.

[0114] Optionally, the prompt words can be compressed based on a preset model, and the compressed group poem can then be input into a preset neural network model to output a military scenario. Compressing the prompt words can speed up the neural network model's response. However, this can also inevitably result in the loss of some valid data, leading to a decrease in the accuracy of the generated scenario and deviation from expectations.

[0115] In particular, both the data in the vector database and the user-configured Gantt chart data may contain errors. Therefore, in one embodiment, when generating supplementary knowledge text, the user-configured start and end times, duration, and inter-task dependencies of the combat mission should be traversed simultaneously. If the user-configured start and end times and / or duration and / or inter-task dependencies of the combat mission conflict with the information stored in the vector database, an alarm signal is returned.

[0116] It should also be noted that, in an embodiment of the present invention, extracting information from a Gantt chart and generating a scenario setting text based on a template; and / or extracting the scenario setting text and the supplementary knowledge text information and generating prompt words based on a template can be implemented based on a pre-trained second neural network model. The training process includes: constructing a second neural network model and setting relevant parameters of the second neural network model; obtaining a training sample set, the training sample set including a preset template, information to be extracted, and expected information, the preset template including one or more placeholders, wherein the expected information contained in the information to be extracted is expected to be written into the placeholders; training the second neural network model based on the training sample set, and modifying the parameters of the second neural network model until the expected information output by the second neural network model based on the input preset template and the information to be extracted has a similarity with the input expected information that is greater than a preset threshold.

[0117] Please refer to Figure 3 As shown, based on the same inventive concept as the aforementioned military scenario generation method, an embodiment of the present invention provides a military scenario generation system 300, which includes: a definition module 301, a conversion module 302, a construction module 303 and an output module 304.

[0118] Specifically, the definition module 301 is used to perform entity modeling on the military units and combat tasks expected to be included in the military scenario, so as to define the attributes of the military units and combat tasks; the conversion module 302 is used to convert the attribute information of the military units and the combat tasks into vectorized data, and store the vectorized data in a preset vector database; the construction module 303 is used to respond to the user's configuration operation, map the military units into the Y-axis elements of the Gantt chart, map the combat tasks into the X-axis timeline elements of the Gantt chart, and edit the start and end times, duration and inter-task dependencies of the combat tasks; the output module 304 is used to input the Gantt chart generated in response to the user's configuration operation into a preset neural network model, and output the military scenario.

[0119] Please refer to Figure 4 As shown, an embodiment of the present invention further provides an electronic device 400, which includes at least one processor 401, a memory 402 (e.g., a non-volatile memory), a storage 403, and a communication interface 404. The at least one processor 401, the memory 402, the storage 403, and the communication interface 404 are connected together via an internal bus 405. The at least one processor 401 is configured to call at least one program instruction stored or encoded in the memory 402, so that the at least one processor 401 executes various operations and functions of the military scenario generation method described in various embodiments of this specification.

[0120] In the embodiments of the present specification, the electronic device 400 may include but is not limited to: a personal computer, a server computer, a workstation, a desktop computer, a laptop computer, a notebook computer, a mobile electronic device, a smart phone, a tablet computer, a cellular phone, a personal digital assistant (PDA), a handheld device, a messaging device, a wearable electronic device, a consumer electronic device, and the like.

[0121] An embodiment of the present invention further provides a computer-readable medium carrying computer-executable instructions. When the computer-executable instructions are executed by a processor, they can be used to implement the various operations and functions of the military scenario generation method described in the various embodiments of this specification.

[0122] The computer-readable medium in the present invention can be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device.

[0123] In the present invention, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0124] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0125] The present invention is described with reference to flowcharts and / or block diagrams of methods, apparatuses, systems, and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0126] The foregoing descriptions of specific exemplary embodiments of the present invention are for purposes of illustration and description. These descriptions are not intended to limit the invention to the precise forms disclosed, and it is apparent that many variations and modifications are possible in light of the foregoing teachings. The exemplary embodiments have been selected and described for the purpose of explaining the specific principles of the invention and their practical application, thereby enabling those skilled in the art to realize and utilize a variety of exemplary embodiments of the invention and various options and modifications. The scope of the invention is intended to be defined by the claims and their equivalents.

