Evidence pollution detection system and method based on reverse mapping positioning

Abstract

The invention discloses an evidence pollution detection system and method based on reverse mapping positioning, and relates to the technical field of medical evidence-based, and the method comprises the steps: calling an operation record in an operation log of an evidence storage system, combing a source path of a target evidence, and generating an evidence circulation time axis; by calculating a pollution risk value, an upstream evidence source of a target pollution point is traced, and a pollution propagation path tree is constructed; and finally, positioning the pollution source according to the pollution source scoring function. The evidence pollution problem can be accurately identified, the pollution source and the pollution propagation path can be traced, guarantee is provided for reliability of evidence-based medicine, and the problem that pollution evidence cannot be accurately identified and traced in a traditional evidence detection mode is solved.

Description

Technical Field

[0001] The present invention relates to the field of medical evidence-based technology, and in particular to an evidence contamination detection system and method based on reverse mapping positioning. Background Art

[0002] With the advent of the era of evidence-based medicine, clinical decisions are increasingly dependent on evidence-based scientific evidence; currently, the amount of evidence accumulated in evidence-based medicine databases is growing exponentially, and this medical evidence has brought huge challenges to the formulation of clinical strategies.

[0003] Traditional medical evidence review methods rely heavily on manual screening or simple literature quality assessment tools, which no longer meet current evidence testing needs. Traditional testing methods are unable to accurately identify evidence contamination such as data fabrication and selective reporting, and are even unable to trace the impact of contaminated evidence on clinical decision-making. This often results in studies containing erroneous data being included in the evidence system, leading to deviations in clinical strategies and inappropriate patient treatment.

[0004] These problems pose great challenges to the reliability of evidence-based medicine, seriously affecting the scientific nature and safety of clinical diagnosis and treatment, hindering the further development of the evidence-based medicine system, and causing waste of medical resources and health risks to patients. Summary of the Invention

[0005] The purpose of the present invention is to provide an evidence contamination detection system and method based on reverse mapping positioning to solve the problems raised in the prior art.

[0006] To achieve the above-mentioned object, the present invention provides the following technical solution: a method for detecting evidence contamination based on reverse mapping positioning, the detection method comprising: Step S100: Retrieving all operation records of evidence generation instructions from the operation log of the evidence storage system; extracting information from each operation record, and sorting out the source path of each piece of evidence based on the extracted operation record information; Step S200: sorting out the source paths of each piece of evidence and generating an evidence flow timeline; calculating the contamination propagation probability and evidence matching degree of each evidence point on the evidence flow timeline; and calculating the contamination risk value for each evidence point based on the contamination propagation probability and evidence matching degree. Step S300: judging the target contamination point based on the pollution risk value of each evidence point, tracing back the upstream evidence source of the target contamination point, and constructing a pollution propagation path tree; Step S400: Calculate the pollution propagation range of the upper-level associated evidence of the target pollution point in the pollution propagation path tree, and construct a pollution source scoring function based on the pollution propagation probability and evidence matching degree to locate the pollution source.

[0007] Furthermore, step S100 includes: Step S101: Retrieving all operation records of evidence generation instructions from the operation log of the evidence storage system, wherein the operation records include derivation, update, and reference of evidence; Step S102: Capturing the generated target evidence in the operation record of each evidence generation instruction; capturing all associated evidence called when generating the target evidence in the operation record of each evidence generation instruction, and acquiring evidence information of the associated evidence, wherein the evidence information includes the evidence source of the associated evidence; the evidence source of the associated evidence includes the evidence chain that generates the associated evidence in the evidence storage system; Step S103: In the operation record of each evidence generation instruction, capture the operation record of the associated evidence when the target evidence is generated. k ; Wherein, k = 1 or 2 or 3; The operation record includes the derivative operation Re 1 , update operationRe 2 , reference operation Re 3 ; Among them, if the operation record of the target evidence is a derivative operation Re 1 , indicating that new evidence is obtained by analyzing the associated evidence, and the new evidence is the target evidence; if the operation record of the target evidence is an update operation Re 2 , which means that new evidence is obtained by updating the differences in the related evidence based on the latest research data; if the operation record of the target evidence is the reference operation Re 3 , indicating that the research results or data of the related evidence are referenced by the target evidence; Step S104: Capture and mark the operation records of all evidence in the evidence chain of the associated evidence in the evidence storage system to obtain the evidence chain ORG; generate the source path L of the target evidence through reverse mapping based on the operation records between the target evidence and the associated evidence, the operation records between the associated evidence and the evidence chain, and the operation records between each piece of evidence in the evidence chain. A {A→Re k →B→Re k →ORG}; among them, L A It represents the source path of target evidence A, and B represents the related evidence of evidence A; In the above steps, "target evidence" refers to the evidence currently generated in the evidence storage system; "associated evidence" is the basis for the generation of "target evidence"; for example, multiple references (associated evidence) cited by a paper (target evidence); "evidence chain" records the generation history of "associated evidence" itself. The evidence chain can ensure the depth of evidence tracing and enable deeper exploration of the source of evidence; through reverse mapping, starting from the target evidence, reversely tracing the associated data and data chain that the target evidence depends on, the source of pollution can be better located.

