Method and system for identifying battlefield casualty status based on multi-dimensional data

Abstract

The present invention discloses a battlefield casualty status identification method and system based on multi-dimensional data. The method comprises: obtaining physiological sensor data and multi-dimensional environmental sensor data of the casualty to be identified; correcting the physiological sensor data according to at least one of the environmental sensor data to obtain corrected physiological data; determining the status identification results corresponding to the corrected physiological data and the environmental sensor data respectively based on a status identification algorithm; and determining the casualty status of the casualty to be identified according to the status identification results corresponding to the corrected physiological data and the environmental sensor data respectively. It can be seen that the present invention can fully combine multi-dimensional data and comprehensive identification to achieve more accurate and efficient casualty status identification, thereby realizing more intelligent and automatic casualty identification and improving rescue effect and efficiency.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a battlefield casualty status recognition method and system based on multi-dimensional data. Background Art

[0002] In modern disaster and war rescue efforts, intelligent data processing technology plays a crucial strategic role in improving the quality of medical support and the efficiency of patient care. With the rapid development of artificial intelligence and IoT sensing technologies, leveraging algorithms to improve the accuracy of battlefield patient status recognition has become a significant technical challenge. However, most existing technologies rely solely on sensors attached to the patient's body to identify their status, failing to fully integrate multi-dimensional data for interactive calibration and further identification. Consequently, these technologies exhibit low accuracy and efficiency, lacking both intelligence and automation. This demonstrates the shortcomings of existing technologies, which urgently need to be addressed. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a battlefield casualty status identification method and system based on multi-dimensional data, which can fully combine multi-dimensional data and comprehensive identification to achieve more accurate and efficient casualty status identification, so as to achieve more intelligent and automatic casualty identification and improve rescue effect and efficiency.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a method for identifying the status of battlefield casualties based on multi-dimensional data, the method comprising:

[0005] Acquire physiological sensor data and multi-dimensional environmental sensor data of the injured person to be identified;

[0006] Correcting the physiological sensor data according to at least one of the environmental sensor data to obtain corrected physiological data;

[0007] Determining state recognition results corresponding to the corrected physiological data and the environmental sensor data, respectively, based on a state recognition algorithm;

[0008] The patient status of the injured person to be identified is determined according to the status identification results corresponding to the corrected physiological data and the environmental sensor data.

[0009] As an optional embodiment, in the first aspect of the present invention, the physiological sensing data includes at least one of blood pressure data, body temperature data, blood sugar data, speed data, acceleration data, respiratory data and pulse data.

[0010] As an optional embodiment, in the first aspect of the present invention, the environmental sensing data includes at least one of environmental images, environmental sounds, environmental light reflection data, environmental temperature, and environmental humidity.

[0011] As an optional embodiment, in the first aspect of the present invention, the correcting the physiological sensor data according to at least one of the environmental sensor data to obtain the corrected physiological data includes:

[0012] For each physiological sensing data, determining at least one related environmental sensing type corresponding to the sensing data type of the physiological sensing data according to a preset data type related rule;

[0013] Filtering relevant environmental sensing data corresponding to the relevant environmental sensing type from all the environmental sensing data;

[0014] Determining reference physiological prediction data based on all the relevant environmental sensor data and a preset prediction neural network;

[0015] An average value of the reference physiological prediction data and the physiological sensing data is calculated to obtain corrected physiological data corresponding to the physiological sensing data.

[0016] As an optional embodiment, in the first aspect of the present invention, determining the reference physiological prediction data based on all the relevant environmental sensor data and a preset prediction neural network includes:

[0017] Inputting each of the relevant environmental sensor data into a physiological prediction neural network corresponding to the sensor data type to obtain physiological prediction data corresponding to each of the relevant environmental sensor data; the physiological prediction neural network is trained using a training data set including a plurality of training relevant environmental sensor data and corresponding training physiological data annotations of the sensor data type;

[0018] Calculate the weighted sum average of the physiological prediction data corresponding to all the relevant environmental sensor data to obtain reference physiological prediction data; wherein the weighted calculation weight of the physiological prediction data corresponding to each of the relevant environmental sensor data includes a first weight and a second weight; the first weight is proportional to the proportion of data of the same data type as the relevant environmental sensor data in the training relevant environmental sensor data; the second weight is proportional to the proportion of the data volume of the relevant environmental sensor data to the total data volume of all the relevant environmental sensor data.

[0019] As an optional embodiment, in the first aspect of the present invention, determining the state recognition results corresponding to the corrected physiological data and the environmental sensor data respectively based on the state recognition algorithm includes:

[0020] For each piece of data to be processed, determining a data type corresponding to the data to be processed; the data to be processed is the corrected physiological data or the environmental sensing data;

[0021] The data to be processed is input into a trained injured person status recognition neural network corresponding to the data type to obtain a status recognition result corresponding to the data to be processed; the injured person status recognition neural network is trained by a training data set including a plurality of training sensor data corresponding to the data type and corresponding injured person status annotations; the status recognition result includes the injury type, injury location, injury duration and consciousness state.

