Post-death interval time deduction method and system, and electronic equipment
By constructing a feature scoring system and electronic devices, screening and scoring based on the body feature information of the corpse, the accuracy and efficiency of inference of post-mortem interval time in the existing technology are solved, and more efficient and accurate post-mortem interval time is achieved. judge.
Patent Information
- Application Number
- CN202410929923.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-11
- Publication Date
- 2024-11-08
AI Technical Summary
In the prior art, the accuracy of calculus interval time based on experience is not high and inefficient, especially in complex environments, and corruption is difficult to accurately judge.
By constructing a feature scoring system, screening and scoring based on the body characteristic information of the corpse, establishing the correspondence between the post-mortem interval time and the evaluation indicators, and using electronic devices to achieve fast and accurate post-mortem interval time inference.
It improves the accuracy and efficiency of post-mortem interval time inference, reduces the influence of human subjectivity, and enhances the judgment ability in complex environments.
Smart Images

Figure CN118919051A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of medical technology, and in particular to a postmortem interval time estimation method and system, and electronic equipment. Background Art
[0002] Inferring the postmortem interval (PMI) of a corpse has always been one of the key issues and major difficulties in forensic practice.
[0003] The method of inferring the postmortem interval is mainly based on the staff's experience to measure body temperature, judge rigor mortis, livor mortis, degree of corneal opacity, degree of gastrointestinal digestion, bladder urine volume, etc., and to infer the postmortem interval of corpses in the early postmortem period, especially corpses within 48 or 24 hours after death.
[0004] However, in some complex environments, the decomposition state of the corpse may be significantly different from the experience of the staff, resulting in the inaccuracy and low efficiency of this method of relying on experience to infer the time interval after the corpse. Summary of the invention
[0005] The present invention provides a method and system for estimating a postmortem interval, and an electronic device, so as to solve the defect that the scheme of estimating a postmortem interval of a corpse relying on experience is not accurate enough. A feature scoring system can be pre-constructed, and the postmortem interval of a corpse can be directly determined based on the feature scoring system during the working process, with higher accuracy and efficiency.
[0006] The present invention provides a method for estimating a postmortem interval time, comprising:
[0007] Determine the physical characteristics of the body to be tested;
[0008] Searching for physical characteristic information of the corpse to be tested in a pre-constructed characteristic scoring system, and outputting a search result, wherein the search result represents the post-mortem interval of the corpse to be tested;
[0009] Among them, the characteristic scoring system is the correspondence between the postmortem interval of the corpse to be tested and the evaluation index, and the evaluation index is the physical characteristic information of the corpse to be tested obtained after at least two screenings.
[0010] According to the postmortem interval inference method provided by the present invention, the process of constructing the feature scoring system includes:
[0011] Constructing a database based on postmortem intervals and physical characteristics of at least a number of corpses;
[0012] Scoring the physical characteristic information in the database, the score representing the postmortem interval of the corpse corresponding to the physical characteristic information;
[0013] Constructing a first evaluation index group based on the physical feature information in the database, wherein the first evaluation index group includes a plurality of evaluation indexes, each evaluation index corresponding to at least one physical feature information;
[0014] Constructing a second evaluation index group based on the physical feature information corresponding to the evaluation indexes that meet the preset screening conditions in the first evaluation index group;
[0015] A corresponding relationship between the physical characteristic information in the second evaluation index group and the corresponding postmortem interval of the corpse is established.
[0016] According to the postmortem interval inference method provided by the present invention, a second evaluation index group is constructed based on the physical characteristic information corresponding to the evaluation indexes that meet the preset screening conditions in the first evaluation index group, including:
[0017] Constructing a first scoring group, wherein each score in the first scoring group corresponds to each physical characteristic information in the first evaluation index group;
[0018] Calculate the percentage of variance for each score in the first score group;
[0019] If the variance percentage of each score in the first scoring group meets the preset screening condition, the physical feature information in the first evaluation index group corresponding to the score is added to the second evaluation index group.
[0020] According to the postmortem interval inference method provided by the present invention, if the variance percentage of each score in the first scoring group meets the preset screening condition, the physical feature information in the first evaluation index group corresponding to the score is added to the second evaluation index group, including:
[0021] Sort the variance percentages of each score in the first score group;
[0022] Based on the sorted variance percentages, a first number of scores are selected in sequence, and the physical feature information in the first evaluation index group corresponding to the selected scores is added to the second evaluation index group.