[0008] Furthermore, step S200 includes: Step S201: sort all evidence on the source path of the target evidence in time sequence to generate an evidence flow timeline; the set of evidence points on the evidence flow timeline is E={e1,…,e i ,…,e n}; Each evidence point is marked with a timestamp t i , e i represents the i-th evidence point, e n Indicates the source of evidence; calculates the probability of contamination spread between two adjacent evidence points Among them, P i represents the probability of contamination propagation between the i-th evidence point and the i+1-th evidence point on the evidence flow timeline, N represents the total number of times the i-th evidence point has been operated in the operation log of the evidence storage system, t j , t j+1 Represents evidence points e i 、e i+1 Timestamp of the tag, k Indicates the operation weight corresponding to the operation record; where k=1 or 2 or 3; Step S202: Obtain the complete content of each evidence point in the evidence flow timeline, wherein the complete content of each evidence point includes text, chart annotations, and data tables; semantically vectorize the complete content of each evidence point obtained using natural language processing technology; use cosine similarity to calculate the content overlap between each piece of evidence after semantic vectorization, and normalize the overlap; set the credibility of each evidence point based on the total number of times each evidence point has been operated in the operation log of the evidence storage system, and the higher the total number of times it has been operated, the higher the credibility; calculate the evidence matching degree between each evidence point Among them, M i represents the evidence matching degree between the i-th evidence point and the i+1-th evidence point, S i represents the content overlap between the i-th evidence point and the i+1-th evidence point, C i Indicates the credibility of the i-th evidence point; Step S203: Calculate the pollution risk value for each evidence point based on the pollution propagation probability and evidence matching degree ; where e→e i represents all evidence points e pointing to evidence point e i ; In the above steps, “e→e i " represents all upstream evidence points pointing to the current evidence point e. By accumulating the product of the propagation probability and mismatch degree of the evidence points in each upstream path, the comprehensive risk of multi-source pollution is evaluated. For example, if evidence e depends on two upstream related evidences e1 and e2 at the same time, the pollution risk value of evidence e is Q=Q (e→e1) +Q (e→e2) .

[0009] Furthermore, step S300 includes: Step S301: Preset a contamination risk value threshold F, which is set based on historical contamination data of the evidence storage system; traverse all evidence points on the evidence flow timeline, and compare the contamination risk value Q of each evidence point with the contamination risk value threshold F; if the contamination risk value Q ≥ F, then the evidence point is designated as a target contamination point; Step S302: Retrieve the source path L of each target pollution point e e {e→Re k →e i →Re k →ORG}; capture all the associated evidences in the upstream path of the target pollution point e on the source path, and form an associated evidence set {u1,u2,…,u n}; Each associated evidence is marked with the operation record and timestamp of the target contamination point e; u n represents the nth associated evidence of the target contamination point e; Step S303: For each associated evidence in the associated evidence set, repeat the tracing logic of step S302 to generate a set of associated evidence in the upstream path of each associated evidence; based on the operation records and timestamps marked on each associated evidence, construct a pollution propagation path tree from the target pollution point e to each layer of upstream paths to visualize the hierarchical relationship of pollution propagation.