[0022] As an optional embodiment, in the first aspect of the present invention, when the data to be processed is the corrected physiological data, the patient status recognition neural network is a first network; when the data to be processed is the environmental sensor data, the patient status recognition neural network is a second network; wherein:

[0023] The first network includes a data corresponding part recognition network and a part state recognition network; the data corresponding part recognition network is used to recognize the human body part corresponding to the corrected physiological data; the part state recognition network is used to predict the corrected physiological data based on a state recognition network trained based on a training data set related to the human body part to obtain a corresponding state recognition result;

[0024] The second network includes a wounded person part identification network and a wounded person state identification network; the wounded person part identification network is used to identify the data part related to the wounded person to be identified in the environmental sensor data; the wounded person state identification network is used to predict the data part to obtain a corresponding state identification result.

[0025] As an optional embodiment, in the first aspect of the present invention, determining the patient status of the injured person to be identified based on the status recognition results corresponding to the corrected physiological data and the environmental sensor data, respectively, includes:

[0026] Calculating the intersection of all state recognition results corresponding to the corrected physiological data to obtain a first reference state recognition result;

[0027] For each state recognition result corresponding to the environmental sensor data, calculating an average value of similarities between the state recognition result corresponding to the environmental sensor data and the state recognition results corresponding to each other environmental sensor data, to obtain a similarity parameter for the state recognition result corresponding to the environmental sensor data;

[0028] Filtering the state recognition results corresponding to all the environmental sensing data, wherein the state recognition results have a similarity parameter greater than a parameter threshold, to obtain a plurality of preferred state recognition results;

[0029] Calculating the intersection of all the preferred state recognition results to obtain a second reference state recognition result;

[0030] The intersection of the first reference state identification result and the second reference state identification result is calculated to obtain the injured person state of the injured person to be identified.

[0031] A second aspect of an embodiment of the present invention discloses a battlefield casualty status recognition system based on multi-dimensional data, the system comprising:

[0032] An acquisition module is used to acquire physiological sensor data and multi-dimensional environmental sensor data of the injured person to be identified;

[0033] a correction module, configured to correct the physiological sensor data according to at least one of the environmental sensor data to obtain corrected physiological data;

[0034] an identification module, configured to determine, based on a state identification algorithm, state identification results corresponding to the corrected physiological data and the environmental sensor data;

[0035] The determination module is used to determine the patient status of the injured person to be identified based on the status identification results corresponding to the corrected physiological data and the environmental sensor data.

[0036] As an optional embodiment, in the second aspect of the present invention, the physiological sensing data includes at least one of blood pressure data, body temperature data, blood sugar data, speed data, acceleration data, respiratory data and pulse data.

[0037] As an optional embodiment, in the second aspect of the present invention, the environmental sensing data includes at least one of environmental images, environmental sounds, environmental light reflection data, environmental temperature, and environmental humidity.

[0038] As an optional embodiment, in the second aspect of the present invention, the correction module corrects the physiological sensor data according to at least one of the environmental sensor data to obtain the corrected physiological data in a specific manner, including:

[0039] For each physiological sensing data, determining at least one related environmental sensing type corresponding to the sensing data type of the physiological sensing data according to a preset data type related rule;

[0040] Filtering relevant environmental sensing data corresponding to the relevant environmental sensing type from all the environmental sensing data;

[0041] Determining reference physiological prediction data based on all the relevant environmental sensor data and a preset prediction neural network;

[0042] An average value of the reference physiological prediction data and the physiological sensing data is calculated to obtain corrected physiological data corresponding to the physiological sensing data.

[0043] As an optional embodiment, in the second aspect of the present invention, the correction module determines a specific manner of reference physiological prediction data based on all the relevant environmental sensor data and a preset prediction neural network, including:

[0044] Inputting each of the relevant environmental sensor data into a physiological prediction neural network corresponding to the sensor data type to obtain physiological prediction data corresponding to each of the relevant environmental sensor data; the physiological prediction neural network is trained using a training data set including a plurality of training relevant environmental sensor data and corresponding training physiological data annotations of the sensor data type;

[0045] Calculate the weighted sum average of the physiological prediction data corresponding to all the relevant environmental sensor data to obtain reference physiological prediction data; wherein the weighted calculation weight of the physiological prediction data corresponding to each of the relevant environmental sensor data includes a first weight and a second weight; the first weight is proportional to the proportion of data of the same data type as the relevant environmental sensor data in the training relevant environmental sensor data; the second weight is proportional to the proportion of the data volume of the relevant environmental sensor data to the total data volume of all the relevant environmental sensor data.

[0046] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the recognition module determines the state recognition results corresponding to the corrected physiological data and the environmental sensor data, respectively, based on the state recognition algorithm, includes:

[0047] For each piece of data to be processed, determining a data type corresponding to the data to be processed; the data to be processed is the corrected physiological data or the environmental sensing data;

[0048] The data to be processed is input into a trained injured person status recognition neural network corresponding to the data type to obtain a status recognition result corresponding to the data to be processed; the injured person status recognition neural network is trained by a training data set including a plurality of training sensor data corresponding to the data type and corresponding injured person status annotations; the status recognition result includes the injury type, injury location, injury duration and consciousness state.