[0023] According to the postmortem interval inference method provided by the present invention, if the variance percentage of each score in the first scoring group meets the preset screening condition, the physical feature information in the first evaluation index group corresponding to the score is added to the second evaluation index group, including:
[0024] Sort the variance percentages of each score in the first score group;
[0025] The sorted variance percentages are sequentially superimposed and summed, and the physical feature information in the first evaluation index group corresponding to the score is added to the second evaluation index group until the result obtained after the summation is greater than the first set value.
[0026] According to the postmortem interval inference method provided by the present invention, if the variance percentage of each score in the first scoring group meets the preset screening condition, the physical feature information in the first evaluation index group corresponding to the score is added to the second evaluation index group, including:
[0027] The physical feature information in the first evaluation index group corresponding to the target score in the first scoring group is added to the second evaluation index group, and the target score is a score in the first scoring group whose variance percentage is greater than the second set value.
[0028] The postmortem interval inference method provided by the present invention further includes: collecting daily accumulated temperature information of corpses in a training set;
[0029] Establishing a corresponding relationship between the physical characteristic information in the second evaluation index group and the corresponding postmortem interval of the corpse, including:
[0030] A second correspondence is established between the score of the physical characteristic information and the daily accumulated temperature information, and a third correspondence is established between the daily accumulated temperature information and the postmortem interval of the corpse.
[0031] According to the postmortem interval inference method provided by the present invention, searching for physical feature information of the corpse to be tested in a pre-constructed feature scoring system includes:
[0032] Based on the second corresponding relationship and the score, determining the daily accumulated temperature of the body to be tested;
[0033] Based on the third corresponding relationship and the daily accumulated temperature, the time of death of the body to be tested is determined.
[0034] The present invention also provides a post-mortem interval time inference system, comprising:
[0035] A data acquisition module, used to determine the physical characteristic information of the corpse to be tested;
[0036] The search output module is used to search for the physical feature information of the corpse to be tested in a pre-built feature scoring system and output the search result, which represents the post-mortem interval of the corpse to be tested.
[0037] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the above-mentioned post-mortem interval time inference methods is implemented.
[0038] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned postmortem interval time inference methods.
[0039] The present invention also provides a computer program product, comprising a computer program, which implements any of the above-mentioned post-mortem interval time inference methods when executed by a processor.
[0040] In the postmortem interval inference method provided by the present invention, a feature scoring system can be constructed based on the corpses in the training set. The feature scoring system is the correspondence between the physical feature information of the corpse and the postmortem interval. When performing postmortem interval inference, the time of death of the corpse to be tested can be directly determined based on the physical feature information of the corpse to be tested and the correspondence, which is highly efficient. In addition, in the present invention, several evaluation indicators can be selected from the physical feature information to construct a first evaluation indicator group, and further selected to obtain a second evaluation indicator group. Through this step-by-step selection method, the evaluation indicators in the obtained second evaluation indicator group can accurately reflect the physical feature information of the corpse to be tested with a lower amount of data, thereby improving work efficiency in the process of postmortem interval inference. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0042] Figure 1 This is one of the flow charts of the postmortem interval time estimation method provided by the embodiment of the present invention;
[0043] Figure 2 This is the second flow chart of the postmortem interval time estimation method provided by the embodiment of the present invention;
[0044] Figure 3 is a schematic diagram of a fitting curve provided by an embodiment of the present invention;
[0045] Figure 4 is a schematic diagram of the structure of a post-mortem interval time estimation system provided by an embodiment of the present invention;
[0046] Figure 5 It is a schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0047] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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 creative work are within the scope of protection of the present invention.
[0048] PMI, also known as the time since death, has always been a core issue and one of the difficult tasks in the application of forensic on-site science and forensic pathology. Effective and accurate PMI inference is of great forensic significance in clarifying the nature of the case, analyzing the identity of the deceased, characterizing the suspect, judging the time of the crime, defining the scope of investigation, providing the direction and ideas of investigation, and even solving the case. For corpses in the late stage of death, the difficulty of PMI inference is greatly increased due to the various signs of high decay of the corpse (such as corpse odor, corpse green, decayed venous network, foam organs, gigantism, etc.), moldy corpse, corpse wax, and skeletonization, etc., and due to the influence of multiple factors such as geography, climate, environment, and cause of death.
[0049] At present, a considerable number of scholars have conducted a series of studies on PMI inference through methods such as developmental indicators of necrophilic insects, changes in vitreous humor ion concentrations, and post-mortem microbial community succession. However, in actual work, the judgment of PMI still mainly relies on the experience and judgment of forensic doctors participating in on-site investigations. It has many disadvantages, such as being greatly affected by the surrounding environment, strong subjectivity in observation and analysis, difficulty in quantifying some observation indicators, and poor repeatability.
