A coding method and device for electronic injury report

Abstract

The present invention discloses a coding method and device for electronic injury records, the method comprising obtaining first data information, injury type information, injury image information, and a historical first data sample set; the first data information comprises injury coding information, injury part coding information, injury type coding information, and blood loss coding information; the injury type information comprises an injury type value and an injury type subvalue; the first data information, the injury type information, and the injury image information are analyzed and processed to obtain a preliminary injury assessment value; the first data information, the preliminary injury assessment value, and the historical first data sample set are fused and processed to obtain target coding information. It can be seen that the present invention is conducive to efficiently, quickly, and accurately obtaining the injury information of the injured person by encoding the injury condition of the injured person, so as to provide timely and rapid rescue to the injured person.

Description

Technical Field

[0001] The present invention relates to the field of emergency rescue technology, and in particular to a coding method and device for electronic injury status sheets. Background Art

[0002] In various emergency rescue operations, monitoring and managing the condition of injured individuals is crucial to ensuring the smooth progress of rescue operations. Traditionally, recording the condition of injured individuals has relied on paper forms or simple spreadsheets, which can be inaccurate and difficult to compile. Furthermore, managing injured individuals' condition information efficiently, quickly, and accurately in complex and rapidly changing rescue scenes has always been a challenge. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a coding method and device for electronic injury report, which is conducive to efficiently, quickly and accurately obtaining the injury information of the injured person by encoding the injury condition of the injured person, so as to provide timely and rapid rescue to the injured person.

[0004] In order to solve the above technical problems, the first aspect of the embodiments of the present invention discloses an encoding method, which includes:

[0005] S1, obtaining first data information, injury type information, injury image information, and a historical first data sample set; the first data information includes injury coding information, injury part coding information, injury type coding information, and blood loss coding information; the injury type information includes an injury type value and an injury type subvalue;

[0006] S2, analyzing and processing the first data information, the injury type information, and the injury image information to obtain a preliminary injury assessment value;

[0007] S3: fusing the first data information, the preliminary injury assessment value, and the first historical data sample set to obtain target coding information.

[0008] As an optional implementation manner, in the first aspect of the embodiment of the present invention, the analyzing and processing the first data information, the injury type information, and the injury image information to obtain a preliminary injury assessment value includes:

[0009] S21, determining whether the injury type value is equal to a preset first injury type value, and obtaining a first determination result;

[0010] When the first judgment result is yes, executing S22;

[0011] When the first judgment result is no, executing S26;

[0012] S22, preprocessing the injury image information to obtain preprocessed injury image information;

[0013] S23, analyzing and processing the pre-processed injury image information to obtain a first evaluation value;

[0014] S24, analyzing and processing the injury type information and the pre-processed injury image information to obtain a second evaluation value;

[0015] S25, calculating and processing the first data information, the first assessment value, and the second assessment value to obtain a preliminary injury assessment value;

[0016] S26: Calculate and process the first data information to obtain the preliminary injury assessment value.

[0017] As an optional implementation manner, in the first aspect of the embodiment of the present invention, preprocessing the injury image information to obtain preprocessed injury image information includes:

[0018] S221, performing image smoothing processing on the injury image information to obtain first image information;

[0019] S222, performing edge enhancement processing on the first image information to obtain second image information;

[0020] S223: Normalize the second image information to obtain pre-processed injury image information.

[0021] As an optional implementation manner, in the first aspect of the embodiment of the present invention, analyzing and processing the pre-processed injury image information to obtain a first evaluation value includes:

[0022] S231, performing binarization processing on the pre-processed injury image information to obtain third image information;

[0023] S232, performing dilation and erosion processing on the third image information to obtain fourth image information;

[0024] S233, using a first injury assessment model, performing calculation processing on the fourth image information to obtain a first assessment value;

[0025] Among them, the first injury assessment model is:

[0026]

[0027] Where AY1 is the first evaluation value, XS i is the value corresponding to the i-th pixel in the fourth image information, α is a preset first coefficient, and N is the number of pixels in the fourth image information.

[0028] As an optional implementation manner, in the first aspect of the embodiment of the present invention, analyzing and processing the injury type information and the pre-processed injury image information to obtain a second evaluation value includes:

[0029] S241, determining whether the injury type sub-value is equal to a preset first injury type sub-value, and obtaining a second determination result;

[0030] When the second judgment result is yes, execute S242;

[0031] When the second judgment result is no, determining 0 as the second evaluation value;

[0032] S242, using a second injury assessment model, performing calculation processing on the pre-processed injury image information to obtain an injury color depth ratio value;

[0033] Among them, the second injury assessment model is:

[0034]

[0035] Where CR is the color depth ratio of the injury, TR j TG j and TB j are the red channel value, green channel value, and blue channel value of the j-th pixel in the pre-processed injury image information, TR′, TG′, and TB′ are the preset red channel threshold, green channel threshold, and blue channel threshold, respectively. M is the number of pixels in the pre-processed injury image information, and ∧ represents a logical AND operator.

[0036] S243, performing texture feature analysis on the pre-processed injury image information to obtain a first eigenvalue, a second eigenvalue, and a third eigenvalue;

[0037] S244: Using a third injury assessment model, calculate and process the injury color depth ratio value, the first eigenvalue, the second eigenvalue, and the third eigenvalue to obtain a second assessment value.