[0049] As an optional embodiment, in the second aspect of the present invention, when the data to be processed is the corrected physiological data, the patient status recognition neural network is a first network; when the data to be processed is the environmental sensor data, the patient status recognition neural network is a second network; wherein:

[0050] The first network includes a data corresponding part recognition network and a part state recognition network; the data corresponding part recognition network is used to recognize the human body part corresponding to the corrected physiological data; the part state recognition network is used to predict the corrected physiological data based on a state recognition network trained based on a training data set related to the human body part to obtain a corresponding state recognition result;

[0051] The second network includes a wounded person part identification network and a wounded person state identification network; the wounded person part identification network is used to identify the data part related to the wounded person to be identified in the environmental sensor data; the wounded person state identification network is used to predict the data part to obtain a corresponding state identification result.

[0052] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the determination module determines the patient status of the to-be-identified injured person based on the status recognition results corresponding to the corrected physiological data and the environmental sensor data includes:

[0053] Calculating the intersection of all state recognition results corresponding to the corrected physiological data to obtain a first reference state recognition result;

[0054] For each state recognition result corresponding to the environmental sensor data, calculating an average value of similarities between the state recognition result corresponding to the environmental sensor data and the state recognition results corresponding to each other environmental sensor data, to obtain a similarity parameter for the state recognition result corresponding to the environmental sensor data;

[0055] Filtering the state recognition results corresponding to all the environmental sensing data, wherein the state recognition results have a similarity parameter greater than a parameter threshold, to obtain a plurality of preferred state recognition results;

[0056] Calculating the intersection of all the preferred state recognition results to obtain a second reference state recognition result;

[0057] The intersection of the first reference state identification result and the second reference state identification result is calculated to obtain the injured person state of the injured person to be identified.

[0058] The third aspect of the present invention discloses another battlefield casualty status recognition system based on multi-dimensional data, the system comprising:

[0059] a memory storing executable program code;

[0060] a processor coupled to the memory;

[0061] The processor calls the executable program code stored in the memory to execute part or all of the steps in the battlefield casualty status identification method based on multi-dimensional data disclosed in the first aspect of the present invention.

[0062] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the battlefield casualty status identification method based on multi-dimensional data disclosed in the first aspect of the present invention.

[0063] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0064] The present invention can correct physiological sensor data according to at least one environmental sensor data to obtain accurate corrected physiological data, and then determine the state recognition results corresponding to the corrected physiological data and the environmental sensor data based on the state recognition algorithm, so as to comprehensively determine the casualty state of the injured person to be identified, thereby being able to fully combine multi-dimensional data and comprehensive recognition to achieve more accurate and efficient casualty state recognition, thereby achieving more intelligent and automatic casualty identification and improving rescue effect and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0066] Figure 1 This is a flow chart of a method for identifying battlefield casualty status based on multi-dimensional data disclosed in an embodiment of the present invention.

[0067] Figure 2 This is a structural diagram of a battlefield casualty status recognition system based on multi-dimensional data disclosed in an embodiment of the present invention.

[0068] Figure 3 This is a structural diagram of another battlefield casualty status recognition system based on multi-dimensional data disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0069] In order to enable those skilled in the art to better understand the 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. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0070] The terms "first," "second," and so on, in the description and claims of the present invention and the accompanying drawings are used to distinguish between different objects, not to describe a specific order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or device comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or device.

[0071] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0072] The present invention discloses a battlefield casualty status identification method and system based on multi-dimensional data. The method can correct physiological sensor data based on at least one piece of environmental sensor data to obtain accurate corrected physiological data. The method then determines the status identification results corresponding to the corrected physiological data and environmental sensor data based on a status identification algorithm to comprehensively determine the status of the casualty to be identified. This method can fully combine multi-dimensional data and comprehensive identification to achieve more accurate and efficient casualty status identification, thereby realizing more intelligent and automatic casualty identification and improving rescue effectiveness and efficiency. These are described in detail below.

[0073] Example 1

[0074] See also Figure 1 , Figure 1 This is a flow chart of a method for identifying battlefield casualty status based on multi-dimensional data disclosed in an embodiment of the present invention. Figure 1 The battlefield casualty status recognition method based on multi-dimensional data described above can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the battlefield casualty status identification method based on multi-dimensional data may include the following operations:

[0075] 101. Obtain physiological sensor data and multi-dimensional environmental sensor data of the injured person to be identified.

[0076] 102. Correct the physiological sensing data according to at least one piece of environmental sensing data to obtain corrected physiological data.

[0077] 103. Based on the state recognition algorithm, determine the state recognition results corresponding to the corrected physiological data and the environmental sensor data.

[0078] 104. Determine the patient status of the patient to be identified based on the status identification results corresponding to the corrected physiological data and the environmental sensor data.

[0079] It can be seen that the above-mentioned embodiments of the invention can correct the physiological sensor data according to at least one environmental sensor data to obtain accurate corrected physiological data, and then determine the state recognition results corresponding to the corrected physiological data and the environmental sensor data based on the state recognition algorithm, so as to comprehensively determine the casualty status of the injured person to be identified, thereby being able to fully combine multi-dimensional data and comprehensive recognition to achieve more accurate and efficient casualty status recognition, so as to achieve more intelligent and automatic casualty identification and improve rescue effect and efficiency.