[0050] For example, in some areas with high precipitation and average temperature, the body decay process progresses quickly and the degree of decay is serious after death. Based on this, the present application provides a more accurate inference method for estimating the time interval after death, as shown below.
[0051] Figure 1 This is one of the flow charts of the postmortem interval time estimation method provided by the embodiment of the present invention;
[0052] like Figure 1 As shown, this embodiment provides a method for estimating a postmortem interval time, including:
[0053] Step 101, determining the physical characteristic information of the corpse to be tested;
[0054] Step 102, searching for physical characteristic information of the corpse to be tested in a pre-constructed characteristic scoring system, and outputting a search result, wherein the search result represents the post-mortem interval of the corpse to be tested;
[0055] Among them, the characteristic scoring system is the correspondence between the postmortem interval of the corpse to be tested and the evaluation index, and the evaluation index is the physical characteristic information of the corpse to be tested obtained after at least two screenings.
[0056] In practical applications, the physical feature information collected in this embodiment refers to the external morphology of the corpse and the morphological changes inside the body, wherein the evaluation indicators in the feature scoring system are selected from all the physical feature information of the corpse. For example, the evaluation indicators may include an overall evaluation indicator, which may be subdivided into a number of secondary indicators. The secondary indicators may include head and face indicators, trunk indicators, and limb indicators. The secondary indicators may be further subdivided into a number of tertiary indicators. The tertiary indicators may include overall status indicators, skin color indicators, skin morphology indicators, venous network indicators, hair indicators, eye indicators, lip indicators, external genitalia indicators, anus indicators, indicators of two arms, indicators of two legs, indicators of two hands, and indicators of two feet.
[0057] In implementation, the feature scoring system constructed in this embodiment can be the correspondence between the physical feature information of the corpse and the postmortem time interval. Taking the physical feature information with only skin color as an example, the skin color can include the following situations: "fresh with no obvious changes", "light pink or light bluish purple", "bright red or bluish purple", "dark red or dark red", "dark yellow-green or gray-brown", "dark blue-purple to black", etc. Several situations can correspond to different death times. When the postmortem time interval of the corpse is actually inferred, the postmortem time interval of the corpse can be determined by combining a variety of physical feature information.
[0058] The basic idea of multiple screening evaluation indicators in this embodiment is to reintegrate the original multiple variables with strong correlation into a set of new independent comprehensive indicators to replace the original variables, and transform the original random vector with related components into a new random vector with independent components by means of an orthogonal transformation. In algebra, it is to transform the covariance matrix of the original random vector into a diagonal matrix, and in geometry, it is to transform the original coordinate system into a new orthogonal coordinate system, so that it points to the P orthogonal directions with the largest sample point distribution, and then perform dimensionality reduction processing on the multi-dimensional variable system so that it can be converted into a low-dimensional variable system with a higher accuracy. Then, by constructing an appropriate value function, several new variables with larger variances can comprehensively reflect the main information contained in the original multiple variables, and these new variables are the main evaluation indicators.
[0059] In this embodiment, by further screening the evaluation indicators, on the one hand, the screened evaluation indicators can still accurately reflect the physical characteristic information of the corpse, and on the other hand, by reducing the number of evaluation indicators, the amount of calculated data can be effectively reduced.
[0060] In the postmortem interval inference method provided in the present embodiment, a feature scoring system can be constructed based on the corpses in the training set. The feature scoring system is the correspondence between the physical feature information of the corpse and the postmortem interval. When performing postmortem interval inference, the time of death of the corpse to be tested can be determined directly based on the physical feature information of the corpse to be tested and the correspondence. In addition, in the present invention, several evaluation indicators can be selected from the physical feature information to construct a first evaluation indicator group, and further selected to obtain a second evaluation indicator group. Through this step-by-step selection method, the evaluation indicators in the obtained second evaluation indicator group can accurately reflect the physical feature information of the corpse to be tested with lower data, thereby improving work efficiency in the process of postmortem interval inference.