[0038] Wherein, the third injury assessment model is:

[0039] AY2=δ1·CR+δ2·TZ1+δ3·TZ2+δ4·TZ3;

[0040] Wherein, AY2 is the second evaluation value, CR is the injury color depth ratio value, TZ1, TZ2 and TZ3 are the first eigenvalue, the second eigenvalue and the third eigenvalue respectively, δ1, δ2, δ3 and δ4 are the first weight parameter, the second weight parameter, the third weight parameter and the fourth weight parameter respectively.

[0041] As an optional implementation manner, in the first aspect of the embodiment of the present invention, the calculating and processing the first data information, the first assessment value, and the second assessment value to obtain a preliminary injury assessment value includes:

[0042] Using a fourth injury assessment model, calculating and processing the first data information, the first assessment value, and the second assessment value to obtain a preliminary injury assessment value;

[0043] Wherein, the fourth injury assessment model is:

[0044] CB=σ1·(SQ·SQW+SB·SBW+SL·SLW+SX·SXW)+σ2·AY1+σ3

[0045] AY2;

[0046] σ1+σ2+σ3=1;

[0047] 0≤σ1,σ2,σ3≤1;

[0048] In the formula, CB is the preliminary injury assessment value, SQ and SQW are respectively the injury coding value and the injury coding weight value in the injury coding information, SB and SBW are respectively the injury part coding value and the injury part coding weight value in the injury part coding information, SL and SLW are respectively the injury type coding value and the injury type coding weight value in the injury type coding information, SX and SXW are respectively the blood loss coding value and the blood loss coding weight value in the blood loss coding information, AY1 and AY2 are respectively the first assessment value and the second assessment value, σ1, σ2 and σ3 are respectively the preset first weight coefficient, second weight coefficient and third weight coefficient.

[0049] As an optional implementation manner, in the first aspect of the embodiment of the present invention, the fusing of the first data information, the preliminary injury assessment value, and the historical first data sample set to obtain target coding information includes:

[0050] S31, preprocessing the first historical data sample set to obtain a preprocessed first historical data sample set;

[0051] S32, processing the first data information and the pre-processed historical first data sample set to obtain a predicted injury assessment value;

[0052] S33: Fusing the preliminary injury assessment value and the predicted injury assessment value to obtain target coding information.

[0053] A second aspect of an embodiment of the present invention discloses an encoding device, comprising:

[0054] an acquisition module, configured to acquire first data information, injury type information, injury image information, and a historical first data sample set; the first data information includes injury coding information, injury part coding information, injury type coding information, and blood loss coding information; the injury type information includes an injury type value and an injury type subvalue;

[0055] a first calculation module, configured to analyze and process the first data information, the injury type information, and the injury image information to obtain a preliminary injury assessment value;

[0056] The second calculation module is used to fuse the first data information, the preliminary injury assessment value and the historical first data sample set to obtain target coding information.

[0057] A third aspect of an embodiment of the present invention discloses another encoding device, comprising:

[0058] processor;

[0059] a memory coupled to the processor and storing executable program code;

[0060] The processor calls the executable program code stored in the memory to execute part or all of the steps of the encoding method disclosed in the first aspect of the embodiment of the present invention.

[0061] A fourth aspect of an embodiment of the present invention discloses a computer-readable storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all steps of the encoding method disclosed in the first aspect of the embodiment of the present invention.

[0062] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0063] In an embodiment of the present invention, first data information, injury type information, injury image information and a historical first data sample set are obtained; the first data information includes injury coding information, injury part coding information, injury type coding information and blood loss coding information; the injury type information includes an injury type value and an injury type sub-value; the first data information, the injury type information and the injury image information are analyzed and processed to obtain a preliminary injury assessment value; the first data information, the preliminary injury assessment value and the historical first data sample set are fused and processed to obtain target coding information. It can be seen that this application is conducive to efficiently, quickly and accurately obtaining the injury information of the injured person by encoding the injury condition of the injured person, so as to provide timely and rapid rescue to the injured person. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] 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.

[0065] Figure 1 A schematic diagram of a flow chart of an encoding method disclosed in an embodiment of the present invention;

[0066] Figure 2 A schematic structural diagram of an encoding device disclosed in an embodiment of the present invention;

[0067] Figure 3 This is a schematic structural diagram of another encoding device disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0068] 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. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0069] 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.

[0070] 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.

[0071] This embodiment discloses a coding method and device that encodes the injury status of an injured person, thereby facilitating efficient, rapid, and accurate acquisition of the injured person's injury information, thereby enabling timely and rapid rescue of the injured person. Detailed descriptions are provided below.

[0072] Example 1

[0073] See also Figure 1 , Figure 1 This is a flow chart of an encoding method disclosed in an embodiment of the present invention. Figure 1 The described encoding method is applied to an encoding device, such as a local server or cloud server for optimized management of encoding, and is not limited in the embodiments of the present invention. Figure 1 As shown, the encoding method may include the following operations:

[0074] S1, obtaining first data information, injury type information, injury image information, and a historical first data sample set; the first data information includes injury coding information, injury part coding information, injury type coding information, and blood loss coding information; the injury type information includes an injury type value and an injury type subvalue;

[0075] It should be noted that the first data information is the electronic injury report information, which is the preliminary judgment information of the injured person by the on-site personnel. The severity of the situation is judged by the coding value and weight value. The more serious the situation, the greater the coding and weight. Specifically, it includes injury coding information, injury part coding information, injury type coding information and blood loss coding information. For example, its preliminary coding information is as follows:

[0076] Injury coding information: The injury is coded according to its severity. The obtained injury coding information is one of minor injury, moderate injury or severe injury.