[0080] As an optional embodiment, in the above steps, the physiological sensing data includes at least one of blood pressure data, body temperature data, blood sugar data, speed data, acceleration data, respiratory data and pulse data.

[0081] It can be seen that through the above optional embodiments, the types of physiological sensing data are limited to comprehensively characterize the physiological characteristics of the injured, so as to facilitate the subsequent accurate identification of the injured person's status, and assist in fully combining multi-dimensional data and comprehensive identification to achieve more accurate and efficient identification of the injured person's status, so as to achieve more intelligent and automatic identification of the injured person and improve rescue effects and efficiency.

[0082] As an optional embodiment, in the above steps, the environmental sensing data includes at least one of environmental images, environmental sounds, environmental light reflection data, environmental temperature, and environmental humidity.

[0083] It can be seen that through the above optional embodiments, the types of environmental sensing data are limited to comprehensively characterize the characteristics related to the rescue environment, so as to facilitate the subsequent accurate correction of physiological data and identification of the status of the wounded, and assist in fully combining multi-dimensional data and comprehensive identification to achieve more accurate and efficient identification of the status of the wounded, so as to achieve more intelligent and automatic identification of the wounded, and improve rescue effects and efficiency.

[0084] As an optional embodiment, in the above step, correcting the physiological sensor data according to at least one environmental sensor data to obtain corrected physiological data includes:

[0085] For each physiological sensor data, determining at least one related environmental sensor type corresponding to the sensor data type of the physiological sensor data according to a preset data type related rule;

[0086] Filtering relevant environmental sensing data corresponding to relevant environmental sensing types from all environmental sensing data;

[0087] Determine reference physiological prediction data based on all relevant environmental sensor data and a preset prediction neural network;

[0088] An average value of the reference physiological prediction data and the physiological sensing data is calculated to obtain corrected physiological data corresponding to the physiological sensing data.

[0089] It can be seen that through the above-mentioned optional embodiments, reference physiological prediction data can be determined based on environmental sensor data related to the data type of specific physiological sensor data, so as to realize the average value correction of the physiological sensor data and obtain more accurate corrected physiological data, so as to facilitate the subsequent accurate identification of the status of the injured person, and assist in realizing more accurate and efficient identification of the status of the injured person by fully combining multi-dimensional data and comprehensive identification, so as to realize more intelligent and automatic identification of the injured person and improve rescue effect and efficiency.

[0090] As an optional embodiment, in the above step, determining the reference physiological prediction data based on all relevant environmental sensor data and a preset prediction neural network includes:

[0091] Inputting each relevant environmental sensor data into a physiological related prediction neural network corresponding to the sensor data type to obtain physiological prediction data corresponding to each relevant environmental sensor data; optionally, the physiological related prediction neural network is trained using a training data set including a plurality of training relevant environmental sensor data and training physiological data annotations of the corresponding sensor data types;

[0092] Calculate the weighted sum average of the physiological prediction data corresponding to all relevant environmental sensor data to obtain reference physiological prediction data; optionally, the weighted calculation weight of the physiological prediction data corresponding to each relevant environmental sensor data includes a first weight and a second weight; the first weight is proportional to the proportion of data of the same data type as the relevant environmental sensor data in the training relevant environmental sensor data; the second weight is proportional to the proportion of the data volume of the relevant environmental sensor data to the total data volume of all relevant environmental sensor data.

[0093] It can be seen that through the above optional embodiments, the predictive neural network trained based on the training data set corresponding to the data type can predict the physiological data corresponding to the relevant environmental sensor data, and the weighted summation of multiple prediction results based on the weights related to the data proportion can be achieved to obtain more accurate reference physiological prediction data, so as to facilitate the subsequent accurate correction of physiological data and identification of the status of the injured, and assist in fully combining multi-dimensional data and comprehensive identification to achieve more accurate and efficient identification of the status of the injured, so as to achieve more intelligent and automatic identification of the injured, and improve rescue effect and efficiency.

[0094] As an optional embodiment, in the above step, determining the state recognition results corresponding to the corrected physiological data and the environmental sensor data based on the state recognition algorithm includes:

[0095] For each piece of data to be processed, determining the data type corresponding to the data to be processed; optionally, the data to be processed is calibrated physiological data or environmental sensor data;

[0096] The data to be processed is input into a trained neural network for identifying the status of the injured person corresponding to the data type to obtain a status identification result corresponding to the data to be processed; optionally, the neural network for identifying the status of the injured person is trained by a training data set including training sensor data corresponding to multiple data types and corresponding injured person status annotations; the status identification result includes the type of injury, the location of the injury, the duration of the injury and the state of consciousness.

[0097] It can be seen that through the above optional embodiments, the state recognition neural network corresponding to the data types of different sensor data can be used to determine the state recognition results corresponding to the corrected physiological data and environmental sensor data respectively, which is convenient for the subsequent accurate and comprehensive identification of the state of the injured, and assists in fully combining multi-dimensional data and comprehensive identification to achieve more accurate and efficient identification of the state of the injured, so as to achieve more intelligent and automatic identification of the injured and improve rescue effects and efficiency.