[0061] In an exemplary embodiment, the process of constructing a feature scoring system includes:
[0062] Constructing a database based on postmortem intervals and physical characteristics of at least a number of corpses;
[0063] Scoring the physical characteristic information in the database, the score representing the postmortem interval of the corpse corresponding to the physical characteristic information;
[0064] Constructing a first evaluation index group based on the physical feature information in the database, wherein the first evaluation index group includes a plurality of evaluation indexes, each evaluation index corresponding to at least one physical feature information;
[0065] Constructing a second evaluation index group based on the physical feature information corresponding to the evaluation indexes that meet the preset screening conditions in the first evaluation index group;
[0066] A corresponding relationship between the physical characteristic information in the second evaluation index group and the corresponding postmortem interval of the corpse is established.
[0067] In actual applications, each evaluation indicator in the physical characteristic information can correspond to different scores according to different situations. Taking skin color as an example, different skin colors can correspond to different scores: "fresh, no obvious changes" corresponds to 0 points, "light pink or light bluish purple" corresponds to 1 point, "bright red or bluish purple" corresponds to 2 points, "dark red or dark red" corresponds to 3 points, "dark yellow-green or gray-brown" corresponds to 4 points, and "dark blue-purple to black" corresponds to 5 points. The higher the score, the longer the time interval since death of the body.
[0068] In this embodiment, the scoring method can more accurately and scientifically reflect the postmortem interval of the corpse.
[0069] In an exemplary embodiment, a second evaluation index group is constructed based on the physical feature information corresponding to the evaluation indexes that meet the preset screening conditions in the first evaluation index group, including:
[0070] Constructing a first scoring group, wherein each score in the first scoring group corresponds to each physical characteristic information in the first evaluation index group;
[0071] Calculate the percentage of variance for each score in the first score group;
[0072] If the variance percentage of each score in the first scoring group meets the preset screening condition, the physical feature information in the first evaluation index group corresponding to the score is added to the second evaluation index group.
[0073] In this embodiment, after the first evaluation indicator group is constructed, each evaluation indicator in the first evaluation indicator group can be scored according to actual conditions, and then a first scoring group composed of scores is obtained. Then, several scores can be selected from them based on the calculation of variance percentage, and the corresponding evaluation indicators can be added to the second evaluation indicator group.
[0074] The variance percentage refers to the percentage of the variance of each data item in a set of data to the average value of all data items. In this embodiment, the variance percentage of each score can reflect the contribution of different evaluation indicators to the inference of the postmortem interval of the corpse. This can reduce the computational workload while reducing the interference of inaccurate evaluation indicators, thereby improving the accuracy of the inference of the postmortem interval.
[0075] In an exemplary embodiment, if the variance percentage of each score in the first scoring group meets the preset screening condition, the physical feature information in the first evaluation index group corresponding to the score is added to the second evaluation index group, including:
[0076] Sort the variance percentages of each score in the first score group;
[0077] Based on the sorted variance percentages, a first number of scores are selected in sequence, and the physical feature information in the first evaluation index group corresponding to the selected scores is added to the second evaluation index group.
[0078] For example, when the first evaluation index group may include skin color, skin morphology and lip features, the score of the skin color index is higher, and the scores of the skin morphology and lip features are lower, which means that according to the skin color, it can be determined that the postmortem interval of the corpse is longer, and according to the skin morphology and lip features, it can be determined that the postmortem interval of the corpse is shorter. In this case, the variance percentage of the calculated skin color score will be higher, and the variance percentage of the skin morphology and lip features score will be lower. However, in actual applications, the skin color index will only have a higher score when the postmortem interval is longer. Therefore, it can be determined that the skin color index is more accurate than the skin morphology and lip features. In this way, in this embodiment, several evaluation indicators that determine that the postmortem interval of the corpse is longer can be screened out. After adding these evaluation indicators to the second evaluation index group, the postmortem interval of the corpse can be more accurately reflected.
[0079] In an exemplary embodiment, if the variance percentage of each score in the first scoring group meets the preset screening condition, the physical feature information in the first evaluation index group corresponding to the score is added to the second evaluation index group, including:
[0080] Sort the variance percentages of each score in the first score group;
[0081] The sorted variance percentages are sequentially superimposed and summed, and the physical feature information in the first evaluation index group corresponding to the score is added to the second evaluation index group until the result obtained after the summation is greater than the first set value.
[0082] In practical applications, the following Table 1 illustrates a specific example of calculating the variance percentage. As shown in the following table, Y1, Y2, Y3 and Y4 can represent four different evaluation indicators in the first evaluation indicator group, and the total represents the score value of each evaluation indicator. In this embodiment, the first set value can be 80%. It can be determined in the following Table 1 by superimposing and summing the variance percentages. The sum of the variance percentages of the three evaluation indicators Y1, Y2 and Y3 is 84.571%, which is more than 80%. Therefore, in this embodiment, the three evaluation indicators Y1, Y2 and Y3 can be added to the second evaluation indicator group.