[0077] Minor injury: the injury coding value is 1, and the injury coding weight value is 1;

[0078] Moderate injury: The injury coding value is 2, and the injury coding weight value is 2;

[0079] Severe injury: The injury coding value is 3, and the injury coding weight value is 3.

[0080] Injury coding information: The injury is coded according to its severity. The obtained injury coding information is one of the limbs, trunk or head.

[0081] Limbs: The injury coding value is 1, and the injury coding weight value is 1;

[0082] Trunk: The injury coding value is 2, and the injury coding weight value is 2;

[0083] Head: The injury coding value is 3, and the injury coding weight value is 3.

[0084] Injury type coding information: The injury is coded according to its severity. The obtained injury type coding information is one of fracture, internal organ injury, burn, head injury or soft tissue injury.

[0085] Fracture: The injury type coding value is 1, and the injury type coding weight value is 1;

[0086] Visceral injury: The injury code value is 2, and the injury code weight value is 2;

[0087] Burn: The injury code value is 3, and the injury code weight value is 2;

[0088] Head injury: The injury type coding value is 4, and the injury type coding weight value is 3;

[0089] Soft tissue injury: The injury type coding value is 5, and the injury type coding weight value is 1.

[0090] Blood loss coding information: According to the blood loss amount coding, the obtained blood loss coding information is one of small blood loss, moderate blood loss or large blood loss.

[0091] Minor blood loss: The coding value of blood loss is 1, and the coding weight of blood loss is 1;

[0092] Moderate blood loss: The blood loss coding value is 2, and the blood loss coding weight value is 2;

[0093] Massive blood loss: The coding value of blood loss is 3, and the coding weight value of blood loss is 3.

[0094] It should be noted that the injury image information is an image of the injured part of the injured person, which can clearly view the specific injury information;

[0095] It should be noted that the injury type information includes an injury type value and an injury type sub-value. When the injury type value is the first injury type value, it indicates that the injured person's injury can be viewed through an image, such as a burn or a knife wound. When it is not the first injury type value, it indicates that the injured person's injury cannot be viewed through an image, such as an internal injury. When the injury type value is the first injury type value and the injury type sub-value is the first injury type sub-value, it indicates that the injured person's injury can be viewed through an image and is caused by a wound, such as a knife wound. When the injury type value is the first injury type value and the injury type sub-value is not the first injury type sub-value, it indicates that the injured person's injury can be viewed through an image, but there is no wound, such as a burn. For example, the first injury type value is 1 and the first injury type sub-value is 1.

[0096] S2, analyzing and processing the first data information, the injury type information, and the injury image information to obtain a preliminary injury assessment value;

[0097] S3: fusing the first data information, the preliminary injury assessment value, and the first historical data sample set to obtain target coding information.

[0098] It can be seen that implementing the encoding method described in the embodiment of the present invention, by encoding the injury conditions of the injured person, is conducive to efficiently, quickly and accurately obtaining the injury information of the injured person, so as to provide timely and rapid rescue to the injured person.

[0099] In an optional embodiment, the analyzing and processing the first data information, the injury type information, and the injury image information to obtain a preliminary injury assessment value includes:

[0100] S21, determining whether the injury type value is equal to a preset first injury type value, and obtaining a first determination result;

[0101] When the first judgment result is yes, executing S22;

[0102] When the first judgment result is no, executing S26;

[0103] S22, preprocessing the injury image information to obtain preprocessed injury image information;

[0104] S23, analyzing and processing the pre-processed injury image information to obtain a first evaluation value;

[0105] S24, analyzing and processing the injury type information and the pre-processed injury image information to obtain a second evaluation value;

[0106] S25, calculating and processing the first data information, the first assessment value, and the second assessment value to obtain a preliminary injury assessment value;

[0107] S26: Calculate and process the first data information to obtain the preliminary injury assessment value.

[0108] It can be seen that implementing the encoding method described in the embodiment of the present invention, by encoding the injury conditions of the injured person, is conducive to efficiently, quickly and accurately obtaining the injury information of the injured person, so as to provide timely and rapid rescue to the injured person.

[0109] In another optional embodiment, the preprocessing the injury image information to obtain preprocessed injury image information includes:

[0110] S221, performing image smoothing processing on the injury image information to obtain first image information;

[0111] It should be noted that the above-mentioned image smoothing process can be performed by using a Gaussian filter or other image smoothing processing tools, and the specific embodiment of the present invention does not limit this.

[0112] It should be noted that injury image information contains a large amount of detailed texture, which affects the detection of the injury area. Through image smoothing, unnecessary details can be reduced, making the main injury features (such as congestion, tearing, ulcers, etc.) more prominent, thereby improving the accuracy of injury analysis. At the same time, it can accurately outline the boundaries of wounds, bruises or damaged areas, thereby improving the accuracy of subsequent processing.