[0010] Furthermore, step S400 includes: Step S401 includes: starting from the root node target pollution point e of the pollution propagation path tree, traversing the associated evidence of each layer upward, counting the number of associated evidences in the lower layer of each associated evidence in the pollution propagation path tree, and calculating the pollution propagation range of each associated evidence. ;in, irepresents the pollution propagation range of the i-th associated evidence on the pollution propagation path tree, Q i represents the contamination risk value of the i-th associated evidence, and m represents the number of lower-level associated evidence of the i-th associated evidence; Step S402: Construct a pollution source scoring function based on the evidence matching degree and the pollution propagation probability ; All associated evidence on the pollution propagation path tree is scored using the pollution source scoring function, the scores of all associated evidence are sorted, and the associated evidence with the highest score is marked. The marked associated evidence is the source of evidence pollution.

[0011] Furthermore, in order to better implement the above method, an evidence pollution detection system based on reverse mapping positioning is also provided. The detection system includes: an operation record processing module, a pollution risk calculation module, a pollution path tracing module, and a pollution source positioning module; The operation record processing module is used to retrieve all operation records of evidence generation instructions from the operation log of the evidence storage system, extract information from each operation record, and sort out the source path of each piece of evidence based on the extracted operation record information; The pollution risk calculation module sorts out the source path of each piece of evidence, generates a timeline of evidence flow, and calculates the probability of pollution transmission, evidence matching degree, and pollution risk value; The pollution path tracing module is used to identify target pollution points, trace the upstream evidence sources of target pollution points, and build a pollution propagation path tree; The pollution source positioning module calculates the pollution propagation range of the upper-level associated evidence of the target pollution point in the pollution propagation path tree, and constructs a pollution source scoring function based on the pollution propagation probability and evidence matching degree to locate the pollution source.

[0012] Furthermore, the operation record processing module includes: an operation record retrieval unit, a correlation evidence capture unit, an operation type marking unit, and a source path generation unit; An operation record retrieving unit, configured to retrieve all operation records of evidence generation instructions from the operation log of the evidence storage system; An associated evidence capturing unit, which captures associated evidence called during the target evidence generation process and obtains the evidence source of the associated evidence; An operation type marking unit, used to mark the operation type of the target evidence on the associated evidence; The source path generation unit is used to generate the source path of the target evidence through reverse mapping.

[0013] Furthermore, the contamination risk calculation module includes: a timeline generation unit, a contamination probability calculation unit, an evidence matching degree calculation unit, and a risk value calculation unit; A timeline generation unit, used to generate a timeline for evidence flow; The contamination probability calculation unit is used to calculate the contamination propagation probability of adjacent evidence points on the evidence flow time axis; An evidence matching degree calculation unit, used to calculate the evidence matching degree between adjacent evidence points; The risk value calculation unit calculates the pollution risk value of each evidence point based on the pollution propagation probability and the evidence matching degree.

[0014] Furthermore, the pollution path tracing module includes: a target pollution point identification unit, an upstream evidence tracing unit, and a path tree construction unit; The target pollution point identification unit determines the target pollution point according to the preset pollution risk value threshold; The upstream evidence tracing unit is used to retrieve the source path of the target pollution point, capture the upstream related evidence in the source path of the target pollution point, and construct a related evidence set; The path tree construction unit constructs a pollution propagation path tree by recursively tracing the upstream paths of each associated evidence.

[0015] Furthermore, the pollution source location module includes: a propagation range calculation unit, a scoring function construction unit, and a pollution source location unit; The propagation range calculation unit counts the number of upper-level associated evidence of each associated evidence in the pollution propagation path tree, and calculates the pollution propagation range of each associated evidence in combination with the pollution risk value; The scoring function construction unit combines the evidence matching degree, pollution spread probability and pollution spread range to construct the pollution source scoring function; The pollution source location unit determines the source of evidence contamination by judging the pollution source score of the associated evidence.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. Accurately trace the source of pollution: By using reverse positioning technology to reversely trace the associated evidence from the target evidence, the present invention can deeply explore the source of evidence and accurately locate the source of pollution.

[0017] 2. Quantitative assessment of pollution risk: The pollution risk value is calculated by calculating indicators such as the probability of pollution transmission and the degree of evidence matching, and comprehensively considering factors such as time interval, number of operations, and content overlap, making the pollution risk assessment more scientific and accurate, overcoming the fuzzy defects of traditional manual assessment.