[0083] In an exemplary embodiment, if the variance percentage of each score in the first scoring group meets the preset screening condition, the physical feature information in the first evaluation index group corresponding to the score is added to the second evaluation index group, including:
[0084] The physical feature information in the first evaluation index group corresponding to the target score in the first scoring group is added to the second evaluation index group, and the target score is a score in the first scoring group whose variance percentage is greater than the second set value.
[0085] In practical applications, still taking Table 1 above as an example, the second setting value can be 5. According to the variance percentages of the four evaluation indicators Y1, Y2, Y3 and Y4 in Table 1, it can be determined that only the variance percentages of Y1 and Y2 are greater than 5. Therefore, in this embodiment, Y1 and Y2 are added to the second evaluation indicator group.
[0086] In an exemplary embodiment, it further includes: collecting daily accumulated temperature information of corpses in a training set;
[0087] Establishing a corresponding relationship between the physical characteristic information in the second evaluation index group and the corresponding postmortem interval of the corpse, including:
[0088] A second correspondence is established between the score of the physical characteristic information and the daily accumulated temperature information, and a third correspondence is established between the daily accumulated temperature information and the postmortem interval of the corpse.
[0089] In the process of corpse decay, as time goes by and heat energy accumulates, the decay degree of the corpse will continue to increase. In other words, the decay speed and degree of the corpse must be inextricably linked to the local temperature. In the scheme of this embodiment, the daily accumulated temperature is combined to predict the time of death of the corpse to be tested. The daily accumulated temperature of the corpse and the time of death are used as independent variables, and the decay degree of the corpse, that is, the score of the physical characteristic information, is used as the dependent variable to establish a corresponding relationship. This is more logical and can more accurately predict the time of death of the corpse.
[0090] In an exemplary embodiment, searching for physical feature information of a corpse to be tested in a pre-built feature scoring system includes:
[0091] Based on the second corresponding relationship and the score, determining the daily accumulated temperature of the body to be tested;
[0092] Based on the third corresponding relationship and the daily accumulated temperature, the time of death of the body to be tested is determined.
[0093] In an exemplary embodiment, the second corresponding relationship includes the following formula (2):
[0094] ADS=mln(ADD)-n(2)
[0095] Where ADS is the score of the physical characteristic information of the corpses in the training set, m and n are constants, and ADD is the daily accumulated temperature.
[0096] In practical applications, m can be 17.6342 and n can be 32.7841.
[0097] The third corresponding relationship includes the following calculation formula (1):
[0098] ADD=T*PMI(1)
[0099] Where ADD is the daily accumulated temperature, T is the average temperature within the death period, and PMI is the death time;
[0100] Based on the daily accumulated temperature of the body to be tested and the third corresponding relationship, the time of death of the body to be tested is determined, including:
[0101] Based on the daily accumulated temperature of the body to be tested, the time of death of the body to be tested is reversed to determine the time of death of the body to be tested.
[0102] In practical applications, after determining the daily accumulated temperature of the body to be tested, the time of death of the body can be determined by reverse calculation. For example, the body is found at 12:00 noon on the 15th of a month. Based on the second correspondence, the daily accumulated temperature of the body is determined to be 50 degrees Celsius. The average temperature of the day is 30 degrees Celsius. Since the body was found at 12 noon, it can be determined that the daily accumulated temperature of the body on the 15th is 15 degrees Celsius. Based on this, it can be determined that the body has accumulated 35 degrees Celsius of accumulated temperature before the 15th. On the 14th of that month, it was found that the average temperature on the 14th of that month was 25 degrees Celsius, which means that after the body to be tested had fully accumulated 25 degrees Celsius in accumulated temperature on the 14th, it was still 10 degrees Celsius short. Continuing to work backwards to the 13th of that month, it was determined that the average temperature on the 13th of that month was 15 degrees Celsius. Based on this, the formula 1015*24=16 can be used to determine that the body to be tested experienced 16 hours of accumulated temperature on the 13th of that month. Starting from 0 o'clock, it can be predicted that the time of death of the body to be tested is 8:00 on the 13th of that month.