[0113] S222, performing edge enhancement processing on the first image information to obtain second image information;

[0114] It should be noted that the above-mentioned edge enhancement processing can be performed by Canny edge detection or by other edge enhancement processing tools, and the specific embodiment of the present invention does not limit this.

[0115] It should be noted that edge enhancement processing can enhance the boundaries of wounds, bruises, tears, burns, etc., making them more prominent and easier to handle later.

[0116] S223: Normalize the second image information to obtain pre-processed injury image information.

[0117] It should be noted that the above normalization process can be performed by a Z-score normalization algorithm or a Min-Max normalization algorithm, or by other normalization processing tools, which is not limited in the embodiment of the present invention.

[0118] It can be seen that implementing the encoding method described in the embodiment of the present invention, by encoding the injury conditions of the injured person, is conducive to efficiently, quickly and accurately obtaining the injury information of the injured person, so as to provide timely and rapid rescue to the injured person.

[0119] In yet another optional embodiment, analyzing and processing the pre-processed injury image information to obtain a first evaluation value includes:

[0120] S231, performing binarization processing on the pre-processed injury image information to obtain third image information;

[0121] It should be noted that the above binarization process can be performed by Otsu's threshold method or fixed threshold method, or by other binarization processing tools, which is not limited in the embodiment of the present invention.

[0122] It should be noted that through binarization processing, the injury area can be significantly distinguished from the background, color and light interference can be avoided, and the analysis effect can be improved. It is especially suitable for injury images with unclear color changes and low contrast (such as subcutaneous congestion and minor burns). In addition, after binarization processing, the amount of data is greatly reduced and the computational complexity is significantly reduced.

[0123] S232, performing dilation and erosion processing on the third image information to obtain fourth image information;

[0124] It should be noted that the above-mentioned dilation and erosion processing can be performed by a closing operation, a basic morphological algorithm, a fast erosion / dilation algorithm, etc., or can be performed by a method specified by a user, or can be performed by other dilation and erosion tools. Specifically, the embodiment of the present invention does not limit this.

[0125] It's important to note that dilation and erosion can further improve recognition accuracy, reduce misjudgments, and enhance the integrity of injury regions. Some injury regions may have broken edges due to lighting, reflections, and other factors. Dilation can make the regions more coherent and avoid incomplete injury segmentation. Erosion after dilation can remove isolated patches and smooth the boundaries of the injury region.

[0126] S233, using a first injury assessment model, performing calculation processing on the fourth image information to obtain a first assessment value;

[0127] Among them, the first injury assessment model is:

[0128]

[0129] Where AY1 is the first evaluation value, XS i is the value corresponding to the i-th pixel in the fourth image information, α is a preset first coefficient, and N is the number of pixels in the fourth image information.

[0130] It should be noted that the first coefficient is the ratio of the wound size in the image to the actual wound size. For example, if the ratio of the actual wound size to the wound size in the image is 20, the first coefficient is 20. This is not limited in the embodiment of the present invention.

[0131] It should be noted that the fourth image information is a binary image, XS i The value is 0 or 1, when XS i When it is 1, it means that the pixel is a damaged area.

[0132] It should be noted that traditional wound assessment often relies on the subjective judgment of on-site personnel, while this embodiment provides an objective assessment method that can reduce the interference of human factors, improve the reliability of wound assessment, and further enhance the accuracy and efficiency of the assessment of the wounded person's injury information.

[0133] It can be seen that implementing the encoding method described in the embodiment of the present invention, by encoding the injury conditions of the injured person, is conducive to efficiently, quickly and accurately obtaining the injury information of the injured person, so as to provide timely and rapid rescue to the injured person.

[0134] In an optional embodiment, the analyzing and processing the injury type information and the pre-processed injury image information to obtain a second evaluation value includes:

[0135] S241, determining whether the injury type sub-value is equal to a preset first injury type sub-value, and obtaining a second determination result;

[0136] When the second judgment result is yes, execute S242;

[0137] When the second judgment result is no, determining 0 as the second evaluation value;

[0138] S242, using a second injury assessment model, performing calculation processing on the pre-processed injury image information to obtain an injury color depth ratio value;

[0139] Among them, the second injury assessment model is:

[0140]

[0141]

[0142] Where CR is the color depth ratio of the injury, TR j TG j and TB j are the red channel value, green channel value, and blue channel value of the j-th pixel in the pre-processed injury image information, TR′, TG′, and TB′ are the preset red channel threshold, green channel threshold, and blue channel threshold, respectively. M is the number of pixels in the pre-processed injury image information, and ∧ represents a logical AND operator.

[0143] Optionally, TR′, TG′, and TB′ are 150, 80, and 80, respectively.

[0144] It should be noted that the second injury assessment model can reflect the difference in color, thereby reflecting the different depths and ranges of the wound, thereby performing a more accurate assessment of the wound depth.

[0145] S243, performing texture feature analysis on the pre-processed injury image information to obtain a first eigenvalue, a second eigenvalue, and a third eigenvalue;

[0146] S244: Using a third injury assessment model, calculate and process the injury color depth ratio value, the first eigenvalue, the second eigenvalue, and the third eigenvalue to obtain a second assessment value.