[0018] 3. Visualization of pollution transmission paths: By constructing a pollution transmission path tree, the hierarchical transmission relationship from the pollution source to the target pollution evidence is intuitively presented, making it easier to take targeted measures to reduce the scope of pollution. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a schematic diagram of a method flow of a system and method for detecting evidence contamination based on reverse mapping positioning according to the present invention; Figure 2 The figure is a schematic diagram of the system structure of an evidence contamination detection system and method based on reverse mapping positioning of the present invention. DETAILED DESCRIPTION

[0020] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative work shall fall within the scope of protection of the present invention.

[0021] Example 1: Figure 1 As shown, the present invention provides a technical solution, a method for detecting evidence contamination based on reverse mapping positioning, the detection method comprising: Step S100: Retrieving all operation records of evidence generation instructions from the operation log of the evidence storage system; extracting information from each operation record, and sorting out the source path of each piece of evidence based on the extracted operation record information; Wherein, step S100 includes: Step S101: Retrieving all operation records of evidence generation instructions from the operation log of the evidence storage system, wherein the operation records include derivation, update, and reference of evidence; Step S102: Capturing the generated target evidence in the operation record of each evidence generation instruction; capturing all associated evidence called when generating the target evidence in the operation record of each evidence generation instruction, and acquiring evidence information of the associated evidence, wherein the evidence information includes the evidence source of the associated evidence; the evidence source of the associated evidence includes the evidence chain that generates the associated evidence in the evidence storage system; Step S103: In the operation record of each evidence generation instruction, capture the operation record of the associated evidence when the target evidence is generated. k ; Wherein, k = 1 or 2 or 3; The operation record includes the derivative operation Re 1 , update operationRe 2 , reference operation Re 3 ; Among them, if the operation record of the target evidence is a derivative operation Re 1 , indicating that new evidence is obtained by analyzing the associated evidence, and the new evidence is the target evidence; if the operation record of the target evidence is an update operation Re 2 , which means that new evidence is obtained by updating the differences in the related evidence based on the latest research data; if the operation record of the target evidence is the reference operation Re 3 , indicating that the research results or data of the related evidence are referenced by the target evidence; Step S104: Capture and mark the operation records of all evidence in the evidence chain of the associated evidence in the evidence storage system to obtain the evidence chain ORG; generate the source path L of the target evidence through reverse mapping based on the operation records between the target evidence and the associated evidence, the operation records between the associated evidence and the evidence chain, and the operation records between each piece of evidence in the evidence chain. A {A→Re k →B→Re k →ORG}; among them, L A It represents the source path of target evidence A, and B represents the related evidence of evidence A; Step S200: sorting out the source paths of each piece of evidence and generating an evidence flow timeline; calculating the contamination propagation probability and evidence matching degree of each evidence point on the evidence flow timeline; and calculating the contamination risk value for each evidence point based on the contamination propagation probability and evidence matching degree. Wherein, step S200 includes: Step S201: sort all evidence on the source path of the target evidence in time sequence to generate an evidence flow timeline; the set of evidence points on the evidence flow timeline is E={e1,…,e i ,…,e n}; Each evidence point is marked with a timestamp t i , e i represents the i-th evidence point, e n Indicates the source of evidence; calculates the probability of contamination spread between two adjacent evidence points Among them, P i represents the probability of contamination propagation between the i-th evidence point and the i+1-th evidence point on the evidence flow timeline, N represents the total number of times the i-th evidence point has been operated in the operation log of the evidence storage system, t j , t j+1 Represents evidence points e j 、e j+1 Timestamp of the tag, k Indicates the operation weight corresponding to the operation record; where k=1 or 2 or 3; Step S202: Obtain the complete content of each evidence point in the evidence flow timeline, wherein the complete content of each evidence point includes text, chart annotations, and data tables; semantically vectorize the complete content of each evidence point