[0103] The following is a specific example to illustrate the method for predicting time of death provided by the solution of the present application, including:
[0104] Figure 2 This is the second flow chart of the postmortem interval time estimation method provided by the embodiment of the present invention;
[0105] like Figure 2 As shown, more than 50 cadaver cases with relatively accurate PMI in practice can be collected to improve and supplement relevant information related to PMI inference and model construction, including geographic information, climate information, time information, cadaver information, image information, etc., to establish an underlying database of PMI inference-related cases, organize cases into categories according to case characteristics, and divide the information into correlation strengths to facilitate the confirmation and screening of the contribution of influencing factors.
[0106] The multi-dimensional information of the above PMI is in the same position on the surface, but in fact, the information contributes to PMI differently, and it is difficult to determine the primary and secondary relationship. The basic idea of the multivariate statistical method of condensing multiple variable indicators into a few principal component indicators through linear transformation is to reintegrate the original multiple variables with strong correlation into a set of new independent comprehensive indicators to replace the original variables, and transform the original random vector with related components into a new random vector with unrelated components by means of an orthogonal transformation. In algebra, it is expressed as transforming the covariance matrix of the original random vector into a diagonal matrix, and in geometry, it is expressed as transforming the original coordinate system into a new orthogonal coordinate system, so that it points to the P orthogonal directions with the largest sample point distribution, and then reducing the dimensionality of the multidimensional variable system so that it can be converted into a low-dimensional variable system with a higher accuracy, and then further converting the low-dimensional system into a one-dimensional system by constructing an appropriate value function. Several new variables with larger variances can comprehensively reflect the main information contained in the original multiple variables, and these new variables are the principal components.
[0107] At the specific operation level, two methods are first used to test the fitness: one is the Bartlett sphericity test, which is used to test whether the variable correlation coefficient matrix is a unit matrix. SPSS software will output the chi-square statistic, degrees of freedom and significance value of the Bartlett sphericity test. If the significance value P≤0.05, it is considered that the correlation coefficient matrix is not a unit matrix and PCA can be performed. At the same time, the larger the chi-square value, the stronger the correlation between the variables. The second is to use the sampling fitness test (Measure of Sampling Adequacy, KMO), the sampling fitness test statistic MSA, and compare the size of the sum of squares of the correlation coefficients and the sum of squares of the partial correlation coefficients between samples to test whether the pseudo-sample is suitable for the subsequent construction of the second evaluation index group. The value of MSA is 0-1. The closer to 1, the stronger the correlation between the variables and the lower the partial correlation, and the more suitable the sample data is for PCA and factor analysis. MSA>0.9 indicates very suitable, 0.8-0.9 indicates suitable, 0.7-0.8 indicates average, 0.6-0.7 indicates acceptable, 0.5-0.6 indicates not very suitable, and below 0.5 indicates extremely unsuitable.
[0108] After the PMI-related time series information is tested and meets the basic conditions for constructing the second evaluation index group, according to the previous test results, the appropriate principal component comprehensive indicators are selected according to the following conditions: a. Cumulative variance contribution rate: When the cumulative variance contribution rate of the current n principal components reaches a certain value (generally 80% or 75% or more), the first n principal components can be retained; b. Eigenvalue: Generally, the principal components with eigenvalues greater than or equal to 1 are selected; c. Scree plot: Generally, the gravel before the node where the curve of the scree plot changes from steep to gentle is selected as the main component. Data analysis and effective dimensionality reduction are applied to PMI-related information, and 5-8 more general and abstract principal component comprehensive indicators are selected under the premise of minimizing the loss of original data information.
[0109] Relying on the PMI database, 80% of the cases were randomly selected as the model training set, and linear or nonlinear regression methods such as Logistic regression were used to explore and establish a feature scoring system. The remaining 20% of the cases in the PMI database were used as the validation set. The accuracy of the PMI inferred by the model was statistically analyzed, and the accuracy and credibility of the methods were compared with expert evaluation or other related models. The results were fed back to the PCA-PMI model for performance tuning, so as to continuously improve the model's inference performance on PMI in forensic practice.
[0110] During the implementation, 21 real cases with clear PMI were sorted out, including 16 males (76.2%) and 5 females (23.8%); the youngest was 6 years old and the oldest was 48 years old, with an average age of 28.1 years old; the bodies were all found in freshwater environments, such as rivers, reservoirs, streams and ponds. The shortest PMI was 1 day, the longest was 41 days, and the average was 5.7 days. The minimum ADD was 34.05, the maximum was 959.7, and the average was 142.3.