[0147] Wherein, the third injury assessment model is:

[0148] AY2=δ1·CR+δ2·TZ1+δ3·TZ2+δ4·TZ3;

[0149] Wherein, AY2 is the second evaluation value, CR is the injury color depth ratio value, TZ1, TZ2 and TZ3 are the first eigenvalue, the second eigenvalue and the third eigenvalue respectively, δ1, δ2, δ3 and δ4 are the first weight parameter, the second weight parameter, the third weight parameter and the fourth weight parameter respectively.

[0150] It should be noted that the first weight parameter, the second weight parameter, the third weight parameter and the fourth weight parameter can be set by the user or obtained based on historical data. The embodiment of the present invention does not make specific limitations, wherein δ1+δ2+δ3+δ4=1, 0≤δ1,δ2,δ3,δ4≤1.

[0151] It should be noted that CR can obtain assessment information about wound bleeding, infection, and necrosis. At the same time, the first eigenvalue, second eigenvalue, and third eigenvalue can be used to further analyze the details of the wound surface and determine whether the wound has characteristics such as tearing and roughness, thereby enabling a more comprehensive prediction of injury information.

[0152] It can be seen that implementing the encoding method described in the embodiment of the present invention, by encoding the injury conditions of the injured person, is conducive to efficiently, quickly and accurately obtaining the injury information of the injured person, so as to provide timely and rapid rescue to the injured person.

[0153] In an optional embodiment, performing texture feature analysis on the pre-processed injury image information to obtain the first eigenvalue, the second eigenvalue, and the third eigenvalue includes:

[0154] S2431, performing grayscale processing on the pre-processed injury image information to obtain grayscale injury image information;

[0155] It should be noted that the grayscale processing can be performed using a YUV model method or an NTSC standard method, and the embodiments of the present invention do not limit this.

[0156] It should be noted that areas such as wounds, bruises, and burns usually have significant differences in brightness. Grayscaling can enhance this information, making the injured areas more obvious while avoiding recognition errors due to color cast and white balance issues.

[0157] S2432, performing calculation processing on the grayscale injury image information to obtain injury matrix information;

[0158] It should be noted that the above calculation process can be performed using the GLCM function in MATLAB or the Texture Analyzer in ImageJ, and the obtained injury matrix information is a gray-level co-occurrence matrix, which is not specifically limited in the embodiment of the present invention.

[0159] S2433, using a first injury matrix calculation model, performing a first calculation process on the injury matrix information to obtain a first eigenvalue;

[0160] Among them, the first injury matrix calculation model is:

[0161]

[0162] Wherein, TZ1 is the first eigenvalue, k1 and k2 are the k1th row and k2th column in the injury matrix information, HD(k1,k2) is the value of the k1th row and k2th column in the injury matrix information, L1 and L2 are the number of rows and columns of the injury matrix information respectively;

[0163] It should be noted that the above-mentioned first eigenvalue can measure the intensity difference between pixels in the image. A large first eigenvalue means that there is an obvious difference between light and dark in the image, which represents a more complex or deep wound surface in wound analysis.

[0164] S2434, using a second injury matrix calculation model, performing a second calculation process on the injury matrix information to obtain a second eigenvalue;

[0165] Among them, the second injury matrix calculation model is:

[0166]

[0167] Wherein, TZ2 is the second eigenvalue;

[0168] It should be noted that the second eigenvalue is used to measure complex textures and uneven color distribution. A larger second eigenvalue indicates a more severe wound.

[0169] S2435, using a third injury matrix calculation model, performing a third calculation process on the injury matrix information to obtain a third eigenvalue;

[0170] The third injury matrix calculation model is:

[0171]

[0172] Wherein, TZ3 is the third eigenvalue, and |·| represents the absolute value.

[0173] It should be noted that the third eigenvalue is used to measure the similarity of pixel values ​​in an image. A large third eigenvalue indicates that the pixel value changes are small, the image area is relatively uniform, and the wound is shallow.

[0174] It can be seen that implementing the encoding method described in the embodiment of the present invention, by encoding the injury conditions of the injured person, is conducive to efficiently, quickly and accurately obtaining the injury information of the injured person, so as to provide timely and rapid rescue to the injured person.

[0175] In an optional embodiment, the calculating and processing the first data information, the first assessment value, and the second assessment value to obtain a preliminary injury assessment value includes:

[0176] Using a fourth injury assessment model, calculating and processing the first data information, the first assessment value, and the second assessment value to obtain a preliminary injury assessment value;

[0177] Wherein, the fourth injury assessment model is:

[0178] CB=σ1·(SQ·SQW+SB·SBW+SL·SLW+SX·SXW)+σ2·AY1+σ3

[0179] AY2;

[0180] σ1+σ2+σ3=1;

[0181] 0≤σ1,σ2,σ3≤1;

[0182] In the formula, CB is the preliminary injury assessment value, SQ and SQW are respectively the injury coding value and the injury coding weight value in the injury coding information, SB and SBW are respectively the injury part coding value and the injury part coding weight value in the injury part coding information, SL and SLW are respectively the injury type coding value and the injury type coding weight value in the injury type coding information, SX and SXW are respectively the blood loss coding value and the blood loss coding weight value in the blood loss coding information, AY1 and AY2 are respectively the first assessment value and the second assessment value, σ1, σ2 and σ3 are respectively the preset first weight coefficient, second weight coefficient and third weight coefficient.