obtained using natural language processing technology; use cosine similarity to calculate the content overlap between each piece of evidence after semantic vectorization, and normalize the overlap; set the credibility of each evidence point based on the total number of times each evidence point has been operated in the operation log of the evidence storage system, and the higher the total number of times it has been operated, the higher the credibility; calculate the evidence matching degree between each evidence point Among them, Mi represents the evidence matching degree between the i-th evidence point and the i+1-th evidence point, S i represents the content overlap between the i-th evidence point and the i+1-th evidence point, C i Indicates the credibility of the i-th evidence point; Step S203: Calculate the pollution risk value for each evidence point based on the pollution propagation probability and evidence matching degree ; where e→e i represents all evidence points e pointing to evidence point e i ; Step S300: judging the target contamination point based on the pollution risk value of each evidence point, tracing back the upstream evidence source of the target contamination point, and constructing a pollution propagation path tree; Wherein, step S300 includes: Step S301: Preset a contamination risk value threshold F, which is set based on historical contamination data of the evidence storage system; traverse all evidence points on the evidence flow timeline, and compare the contamination risk value Q of each evidence point with the contamination risk value threshold F; if the contamination risk value Q ≥ F, then the evidence point is designated as a target contamination point; Step S302: Retrieve the source path L of each target pollution point e e {e→Re k →e i →Re k →ORG}; capture all the associated evidences in the upstream path of the target pollution point e on the source path, and form an associated evidence set {u1,u2,…,u n}; Each associated evidence is marked with the operation record and timestamp of the target contamination point e; u n represents the nth associated evidence of the target contamination point e; Step S303: Repeat the tracing logic of step S302 for each associated evidence in the associated evidence set to generate a set of associated evidence in the upstream path of each associated evidence; construct a pollution propagation path tree from the target pollution point e to each layer of upstream paths based on the operation records and timestamps marked on each associated evidence, to visualize the hierarchical relationship of pollution propagation; Step S400: Calculate the pollution spread range of the upper-level associated evidence of the target pollution point in the pollution propagation path tree, and construct a pollution source scoring function based on the pollution propagation probability and evidence matching degree to locate the pollution source; Wherein, step S400 includes: Step S401 includes: starting from the root node target pollution point e of the pollution propagation path tree, traversing the associated evidence of each layer upward, counting the number of associated evidences in the lower layer of each associated evidence in the pollution propagation path tree, and calculating the pollution propagation range of each associated evidence. ;in, i represents the pollution propagation range of the i-th associated evidence on the pollution propagation path tree, Q i represents the contamination risk value of the i-th associated evidence, and m represents the number of lower-level associated evidence of the i-th associated evidence; Step S402: Construct a pollution source scoring function based on the evidence matching degree and the pollution propagation probability ; Score all associated evidence on the pollution propagation path tree using the pollution source scoring function, sort the scores of all associated evidence, and mark the associated evidence with the highest score. The marked associated evidence is the source of evidence pollution; Example 2: Figure 2 As shown, in order to better implement the above method, an evidence pollution detection system based on reverse mapping positioning is also provided, which includes: an operation record processing module, a pollution risk calculation module, a pollution path tracing module, and a pollution source positioning module; The operation record processing module is used to retrieve all operation records of evidence generation instructions from the operation log of the evidence storage system, extract information from each operation record, and sort out the source path of each piece of evidence based on the extracted operation record information; The pollution risk calculation module sorts out the source path of each piece of evidence, generates a timeline of evidence flow, and calculates the probability of pollution transmission, evidence matching degree, and pollution risk value; The pollution path tracing module is used to identify target pollution points, trace the upstream evidence sources of target pollution points, and build a pollution propagation path tree; The pollution source positioning module calculates the pollution spread range of the upper-level associated evidence of the target pollution point in the pollution propagation path tree, and