[0111] The research and literature related to the inference of PMI of underwater bodies were consulted and retrieved. Combined with expert interviews and surveys, the prototype of the visual scoring scale for PMI of underwater bodies was initially constructed. Two rounds of expert consultation were carried out. The experts evaluated the indicators of the visual scoring system, put forward suggestions for modifying and increasing or decreasing indicators, and continuously adjusted the system. The positive coefficient of the experts was 100%, and the authority coefficient was Cr=0.83>0.70, which means that the experts were authoritative. All W values of the Kendall coordination coefficient of the expert coordination degree were less than 0.05, which was statistically significant. The coordination of expert opinions was good, and the research results were credible and desirable. After two rounds of expert consultation, a visual scoring system was formed, which included 1 level I indicator, 3 level II indicators and 17 level III indicators. The level I indicator was the overall decomposition score Y, the level II indicators were the head and face decomposition score, the body decomposition score and the limbs decomposition score, and the level III indicators included 17 indicators, including overall state, skin color, skin morphology, corrupt venous network, hair, eyes, lips, external genitalia, anus, arms × 2, legs × 2, hands × 2, and feet × 2.
[0112] Five forensic workers (who did not participate in the formulation of the ADS score sheet) independently scored each case according to the ADS score sheet I indicators, requiring the coefficient of variation CV≤0.30, otherwise it needs to be re-scored. If the CV is still greater than 0.3 after multiple rounds of scoring, the case will be discarded for further analysis. The average score of the five people is used as the final score ADS of this indicator, and the calculation formula is:
[0113] (n = number of level I indicators)
[0114] After extracting the second evaluation index group according to the variance percentage of the above indicators, the daily accumulated temperature ADD=T(℃ / h)*PMI(h) of each case was calculated according to the meteorological data, and the regression model ADS=2.651ln(ADD)-5.98 was established.
[0115] Figure 3 It is a schematic diagram of a fitting curve provided by an embodiment of the present invention.
[0116] like Figure 3 As shown, it can be determined that R=0.823>0.8, R2=0.678, proving that the independent variable is highly correlated with the dependent variable. Therefore, it can be determined that the regression model established by the above embodiment can determine the postmortem interval time of the corpse.
[0117] The postmortem interval time inference system provided by the present invention is described below. The postmortem interval time inference system described below and the postmortem interval time inference method described above can be referenced to each other.
[0118] Figure 4It is a schematic diagram of the structure of a post-mortem interval time inference system provided in an embodiment of the present invention.
[0119] like Figure 4 As shown, the postmortem interval time inference system provided by the present invention includes:
[0120] Data collection module 401, a data collection module, is used to determine the physical characteristic information of the corpse to be tested;
[0121] The search output module 402 is used to search for the physical feature information of the corpse to be tested in the pre-constructed feature scoring system and output the search result, which represents the post-mortem interval of the corpse to be tested.
[0122] The specific implementation method of the post-mortem interval time estimation system provided in this embodiment can be implemented with reference to the above-mentioned embodiments, which will not be described in detail here.
[0123] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5 As shown, the electronic device may include: a processor 510, a communications interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communications interface 520 and the memory 530 communicate with each other via the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute the postmortem interval time inference method, which includes:
[0124] Determine the physical characteristics of the body to be tested;
[0125] Searching for physical characteristic information of the corpse to be tested in a pre-constructed characteristic scoring system, and outputting a search result, wherein the search result represents the post-mortem interval of the corpse to be tested;
[0126] Among them, the characteristic scoring system is the correspondence between the postmortem interval of the corpse to be tested and the evaluation index, and the evaluation index is the physical characteristic information of the corpse to be tested obtained after at least two screenings.
[0127] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.
[0128] On the other hand, the present invention further provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the post-mortem interval time estimation method provided by the above methods, and the method includes:
[0129] Determine the physical characteristics of the body to be tested;
[0130] Searching for physical characteristic information of the corpse to be tested in a pre-constructed characteristic scoring system, and outputting a search result, wherein the search result represents the post-mortem interval of the corpse to be tested;
[0131] Among them, the characteristic scoring system is the correspondence between the postmortem interval of the corpse to be tested and the evaluation index, and the evaluation index is the physical characteristic information of the corpse to be tested obtained after at least two screenings.
[0132] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to perform the post-mortem interval time estimation method provided by the above methods, the method comprising:
[0133] Determine the physical characteristics of the body to be tested;
[0134] Searching for physical characteristic information of the corpse to be tested in a pre-constructed characteristic scoring system, and outputting a search result, wherein the search result represents the post-mortem interval of the corpse to be tested;
[0135] Among them, the characteristic scoring system is the correspondence between the postmortem interval of the corpse to be tested and the evaluation index, and the evaluation index is the physical characteristic information of the corpse to be tested obtained after at least two screenings.