[0098] As an optional embodiment, in the above steps, when the data to be processed is corrected physiological data, the patient status recognition neural network is the first network; when the data to be processed is environmental sensor data, the patient status recognition neural network is the second network; wherein:

[0099] The first network includes a data corresponding part recognition network and a part state recognition network; optionally, the data corresponding part recognition network is used to recognize the human body part corresponding to the corrected physiological data; the part state recognition network is used to predict the corrected physiological data based on a state recognition network trained based on a training data set related to the human body part to obtain a corresponding state recognition result;

[0100] The second network includes a wounded person part recognition network and a wounded person state recognition network; optionally, the wounded person part recognition network is used to identify the data part related to the wounded person to be identified in the environmental sensor data; the wounded person state recognition network is used to predict the data part to obtain the corresponding state recognition result.

[0101] It can be seen that through the above optional embodiments, the network architecture and functions of the state neural network corresponding to different data types are clarified to achieve accurate prediction of the corresponding state recognition results, facilitate subsequent accurate and comprehensive identification of the state of the wounded, and assist in fully combining multi-dimensional data and comprehensive identification to achieve more accurate and efficient identification of the state of the wounded, so as to achieve more intelligent and automatic identification of the wounded, and improve rescue effects and efficiency.

[0102] As an optional embodiment, in the above steps, determining the patient status of the injured person to be identified based on the status recognition results corresponding to the corrected physiological data and the environmental sensor data respectively includes:

[0103] Calculating the intersection of the state recognition results corresponding to all the corrected physiological data to obtain a first reference state recognition result;

[0104] For each state recognition result corresponding to the environmental sensor data, calculating the average of the similarities between the state recognition result corresponding to the environmental sensor data and the state recognition results corresponding to each other environmental sensor data, to obtain a similarity parameter for the state recognition result corresponding to the environmental sensor data;

[0105] Filter out state recognition results whose similarity parameters are greater than a parameter threshold from state recognition results corresponding to all environmental sensor data, and obtain multiple preferred state recognition results;

[0106] Calculate the intersection of all the preferred state recognition results to obtain the second reference state recognition result;

[0107] The intersection of the first reference state recognition result and the second reference state recognition result is calculated to obtain the patient state of the patient to be identified.

[0108] It can be seen that through the above-mentioned optional embodiments, the first reference state identification result can be obtained according to the intersection of the state identification results corresponding to all the corrected physiological data. The prediction result based on physiological data is more accurate, so the intersection can be directly calculated as the reference state. For the prediction result of environmental data with insufficient accuracy, the intersection of the state identification results of the screened environmental sensor data is determined based on similarity screening and intersection calculation to obtain the second reference state identification result, so as to obtain a more accurate state of the injured person to be identified based on the intersection calculation, and realize more accurate and efficient state identification of the injured person by fully combining multi-dimensional data and comprehensive identification, so as to realize more intelligent and automatic identification of the injured person and improve rescue effect and efficiency.

[0109] Example 2

[0110] See also Figure 2 , Figure 2 This is a schematic diagram of the structure of a battlefield casualty status recognition system based on multi-dimensional data disclosed in an embodiment of the present invention. Figure 2 The battlefield casualty status recognition system based on multi-dimensional data described above can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the battlefield casualty status recognition system based on multi-dimensional data may include:

[0111] The acquisition module 201 is used to acquire physiological sensor data and multi-dimensional environmental sensor data of the injured person to be identified.

[0112] The correction module 202 is configured to correct the physiological sensing data according to at least one piece of environmental sensing data to obtain corrected physiological data.

[0113] The identification module 203 is configured to determine the state identification results corresponding to the corrected physiological data and the environmental sensor data based on a state identification algorithm.

[0114] The determination module 204 is configured to determine the patient status of the patient to be identified based on the status identification results corresponding to the corrected physiological data and the environmental sensor data.

[0115] It can be seen that the above-mentioned embodiments of the invention can correct the physiological sensor data according to at least one environmental sensor data to obtain accurate corrected physiological data, and then determine the state recognition results corresponding to the corrected physiological data and the environmental sensor data based on the state recognition algorithm, so as to comprehensively determine the casualty status of the injured person to be identified, thereby being able to fully combine multi-dimensional data and comprehensive recognition to achieve more accurate and efficient casualty status recognition, so as to achieve more intelligent and automatic casualty identification and improve rescue effect and efficiency.

[0116] As an optional embodiment, the physiological sensing data includes at least one of blood pressure data, body temperature data, blood sugar data, speed data, acceleration data, respiration data and pulse data.

[0117] It can be seen that through the above optional embodiments, the types of physiological sensing data are limited to comprehensively characterize the physiological characteristics of the injured, so as to facilitate the subsequent accurate identification of the injured person's status, and assist in fully combining multi-dimensional data and comprehensive identification to achieve more accurate and efficient identification of the injured person's status, so as to achieve more intelligent and automatic identification of the injured person and improve rescue effects and efficiency.