[0183] Optionally, the first weight coefficient, the second weight coefficient and the third weight coefficient are 0.4, 0.3 and 0.3 respectively.

[0184] It can be seen that implementing the encoding method described in the embodiment of the present invention, by encoding the injury conditions of the injured person, is conducive to efficiently, quickly and accurately obtaining the injury information of the injured person, so as to provide timely and rapid rescue to the injured person.

[0185] In an optional embodiment, calculating and processing the first data information to obtain the preliminary injury assessment value includes:

[0186] Using a fifth injury assessment model, calculating and processing the first data information to obtain the preliminary injury assessment value;

[0187] Wherein, the fifth injury assessment model is:

[0188] CB=SQ·SQW+SB·SBW+SL·SLW+SX·SXW;

[0189] In the formula, CB is the preliminary injury assessment value, SQ and SQW are the injury coding value and the injury coding weight value in the injury coding information, respectively; SB and SBW are the injury coding value and the injury coding weight value in the injury coding information, respectively; SL and SLW are the injury type coding value and the injury type coding weight value in the injury type coding information, respectively; SX and SXW are the blood loss coding value and the blood loss coding weight value in the blood loss coding information, respectively.

[0190] It should be noted that, through this embodiment, human judgment can be combined with image analysis, which not only improves the accuracy and consistency of injury assessment, but also speeds up the assessment.

[0191] It can be seen that implementing the encoding method described in the embodiment of the present invention, by encoding the injury conditions of the injured person, is conducive to efficiently, quickly and accurately obtaining the injury information of the injured person, so as to provide timely and rapid rescue to the injured person.

[0192] In an optional embodiment, the fusing of the first data information, the preliminary injury assessment value, and the historical first data sample set to obtain target coding information includes:

[0193] S31, preprocessing the first historical data sample set to obtain a preprocessed first historical data sample set;

[0194] The above-mentioned preprocessing includes data cleaning and normalization. The data cleaning can be performed using tools such as Apache NiFi, Talend, Informatica, or other tools or algorithms. The normalization can be performed using the Min-Max normalization algorithm or Z-Score normalization. Specifically, the embodiment of the present invention does not limit this.

[0195] S32, processing the first data information and the pre-processed historical first data sample set to obtain a predicted injury assessment value;

[0196] S33: Fusing the preliminary injury assessment value and the predicted injury assessment value to obtain target coding information.

[0197] It can be seen that implementing the encoding method described in the embodiment of the present invention, by encoding the injury conditions of the injured person, is conducive to efficiently, quickly and accurately obtaining the injury information of the injured person, so as to provide timely and rapid rescue to the injured person.

[0198] In an optional embodiment, the processing of the first data information and the pre-processed historical first data sample set to obtain a predicted injury assessment value includes:

[0199] S321, using a linear regression model, performing training processing on the pre-processed historical first data sample set to obtain training result information;

[0200] S322, using the injury prediction and evaluation model, performing calculations on the preprocessed first historical data sample set and the training result information to obtain a model evaluation value;

[0201] Wherein, the injury prediction and assessment model is:

[0202]

[0203] Where MXPG is the model evaluation value, is the training result information, is the zth training result value in the training result information, Y is the real result information, is the mean of all true result values ​​in the true result information, Y z is the zth true result value in the true result information, and V1 is the number of samples in the first preprocessing history data sample set;

[0204] It should be noted that the above-mentioned injury prediction and assessment model can quantify the accuracy of the model and help identify and correct potential prediction errors.

[0205] S323, determining whether the model evaluation value is greater than a preset model evaluation threshold, and obtaining a third determination result;

[0206] When the third judgment result is yes, execute S325;

[0207] When the third judgment result is no, executing S324;

[0208] It should be noted that the preset model evaluation threshold value ranges from [0.92, 0.95], which is not specifically limited in the embodiment of the present invention.

[0209] S324, using a gradient descent model, updating the model parameter information in the linear regression model to obtain an updated linear regression model, and determining the updated linear regression model as the linear regression model, and executing S322;

[0210] S325: Utilize the linear regression model to perform calculations on the first data information to obtain a predicted injury assessment value.

[0211] It can be seen that implementing the encoding method described in the embodiment of the present invention, by encoding the injury conditions of the injured person, is conducive to efficiently, quickly and accurately obtaining the injury information of the injured person, so as to provide timely and rapid rescue to the injured person.

[0212] In an optional embodiment, the preliminary injury assessment value and the predicted injury assessment value are fused to obtain target coding information, including:

[0213] S331, using a sixth injury assessment model, calculating and processing the preliminary injury assessment value and the predicted injury assessment value to obtain a target assessment value;

[0214] Among them, the sixth injury assessment model is:

[0215] MB=σ4·CB+σ5·YC;

[0216] σ4+σ5=1;

[0217] 0≤σ4,σ5≤1;

[0218] Wherein, MB is the target assessment value, CB is the preliminary injury assessment value, YC is the predicted injury assessment value, σ4 and σ5 are the fourth and fifth preset weight coefficients, respectively;

[0219] Optionally, the fourth weight coefficient and the fifth weight coefficient are 0.6 and 0.4 respectively.

[0220] It's important to note that this step combines the initial injury assessment with historical analysis data to improve the accuracy and consistency of the assessment. Comparing historical data can identify trends and anomalies in wound changes, enhancing the reliability of the assessment and helping to adjust and optimize current assessment criteria, thereby providing a more accurate assessment.