[0136] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.
[0137] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.
[0138] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. 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 embodiments of the present invention.
Claims
1. A method for estimating a postmortem interval, characterized in that: include: Determine the physical characteristics of the body to be tested; Searching for the physical feature information of the corpse to be tested in a pre-constructed feature scoring system, and outputting a search result, wherein the search result represents the post-mortem interval of the corpse to be tested; The characteristic scoring system is the correspondence between the postmortem interval of the corpse to be tested and the evaluation index, and the evaluation index is obtained by screening the physical characteristic information of the corpse to be tested at least twice.
2. The method for estimating postmortem interval according to claim 1, characterized in that: The construction process of the feature scoring system includes: Constructing a database based on postmortem intervals and physical characteristics of at least a number of corpses; Scoring the physical characteristic information in the database, the score representing the postmortem interval of the corpse corresponding to the physical characteristic information; Constructing a first evaluation index group based on the physical feature information in the database, wherein the first evaluation index group includes a plurality of evaluation indexes, each of which corresponds to at least one of the physical feature information; Constructing a second evaluation index group based on the physical feature information corresponding to the evaluation indexes that meet the preset screening conditions in the first evaluation index group; A correspondence between the physical characteristic information in the second evaluation index group and the corresponding postmortem interval of the corpse is established.
3. The method for estimating postmortem interval according to claim 2, characterized in that: The step of constructing a second evaluation index group based on the physical feature information corresponding to the evaluation indexes meeting the preset screening conditions in the first evaluation index group includes: Constructing a first scoring group, wherein each score in the first scoring group corresponds to each physical characteristic information in the first evaluation index group; Calculating the variance percentage of each score in the first score group; If the variance percentage of each score in the first scoring group meets the preset screening condition, the physical feature information in the first evaluation index group corresponding to the score is added to the second evaluation index group.
4. The method for estimating postmortem interval according to claim 3, characterized in that: If the variance percentage of each score in the first scoring group meets the preset screening condition, the physical feature information in the first evaluation index group corresponding to the score is added to the second evaluation index group, including: sorting the variance percentages of the scores in the first scoring group; Based on the sorted variance percentages, a first number of scores are selected in sequence, and the physical feature information in the first evaluation index group corresponding to the selected scores is added to the second evaluation index group.
5. The method for estimating postmortem interval according to claim 3, characterized in that: If the variance percentage of each score in the first scoring group meets the preset screening condition, the physical feature information in the first evaluation index group corresponding to the score is added to the second evaluation index group, including: Sorting the variance percentages of the scores in the first scoring group; The sorted variance percentages are sequentially superimposed and summed, and the physical feature information in the first evaluation index group corresponding to the score is added to the second evaluation index group until the result obtained after the summation is greater than the first set value.
6. The method for estimating postmortem interval according to claim 3, characterized in that: If the variance percentage of each score in the first scoring group meets the preset screening condition, the physical feature information in the first evaluation index group corresponding to the score is added to the second evaluation index group, including: The physical feature information in the first evaluation index group corresponding to the target score in the first scoring group is added to the second evaluation index group, wherein the target score is a score in the first scoring group whose variance percentage is greater than a second set value.
7. The method for estimating postmortem interval according to claim 2, characterized in that: Also includes: Collecting daily accumulated temperature information of corpses in the training set; The step of establishing a corresponding relationship between the physical feature information in the second evaluation index group and the postmortem interval of the corresponding corpse includes: A second corresponding relationship between the score of the physical characteristic information and the daily accumulated temperature information is established, and a third corresponding relationship between the daily accumulated temperature information and the postmortem interval time of the corpse is established.
8. The method for estimating postmortem interval according to claim 7, characterized in that: The step of searching for the physical characteristic information of the corpse to be tested in the pre-constructed characteristic scoring system includes: Determining the daily accumulated temperature of the corpse to be tested based on the second corresponding relationship and the score; The time of death of the corpse to be tested is determined based on the third corresponding relationship and the daily accumulated temperature.
9. A postmortem interval estimation system, characterized in that: include: A data acquisition module, used to determine the physical characteristic information of the corpse to be tested; The search output module is used to search for the physical feature information of the corpse to be tested in a pre-constructed feature scoring system and output a search result, wherein the search result represents the post-mortem interval of the corpse to be tested.
10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the post-mortem interval time estimation method according to any one of claims 1 to 8 is implemented.