[0118] As an optional embodiment, the environmental sensing data includes at least one of environmental images, environmental sounds, environmental light reflection data, environmental temperature, and environmental humidity.

[0119] It can be seen that through the above optional embodiments, the types of environmental sensing data are limited to comprehensively characterize the characteristics related to the rescue environment, so as to facilitate the subsequent accurate correction of physiological data and identification of the status of the wounded, and assist in fully combining multi-dimensional data and comprehensive identification to achieve more accurate and efficient identification of the status of the wounded, so as to achieve more intelligent and automatic identification of the wounded, and improve rescue effects and efficiency.

[0120] As an optional embodiment, the correction module corrects the physiological sensor data according to the at least one environmental sensor data to obtain the corrected physiological data in a specific manner including:

[0121] For each physiological sensor data, determining at least one related environmental sensor type corresponding to the sensor data type of the physiological sensor data according to a preset data type related rule;

[0122] Filtering relevant environmental sensing data corresponding to relevant environmental sensing types from all environmental sensing data;

[0123] Determine reference physiological prediction data based on all relevant environmental sensor data and a preset prediction neural network;

[0124] An average value of the reference physiological prediction data and the physiological sensing data is calculated to obtain corrected physiological data corresponding to the physiological sensing data.

[0125] It can be seen that through the above-mentioned optional embodiments, reference physiological prediction data can be determined based on environmental sensor data related to the data type of specific physiological sensor data, so as to realize the average value correction of the physiological sensor data and obtain more accurate corrected physiological data, so as to facilitate the subsequent accurate identification of the status of the injured person, and assist in realizing more accurate and efficient identification of the status of the injured person by fully combining multi-dimensional data and comprehensive identification, so as to realize more intelligent and automatic identification of the injured person and improve rescue effect and efficiency.

[0126] As an optional embodiment, the correction module determines a specific method of referencing the physiological prediction data based on all relevant environmental sensor data and a preset prediction neural network, including:

[0127] Inputting each relevant environmental sensor data into a physiological related prediction neural network corresponding to the sensor data type to obtain physiological prediction data corresponding to each relevant environmental sensor data; optionally, the physiological related prediction neural network is trained using a training data set including a plurality of training relevant environmental sensor data and training physiological data annotations of the corresponding sensor data types;

[0128] Calculate the weighted sum average of the physiological prediction data corresponding to all relevant environmental sensor data to obtain reference physiological prediction data; optionally, the weighted calculation weight of the physiological prediction data corresponding to each relevant environmental sensor data includes a first weight and a second weight; the first weight is proportional to the proportion of data of the same data type as the relevant environmental sensor data in the training relevant environmental sensor data; the second weight is proportional to the proportion of the data volume of the relevant environmental sensor data to the total data volume of all relevant environmental sensor data.

[0129] It can be seen that through the above optional embodiments, the predictive neural network trained based on the training data set corresponding to the data type can predict the physiological data corresponding to the relevant environmental sensor data, and the weighted summation of multiple prediction results based on the weights related to the data proportion can be achieved to obtain more accurate reference physiological prediction data, so as to facilitate the subsequent accurate correction of physiological data and identification of the status of the injured, and assist in fully combining multi-dimensional data and comprehensive identification to achieve more accurate and efficient identification of the status of the injured, so as to achieve more intelligent and automatic identification of the injured, and improve rescue effect and efficiency.

[0130] As an optional embodiment, the recognition module determines, based on the state recognition algorithm, a specific method for correcting the state recognition results corresponding to the physiological data and the environmental sensor data, including:

[0131] For each piece of data to be processed, determining the data type corresponding to the data to be processed; optionally, the data to be processed is calibrated physiological data or environmental sensor data;

[0132] The data to be processed is input into a trained neural network for identifying the status of the injured person corresponding to the data type to obtain a status identification result corresponding to the data to be processed; optionally, the neural network for identifying the status of the injured person is trained by a training data set including training sensor data corresponding to multiple data types and corresponding injured person status annotations; the status identification result includes the type of injury, the location of the injury, the duration of the injury and the state of consciousness.

[0133] It can be seen that through the above optional embodiments, the state recognition neural network corresponding to the data types of different sensor data can be used to determine the state recognition results corresponding to the corrected physiological data and environmental sensor data respectively, which is convenient for the subsequent accurate and comprehensive identification of the state of the injured, and assists in fully combining multi-dimensional data and comprehensive identification to achieve more accurate and efficient identification of the state of the injured, so as to achieve more intelligent and automatic identification of the injured and improve rescue effects and efficiency.

[0134] As an optional embodiment, when the data to be processed is corrected physiological data, the patient status recognition neural network is the first network; when the data to be processed is environmental sensor data, the patient status recognition neural network is the second network; wherein:

[0135] The first network includes a data corresponding part recognition network and a part state recognition network; optionally, the data corresponding part recognition network is used to recognize the human body part corresponding to the corrected physiological data; the part state recognition network is used to predict the corrected physiological data based on a state recognition network trained based on a training data set related to the human body part to obtain a corresponding state recognition result;

[0136] The second network includes a wounded person part recognition network and a wounded person state recognition network; optionally, the wounded person part recognition network is used to identify the data part related to the wounded person to be identified in the environmental sensor data; the wounded person state recognition network is used to predict the data part to obtain the corresponding state recognition result.