constructs a pollution source scoring function based on the pollution propagation probability and evidence matching degree to locate the pollution source; The operation record processing module includes: an operation record retrieval unit, a correlation evidence capture unit, an operation type marking unit, and a source path generation unit; An operation record retrieving unit, configured to retrieve all operation records of evidence generation instructions from the operation log of the evidence storage system; An associated evidence capturing unit, which captures associated evidence called during the target evidence generation process and obtains the evidence source of the associated evidence; An operation type marking unit, used to mark the operation type of the target evidence on the associated evidence; a source path generation unit, configured to generate a source path of target evidence through reverse mapping; Among them, the pollution risk calculation module includes: timeline generation unit, pollution probability calculation unit, evidence matching degree calculation unit, and risk value calculation unit; A timeline generation unit, used to generate a timeline for evidence flow; The contamination probability calculation unit is used to calculate the contamination propagation probability of adjacent evidence points on the evidence flow time axis; An evidence matching degree calculation unit, used to calculate the evidence matching degree between adjacent evidence points; The risk value calculation unit calculates the pollution risk value of each evidence point based on the pollution transmission probability and the evidence matching degree; Among them, the pollution path tracing module includes: target pollution point identification unit, upstream evidence tracing unit, and path tree construction unit; The target pollution point identification unit determines the target pollution point according to the preset pollution risk value threshold; The upstream evidence tracing unit is used to retrieve the source path of the target pollution point, capture the upstream related evidence in the source path of the target pollution point, and construct a related evidence set; The path tree construction unit constructs a pollution propagation path tree by recursively tracing the upstream paths of each associated evidence; Among them, the pollution source positioning module includes: a propagation range calculation unit, a scoring function construction unit, and a pollution source positioning unit; The propagation range calculation unit counts the number of upper-level associated evidence of each associated evidence in the pollution propagation path tree, and calculates the pollution propagation range of each associated evidence in combination with the pollution risk value; The scoring function construction unit combines the evidence matching degree, pollution spread probability and pollution spread range to construct the pollution source scoring function; The pollution source location unit determines the source of evidence contamination by judging the pollution source score of the associated evidence; In an embodiment of the present invention, the generation record of evidence A is retrieved from the operation log of the evidence storage system. The generation record records that evidence A is generated by analyzing the association of evidence B through derivative operations. Evidence association B references the basic research data C in the evidence chain ORG through a reference operation. The basic research evidence C is the directly associated evidence of B in the evidence chain. The source path of evidence A is generated through reverse mapping: A→Re1→B→Re3→ORG. The timestamps on the evidence chain are C(2022.1), B(2023.5), and A(2024.1), generating the evidence flow timeline A(2024.1)→B(2023.5)→C(2022.1). According to the evidence flow timeline, it can be seen that A→B: the time interval is 8 months, B is operated N times 50 times, 1 =3Propagation probability P B→A =(3×8) / 50=0.48; B→C: The time interval is 16 months, and the number of operations on C is N=100. 3 =1 Propagation probability P B→C =(1×16) / 100=0.16; the content overlap between B and A is S i =0.7, B's credibility C i =0.8, M B =(0.7×0.8×3) / 8=0.21; the content overlap between C and B is S i =0.9, the credibility of C i =0.9, M C =(0.9×0.9×1) / 16=0.05; therefore, the contamination risk value of evidence A is Q A =0.48×(1-0.21)+0.16×(1-0.05)=0.53; the system preset pollution risk value threshold F=0.3, Q A =0.53>0.3, mark A as the target pollution point; trace the upstream evidence chain, capture the associated evidence B and C, and construct a pollution propagation path tree with the target pollution evidence point A as the root and the associated evidence B and C as the branches; in the pollution propagation path tree, the number of lower-level associated evidence of C is m=2, so the pollution propagation range of C is C =0.16×2=0.32; in the contamination path tree, the number of lower-level associated evidence of B is m=1, so the contamination propagation range of B is B =0.48×1=0.48; G is calculated based on the pollution source scoring function. C =(1-0.05)×0.16×0.32=0.05, G B =(1-0.21)×0.48×0.48=0.18>0.05, so B is determined to be the source of evidence contamination.