[0127] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

[0128] In addition, it should be understood that although this specification is described in terms of implementation methods, not every implementation method contains only one independent technical solution. This narrative method of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other implementation methods that can be understood by those skilled in the art.

Claims

1. A military scenario generation method, characterized in that: include: Conduct entity modeling of the military units and combat missions expected to be included in the military scenario to define the attributes of the military units and combat missions; Converting the attribute information of the military unit and the combat mission into vectorized data, and storing the vectorized data in a preset vector database; In response to the user's configuration operation, the military unit is mapped to the Y-axis element of the Gantt chart, the combat mission is mapped to the X-axis timeline element of the Gantt chart, and the start and end time, duration and inter-task dependency of the combat mission are edited; The Gantt chart generated in response to user configuration operations is input into a preset neural network model to output military scenarios.

2. The military scenario generation method according to claim 1, characterized in that: The attributes of the military units and combat missions include: Military unit name, military unit composition, and military unit capabilities; The name of the combat mission, the type of combat mission, the restrictive factors of the combat mission, and the prerequisites for executing the combat mission.

3. The military scenario generation method according to claim 1, characterized in that: The Gantt chart generated in response to the user configuration operation is input into a preset neural network model to output a military scenario, including: Extracting vectorized data corresponding to military units and combat tasks in the Gantt chart, and generating a scenario setting text based on a preset scenario setting template; Based on the vectorized data corresponding to the military units and combat tasks in the Gantt chart, traverse a preset vector database to obtain associated knowledge of the military units and / or the combat tasks, and generate supplementary knowledge text; Based on the assumption setting text and the supplementary knowledge text information, prompt words are generated and input into the preset neural network model, so that the neural network model generates and outputs military assumptions based on the prompt words.

4. The military scenario generation method according to claim 3, characterized in that: The acquiring of the associated knowledge of the military unit and / or the combat mission includes: Calculating cosine similarity between the vectorized data corresponding to the military units and / or the combat missions collected in the Gantt chart and each vectorized data stored in the vector database; If the cosine similarity is less than or equal to a preset similarity threshold, the vectorized data stored in the vector database is the associated knowledge of the military unit and / or the combat mission in the Gantt chart; If the cosine similarity is greater than a preset similarity threshold, the vectorized data stored in the vector database is not associated knowledge of the military unit and / or the combat mission in the Gantt chart.

5. The military scenario generation method according to claim 3, characterized in that: The generating of prompt words for input into the preset neural network model based on the assumption setting text and the supplementary knowledge text information includes: Extracting the scenario setting text and the supplementary knowledge text information based on a preset prompt word template; The extracted information is used to replace the placeholders in the preset prompt word template to generate prompt words for input into the preset neural network model.

6. The military scenario generation method according to claim 5, characterized in that: The method further comprises: Constructing a second neural network model and setting relevant parameters of the second neural network model; Acquire a training sample set, wherein the training sample set includes a preset template, information to be extracted, and expected information, wherein the preset template includes one or more placeholders, and the expected information included in the information to be extracted is expected to be written into the placeholders; The second neural network model is trained based on the training sample set, and the parameters of the second neural network model are corrected until the similarity between the expected information output by the second neural network model based on the input preset template and the information to be extracted and the input expected information is greater than a preset threshold.

7. The military scenario generation method according to claim 1, characterized in that: The method further comprises: Traversing the start and end time, duration and inter-task dependencies of the combat missions configured by the user; If the start and end time and / or duration and / or inter-task dependency of the combat mission configured by the user is in logical conflict with the information stored in the vector database, an alarm signal is returned.

8. A military scenario generation system, characterized in that: include: A definition module is used to perform entity modeling on the military units and combat missions expected to be included in the military scenario, so as to define the attributes of the military units and combat missions; a conversion module, configured to convert the attribute information of the military unit and the combat mission into vectorized data, and store the vectorized data in a preset vector database; a construction module, configured to map the military units to Y-axis elements of the Gantt chart, map the combat tasks to X-axis timeline elements of the Gantt chart, and edit the start and end times, durations, and dependencies between tasks of the combat tasks in response to a user's configuration operation; The output module is used to input the Gantt chart generated in response to the user configuration operation into the preset neural network model and output the military scenario.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the military scenario generation method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to cause a computer to execute the military scenario generation method according to any one of claims 1 to 7.

Images