[0137] It can be seen that through the above optional embodiments, the network architecture and functions of the state neural network corresponding to different data types are clarified to achieve accurate prediction of the corresponding state recognition results, facilitate subsequent accurate and comprehensive identification of the state of the wounded, and assist in fully combining multi-dimensional data and comprehensive identification to achieve more accurate and efficient identification of the state of the wounded, so as to achieve more intelligent and automatic identification of the wounded, and improve rescue effects and efficiency.

[0138] As an optional embodiment, the specific manner in which the determination module determines the patient status of the injured person to be identified based on the status identification results corresponding to the corrected physiological data and the environmental sensor data includes:

[0139] Calculating the intersection of the state recognition results corresponding to all the corrected physiological data to obtain a first reference state recognition result;

[0140] For each state recognition result corresponding to the environmental sensor data, calculating the average of the similarities between the state recognition result corresponding to the environmental sensor data and the state recognition results corresponding to each other environmental sensor data, to obtain a similarity parameter for the state recognition result corresponding to the environmental sensor data;

[0141] Filter out state recognition results whose similarity parameters are greater than a parameter threshold from state recognition results corresponding to all environmental sensor data, and obtain multiple preferred state recognition results;

[0142] Calculate the intersection of all the preferred state recognition results to obtain the second reference state recognition result;

[0143] The intersection of the first reference state recognition result and the second reference state recognition result is calculated to obtain the patient state of the patient to be identified.

[0144] It can be seen that through the above-mentioned optional embodiments, the first reference state identification result can be obtained according to the intersection of the state identification results corresponding to all the corrected physiological data. The prediction result based on physiological data is more accurate, so the intersection can be directly calculated as the reference state. For the prediction result of environmental data with insufficient accuracy, the intersection of the state identification results of the screened environmental sensor data is determined based on similarity screening and intersection calculation to obtain the second reference state identification result, so as to obtain a more accurate state of the injured person to be identified based on the intersection calculation, and realize more accurate and efficient state identification of the injured person by fully combining multi-dimensional data and comprehensive identification, so as to realize more intelligent and automatic identification of the injured person and improve rescue effect and efficiency.

[0145] Example 3

[0146] See also Figure 3 , Figure 3 This is another battlefield casualty status recognition system based on multi-dimensional data disclosed in an embodiment of the present invention. Figure 3 The battlefield casualty status recognition system based on multi-dimensional data is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the battlefield casualty status recognition system based on multi-dimensional data may include:

[0147] A memory 301 storing executable program code;

[0148] a processor 302 coupled to the memory 301;

[0149] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the battlefield casualty status identification method based on multi-dimensional data described in the first embodiment.

[0150] Example 4

[0151] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the battlefield casualty status identification method based on multi-dimensional data described in the first embodiment.

[0152] Example 5

[0153] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the battlefield casualty status identification method based on multi-dimensional data described in Example 1.

[0154] The foregoing description of specific embodiments of the present disclosure is intended to illustrate a method for performing a multi-tasking process. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0155] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0156] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0157] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the embodiments of this specification 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.

[0158] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, 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 flowchart and / or block diagram. 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.

[0159] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0160] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0161] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0162] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0163] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0164] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0165] This specification may be described in the general context of computer-executable instructions, such as program modules, executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media, including storage devices.

[0166] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0167] Finally, it should be noted that the battlefield casualty status identification method and system based on multi-dimensional data disclosed in the embodiment of the present invention only discloses a preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, ordinary technicians in this field should understand that it is still possible to modify the technical solutions recorded in the aforementioned embodiments, or to replace some of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A battlefield casualty status identification method based on multi-dimensional data, characterized in that: The method comprises: Acquire physiological sensor data and multi-dimensional environmental sensor data of the injured person to be identified; Correcting the physiological sensor data according to at least one of the environmental sensor data to obtain corrected physiological data; Determining state recognition results corresponding to the corrected physiological data and the environmental sensor data, respectively, based on a state recognition algorithm; Determining the patient status of the injured person to be identified according to the status identification results corresponding to the corrected physiological data and the environmental sensor data, including: Calculating the intersection of all state recognition results corresponding to the corrected physiological data to obtain a first reference state recognition result; For each state recognition result corresponding to the environmental sensor data, calculating an average value of similarities between the state recognition result corresponding to the environmental sensor data and the state recognition results corresponding to each other environmental sensor data, to obtain a similarity parameter for the state recognition result corresponding to the environmental sensor data; Filtering the state recognition results corresponding to all the environmental sensing data, wherein the state recognition results have a similarity parameter greater than a parameter threshold, to obtain a plurality of preferred state recognition results; Calculating the intersection of all the preferred state recognition results to obtain a second reference state recognition result; The intersection of the first reference state identification result and the second reference state identification result is calculated to obtain the injured person state of the injured person to be identified.