[0221] S332, determining whether the target evaluation value is less than a preset first evaluation threshold, and obtaining a fourth determination result;

[0222] When the fourth judgment result is yes, determining that the first coding value is target coding information;

[0223] When the fourth judgment result is no, determining whether the target evaluation value is less than a preset second evaluation threshold value to obtain a fifth judgment result;

[0224] When the fifth judgment result is yes, determining the second coding value to be the target coding information;

[0225] When the fifth judgment result is no, the third coding value is determined to be the target coding information.

[0226] Optionally, the first evaluation threshold is 8 and the second evaluation threshold is 13.

[0227] It should be noted that the target coding information is one of 01 (first coding value), 02 (second coding value) or 03 (third coding value). When the target evaluation value is between [0,8), the target coding information is set to 01, indicating that it is a minor injury and the urgency of rescue is low; when the target evaluation value is between [8,13), the target coding information is set to 02, indicating that it is a moderate injury and the urgency of rescue is medium; when the target evaluation value is between [13,+∞), the target coding information is set to 03, indicating that it is a severe injury, the urgency of rescue is high, and emergency rescue is required.

[0228] It can be seen that implementing the encoding method described in the embodiment of the present invention, by encoding the injury conditions of the injured person, is conducive to efficiently, quickly and accurately obtaining the injury information of the injured person, so as to provide timely and rapid rescue to the injured person.

[0229] It should be noted that, in the embodiment of the present invention, preprocessing the first historical data sample set is optional, and the preprocessing first historical data sample set may not be used. When the preprocessing first historical data sample set is not used, step S3 will be changed to the following steps:

[0230] Determining whether the preliminary injury assessment value is less than a preset first assessment threshold to obtain a sixth determination result;

[0231] When the sixth judgment result is yes, determining the first coding value to be the target coding information;

[0232] When the sixth judgment result is no, determining whether the preliminary injury assessment value is less than a preset second assessment threshold value to obtain a seventh judgment result;

[0233] When the seventh judgment result is yes, determining the second coding value to be the target coding information;

[0234] When the seventh judgment result is no, the third coding value is determined to be the target coding information.

[0235] Example 2

[0236] See also Figure 2 , Figure 2 This is a schematic diagram of the structure of an encoding device disclosed in an embodiment of the present invention. Figure 2 The encoding device described is applied to an encoding optimization system, such as a local server or cloud server for encoding, etc., which is not limited in the embodiment of the present invention. Figure 2 As shown, the encoding device includes:

[0237] Acquisition module 201 is used to acquire first data information, injury type information, injury image information, and a historical first data sample set; the first data information includes injury coding information, injury part coding information, injury type coding information, and blood loss coding information; the injury type information includes an injury type value and an injury type sub-value;

[0238] A first calculation module 202 is configured to analyze and process the first data information, the injury type information, and the injury image information to obtain a preliminary injury assessment value;

[0239] The second calculation module 203 is used to perform a fusion process on the first data information, the preliminary injury assessment value and the historical first data sample set to obtain target coding information.

[0240] It can be seen that implementing the encoding device described in the embodiment of the present invention, by encoding the injury conditions of the injured person, is conducive to efficiently, quickly and accurately obtaining the injury information of the injured person, so as to provide timely and rapid rescue to the injured person.

[0241] Example 3

[0242] See also Figure 3 , Figure 3 This is a schematic diagram of the structure of another encoding device disclosed in an embodiment of the present invention. Figure 3 The encoding device described is applied to an encoding optimization system, such as a local server or cloud server for encoding, etc., which is not limited in the embodiment of the present invention. Figure 3 As shown, the encoding device includes:

[0243] Processor 301;

[0244] A memory 302 coupled to the processor 301 and storing executable program code;

[0245] The processor 301 calls the executable program code stored in the memory 302 to execute part or all of the steps in the encoding method described in the first embodiment.

[0246] It can be seen that implementing the encoding device described in the embodiment of the present invention, by encoding the injury conditions of the injured person, is conducive to efficiently, quickly and accurately obtaining the injury information of the injured person, so as to provide timely and rapid rescue to the injured person.

[0247] Example 4

[0248] An embodiment of the present invention discloses a computer-readable 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 encoding method described in Example 1.

[0249] Example 5

[0250] 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 cause a computer to execute some or all of the steps in the encoding method described in the first embodiment.