[0022] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A method for detecting evidence contamination based on reverse mapping positioning, characterized by: The detection method comprises: Step S100: Retrieving all operation records of evidence generation instructions from the operation log of the evidence storage system; extracting information from each operation record, and sorting out the source path of each piece of evidence based on the extracted operation record information; Step S200: sorting out the source paths of each piece of evidence and generating an evidence flow timeline; calculating the contamination propagation probability and evidence matching degree of each evidence point on the evidence flow timeline; and calculating the contamination risk value for each evidence point based on the contamination propagation probability and evidence matching degree. Step S300: judging the target contamination point based on the pollution risk value of each evidence point, tracing back the upstream evidence source of the target contamination point, and constructing a pollution propagation path tree; Step S400: Calculate the pollution propagation range of the upper-level associated evidence of the target pollution point in the pollution propagation path tree, and construct a pollution source scoring function based on the pollution propagation probability and evidence matching degree to locate the pollution source.

2. The method for detecting evidence contamination based on reverse mapping positioning according to claim 1, characterized in that: Step S100 includes: Step S101: Retrieving all operation records of evidence generation instructions from the operation log of the evidence storage system, wherein the operation records include derivation, update, and reference of evidence; Step S102: Capturing the generated target evidence in the operation record of each evidence generation instruction; capturing all associated evidence called when generating the target evidence in the operation record of each evidence generation instruction, and acquiring evidence information of the associated evidence, wherein the evidence information includes the evidence source of the associated evidence; the evidence source of the associated evidence includes the evidence chain that generates the associated evidence in the evidence storage system; Step S103: In the operation record of each evidence generation instruction, capture the operation record of the associated evidence when the target evidence is generated. k ; Wherein, k = 1 or 2 or 3; The operation record includes the derivative operation Re 1 , update operationRe 2 , reference operation Re 3 ; Among them, if the operation record of the target evidence is a derivative operation Re 1 , indicating that new evidence is obtained by analyzing the associated evidence, and the new evidence is the target evidence; if the operation record of the target evidence is an update operation Re 2 , which means that new evidence is obtained by updating the differences in the related evidence based on the latest research data; if the operation record of the target evidence is the reference operation Re 3 , indicating that the research results or data of the related evidence are referenced by the target evidence; Step S104: Capture and mark the operation records of all evidence in the evidence chain of the associated evidence in the evidence storage system to obtain the evidence chain ORG; generate the source path L of the target evidence through reverse mapping based on the operation records between the target evidence and the associated evidence, the operation records between the associated evidence and the evidence chain, and the operation records between each piece of evidence in the evidence chain. A {A→Re k →B→Re k →ORG}; among them, L A It represents the source path of target evidence A, and B represents the associated evidence of evidence A.

3. The method for detecting evidence contamination based on reverse mapping positioning according to claim 1, characterized in that: Step S200 includes: Step S201: sort all evidence on the source path of the target evidence in time sequence to generate an evidence flow timeline; the set of evidence points on the evidence flow timeline is E={e1,…,e i ,…,e n }; Each evidence point is marked with a timestamp t i , e i represents the i-th evidence point, e n Indicates the source of evidence; calculates the probability of contamination spread between two adjacent evidence points Among them, P i represents the probability of contamination propagation between the i-th evidence point and the i+1-th evidence point on the evidence flow timeline, N represents the total number of times the i-th evidence point has been operated in the operation log of the evidence storage system, t j , t j+1 Represents evidence points e j 、e j+1 Timestamp of the tag, k Indicates the operation weight corresponding to the operation record; where k=1 or 2 or 3; Step S202: Obtain the complete content of each evidence point in the evidence flow timeline, wherein the complete content of each evidence point includes text, chart annotations, and data tables; semantically vectorize the complete content of each evidence point obtained using natural language processing technology; use cosine similarity to calculate the content overlap between each piece of evidence after semantic vectorization, and normalize the overlap; set the credibility of each evidence point based on the total number of times each evidence point has been operated in the operation log of the evidence storage system, and the higher the total number of times it has been operated, the higher the credibility; calculate the evidence matching degree between each evidence point Among them, M i represents the evidence matching degree between the i-th evidence point and the i+1-th evidence point, S i represents the content overlap between the i-th evidence point and the i+1-th evidence point, C i Indicates the credibility of the i-th evidence point; Step S203: Calculate the pollution risk value for each evidence point based on the pollution propagation probability and evidence matching degree ; where e→e i represents all evidence points e pointing to evidence point e i .

4. The method for detecting evidence contamination based on reverse mapping positioning according to claim 1, characterized in that: Step S300 includes: Step S301: Preset a contamination risk value threshold F, which is set based on historical contamination data of the evidence storage system; traverse all evidence points on the evidence flow timeline, and compare the contamination risk value Q of each evidence point with the contamination risk value threshold F; if the contamination risk value Q ≥ F, then the evidence point is designated as a target contamination point; Step S302: Retrieve the source path L of each target pollution point e e {e→Re k →e i →Re k →ORG}; capture all the associated evidences in the upstream path of the target pollution point e on the source path, and form an associated evidence set {u1,u2,…,u n }; Each associated evidence is marked with the operation record and timestamp of the target contamination point e; u n represents the nth associated evidence of the target contamination point e; Step S303: For each associated evidence in the associated evidence set, repeat the tracing logic of step S302 to generate a set of associated evidence in the upstream path of each associated evidence; based on the operation records and timestamps marked on each associated evidence, construct a pollution propagation path tree from the target pollution point e to each layer of upstream paths to visualize the hierarchical relationship of pollution propagation.