2. The battlefield casualty status identification method based on multi-dimensional data according to claim 1 is characterized in that: The physiological sensing data includes at least one of blood pressure data, body temperature data, blood sugar data, speed data, acceleration data, respiration data and pulse data.

3. The battlefield casualty status identification method based on multi-dimensional data according to claim 1, characterized in that: The environmental sensing data includes at least one of environmental images, environmental sounds, environmental light reflection data, environmental temperature, and environmental humidity.

4. The battlefield casualty status identification method based on multi-dimensional data according to claim 1, characterized in that: The correcting the physiological sensor data according to at least one of the environmental sensor data to obtain corrected physiological data includes: For each physiological sensing data, determining at least one related environmental sensing type corresponding to the sensing data type of the physiological sensing data according to a preset data type related rule; Filtering relevant environmental sensing data corresponding to the relevant environmental sensing type from all the environmental sensing data; Determining reference physiological prediction data based on all the relevant environmental sensor data and a preset prediction neural network; An average value of the reference physiological prediction data and the physiological sensing data is calculated to obtain corrected physiological data corresponding to the physiological sensing data.

5. The battlefield casualty status identification method based on multi-dimensional data according to claim 4 is characterized in that: Determining reference physiological prediction data based on all the relevant environmental sensor data and a preset prediction neural network includes: Inputting each of the relevant environmental sensor data into a physiological prediction neural network corresponding to the sensor data type to obtain physiological prediction data corresponding to each of the relevant environmental sensor data; the physiological prediction neural network is trained using a training data set including a plurality of training relevant environmental sensor data and corresponding training physiological data annotations of the sensor data type; Calculate the weighted sum average of the physiological prediction data corresponding to all the relevant environmental sensor data to obtain reference physiological prediction data; wherein the weighted calculation weight of the physiological prediction data corresponding to each of the relevant environmental sensor data includes a first weight and a second weight; the first weight is proportional to the proportion of data of the same data type as the relevant environmental sensor data in the training relevant environmental sensor data; the second weight is proportional to the proportion of the data volume of the relevant environmental sensor data to the total data volume of all the relevant environmental sensor data.

6. The battlefield casualty status identification method based on multi-dimensional data according to claim 1, characterized in that: The determining, based on a state recognition algorithm, state recognition results corresponding to the corrected physiological data and the environmental sensor data, respectively, includes: For each piece of data to be processed, determining a data type corresponding to the data to be processed; the data to be processed is the corrected physiological data or the environmental sensing data; The data to be processed is input into a trained injured person status recognition neural network corresponding to the data type to obtain a status recognition result corresponding to the data to be processed; the injured person status recognition neural network is trained by a training data set including a plurality of training sensor data corresponding to the data type and corresponding injured person status annotations; the status recognition result includes the injury type, injury location, injury duration and consciousness state.

7. The battlefield casualty status identification method based on multi-dimensional data according to claim 6, characterized in that: When the data to be processed is the corrected physiological data, the patient status recognition neural network is a first network; when the data to be processed is the environmental sensor data, the patient status recognition neural network is a second network; wherein: The first network includes a data corresponding part recognition network and a part state recognition network; the data corresponding part recognition network is used to recognize the human body part corresponding to the corrected physiological data; the part state recognition network is used to predict the corrected physiological data based on a state recognition network trained based on a training data set related to the human body part to obtain a corresponding state recognition result; The second network includes a wounded person part identification network and a wounded person state identification network; the wounded person part identification network is used to identify the data part related to the wounded person to be identified in the environmental sensor data; the wounded person state identification network is used to predict the data part to obtain a corresponding state identification result.

8. A battlefield casualty status recognition system based on multi-dimensional data, characterized in that: The system comprises: An acquisition module is used to acquire physiological sensor data and multi-dimensional environmental sensor data of the injured person to be identified; a correction module, configured to correct the physiological sensor data according to at least one of the environmental sensor data to obtain corrected physiological data; an identification module, configured to determine, based on a state identification algorithm, state identification results corresponding to the corrected physiological data and the environmental sensor data; A determination module, configured to determine the patient status of the to-be-identified patient based on the status recognition results corresponding to the corrected physiological data and the environmental sensor data, including: Calculating the intersection of all state recognition results corresponding to the corrected physiological data to obtain a first reference state recognition result; For each state recognition result corresponding to the environmental sensor data, calculating an average value of similarities between the state recognition result corresponding to the environmental sensor data and the state recognition results corresponding to each other environmental sensor data, to obtain a similarity parameter for the state recognition result corresponding to the environmental sensor data; Filtering the state recognition results corresponding to all the environmental sensing data, wherein the state recognition results have a similarity parameter greater than a parameter threshold, to obtain a plurality of preferred state recognition results; Calculating the intersection of all the preferred state recognition results to obtain a second reference state recognition result; The intersection of the first reference state identification result and the second reference state identification result is calculated to obtain the injured person state of the injured person to be identified.

9. A battlefield casualty status recognition system based on multi-dimensional data, characterized in that: The system comprises: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the battlefield casualty status identification method based on multi-dimensional data as described in any one of claims 1 to 7.

Images