[0251] The system embodiments described above are merely illustrative. Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules. They may be located in one place or distributed across multiple network modules. Some or all of these modules may be selected based on actual needs to achieve the objectives of this embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0252] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus the necessary general hardware platform, or of course, by means of hardware. Based on this understanding, the above technical solution, in essence, or the portion that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0253] Finally, it should be noted that the encoding method and device disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A coding method, characterized in that: The method comprises: S1. Obtain first data information, injury type information, injury image information, and a historical first data sample set; the first data information includes injury coding information, injury part coding information, injury type coding information, and blood loss coding information; the injury type information includes an injury type value and an injury type subvalue; the injury type value is used to indicate whether the injury can be viewed through an image; the injury type subvalue is used to further indicate whether the injury contains a wound when the injury type value is the first injury type value; the first injury type value is used to identify the type of externally visible injury that can be visually viewed through an image; S2, analyzing and processing the first data information, the injury type information, and the injury image information to obtain a preliminary injury assessment value; S3, fusing the first data information, the preliminary injury assessment value, and the first historical data sample set to obtain target coding information; Among them, S2 includes: S21, determining whether the injury type value is equal to the first injury type value, and obtaining a first determination result; When the first judgment result is yes, executing S22; When the first judgment result is no, executing S26; S22, preprocessing the injury image information to obtain preprocessed injury image information; S23, analyzing and processing the pre-processed injury image information to obtain a first evaluation value; S24, analyzing and processing the injury type information and the pre-processed injury image information to obtain a second evaluation value; S25, calculating and processing the first data information, the first assessment value, and the second assessment value to obtain a preliminary injury assessment value; S26, performing calculation processing on the first data information to obtain the preliminary injury assessment value; Among them, S3 includes: S31, preprocessing the first historical data sample set to obtain a preprocessed first historical data sample set; S32, processing the first data information and the pre-processed historical first data sample set to obtain a predicted injury assessment value; S33, fusing the preliminary injury assessment value and the predicted injury assessment value to obtain target coding information, including: S331, using a sixth injury assessment model, calculating and processing the preliminary injury assessment value and the predicted injury assessment value to obtain a target assessment value; Among them, the sixth injury assessment model is: Where, is the target evaluation value, is the preliminary injury assessment value, is the predicted injury assessment value, and are respectively the preset fourth weight coefficient and the fifth weight coefficient; S332, determining whether the target evaluation value is less than a preset first evaluation threshold, and obtaining a fourth determination result; When the fourth judgment result is yes, determining that the first coding value is target coding information; When the fourth judgment result is no, determining whether the target evaluation value is less than a preset second evaluation threshold value to obtain a fifth judgment result; When the fifth judgment result is yes, determining the second coding value to be the target coding information; When the fifth judgment result is no, the third coding value is determined to be the target coding information.

2. The encoding method according to claim 1, wherein The preprocessing of the injury image information to obtain preprocessed injury image information includes: S221, performing image smoothing processing on the injury image information to obtain first image information; S222, performing edge enhancement processing on the first image information to obtain second image information; S223: Normalize the second image information to obtain pre-processed injury image information.

3. The encoding method according to claim 1, wherein: The analyzing and processing the pre-processed injury image information to obtain a first evaluation value includes: S231, performing binarization processing on the pre-processed injury image information to obtain third image information; S232, performing dilation and erosion processing on the third image information to obtain fourth image information; S233, using a first injury assessment model, performing calculation processing on the fourth image information to obtain a first assessment value; Wherein, the first injury assessment model is: Where, is the first evaluation value, is the value corresponding to the i-th pixel in the fourth image information, is a preset first coefficient, and N is the number of pixels in the fourth image information.

4. The encoding method according to claim 1, wherein The analyzing and processing the injury type information and the pre-processed injury image information to obtain a second evaluation value includes: S241, determining whether the injury type sub-value is equal to a preset first injury type sub-value, and obtaining a second determination result; When the second judgment result is yes, execute S242; When the second judgment result is no, determining 0 as the second evaluation value; S242, using a second injury assessment model, performing calculation processing on the pre-processed injury image information to obtain an injury color depth ratio value; Among them, the second injury assessment model is: Where, is the color depth ratio value of the injury condition, 、 and are respectively the red channel value, green channel value and blue channel value of the j-th pixel in the pre-processed injury image information, 、 and are respectively the preset red channel threshold, green channel threshold and blue channel threshold, M is the number of pixels in the pre-processed injury image information, Represents the logical AND operator; S243, performing texture feature analysis on the pre-processed injury image information to obtain a first eigenvalue, a second eigenvalue, and a third eigenvalue; S244: Using a third injury assessment model, calculate and process the injury color depth ratio value, the first eigenvalue, the second eigenvalue, and the third eigenvalue to obtain a second assessment value. Wherein, the third injury assessment model is: Where, is the second evaluation value, is the color depth ratio value of the injury condition, 、 and are the first eigenvalue, the second eigenvalue and the third eigenvalue respectively, 、 、 and They are the first weight parameter, the second weight parameter, the third weight parameter and the fourth weight parameter respectively.

5. The encoding method according to claim 1, wherein: The calculating and processing the first data information, the first assessment value, and the second assessment value to obtain a preliminary injury assessment value includes: Using a fourth injury assessment model, calculating and processing the first data information, the first assessment value, and the second assessment value to obtain a preliminary injury assessment value; Wherein, the fourth injury assessment model is: Where, is the preliminary injury assessment value, and are the injury coding value and injury coding weight value in the injury coding information respectively, and are the injury part coding value and the injury part coding weight value in the injury part coding information respectively, and are the injury type coding value and the injury type coding weight value in the injury type coding information respectively, and are respectively the blood loss coding value and the blood loss coding weight value in the blood loss coding information, and are the first evaluation value and the second evaluation value respectively, 、 and They are respectively the preset first weight coefficient, second weight coefficient and third weight coefficient.

6. A coding device, characterized in that The device comprises: processor; a memory coupled to the processor and storing executable program code; The processor calls the executable program code stored in the memory to execute the encoding method according to any one of claims 1 to 5.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the encoding method according to any one of claims 1 to 5.

Images