5. The method for detecting evidence contamination based on reverse mapping positioning according to claim 1, characterized in that: Step 400 includes: Step S401 includes: starting from the root node target pollution point e of the pollution propagation path tree, traversing the associated evidence of each layer upward, counting the number of associated evidences in the lower layer of each associated evidence in the pollution propagation path tree, and calculating the pollution propagation range of each associated evidence. ;in, i represents the pollution propagation range of the i-th associated evidence on the pollution propagation path tree, Q i represents the contamination risk value of the i-th associated evidence, and m represents the number of lower-level associated evidence of the i-th associated evidence; Step S402: Construct a pollution source scoring function based on the evidence matching degree and the pollution propagation probability ; All associated evidence on the pollution propagation path tree is scored using the pollution source scoring function, the scores of all associated evidence are sorted, and the associated evidence with the highest score is marked. The marked associated evidence is the source of evidence pollution.

6. A system for detecting evidence contamination based on reverse mapping positioning, configured to execute the method for detecting evidence contamination based on reverse mapping positioning according to any one of claims 1 to 5, characterized in that: The detection system includes: an operation record processing module, a pollution risk calculation module, a pollution path tracing module, and a pollution source positioning module; The operation record processing module is used to retrieve all operation records of evidence generation instructions from the operation log of the evidence storage system, extract information from each operation record, and sort out the source path of each piece of evidence based on the extracted operation record information; The contamination risk calculation module sorts out the source path of each piece of evidence, generates a timeline of evidence flow, and calculates the probability of contamination transmission, the degree of evidence matching, and the contamination risk value; The pollution path tracing module is used to identify the target pollution point, trace the upstream evidence source of the target pollution point, and construct a pollution propagation path tree; The pollution source positioning module calculates the pollution propagation range of the upper-level associated evidence of the target pollution point in the pollution propagation path tree, and constructs a pollution source scoring function based on the pollution propagation probability and evidence matching degree to locate the pollution source.

7. The evidence contamination detection system based on reverse mapping positioning according to claim 6, characterized in that: The operation record processing module includes: an operation record retrieval unit, a correlation evidence capture unit, an operation type marking unit, and a source path generation unit; The operation record retrieving unit is used to retrieve all operation records of the evidence generation instruction from the operation log of the evidence storage system; The associated evidence capturing unit captures associated evidence called during the target evidence generation process and obtains the evidence source of the associated evidence; The operation type marking unit is used to mark the operation type of the target evidence on the associated evidence; The source path generation unit is used to generate the source path of the target evidence through reverse mapping.

8. The evidence contamination detection system based on reverse mapping positioning according to claim 6, characterized in that: The pollution risk calculation module includes: a timeline generation unit, a pollution probability calculation unit, an evidence matching degree calculation unit, and a risk value calculation unit; The timeline generation unit is used to generate a timeline for evidence circulation; The contamination probability calculation unit is used to calculate the contamination propagation probability of adjacent evidence points on the evidence flow time axis; The evidence matching degree calculation unit is used to calculate the evidence matching degree between adjacent evidence points; The risk value calculation unit calculates the pollution risk value of each evidence point according to the pollution propagation probability and the evidence matching degree.

9. The evidence contamination detection system based on reverse mapping positioning according to claim 6, characterized in that: The pollution path tracing module includes: a target pollution point identification unit, an upstream evidence tracing unit, and a path tree construction unit; The target pollution point identification unit determines the target pollution point according to a preset pollution risk value threshold; The upstream evidence tracing unit is used to retrieve the source path of the target pollution point, and capture the upstream related evidence in the source path of the target pollution point to construct a related evidence set; The path tree construction unit constructs a pollution propagation path tree by recursively tracing the upstream path of each associated evidence.

10. The evidence contamination detection system based on reverse mapping positioning according to claim 6, characterized in that: The pollution source positioning module includes: a propagation range calculation unit, a scoring function construction unit, and a pollution source positioning unit; The propagation range calculation unit counts the number of upper-level associated evidence of each associated evidence in the pollution propagation path tree, and calculates the pollution propagation range of each associated evidence in combination with the pollution risk value; The scoring function construction unit constructs a pollution source scoring function by combining the evidence matching degree, the pollution spread probability and the pollution spread range; The pollution source locating unit determines the source of evidence pollution by judging the pollution source score of the associated evidence.

Images